Role of Artificial Intelligence in Infectious Diseases and Antimicrobial Resistance: A Comprehensive Review on Diagnostic, Treatment, and Prevention Aspects.

Role of Artificial Intelligence in Infectious Diseases and Antimicrobial Resistance: A Comprehensive Review on Diagnostic, Treatment, and Prevention Aspects - PMC Skip to main content An official website of the United States government Here's how you know Here's how you know Search Log in Primary site navigation Search Log in Search PMC Full-Text Archive Search in PMC Journal List User Guide As a library, NLM provides access to scientific literature. Inclusion in an NLM database does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: PMC Disclaimer | PMC Copyright Notice Saudi Med J . 2026 Feb 7;47(2):219–236. doi: 10.15537/1658-3175.1003 Role of Artificial Intelligence in Infectious Diseases and Antimicrobial Resistance: A Comprehensive Review on Diagnostic, Treatment, and Prevention Aspects Naveed Ahmed a , Mansoor Alghamdi b, * Author information Article notes Copyright and License information a From the Department of Assistance Medical Sciences, Applied College, University of Tabuk, Tabuk, Kingdom of Saudi Arabia (Ahmed) b From the Department of Computer Science, Applied College, University of Tabuk, Tabuk, Kingdom of Saudi Arabia (Alghamdi) * Corresponding author. Received 2025 Sep 7; Accepted 2025 Nov 6; Issue date 2026 Feb. Copyright: © Saudi Medical Journal This is an Open Access journal and articles published are distributed under the terms of the Creative Commons Attribution-NonCommercial License (CC BY-NC). Readers may copy, distribute, and display the work for non-commercial purposes with the proper citation of the original work. PMC Copyright notice PMCID: PMC13170470  PMID: 42239923 Summary Artificial intelligence (AI) plays a significant role in managing infectious diseases by enhancing diagnosis, treatment, and preventive measures. AI-assisted tools have predictive analysis ability for incoming outbreaks, including the emergence of antimicrobial resistance (AMR). AI-assisted tools facilitate the treatment methods by tailoring personalized medicine according to the specific disease history of the patient, immune response, and genetics. Advanced vaccine development by various AI-assisted in silico tools is becoming easy, leading to faster vaccine discovery and more efficient vaccine design with a more immunogenic response. Despite huge benefits, a few limitations are also encountered, including biases in algorithms, data privacy, and ethical considerations. This review provides a thorough review of the existing uses of AI and Machine Learning in diagnosing, treating, and preventing infectious diseases, with particular focus on approaches for detecting, monitoring, and containing AMR. Keywords: Machine Learning, Drug dosage calculations, Computer Simulation, Epidemiological models, Algorithms Introduction Infectious diseases caused by different pathogens, including bacteria, fungi, and viruses, have been a continuing health challenge for humans and animals. The infectious diseases caused by these microbes are illustrated in Fig. 1 . These infections are transmitted through several means, including body fluids, mucous, saliva, and blood, through consumption of indigestion contaminated food or water, and contact with infected surfaces. These pathogens are responsible for the broad spectrum of communicable diseases like influenza and cold, having the potential to spread through the environment and atmosphere. Infectious diseases caused major pandemics, including Black Death, COVID-19, and the Spanish flu, globally [ 1 ]. For the treatment of infectious diseases, antimicrobial drugs are utilized. The infectious diseases are asymptomatic or symptomatic, as AIDS has an asymptomatic phase as well as a symptomatic phase, while cholera is a symptomatic disease [ 2 , 3 ]. Fig. 1. Open in a new tab Common diseases caused by bacteria, viruses, fungi, and parasites. Examples include Strep throat (bacterial), HIV (viral), Aspergillosis (fungal), and Malaria (parasitic). Abbreviations: UTIs, urinary tract infections. HIV, human immunodeficiency virus. HAV, hepatitis A virus. HBV, hepatitis B virus. HCV, hepatitis C virus. In recent years, though, the mounting risk of antimicrobial resistance (AMR) has placed a fresh layer of pressure on infectious disease management, calling for new thinking like Artificial Intelligence (AI) to improve detection, prevention, and treatment. Currently, over the past two decades, the worldwide health community has confronted an alarming escalation of AMR, a challenge that promises to reverse decades of advances in infectious disease control [ 4 ]. AMR not only makes treatment of routine bacterial, viral, fungal, and parasitic infections more difficult but also raises the cost of healthcare, length of hospital stays, and mortality. Rapid detection of resistant pathogens, in combination with rational treatment, has thus emerged as a pressing priority. AI and Machine Learning (ML) are proving to be key enablers of this endeavor, allowing for accelerated diagnostic turnaround, predictive modeling to contain outbreaks, optimizing antibiotic regimens, and ongoing surveillance of resistance patterns across local, national, and worldwide levels [ 5 ]. In the last century, several infectious disease outbreaks have occurred in various countries, impacting global health. Some countries have become the hub for the transmission of these infectious diseases. Different infectious diseases like SARS, AIDS, H5N1, HPAI, and COVID-19 impact human health, as well as the economic state and social stability was also affected [ 6 ]. Different zoonotic infections are transmitted from animals to humans and then are transmitted among them. From 1918 to 1919, the Spanish flu caused more than 50 million deaths globally [ 7 ]. In World Wars I and II, more than 77 million people were killed due to infectious diseases. However, the Spanish flu pandemic was the worst infection of the 20 th century [ 8 ]. Infectious diseases are prevalent in both developing and developed countries and have detrimental effects on the economy. According to the reports of the World Health Organization, in the present century, several infectious diseases have caused numerous deaths. In 2014 and 2015, measles and Zika virus outbreaks occurred in California and Brazil, respectively. However, the latter caused above 1.5 million deaths in more than 60 countries. About 600 people were affected with Hepatitis A virus (HAV) in 2017 [ 9 ]. Moreover, climate change is also increasing the burden of infectious diseases and health threats. Some vector-borne diseases, like Malaria, prevalence is highly dependent on climate change as they are more prevalent in Asia, South America, and Africa. Mosquitos responsible for carrying Zika, Dengue, and Chikungunya also expand the disease zone in temperate and regions with the greenhouse effect [ 10 ]. The warm climate of spring is responsible for the expansion of infection of the West Nile virus in Europe. In Europe and North America, tick-borne encephalitis and Lyme disease spread due to climate suitability [ 11 ]. Climate change is responsible for both disease expansion and contraction, as Schistosomiasis, which is a water-borne disease, is a serious health concern in Africa, the Middle East, Latin America, and Southeast Asia, while a few water-borne diseases, including diarrhea, have decreased significantly due to public awareness, socioeconomic, and climate improvement [ 12 ]. It is quite challenging to diagnose, treat, and prevent these infectious diseases, as during diagnosis, false positive or false negative detection is a major problem. As infectious diseases are sometimes asymptomatic, early detection is not possible. Moreover, advanced diagnostic methods and equipment are also a limitation, especially in developing countries. Due to the unavailability of advanced molecular diagnostic methods, underdeveloped countries mostly rely on symptom-based diagnosis. Over the past 100 years, immunodiagnostics and microscopic and cultural techniques have been used to diagnose infections, and they have been replaced with molecular diagnostic methods to detect bacterial infections with more efficiency [ 7 ]. With the emergence of AMR bacteria, the diagnosis has become quite challenging due to a lack of specificity and sensitivity. The improper diagnosis also led to improper treatment, and it further enhanced AMR. The diagnostic methods have been revolutionized with computational biology and AI-based approaches [ 4 ]. Artificial intelligence and ML improved diagnostic methods through automation processes, including processing and interpretation of data, prediction modeling, and recognition of disease patterns. Artificial intelligence is considered a machine performing all the processes that require human intelligence, such as solving problems, analyzing results, and making decisions. ML uses algorithms to analyze and improve the input data. Both AI and ML play a role in the diagnosis and treatment methods, prevention programs, and surveillance. These AI tools have applications in the healthcare sector for diagnosis and prediction of outbreaks, as well as customized medicine for a specific disease [ 13 , 14 ]. Different AI methods, including ML algorithms, deep learning, Natural language processing (NLP), and computer vision robotics, are employed in the healthcare sector. Machine Learning makes predictions on a given dataset by collecting input data, then data preparation and wrangling, analysis of the given data, model testing, and deployment. Different kinds of input data can be used by ML, including genomic data, medical records, and image data. The unstructured data is formatted according to the formats of ML algorithms. Machine Learning is of two types, i.e., supervised learning and unsupervised learning. In the case of supervised learning, previously available data is used for the training of the model, and based on behalf of it, predictions about unknown data are made. It includes classification and regression. Classification is used to predict the susceptibility of microorganisms to proposing, while regression analysis is used for the prediction of outcomes in the form of numeric [ 15 ]. Unsupervised learning is involved in class clustering and includes fuzzy logic, K-medoids, hierarchical, K-means, neural networks, the Hidden Markov model, and the Gaussian mixture [ 1 ]. The most commonly used model in diagnosis is the Support Vector Machine. One of the simplest models used in healthcare settings is linear regression. The widely used ML program is CNN, a deep-learning model that is used to process grid data with images [ 1 ]. The use of AI in medical science assists in the analysis of reports, processing the data, and detection of disease, and by the use of algorithms, vast results and epidemiological data could be analyzed to identify disease patterns, predict outbreaks, and assist in deciding treatment methods. By using these powerful tools, lab results, medical reports, and records of patients with different diseases like COVID-19, malaria, and tuberculosis can be detected [ 16 , 17 ] The genome sequences of novel pathogens and their mutants could be analyzed by using ML programs, so by analyzing the sequence, targeted therapeutic agents can be designed. By analyzing the travel data, social media, and public health reports, incoming outbreaks could be detected easily with AI tools. It also helps to identify potential drugs and therapeutic agents by evaluating the immune response and molecular interactions. The accuracy, speed, and detection of infectious diseases became accessible and improved by AI [ 18 ]. For the traditional methods of diagnosis, specific laboratories and trained staff were required, but with the help of AI-based detection, fast and more accurate diagnosis of a particular disease can be achieved through automatic and machine-based learning programs. By using AI models detection of disease markers is possible from blood test reports, images, and biosensors, facilitating the early diagnosis of disease. A few AI tools, such as AI-assisted microscopy, help in quick detection and reliable results. Timely interventions against incoming outbreaks could be implemented by analyzing the public health reports. Moreover, it helps to tailor and optimize the drug for a particular disease [ 19 ]. Despite its advantages, AI-based detection faced a few challenges as well, such as the requirement of huge datasets, privacy concerns, and approvals. However, researchers and policymakers are collaborating to find more effective ways to manage infectious diseases with AI tools [ 20 ]. This review provides an exhaustive and example-based synthesis of ML and AI applications for diagnosing, treating, and preventing infectious diseases, with specific emphasis on fighting AMR. The manuscript identifies particular AI tools, methods, and case examples to demonstrate their potential for speeding up pathogen detection, anticipating resistance patterns, identifying optimal antimicrobial treatments, and enhancing surveillance systems. Particular attention is paid to strategies that can be applied in settings with limited resources to aid global AMR mitigation efforts. AI in the diagnosis of infectious diseases Artificial intelligence can integrate vast quantitative data related to the biological system and control biology; it is useful for the diagnosis of complex infectious diseases from an individual to communities as well, and it plays an important role in the progression of the field of medicine and biotechnology. By using AI predictive algorithms, the accuracy of molecular diagnostics and imaging technologies has improved [ 21 ]. AI-based diagnostic tools AI-based diagnostic tools revolutionized the medical world by identifying and managing infectious diseases efficiently. By using advanced algorithms, these tools analyze the vast data and provide information from clinical symptoms to the genetics of the disease [ 7 ]. They have been used across varied applications, for instance, CAD4TB for computer-aided chest X-ray screening for tuberculosis, CT scan analysis with AI for COVID-19 early detection, convolutional neural networks for recognizing malaria parasites in blood smears, and ResNet-based models for quick bacterial identification from images of colonies. These tools assisted in the identification of pathogens and disease treatment options according to the progression level of the disease [ 21 ]. Machine learning models for rapid pathogen identification Machine Learning models are novel ways of pathogen detection as compared to traditional molecular methods like polymerase chain reaction (PCR) and culture-based methods. The oldest method of pathogen detection is Culture-based, in which the pathogen is grown on some broth, and from the growth pathogen is identified. However, a few pathogens are not culturable, so this method is not used for the identification of all pathogens. In molecular diagnostics, PCR uses primers to amplify the genome of the pathogen, but for each microorganism, a different set of primers is needed, so there is a need to know the suspected pathogens to design specific primers, and there are chances of false-positive and false-negative results [ 22 ]. Different viral pathogens also present problems as they cannot grow on media, so for their detection, traditionally, molecular methods like PCR, electron microscopy, and cell culture methods are used. The PCR is considered the gold standard method of viral load detection, while electron microscopy directly visualizes the virus, but a heavy viral load is required for proper visualization. In the case of cell culture, some viruses cannot able to be cultured in media or they need specific conditions for growth [ 23 ]. Fungal infections are traditionally identified by culturing methods, microscopy, and staining methods. For the detection of fungal pathogens, culturing methods are time-consuming as they may take days or even weeks, and specific media and growth conditions are also needed. However, PCR and Immunoassays also detect fungal pathogens, which analyze fungal DNA and fungal antigens or toxins, respectively [ 24 ]. With the advancement in AI, traditional methods were modified for more advanced detection, and the limitations were also limited by ML and AI. The modification of pathogen detection methods is illustrated in Fig. 2 . Diagnostic pipelines have transformed from classical culture-based and PCR strategies to AI-augmented pipelines with ML algorithms for curve analysis, sequence alignment, and resistance prediction. This integration diminishes turnaround time, enhances sensitivity/specificity, and facilitates earlier initiation of targeted therapy [ 4 ]. Fig. 2. Open in a new tab Modification of the pathogen detection method with Machine Learning. Workflow: Traditional culture/PCR → AI-enhanced PCR curve analysis and metagenomic NGS/WGS → genotype-to-phenotype resistance inference automated. Advantages are quicker results, enhanced precision, and earlier resistance identification. Abbreviations: PCR, polymerase chain reaction. ML, machine learning. Integration of AI with molecular diagnostics like PCR, NGS, and WGS Molecular diagnostics aims to identify the pathogen at the molecular level. AI improved molecular diagnostics through its assistance at various steps of data analysis and visualization. The major molecular diagnostics include Polymerase chain reactions, next-generation sequencing, and whole genome sequencing (WGS) [ 7 ]. Polymerase chain reaction The PCR is used to detect various infectious diseases. Artificial intelligence can assist in the interpretation of PCR results. By using its ML modules, the detection of pathogens by identifying their specific genes can be done with more accuracy and in less time [ 25 ]. For instance, AI algorithms like PCR.ai and Thermo Fisher's AmpliSeq analysis software can analyze real-time amplification curves, detect anomalies, and make automatic positive/negative calls more accurately than manual thresholding, saving time and minimizing the role of human error. Next-Generation sequencing The NGS is used to identify unknown pathogens by sequencing and analyzing mutations in known pathogenic strains. NGS can track all the genetic alterations over time. With the advancement in AI, the NGS technique has improved by incorporating various computational tools and ML [ 26 ]. Large-scale data analysis is possible through the integration of systems biology to build better prediction models and to identify the improved characteristics of various predictive models. Deep neural networks and graph neural networks can be implemented in biological systems to obtain more accurate results. By using the NGS technique along with AI modules, it became feasible to analyze the pathways that are involved in cancer, and it became easy to understand the characteristics of tumors and their subtypes [ 27 ]. For instance, Google AI-developed DeepVariant uses deep learning to call high-accuracy genetic variants from NGS data, whereas PathoScope combines metagenomics reads classification and pathogen identification. For AMR sequencing, ARIBA and DeepARG predict resistance determinants from sequence data. Whole genome sequencing Whole genome sequencing is usually done to find out various diseases that occur due to mutations. The limitation of WGS is the large output data; dealing with such huge data is quite complicated. With the advancement in computer technology and AI, ML, and deep learning algorithms can analyze such huge data. By using WGS, it became easy to identify microbes and their virulent nature. The introduction of ML makes the presently available diagnostic methods efficient and reliable [ 28 ]. For instance, Mykrobe Predictor employs WGS data to predict antimicrobial susceptibility for pathogens like Mycobacterium tuberculosis and Staphylococcus aureus within hours of sequencing, allowing clinicians to modify treatment regimens early. Imaging diagnostics For the diagnosis of infectious diseases, imaging diagnostics has a crucial role. For the management of infectious diseases, several conventional imaging techniques are available, such as X-rays, MRIs, and CT scans, for which the expertise of radiologists is needed for the interpretation of imaging results. With the advancement in AI, imaging outcomes prediction is becoming much easier, more accurate, and faster [ 29 ]. The automated analysis of these medical images ensures more accurate detection, removes personal errors, and improves diagnostic ability. For instance, CAD4TB is globally implemented in regions where TB is prevalent to routinely score chest X-rays for suspicion of tuberculosis, enabling fast triage in community screening campaigns. Analogously, COVID-Net, an open-source deep learning framework, interprets chest radiographs for patterns of COVID-19, and Lunit INSIGHT CXR delivers multi-disease detection from radiographs [ 7 ]. Use of AI in interpreting radiological imaging for diseases As imaging diagnostics are improved with AI, it improves the diagnostic capabilities of various radiological techniques, including X-rays, CT scans, and MRI. Various infectious diseases like TB and COVID-19 are also diagnosed and analyzed by imaging techniques. In developed countries with a high prevalence of TB, chest radiography is performed for a more improved and accurate evaluation of active pulmonary tuberculosis [ 30 ]. However, for the interpretation of these radiographic images, resources are limited. But with the development of AI, it became quite easy to interpret these radiographic images in an automated way and to analyze abnormalities more accurately. The two most common approaches of AI are ML and deep learning, which are read by computer-aided detection (CAD). The algorithms use neural networks to analyze the data in a more meaningful way and to make more accurate predictions [ 31 ]. Fig. 3 illustrates AI uses in the interpretation of infectious disease data from imaging modalities (X-ray, CT, MRI), histopathology, and lab analysis. It points to major use cases including automated TB triage from chest X-rays, AI-supported CT interpretation for COVID-19, and digital pathology for malaria and fungal diseases. Fig. 3. Open in a new tab Applications of AI for the interpretation of infectious diseases. During the COVID-19 pandemic, AI assisted in analyzing the CT scans of the chest for the early detection of infection. By using the algorithms of AI, it became easy to comprehend the patterns of lung infection. AI reduced the diagnostic burden of healthcare expert radiologists, and it differentiated the normal pulmonary infection from the SARS-CoV-2 infection, leading to more accurate and early diagnosis [ 32 ]. The XR by Qure.ai and Lunit INSIGHT CXR are clinically proven for TB and other lung disease detection in large-scale screening, fitting well into radiology workflows. In MRI, AI solutions like Aidoc and Viz.ai help detect infectious lesions in the brain and central nervous system ( Fig. 4 ). Fig. 4. Open in a new tab AI in histopathological analysis for malaria diagnosis. AI in histopathological analysis for infectious agents Artificial Intelligence changes the way scientists examine infected body tissues as part of histopathological research. The examination of infected tissues for bacterial, fungal, or viral analysis through strict microscopic evaluation of tissue stains defines the traditional histopathological process [ 21 ]. Technical analysis using this procedure takes significant time, while human mistakes are possible in such cases. The analysis performed by ML algorithms enables the detection of infected tissue versus healthy tissue, while their classification system identifies multiple kinds of infections along with forecasting disease development. The detection of malaria parasites in blood smears, combined with biopsy sample fungal infection identification and viral infection analysis through tissue morphology, represents some capabilities of AI. AI mesh technology enables pathologists to use whole-slide imaging systems, which allow them to conduct remote diagnoses of infections through digital examination [ 33 ]. Through its assistance for pathology professionals and radiologists, AI speeds up diagnosis procedures to provide better patient services and strengthen healthcare facilities that lack sufficient resources [ 34 ]. Predictive diagnostics Predictive diagnostics is the use of AI and ML to identify incoming threats and disease outbreaks. By using public health data, epidemiological data, environmental data, and genomic data, AI helps in the prediction of incoming threats and facilitates medical researchers to take preventive measures and control them [ 35 ]. Predictive diagnostics is very important, as it prepares the researchers to cope with incoming disease outbreaks by identifying the causative agent or by introducing more robust diagnostic and treatment methods. Algorithms for predicting outbreaks For the prediction of future outbreaks, different ML programs like deep learning and ensemble strategies are used to fight against different infections. These AI-powered tools analyze the data from different sources, including public health data, climate patterns, genomic data, and human mobility data or epidemiological data, and make predictions by identifying the significant correlation between different factors involved in the disease transmission. And outbreaks. The ability of these AI tools to investigate and analyze historical and epidemiological data enables researchers to develop early diagnostic methods and to make well-informed judgments. The combination of ML programs and epidemiological data improves the accuracy of prediction and understanding of the disease dynamics [ 36 ]. During the COVID-19 pandemic, the tracking of new variants of SARS-CoV-2 was monitored by analyzing the genomic data using AI surveillance tools. Due to the high level of uncertainty, there was a low accuracy rate for incoming variants. However, several ML models, including susceptible infected recovered (SIR) and susceptible exposed infectious removed (SEIR) models, were utilized and modified for the prediction of new variant outbreaks. Several other ML models were utilized, but the adaptive network-based fuzzy inference system (ANFIS) and the multilayered perceptron (MLP) proved to be quite effective [ 37 ]. AI models are also used to analyze environmental and climate data and make predictions about outbreaks of vector-borne diseases like dengue fever and malaria by using epidemiological data and satellite images to make effective preventive measures [ 38 ]. HealthMap and BlueDot AI prediction systems show a successful rate of disease outbreak prediction as compared to traditional methods. These models utilized real-time reports and provided alerts to the Government about incoming threats [ 39 ]. Artificial Intelligence for early detection of antimicrobial resistance Artificial intelligence has a leading role in identifying AMR sooner than conventional laboratory protocols so that clinicians can adapt treatments in a timely fashion and minimize resistant organisms. Machine learning algorithms such as ResFinder, DeepARG, and PointFinder inspect genomic sequences to detect existing and new resistance genes, directly predicting phenotypic resistance profiles from NGS or WGS data [ 4 ]. Hospitals have started incorporating AI-driven Antibiotic Stewardship Platforms, for instance, Sentinel AMR and Epic's AMR Surveillance Module that integrate local antibiograms, electronic health records (EHR), and patient demographics to suggest targeted empiric therapy and ideal treatment durations. Predictive platforms such as MICNet predict minimum inhibitory concentrations (MICs) from genomic and phenotypic inputs, allowing for earlier optimization of antimicrobial regimens [ 40 ]. In low-resource environments, handheld sequencing machines combined with on-device AI classifiers (e.g., MinION with ARMA software) enable point-of-care resistance profiling without central laboratories. AI-based metagenomic analysis software like Meta-MARC and AMRPlusPlus determines resistance determinants in high-complexity, mixed-species samples, which is essential for syndromic infections and environmental monitoring [ 4 ]. These systems are progressively confirmed in prospective trials, demonstrating reductions in time-to-effective therapy, more appropriate use of last-resort antibiotics, and better patient outcomes. By incorporating resistance prediction into initial diagnostic streams, AI not only speeds up individual patient care but also enhances public health surveillance of resistance patterns at local, national, and international levels [ 38 ]. AI in the treatment of infectious diseases Before the advancement in AI, infectious diseases were treated by generalized methods, but now specific treatment methods are introduced by designing personalized medicines for patients and optimizing the treatment regimen. By using ML programs and prediction analysis, treatment methods have improved by reducing the possible side effects [ 41 ]. In the case of personalized medicine, treatment methods are designed by keeping in view the infection profile, immune response, and genetic makeup of the individual. By using AI, the genetic information, microbiome analysis, and overall health profile of the individual studied customized and treated [ 42 ]. Role of AI in tailoring antimicrobial therapies and patient response to treatment According to the particular infection and antibiotic-resistant profile, a customized treatment method is tailored for the patient by using AI models. The genetic makeup of the pathogen, as well as specific biomarkers for the patient, are analyzed by ML algorithms to shortlist the most effective therapeutic agents. For instance, DeepAMR, an AI-assisted tool, analyzes the antibiotic-resistant genes within the genomes of bacteria and suggests effective therapeutics. Similarly, IDSeq is another AI-assisted tool that integrates epidemiological data and genomic sequencing to make an appropriate decision for therapy [ 40 ]. It reduces the overuse of unnecessary antimicrobials, so it assists in combating AMR and treatment methods [ 43 ]. All patients undergoing drug treatment do not behave similarly due to their genetic variability, immune response, and health conditions. The AI models analyze the immune response of patients by analyzing the real-time data, outcomes of treatment, and pharmacogenomics. The clinical decision support systems (CDSS) examine the history of the patient and the consequences of a particular treatment method by using ML algorithms, and they assist the medical staff in making adjustments to the treatment methods, altering the dose or the use of combined therapies [ 44 ]. Drug discovery Drug discovery is a costly and time-consuming process; for the development of a drug or antibiotics, several years are required. However, with the help of AI, it became easy to identify novel therapeutic candidates, analyze their structure at the molecular level, and alter the properties of existing drugs for better therapeutic effects [ 45 ]. Different AI-assisted tools, such as AtomNet and AlphaFold, used for the prediction of drug-ligand interaction and protein structure, facilitate researchers in finding ideal drug candidates [ 46 ]. By using these tools, several million compounds were screened for their efficacy as drugs, antibiotics, antivirals, and antifungal activity. Halicin is an example of such a drug discovered by screening several antibiotics using AI tools, and it is used for the treatment of multidrug-resistant bacteria [ 47 ]. The recent pandemic COVID-19 highlighted the importance of different antiviral drugs for the treatment of emerging diseases. Different databases like STRING, HPIDB, and HU.MAP is used to provide information about human-virus and human-human protein interactions. These tools are provided with AI algorithms that facilitate to filtering of millions of drug candidates and the drug discovery process. DeepDrug is also an AI-assisted tool able to synthesize novel drugs and improve existing drugs [ 5 ]. Some of the emerging AI tools facilitating drug discovery are the following. Table 1 illustrates exemplary AI tools for antiviral and antimicrobial discovery and repurposing, describing their primary functions, application steps (in vitro, in vivo, clinical trials), and common use scenarios. Table 1. Comparison of AI tools and their features for Drug development. AI-assisted tool Feature In-vitro In-vivo Clinical Trials Atomwise [ 48 ] De novo chemotypes synthesis (GAN), Molecular docking Yes - - DeepDrug [ 49 ] eSynth, eDrugRes, eComb, eToxPred, eMolFrag Yes Yes Approved since May 2021 ComboNet, Insilico medicine [ 50 ] Drug combination analysis Yes - - Benevolent AI [ 51 ] Protein cleft analysis Yes Yes Yes Open in a new tab Drug repurposing for new therapeutic applications is also revolutionized by AI. By using AI tools, approved existing drugs are reevaluated for other infectious diseases [ 52 ]. During COVID-19, Baricitinib and Remdesivir were predicted as potential therapeutic candidates by deep learning programs [ 53 , 54 ]. Recursion Pharmaceuticals and Benevolent AI work on the prediction of the therapeutic potential of existing drugs for other infectious diseases [ 55 ]. Optimization of treatment regimens AI also plays a role in the optimization of doses, reducing drug toxicity, and monitoring side effects by using predictive analysis and health data. To treat infectious diseases like AIDS, TB, and Hepatitis C, adherence to prescribed medication is mandatory. If the infection is left untreated or the adherence to the treatment is incomplete, it will lead to the development of resistance against treatment and relapse of the disease. By using AI applications, such as mobile health (mHealth) or different reminder applications, treatment adherence is made effective by tracking the dose reminders [ 56 ]. AI applications like AiCure ensure treatment adherence by facial recognition. These applications reduce the risk of non-adherence [ 57 ]. Different AI models also optimize the drug by ensuring the optimal dose with minimum side effects. By using ML programs, the optimum dose for a patient is decided by looking at the overall health state, age, genetic makeup, and weight. The drug metabolism rate of the individual is predicted by using AI models like Bayesian AI and IBM Watson to maintain the efficacy of treatment and to reduce side effects [ 58 , 59 ]. AI in the prevention of infectious diseases The involvement of AI in the prevention programs of infectious diseases has significant effects on the mitigation of diseases. With the help of these technologies, surveillance, optimization of vaccines, and better Preventive programs with limited resources are achieved. Artificial intelligence can analyze vast amounts of clinical, social, environmental, and genomic data, which enables it to predict incoming health threats [ 60 ]. Disease surveillance Disease surveillance includes reporting, epidemiological studies, and confirmation by laboratory; these traditional methods are slow and reactive but not proactive [ 48 ]. The limitations of these traditional methods were already faced during the COVID-19 pandemic, as diagnosis delays led to the worldwide pandemic. This highlights the importance of more innovative methods of data analysis with efficient predictive capabilities to cope with incoming pandemics [ 39 ]. However, with the emergence of AI, a quick transformation was observed in fighting against infectious diseases. The ML programs are capable of dealing with large data files by using their algorithms and making predictions about incoming health threats. So, AI integration into health sciences not only prepares the public for outbreaks but also plays a role in the mitigation of pandemics [ 61 , 62 ]. The disease dynamics and forecasting are done with recurrent neural networks (RNNs) and long short-term memory (LSTM) models of ML. As an AI-assisted program, “BlueDot” already predicted the COVID-19 outbreak before the official announcement by the media and health reports. Other AI tools, including the HealthMap system and ProMED, predict incoming epidemics by analyzing global reports and facilitating health agencies to prevent disease [ 63 ]. Disease tracking can also be done by using social media platforms and big data analysis, as AI scans the trends on social media platforms about disease symptoms and hotspots of the outbreak. Through Google Flu Trends, AI confirms that it produces faster outbreak predictions than standard surveillance methods while it analyzes search engine trends. Geospatial AI tools utilize satellite pictures together with mobility statistics to detect environmental elements suitable for illness propagation, such as the locations where mosquitoes reproduce for malaria transmission and dengue. Public health interventions focus more efficiently by using these implementations, which reduce the impact of infectious diseases [ 39 , 64 ]. Vaccination strategies With the fastest discovery of new antigens and the in-silico prediction of their immune response, AI revolutionized vaccine development and optimization. With the usage of computational modeling and reverse vaccinology, the vaccine development time was reduced to a great extent [ 65 ]. Traditionally, vaccine development was a time-consuming process, but the use of reverse vaccinology facilitated the vaccine development process by streamlining the process from the analysis of the genetic makeup of pathogens to the identification of potential antigens. The vaccine candidates are selected by shortlisting the highly immunogenic epitope regions [ 66 ]. The selection of these epitopes is done with the help of ML algorithms. The comparison of the overall layout of conventional and reverse vaccinology is given in Table 2 . Table 2. Comparison of conventional vaccinology and reverse vaccinology [ 46 ]. Vaccinology (Conventional) Vaccinology (Reverse) Microbe cultivation Protein sequence retrieval Targeted compound extraction Sequence analysis of the target gene Selection of antigen Novel antigen prediction Purification of the compound or cloning Expression and purification Trials on an Animal model In-silico trials Trials on humans Vaccine development Open in a new tab For the understanding of SARS-CoV-2 proteins, especially the spike protein, AlphaFold and other protein 3D structure predicting tools were used, which aid in better understanding of structural proteins and the development of a vaccine in this pandemic [ 67 ]. Furthermore, these computer-based AI programs facilitated the in-silico vaccine trials, reducing the efforts and time-consuming process of animal trials. These AI tools predict the effectiveness, safety, and side effects of a potential vaccine before trial on humans [ 68 ]. AI also ensures the distribution of vaccines in remote areas, especially in developing and underdeveloped countries. Different logistic platforms of AI use supply chain optimization and predictive analysis algorithms to provide vaccines in remote and dense areas [ 69 ]. AI models predict the safest and most efficient route for vaccine delivery by the assessment of transportation routes, availability of cold chain storage, and population density. In African remote areas, a Zipline (a drone-based logistics system assisted by AI) was used to deliver vaccines despite geographical barriers [ 70 ]. Moreover, different AI applications like chatbots guide people about the use of the vaccine, encouraging vaccination, nullifying false information, and ensuring the immunization success rate in highly prevalent populations [ 71 ]. Pilot programs showing scalable AI in low-resource environments Automated chest X-ray (CXR) triage algorithms have been employed by large screening programs in high-TB-burden locations to quickly identify presumptive TB cases, allowing for focused sputum testing and minimizing radiology bottlenecks. These initiatives show how portable X-ray machines combined with small AI inference pipelines may expand to screening campaigns in rural areas [ 72 ]. Zipline drone logistics for vaccination and specimen delivery in Ghana and Rwanda, autonomous drones and AI-optimized logistics have been effectively used to transport diagnostic samples, blood supplies, and vaccinations to distant clinics, cutting down on turnaround times and preserving cold chain supply in difficult-to-reach locations [ 73 ]. On-device analysis and mobile nanopore sequencing by Rapid pipelines, lightweight on-device classifiers, and portable sequencing (like Oxford Nanopore MinION) have been tested for outbreak sequencing and point-of-care pathogen monitoring in field settings, allowing for genomic surveillance of pathogens without the need for centralized labs [ 74 ]. Practical enablers are highlighted in each project, including connection with current clinical procedures, local staff training, robust local governance for data use, and lightweight models that operate on edge hardware. Incorporate local result measures from prospective evaluations, such as logistic dependability, turnaround time savings, or case detection rate uplift, whenever feasible [ 56 ]. Public health interventions AI strengthens public health strategies by performing behavioral pattern evaluations together with intervention assessment and forecasting disease prevention rule compliance [ 75 ]. The acquired information enables health authorities to create data-informed policies that achieve maximum preventive measures compliance [ 76 ]. The system examines collected epidemiological information alongside hospital resources and population movements to estimate how these policies affect disease spread rates [ 77 ]. During the COVID-19 pandemic, the AI system provides effective awareness about the implementation of lockdowns and other health measures. Evaluative predictive models helped authorities understand how different early intervention approaches could decrease disease cases to make evidence-based public policy choices. Through a digital tracing system, AI showed its capability to observe and manage outbreaks [ 78 ]. Users can protect their privacy when tracking COVID-19 exposure through Apple-Google's Exposure Notification API, which uses Bluetooth and an AI algorithm for processing. AI-powered interventions cut down infectious disease spread because they give people the chance to begin isolation independently and receive testing immediately. Analyzing human behavior leads to successful public health policy design. AI systems evaluate social and psychological elements that affect compliance rates regarding preventative actions such as wearing masks and maintaining distance between individuals while receiving vaccinations [ 79 ]. From social media and psychological research, AI algorithms trace information about vaccine refusal by people with low knowledge, and they help to find effective intervention strategies to boost the vaccine acceptance rate [ 80 ]. Validation of AI applications, ethical and regulatory issues Clinical use of AI tools in infectious disease and AMR management needs strong validation for reliability, reproducibility, and safety. Models need to be tested prospectively on external data from more than one site and heterogeneous patient populations to validate performance outside the development set. Reporting needs to include measures of sensitivity, specificity, calibration curves, and decision-curve analysis, along with a description of limitations and failure modes [ 56 ]. Generalizability is usually lost when homogeneous datasets that do not reflect real-world variability are used to train models. Such situations can be improved through balanced sampling, data augmentation of underrepresented classes, and ongoing model retraining on newly incoming data. From a values perspective, AI systems have to address data privacy, informed consent, and fairness in access. Bias mitigation is essential; otherwise, algorithms will exacerbate healthcare disparities by performing poorly in minority or underserved groups [ 73 ]. The deployment of Explainable AI (XAI) strategies, which explain the decision-making process to clinicians, is important to establish trust and permit clinical surveillance. Regulatory compliance is also at the heart of deployment. AI systems used for diagnosis or treatment choice are under Software as a Medical Device (SaMD) regulation in most places and have to go through risk assessment, documentation, and re-certification at regular intervals. Regulatory models like the U.S. FDA's AI/ML-Based SaMD Action Plan and the EU's AI Act demand openness in algorithm architecture, version control, and post-market monitoring. Developers have to keep change-control logs for adaptive models and institute human-in-the-loop review mechanisms for high-stakes choices [ 56 ]. By integrating robust validation, ethical protections, and regulatory acceptability into the AI development process, these technologies have the potential to move from encouraging prototypes to reliable clinical instruments for fighting infectious diseases and AMR [ 73 ]. Data privacy laws, algorithmic bias mitigation, explainability, accountability Jurisdiction-specific data-protection laws severely limit the use of AI in therapeutic settings. Regulations on legitimate processing, data minimization, purpose limitation, and individual rights (access, rectification, and erasure) are enforced by the General Data Protection Regulation (GDPR) in the European Union [ 73 ]. According to GDPR, secondary uses of clinical data (for algorithm improvement or model training) typically need a legitimate reason (such as explicit consent or a public interest/legal basis) and must be executed with robust governance and de-identification measures. Protecting personally identifiable health information (PHI) is the main goal of the Health Insurance Portability and Accountability Act (HIPAA) in the United States (US). These data privacy regulations in Europe and in the US impose significant implications on AI-based healthcare systems, particularly concerning data sharing and model deployment. It mandates that covered entities and business associates put in place administrative, technical, and physical safeguards [ 81 ]. These laws do not merely pose barriers but actively dictate the methodologies for data collection, sharing, storage, and model deployment. A nuanced understanding of their specific requirements is essential for developing compliant and ethically sound AI systems [ 82 ]. Both frameworks emphasize the lawful, fair, and transparent processing of personal data, requiring AI developers to ensure that patient data used for model training and validation is obtained under informed consent and handled according to strict privacy safeguards [ 83 ]. GDPR specifically restricts cross-border data transfers and mandates data minimization, collecting only what is necessary, while HIPAA enforces PHI through administrative, physical, and technical safeguards. These regulations directly affect how AI systems in healthcare can access, process, and share patient data across institutions or countries [ 84 ]. The way health systems share data for AI development is influenced by both frameworks. They encourage developers to use privacy-preserving methods (de-identification, pseudonymization, secure enclaves, and federated learning), obtain explicit patient consent when possible, and have strong contractual controls with technology vendors [ 73 ]. The influence of these regulations extends across the entire AI development pipeline. To maintain compliance and facilitate research, data anonymization and pseudonymization have become essential strategies. Anonymization involves removing all personally identifiable information (PII) to prevent any re-identification of individuals, making the data exempt from GDPR constraints [ 82 ]. Pseudonymization, on the other hand, replaces identifiers with coded references, allowing data to remain useful for research while still protected under regulated access conditions. In addition, adopting secure data exchange protocols such as encrypted data transmission, blockchain-based audit trails, and federated learning models allows multiple institutions to collaborate on AI training without sharing raw patient data. This approach minimizes privacy risks while preserving data diversity and model robustness [ 85 ]. Unrepresentative training data, label noise, and confounding factors that indicate structural injustices are the main causes of bias in AI models. Recommendations for mitigating bias include: (1) selecting diverse, multi-site training sets that capture heterogeneity in demographics and devices; (2) stratifying performance reporting across age, sex, ethnicity, device, and socioeconomic groups; (3) correcting class imbalances through data augmentation and re-weighting; (4) implementing adversarial de-biasing or fairness-aware optimization objectives; and (5) continuously monitoring performance after deployment with feedback loops to identify performance drift. Explainable AI (XAI) techniques, such as concept activation vectors, SHAP, LIME, and saliency maps, should be used to enable human-in-the-loop evaluation for high-risk decisions and to give doctors human-interpretable explanations for model outputs. Transparency and regulatory review require clear provenance, versioning, and documentation (data sheets, model cards) [ 86 ]. Clinical deployment necessitates a governance framework that establishes accountability for results: institutions must run oversight committees for model approval and post-market surveillance, vendors must maintain change logs and provide validation evidence, and clinicians must maintain ultimate responsibility for patient care decisions (human-in-the-loop). The degree of proof and monitoring necessary is determined by the risk classification (e.g., Software as a Medical Device frameworks) [ 21 ]. For AI malfunctions or detrimental biases, institutions should have incident reporting procedures and quick mitigation strategies. In Saudi Arabia, data privacy and AI deployment in healthcare are governed primarily by the Personal Data Protection Law (PDPL), enforced by the Saudi Data and Artificial Intelligence Authority (SDAIA). The PDPL aligns closely with international frameworks like GDPR, emphasizing lawful data processing, consent-based collection, and strict limitations on cross-border data transfers. Within the healthcare sector, this law mandates that any use of patient information for AI model development, data sharing, or analytics must ensure confidentiality, integrity, and minimal identifiability of personal data [ 87 ]. Hospitals and research institutions deploying AI systems must adopt privacy-preserving measures such as data anonymization, encryption, and secure cloud-based storage approved by SDAIA. Moreover, initiatives like the National SDAI encourage innovation while maintaining compliance through structured governance frameworks. These policies collectively ensure that AI-driven health research in Saudi Arabia advances responsibly, balancing innovation with the protection of individuals' health information and privacy rights [ 88 ]. Privacy-preserving and real-time architectures for AI in infectious disease With federated learning (FL), clients compute gradient updates on local data and only exchange aggregated model updates with a central server, allowing collaborative model training across different institutions while maintaining local raw data [ 4 ]. Although it needs to be used in conjunction with safe aggregation, differential privacy, and strong defenses against model inversion or poisoning assaults, FL can assist in complying with privacy rules and lessen the need to transfer patient data across borders. When data centralization is not practicable because of institutional or regulatory constraints, FL is especially helpful for multi-center clinical tasks [ 73 ]. Near-real-time surveillance algorithms can be fed by high-frequency, geographically dispersed signals from Internet of Things devices, such as wearables, portable microscopes, smart thermometers, and greenhouse sensors for vector habitats. Running inference on local devices, or edge analytics, reduces data transfer, protects privacy, and allows for quick alarms for public health authorities or healthcare teams. These systems provide continuous monitoring for indications of clinical worsening, contact tracing augmentation, and early warning [ 4 ]. Diagnostic loops can be shortened from days to minutes with real-time AI pipelines (e.g., CXR triage at point-of-care, on-device smear microscopy, or quick nanopore base calling with streaming classifiers). Deterministic latency guarantees, clinician feedback pathways, and in-built safety checks (confidence limits, human verification prompts) prior to autonomous actions are necessary for clinical acceptability in real-time systems [ 4 , 69 ]. Federated learning in privacy-preserving The FL represents a major leap forward in privacy-preserving AI, particularly for healthcare and infectious disease research. Traditional AI models require centralized data pooling, which raises ethical and regulatory concerns under frameworks such as GDPR, HIPAA, and Saudi Arabia's PDPL [ 87 ]. In contrast, federated learning enables multi-center AI training without moving raw data from local servers. Instead, models are trained locally across multiple hospitals, laboratories, or public health centers, and only the learned parameters are shared with a central aggregator. This distributed approach allows for large-scale, collaborative model development while maintaining patient confidentiality and institutional data sovereignty [ 89 ]. In infectious disease research, FL has been applied for predictive modeling of disease outbreaks, improving diagnostic algorithms for tuberculosis and COVID-19, and harmonizing AMR data across countries [ 90 ]. The real strength of federated learning lies in its ability to incorporate diverse, heterogeneous datasets, for example, data from different hospital systems or geographic regions, thereby improving model generalizability and bias mitigation. This capability is especially crucial for infectious diseases that vary in prevalence and presentation across populations [ 91 ]. Furthermore, ongoing innovations such as federated transfer learning and secure aggregation protocols enhance model efficiency and protection against data leakage. In the future, national and regional federated AI networks could connect microbiology laboratories, radiology centers, and surveillance systems to create real-time, adaptive infectious disease intelligence frameworks that respect patient privacy while enhancing responsiveness [ 92 ]. IoT-enabled disease monitoring and smart surveillance systems The Internet of Things (IoT) has emerged as a transformative technology for disease surveillance, outbreak detection, and post-treatment monitoring. IoT-enabled devices such as wearable biosensors, connected thermometers, and smart diagnostic kits continuously collect physiological, behavioral, and environmental data [ 77 ]. When integrated with AI analytics, these data streams provide early warnings of infectious disease outbreaks or relapses. For instance, IoT-based platforms were used during the COVID-19 pandemic to track vital signs remotely, detect fever clusters, and monitor quarantine compliance in real time. In hospital and community settings, IoT networks now assist in monitoring infection control indicators, such as hand hygiene compliance, air quality, and device sterilization, reducing HAIs [ 62 ]. Importantly, IoT-enabled surveillance systems enhance public health situational awareness by combining personal health data with environmental and epidemiological information. When deployed at the population level, they can map emerging hotspots, predict transmission trends, and facilitate targeted interventions [ 93 ]. The IoT-driven health systems are being integrated into smart healthcare initiatives, enabling continuous disease monitoring through mobile health (mHealth) platforms and remote diagnostics. However, ensuring data security and interoperability remains a key challenge; this is where blockchain integration and encrypted communication protocols can play a critical role, ensuring trust, transparency, and resilience in IoT-based disease monitoring frameworks [ 82 ]. Edge computing and real-time diagnostic intelligence Edge computing complements both IoT and AI by bringing computation closer to the data source, minimizing latency and enhancing speed for time-sensitive applications such as infection detection and outbreak response. Unlike traditional cloud-based systems, which depend on high bandwidth and centralized servers, edge computing processes data locally on diagnostic devices, hospital servers, or even portable biosensors [ 82 ]. This decentralized architecture enables rapid decision-making in clinical environments where timely responses are crucial, such as emergency departments, rural clinics, or epidemic field sites. In infectious disease management, edge AI models can instantly interpret diagnostic test results (e.g., from PCR, imaging, or biosensors), guide triage decisions, and trigger automated alerts for infection control teams [ 4 ]. The integration of edge AI in POCT represents a major advancement toward autonomous, intelligent diagnostics. Portable platforms equipped with microcontrollers or neuromorphic chips can analyze molecular signals on-site without requiring internet connectivity, ensuring continuity of care in low-resource or outbreak-prone settings [ 4 ]. For example, AI-enabled microfluidic biosensors embedded with edge processors have been used for real-time pathogen identification, including SARS-CoV-2 and antimicrobial-resistant bacteria. By reducing dependence on centralized computing infrastructure, edge computing enhances scalability, privacy, and cost-effectiveness, making it a critical enabler of sustainable infectious disease management systems [ 84 ]. Beyond federated learning, IoT, and edge computing, blockchain technology and digital twin systems are gaining traction in AI-based infectious disease management. Blockchain offers a tamper-proof, decentralized data exchange that ensures traceability, auditability, and compliance, essential for multi-center clinical collaborations [ 83 ]. Meanwhile, digital twins, virtual replicas of biological systems or hospital environments, allow simulation of infection dynamics, treatment outcomes, and intervention strategies before real-world implementation. These models, integrated with cloud-edge architectures, can accelerate personalized infection control and outbreak forecasting [ 91 ]. Together, these innovations form the foundation of next-generation AI ecosystems that are privacy-preserving, adaptive, and globally interconnected. By integrating federated learning for secure data collaboration, IoT for real-time monitoring, and edge computing for rapid analytics, healthcare systems can achieve unprecedented responsiveness to infectious threats [ 83 ]. Incorporating these concepts into the revised manuscript will not only address the reviewer's comment but also significantly strengthen the paper's novelty, aligning it with recent trends in digital epidemiology and AI-driven infection control [ 85 ]. Recent innovations in the management of infectious diseases using AI Recent innovations in the management of infectious diseases using AI have transformed how clinicians detect, monitor, and respond to outbreaks. AI-powered systems are now being used to predict the spread of infectious agents, identify emerging pathogens, and guide real-time decision-making during epidemics [ 59 ]. The ML models trained on epidemiological and genomic data can forecast disease transmission patterns and identify hotspots before traditional surveillance methods. The AI-based predictive analytics were instrumental in modeling COVID-19 spread and in designing public health interventions, demonstrating how data-driven intelligence can revolutionize epidemic preparedness and response. These models continue to evolve for other infectious diseases such as influenza, tuberculosis, and dengue, providing faster and more precise tools for outbreak containment [ 39 ]. In diagnostics, AI has enhanced the sensitivity and specificity of infectious disease detection by integrating deep learning algorithms with imaging and molecular platforms. Computer vision technologies can now analyze chest X-rays, CT scans, or microscopy slides to detect diseases like pneumonia, malaria, and tuberculosis with accuracy comparable to or exceeding that of human experts [ 41 ]. Furthermore, AI is increasingly being embedded into point-of-care diagnostic devices and biosensors, enabling rapid, low-cost testing in resource-limited settings. The NLP tools also aid clinicians by analyzing unstructured EHR data to identify early infection signs, track antimicrobial resistance patterns, and guide empirical treatment decisions [ 39 ]. Therapeutically, AI is accelerating drug discovery and optimizing treatment regimens for infectious diseases. By screening vast chemical libraries and predicting molecular interactions, AI algorithms can identify potential antiviral or antibacterial candidates in a fraction of the time required by conventional methods [ 41 ]. In AMR management, AI-driven models predict resistance mechanisms and guide personalized therapy based on pathogen genomics, minimizing treatment failure. The integration of AI into clinical workflows represents a paradigm shift toward precision infectious disease medicine, where data-driven insights improve outcomes, reduce costs, and enhance global health security [ 25 ]. Particularly, those integrating AI, nanotechnology, and genomics are reshaping the landscape of diagnosis, treatment, and personalized care. In the context of HIV, for example, recent studies in 2025 have highlighted AI-driven predictive algorithms that analyze host–virus interactions and patient-specific genomic profiles to optimize antiretroviral therapy (ART) regimens [ 60 ]. These personalized HIV management systems leverage machine learning to forecast treatment outcomes and drug resistance, reducing adverse effects and improving patient adherence. Additionally, nanomedicine-based drug delivery systems, such as nanoparticle-encapsulated ART, are being explored to enhance bioavailability and facilitate sustained release, marking a significant shift toward precision medicine in virology and immunology [ 94 ]. Beyond HIV, the broader biomedical field is witnessing a surge in integrative technologies that combine molecular diagnostics with AI and nanomaterials for point-of-care detection. For instance, nanoparticle-based biosensors, coupled with deep learning algorithms, are improving early detection of viral infections and antimicrobial resistance patterns with unprecedented accuracy [ 36 ]. These developments emphasize the growing convergence of computational biology and material science to address complex infectious diseases. Furthermore, real-time surveillance systems powered by AI are being implemented for rapid outbreak prediction and containment, especially relevant for emerging pathogens and global health preparedness [ 9 , 11 , 39 ]. The limitations and future prospects of AI In infectious diseases Artificial intelligence revolutionized the medical field by improving diagnostic methods, treatments, enhanced surveillance, and more optimized Preventive measures. Despite its huge benefits, there are several limitations of AI as well. One of the major limitations is the availability of quality data [ 4 ]. For more accurate prediction, AI models need elaborate data for training sets, but usually, very small datasets with inconsistent and missing values are available. The data also show variability within variable regions. In developing or underdeveloped countries, the available health data is poorly maintained, and it is difficult to build a more accurate and comprehensive AI model for diagnostic purposes or treatment methods. Moreover, various security regulations and data privacy by different regulations and acts like HIPAA and GDPR also limit the sharing of data across borders for collaborations [ 95 ]. The models built for a specific population are not generalized, and they are usually biased for a specific dataset. This model gives the best interpretation for the data, they are trained on, but shows discrepancies for other data. If the given data is not diverse or not related to the specific data for which the model was trained, then the accuracy of that model is compromised for the given data [ 95 ]. So, the models are validated only for specific ethnic, socioeconomic, or racial groups. There is a need to train the model for a specific population separately for more accurate predictions. Moreover, several AI models have a Black-box nature, which reduces the authenticity and transparency of the model. In the medical field, healthcare officers usually prefer explainable AI models for a clearer understanding of decision criteria, but still, deep learning AI algorithms possess problems and give ambiguous results, limiting the credibility of AI tools [ 4 ]. To look for AI tools in healthcare systems, extensive computational programs, data processing power, and storage capabilities are required. Low and middle-income countries face problems due to constrained resources, and access to several AI tools remains unavailable. Different formats of data storage at different places are also a problem, making data integration difficult. Most healthcare policies currently used are for traditional methods; there is a need to design more specific guidelines for AI-based diagnostics, as the current framework is not suitable for AI-assisted technologies. One of the most significant restrictions of AI tools is the lack of literacy about AI among healthcare specialists, and they remain skeptical about recent advancements due to a lack of exposure to the latest technologies. There is a need for proper AI training for healthcare experts, so that adaptation to modern AI technologies becomes possible [ 95 ]. Future research should focus on ethical AI deployment, scalable nanomedicine production, and adaptive clinical trial designs that accommodate dynamic data integration. There is immense potential in exploring how multi-omics approaches (metabolomics, proteomics, genomics) can be combined with nanotechnology and AI to advance personalized infection control strategies. Additionally, interdisciplinary collaboration between computational scientists, microbiologists, and clinicians will be critical in translating laboratory discoveries into practical healthcare solutions. By integrating these recent innovations and forward-looking perspectives, both the current progress and transformative potential of technology-driven research in infectious diseases and personalized medicine can be achieved. In conclusion, artificial intelligence has the potential for disease management and predictive ability of future outbreaks. By the analysis of epidemiological, genomic, and health reports, AI has disease forecasting ability. AI can detect novel diseases and novel pathogens, which may play a huge role in the prevention of future diseases. AI can combat AMR and personalize treatment methods for a person according to the disease patterns and specific microbes. Several AI-assisted tools are used for the screening of therapeutic candidates in less time, and they play a major role in the vaccine development programs. By behavioral modeling, AI can enhance the Interactive program's success rate by educating and targeting specific public and through the use of chatbots. For more advancement, there is a need for collaboration among researchers globally. Moreover, there is a need to fill the gap between developed and low to middle-income countries by providing advanced facilities to them through collaborations. Acknowledgments The author(s) would like to acknowledge the Applied College, University of Tabuk for providing facilities for this work. Additionally, the authors would like to acknowledge the RES Research solutions and Publishers for providing their services of English proofreading for our manuscript. Disclosure Authors have no conflict of interests, and the work was not supported or funded by any drug company. The authors would like to acknowledge the RES Research solutions and Publishers for providing their services of English proofreading for our manuscript. Contributor Information Naveed Ahmed, Email: nahmed@ut.edu.sa. Mansoor Alghamdi, Email: malghamdi@ut.edu.sa. References [1]. Rabaan AA, Bakhrebah MA, Alotaibi J, Natto ZS, Alkhaibari RS, Alawad E, et al. Unleashing the power of artificial intelligence for diagnosing and treating infectious diseases: A comprehensive review. Journal of Infection and Public Health 2023;16:1837–47. 10.1016/j.jiph.2023.08.021 [ DOI ] [ PubMed ] [ Google Scholar ] [2]. Upadhayay A, Ling J, Pal D, Xie Y, Ping F-F, Kumar A. Resistance-proof antimicrobial drug discovery to combat global antimicrobial resistance threat. Drug Resistance Updates 2023;66:100890. 10.1016/j.drup.2022.100890 [ DOI ] [ PubMed ] [ Google Scholar ] [3]. Spernovasilis N, Tsiodras S, Poulakou G. Emerging and re-emerging infectious diseases: humankind's companions and competitors. Microorganisms 2022;10:98. 10.3390/microorganisms10010098 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [4]. Bindra S, Jain R. Artificial intelligence in medical science: a review. Irish Journal of Medical Science (1971-) 2024;193:1419–29. 10.1007/s11845-023-03570-9 [ DOI ] [ PubMed ] [ Google Scholar ] [5]. Bess A, Berglind F, Mukhopadhyay S, Brylinski M, Griggs N, Cho T, et al. Artificial intelligence for the discovery of novel antimicrobial agents for emerging infectious diseases. Drug discovery today 2022;27:1099–107. 10.1016/j.drudis.2021.10.022 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [6]. Wiertsema SP, van Bergenhenegouwen J, Garssen J, Knippels LM. The interplay between the gut microbiome and the immune system in the context of infectious diseases throughout life and the role of nutrition in optimizing treatment strategies. Nutrients 2021;13:886. 10.3390/nu13030886 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [7]. Schmitz JE, Stratton CW, Persing DH, Tang Y-W. Forty years of molecular diagnostics for infectious diseases. Journal of clinical microbiology 2022;60:e02446–21. 10.1128/jcm.02446-21 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [8]. Bloom DE, Cadarette D. Infectious disease threats in the twenty-first century: strengthening the global response. Frontiers in immunology 2019;10:549. 10.3389/fimmu.2019.00549 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [9]. Dembek ZF, Chekol T, Wu A. Best practice assessment of disease modelling for infectious disease outbreaks. Epidemiology & Infection 2018;146:1207–15. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [10]. Semenza JC, RocklÖv J, Ebi KL. Climate change and cascading risks from infectious disease. Infectious diseases and therapy 2022;11:1371–90. 10.1007/s40121-022-00647-3 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [11]. Farooq Z, RocklÖv J, Wallin J, Abiri N, Sewe MO, SjÖdin H, et al. Artificial intelligence to predict West Nile virus outbreaks with eco-climatic drivers. The Lancet Regional Health–Europe 2022;17. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [12]. Mbereko A, Chimbari MJ, Manyangadze T, Mukaratirwa S. Knowledge and perceptions of schistosomiasis, a water-borne disease, in two semi-arid rural areas of South Africa (Ndumo) and Zimbabwe (Ntalale). Food and waterborne parasitology 2020;21:e00091. 10.1016/j.fawpar.2020.e00091 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [13]. Ghaffar Nia N, Kaplanoglu E, Nasab A. Evaluation of artificial intelligence techniques in disease diagnosis and prediction. Discover Artificial Intelligence 2023;3:5. 10.1007/s44163-023-00049-5 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [14]. Kaur S, Singla J, Nkenyereye L, Jha S, Prashar D, Joshi GP, et al. Medical diagnostic systems using artificial intelligence (ai) algorithms: Principles and perspectives. Ieee Access 2020;8:228049–69. 10.1109/ACCESS.2020.3042273 [ DOI ] [ Google Scholar ] [15]. Bobkov YV, Walker III WB, Cattaneo AM. Altered functional properties of the codling moth Orco mutagenized in the intracellular loop-3. Scientific reports 2021;11:3893. 10.1038/s41598-021-83024-3 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [16]. Ahmad M, Saeed MU, Hafeez M, Cheema SM, Pervaiz J. Pulmonary Tuberculosis and COVID-19 Co-infections in Lahore, Pakistan: A retrospective cohort study: Pulmonary Tuberculosis and COVID-19 Co-infections. Electronic Journal of Medical Research 2025;1:45–53. 10.64813/ejmr.2025.003 [ DOI ] [ Google Scholar ] [17]. Chaudhary SRA, Singh KKB, Rabaan AA. Clinicopathological presentation of COVID-19 patients presented at the rural healthcare center: Clinicopathological presentation of COVID-19 patients. Electronic Journal of Medical Research 2025;1:54–60. 10.64813/ejmr.2025.011 [ DOI ] [ Google Scholar ] [18]. Karako K, Song P, Chen Y, Tang W. New possibilities for medical support systems utilizing artificial intelligence (AI) and data platforms. BioScience Trends 2023;17:186–9. 10.5582/bst.2023.01138 [ DOI ] [ PubMed ] [ Google Scholar ] [19]. Karimi A, HaddadPajouh H. Artificial intelligence, important assistant of scientists and physicians. Galen Medical Journal 2020;9:e2048. 10.31661/gmj.v9i0.2048 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [20]. Surya L. How government can use AI and ML to identify spreading infectious diseases. International Journal of Creative Research Thoughts (IJCRT), ISSN 2018;6:2320–882. [ Google Scholar ] [21]. Shelke YP, Badge AK, Bankar NJ, Badge A. Applications of artificial intelligence in microbial diagnosis. Cureus 2023;15. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [22]. Liu HY, Hopping GC, Vaidyanathan U, Ronquillo YC, Hoopes PC, Moshirfar M. Polymerase chain reaction and its application in the diagnosis of infectious keratitis. Medical Hypothesis, Discovery and Innovation in Ophthalmology 2019;8:152. [ PMC free article ] [ PubMed ] [ Google Scholar ] [23]. Haramoto E, Kitajima M, Hata A, Torrey JR, Masago Y, Sano D, et al. A review on recent progress in the detection methods and prevalence of human enteric viruses in water. Water research 2018;135:168–86. 10.1016/j.watres.2018.02.004 [ DOI ] [ PubMed ] [ Google Scholar ] [24]. Yousaf A. DNA replication: causes of replication stress and DNA damage response pathways: A review on DNA replication. Electronic Journal of Medical Research 2025;1:8–27. 10.64813/ejmr.2025.008 [ DOI ] [ Google Scholar ] [25]. Hong P, Tan Y. Enhancing personalized medicine through molecular diagnostics: implications for nursing care. Theoretical and Natural Science 2024;37:283–8. 10.54254/2753-8818/37/20240182 [ DOI ] [ Google Scholar ] [26]. Choon YW, Choon YF, Nasarudin NA, Al Jasmi F, Remli MA, Alkayali MH, et al. Artificial intelligence and database for NGS-based diagnosis in rare disease. Frontiers in Genetics 2024;14:1258083. 10.3389/fgene.2023.1258083 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [27]. Park Y, Heider D, Hauschild A-C. Integrative analysis of next-generation sequencing for next-generation cancer research toward artificial intelligence. Cancers 2021;13:3148. 10.3390/cancers13133148 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [28]. Alagarswamy K, Shi W, Boini A, Messaoudi N, Grasso V, Cattabiani T, et al. Should AI-Powered Whole-Genome Sequencing Be Used Routinely for Personalized Decision Support in Surgical Oncology—A Scoping Review. BioMedInformatics 2024;4:1757–72. 10.3390/biomedinformatics4030096 [ DOI ] [ Google Scholar ] [29]. Chauhan AS, Singh R, Priyadarshi N, Twala B, Suthar S, Swami S. Unleashing the power of advanced technologies for revolutionary medical imaging: pioneering the healthcare frontier with artificial intelligence. Discover Artificial Intelligence 2024;4:58. 10.1007/s44163-024-00161-0 [ DOI ] [ Google Scholar ] [30]. Geric C, Qin Z, Denkinger C, Kik S, Marais B, Anjos A, et al. , The rise of artificial intelligence reading of chest X-rays for enhanced TB diagnosis and elimination. The International Journal of Tuberculosis and Lung Disease 2023;27: 367–72. 10.5588/ijtld.22.0687 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [31]. Harris M, Qi A, Jeagal L, Torabi N, Menzies D, Korobitsyn A, et al. , A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis. PloS one 2019;14:e0221339. 10.1371/journal.pone.0221339 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [32]. Wang B, Jin S, Yan Q, Xu H, Luo C, Wei L, et al. AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system. Applied soft computing 2020;98:106897. 10.1016/j.asoc.2020.106897 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [33]. Maturana CR, De Oliveira AD, Nadal S, Bilalli B, Serrat FZ, Soley ME, et al. , Advances and challenges in automated malaria diagnosis using digital microscopy imaging with artificial intelligence tools: A review. Frontiers in microbiology 2022;13:1006659. 10.3389/fmicb.2022.1006659 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [34]. Marletta S, L'Imperio V, Eccher A, Antonini P, Santonicco N, Girolami I, et al. Artificial intelligence-based tools applied to pathological diagnosis of microbiological diseases. Pathology-Research and Practice 2023;243:154362. 10.1016/j.prp.2023.154362 [ DOI ] [ PubMed ] [ Google Scholar ] [35]. Behera B, Irshad A, Rida I, Shabaz M. AI-driven predictive modeling for disease prevention and early detection. SLAS technology 2025;31. [ DOI ] [ PubMed ] [ Google Scholar ] [36]. Rahman SZ, Senthil R, Ramalingam V, Gopal R. Predicting Infectious Disease Outbreaks with Machine Learning and Epidemiological Data. Journal of Advanced Zoology 2023;44:110–21. 10.17762/jaz.v44iS4.2177 [ DOI ] [ Google Scholar ] [37]. Ardabili SF, Mosavi A, Ghamisi P, Ferdinand F, Varkonyi-Koczy AR, Reuter U, et al. , COVID-19 outbreak prediction with machine learning. Algorithms 2020;13:249. 10.3390/a13100249 [ DOI ] [ Google Scholar ] [38]. Kaur I, Sandhu AK, Kumar Y. Artificial intelligence techniques for predictive modeling of vector-borne diseases and its pathogens: a systematic review. Archives of Computational Methods in Engineering 2022;29:3741–71. 10.1007/s11831-022-09724-9 [ DOI ] [ Google Scholar ] [39]. Tripathi A, Rathore R. AI in Disease Surveillance—An Overview of How AI Can Be Used in Disease Surveillance and Outbreak Detection in Real-World Scenarios. AI in Disease Detection: Advancements and Applications 2025:337–59. [ Google Scholar ] [40]. Gao Y, Liu M. Application of machine learning based genome sequence analysis in pathogen identification. Frontiers in Microbiology 2024;15:1474078. 10.3389/fmicb.2024.1474078 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [41]. Srivastava V, Kumar R, Wani MY, Robinson K, Ahmad A. Role of artificial intelligence in early diagnosis and treatment of infectious diseases. Infectious Diseases 2025;57:1–26. 10.1080/23744235.2024.2425712 [ DOI ] [ PubMed ] [ Google Scholar ] [42]. Allami RH, Yousif MG. Integrative AI-driven strategies for advancing precision medicine in infectious diseases and beyond: a novel multidisciplinary approach. arXiv preprint arXiv:230715228 2023. [ Google Scholar ] [43]. Pennisi F, Pinto A, Ricciardi GE, Signorelli C, Gianfredi V. The Role of Artificial Intelligence and Machine Learning Models in Antimicrobial Stewardship in Public Health: A Narrative Review. Antibiotics 2025;14:134. 10.3390/antibiotics14020134 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [44]. de Jong J, Cutcutache I, Page M, Elmoufti S, Dilley C, FrÖhlich H, et al. Towards realizing the vision of precision medicine: AI based prediction of clinical drug response. Brain 2021;144:1738–50. 10.1093/brain/awab108 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [45]. Blanco-Gonzalez A, Cabezon A, Seco-Gonzalez A, Conde-Torres D, Antelo-Riveiro P, Pineiro A, et al. , The role of AI in drug discovery: challenges, opportunities, and strategies. Pharmaceuticals 2023;16:891. 10.3390/ph16060891 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [46]. Khalid K, Poh CL. The promising potential of reverse vaccinology-based next-generation vaccine development over conventional vaccines against antibiotic-resistant bacteria. Vaccines 2023;11:1264. 10.3390/vaccines11071264 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [47]. Eissa M. AI-based discovery of a new class of antibiotics: a minireview on implications, challenges, and opportunities for combating antibiotic resistance. Journal of Medical Research and Reviews 2024. [ Google Scholar ] [48]. Gawande MS, Zade N, Kumar P, Gundewar S, Weerarathna IN, Verma P. The role of artificial intelligence in pandemic responses: from epidemiological modeling to vaccine development. Molecular Biomedicine 2025;6:1. 10.1186/s43556-024-00238-3 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [49]. Mukhopadhyay S, Brylinski M, Bess A, Berglind F, Galliano C, McGrew PF, editors. Deepdrug: Applying ai for the advancement of drug discovery. 2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS). 2022:IEEE. [ Google Scholar ] [50]. Jin W, Stokes JM, Eastman RT, Itkin Z, Zakharov AV, Collins JJ, et al. Deep learning identifies synergistic drug combinations for treating COVID-19. Proceedings of the National Academy of Sciences. 2021;118:e2105070118. 10.1073/pnas.2105070118 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [51]. Karpus J, Krüger A, Verba JT, Bahrami B, Deroy O. Algorithm exploitation: Humans are keen to exploit benevolent AI. Iscience 2021;24. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [52]. Choudhury C, Murugan NA, Priyakumar UD. Structure-based drug repurposing: Traditional and advanced AI/ML-aided methods. Drug discovery today 2022;27:1847–61. 10.1016/j.drudis.2022.03.006 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [53]. Kalil AC, Patterson TF, Mehta AK, Tomashek KM, Wolfe CR, Ghazaryan V, et al. , Baricitinib plus remdesivir for hospitalized adults with Covid-19. New England Journal of Medicine 2021;384:795–807. 10.1056/NEJMoa2031994 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [54]. Smith DP, Oechsle O, Rawling MJ, Savory E, Lacoste AM, Richardson PJ. Expert-augmented computational drug repurposing identified baricitinib as a treatment for COVID-19. Frontiers in pharmacology 2021;12:709856. 10.3389/fphar.2021.709856 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [55]. Anokian E, Bernett J, Freeman A, List M, Santamaría LP, Tanoli Z, et al. Machine Learning and Artificial Intelligence in Drug Repurposing—Challenges and Perspectives. Drug Repurposing 2024;1:20240004. 10.58647/DRUGREPO.24.1.0004 [ DOI ] [ Google Scholar ] [56]. Agnihothri S, Cui L, Delasay M, Rajan B. The value of mHealth for managing chronic conditions. Health care management Science 2020;23:185–202. 10.1007/s10729-018-9458-2 [ DOI ] [ PubMed ] [ Google Scholar ] [57]. Ghozali MT, editor Predicting Patient Adherence in Healthcare using Artificial Intelligence and Machine Learning Techniques: A Narrative Review. 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud)(I-SMAC). 2024:IEEE. [ Google Scholar ] [58]. Aggarwal M, Madhukar M. IBM's Watson analytics for health care: A miracle made true. Cloud Computing Systems and Applications in Healthcare 2016:117–34. [ Google Scholar ] [59]. Willard J, Golchi S, Moodie EE, Boulanger B, Carlin BP. Bayesian optimization for personalized dose-finding trials with combination therapies. Journal of the Royal Statistical Society Series C: Applied Statistics 2025;74:373–90. 10.1093/jrsssc/qlae058 [ DOI ] [ Google Scholar ] [60]. Sah AK, Elshaikh RH, Shalabi MG, Abbas AM, Prabhakar PK, Babker AM, et al. , Role of artificial intelligence and personalized medicine in enhancing hiv management and treatment outcomes. Life 2025;15:745. 10.3390/life15050745 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [61]. Butt ZA. Big data and artificial intelligence for pandemic preparedness. Artificial Intelligence, Big Data, Blockchain and 5G for the Digital Transformation of the Healthcare Industry: Elsevier. 2024. p. 403–18. [ Google Scholar ] [62]. Wongpituk K, Laosupap K, Butsorn A, Boonsang A, Thammaboribal P, Chankong W, et al. , Advancements in Disease Surveillance: The Role of GIS in Global Health Preparedness. International Journal of Geoinformatics 2024;20. [ Google Scholar ] [63]. Allam Z. The rise of machine intelligence in the COVID-19 pandemic and its impact on health policy. Surveying the COVID-19 Pandemic and its Implications 2020:89. [ Google Scholar ] [64]. Chowdhury AT, Newaz M, Saha P, Pedersen S, Khan MS, Chowdhury ME. Use of Artificial Intelligence in the Surveillance of Seasonal Respiratory Infections. Surveillance, Prevention, and Control of Infectious Diseases: An AI Perspective 2024:219–37. [ Google Scholar ] [65]. Ananya, Panchariya DC, Karthic A, Singh SP, Mani A, Chawade A, et al. Vaccine design and development: exploring the interface with computational biology and AI. International Reviews of Immunology 2024;43:361–80. 10.1080/08830185.2024.2374546 [ DOI ] [ PubMed ] [ Google Scholar ] [66]. Bhakta S, Choudhury S, Paul J, Bhattacharya A. Vaccine Development Through Reverse Vaccinology Using Artificial Intelligence and Machine Learning Approach. COVID-19: Tackling Global Pandemics through Scientific and Social Tools: Elsevier. 2022. p. 33–49. [ Google Scholar ] [67]. Liang B, Zhu Y, Shi W, Ni C, Tan B, Tang S. SARS-CoV-2 spike protein post-translational modification landscape and its impact on protein structure and function via computational prediction. Research 2023;6:0078. 10.34133/research.0078 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [68]. Saldanha L, Langel U, Vale N. In silico studies to support vaccine development. Pharmaceutics 2023;15:654. 10.3390/pharmaceutics15020654 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [69]. Addy A. Artificial intelligence in the supply chain management for vaccine distribution in the West Africa n healthcare sector with a focus on Ghana. Int J Legal Sci Innovation 2023;10. [ Google Scholar ] [70]. Musa SM, Haruna UA, Aliyu LJ, Zubairu M, Lucero-Prisno III DE. Leveraging AI to optimize vaccines supply chain and logistics in Africa: opportunities and challenges. Frontiers in Pharmacology 2025;16:1531141. 10.3389/fphar.2025.1531141 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [71]. Cosma C, Radi A, Cattano R, Zanobini P, Bonaccorsi G, Lorini C, et al. , Exploring Chatbot contributions to enhancing vaccine literacy and uptake: A scoping review of the literature. Vaccine 2025;44:126559. 10.1016/j.vaccine.2024.126559 [ DOI ] [ PubMed ] [ Google Scholar ] [72]. Kik SV, Gelaw SM, Ruhwald M, Song R, Khan FA, van Hest R, et al. , Diagnostic accuracy of chest X-ray interpretation for tuberculosis by three artificial intelligence-based software in a screening use-case: an individual patient meta-analysis of global data. medRxiv 2022:2022.01.24.22269730. [ Google Scholar ] [73]. Andigema AS, Cyrielle NNT, Ekwelle E. Artificial Intelligence in African Healthcare: Catalyzing Innovation While Confronting Structural Challenges. Preprints 2025. [ Google Scholar ] [74]. Williams TG, Snell LB, Alder C, Charalampous T, Alcolea-Medina A, Sehmi JK, et al. , Feasibility and clinical utility of local rapid Nanopore influenza A virus whole genome sequencing for integrated outbreak management, genotypic resistance detection and timely surveillance. Microbial Genomics 2023;9:001083. [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [75]. Ali H. AI for pandemic preparedness and infectious disease surveillance: predicting outbreaks, modeling transmission, and optimizing public health interventions. Int J Res Publ Rev 2024;5:4605–19. 10.55248/gengpi.5.0124.0337 [ DOI ] [ Google Scholar ] [76]. Schwalbe N, Wahl B. Artificial intelligence and the future of global health. The Lancet 2020;395:1579–86. 10.1016/S0140-6736(20)30226-9 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [77]. Zeng D, Cao Z, Neill DB. Artificial intelligence–enabled public health surveillance—from local detection to global epidemic monitoring and control. Artif Intell Med: Elsevier. 2021. p. 437–53. [ Google Scholar ] [78]. Payedimarri AB, Concina D, Portinale L, Canonico M, Seys D, Vanhaecht K, et al. , Prediction models for public health containment measures on COVID-19 using artificial intelligence and machine learning: a systematic review. International journal of environmental research and public health 2021;18:4499. 10.3390/ijerph18094499 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [79]. Duarte T, editor Google and Apple Exposure Notifications System: Exposure Notifications or Notified Exposures? Annual Privacy Forum. 2022:Springer. [ Google Scholar ] [80]. Qureshi MS, Qureshi MB, Iqrar U, Raza A, Ghadi YY, Innab N, et al. , AI based predictive acceptability model for effective vaccine delivery in healthcare systems. Scientific Reports 2024;14:26657. 10.1038/s41598-024-76891-z [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [81]. Subramanian H, Sengupta A, Xu Y. Patient health record protection beyond the health insurance portability and accountability Act: mixed methods study. Journal of Medical Internet Research 2024;26:e59674. 10.2196/59674 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [82]. Kubanek M, Szymoniak S. Ethical challenges in AI integration: a comprehensive review of bias, privacy, and accountability issues. The Leading Role of Smart Ethics in the Digital World 2024:75–85. [ Google Scholar ] [83]. Patil D. Ethical Challenges in Industrial Artificial Intelligence Applications: Bias, Privacy, And Accountability. Privacy, And Accountability (November 18, 2024) 2024. [ Google Scholar ] [84]. Ford RA, Price W, Nicholson I. Privacy and accountability in black-box medicine. Mich Telecomm & Tech L Rev 2016;23:1. [ Google Scholar ] [85]. Singhal A, Neveditsin N, Tanveer H, Mago V. Toward fairness, accountability, transparency, and ethics in AI for social media and health care: scoping review. JMIR Medical Informatics 2024;12:e50048. 10.2196/50048 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [86]. Hashemi M, Darejeh A, Cruz F. Understanding User Preferences in Explainable Artificial Intelligence: A Mapping Function Proposal. ACM Transactions on Intelligent Systems and Technology 2025;16:1–37. 10.1145/3733837 [ DOI ] [ Google Scholar ] [87]. Memish ZA, Altuwaijri MM, Almoeen AH, Enani SM. The Saudi Data & Artificial Intelligence Authority (SDAIA) vision: leading the kingdom's journey toward global leadership. Journal of epidemiology and global health 2021;11:140–2. 10.2991/jegh.k.210405.001 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [88]. Aljerian N, Arafat M, Aldhubib A, Almohaimeed I, Alsultan A, Alhosaini A, et al. , Artificial intelligence in health care and its application in Saudi Arabia. Int J Innov Res Med Sci 2022;7. [ Google Scholar ] [89]. Yin X, Zhu Y, Hu J. A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions. ACM Computing Surveys (CSUR) 2021;54:1–36. 10.1145/3460427 [ DOI ] [ Google Scholar ] [90]. Orthi SM, Rahman MH, Siddiqa KB, Uddin M, Hossain S, Al Mamun A, et al. , Federated learning with privacy-preserving big data analytics for distributed healthcare systems. Journal of computer science and technology studies 2025;7:269–81. 10.32996/jcsts.2025.7.8.31 [ DOI ] [ Google Scholar ] [91]. Chen J, Yan H, Liu Z, Zhang M, Xiong H, Yu S. When federated learning meets privacy-preserving computation. ACM Computing Surveys 2024;56:1–36. [ Google Scholar ] [92]. Hasan MM. Federated Learning Models for Privacy-Preserving AI In Enterprise Decision Systems. International Journal of Business and Economics Insights 2025;5:238–69. 10.63125/ry033286 [ DOI ] [ Google Scholar ] [93]. Reddy KS, Kethan M, Basha SM, Singh A, Kumar P, Ashalatha D, editors. Ethical and Legal Implications of AI on Business and Employment: Privacy, Bias, and Accountability. 2024 International Conference on Knowledge Engineering and Communication Systems (ICKECS). 2024:IEEE. [ Google Scholar ] [94]. Drake AL, Unger JA, Ronen K, Matemo D, Perrier T, DeRenzi B, et al. Evaluation of mHealth strategies to optimize adherence and efficacy of Option B+ prevention of mother-to-child HIV transmission: Rationale, design and methods of a 3-armed randomized controlled trial. Contemporary clinical trials 2017;57:44–50. 10.1016/j.cct.2017.03.007 [ DOI ] [ PMC free article ] [ PubMed ] [ Google Scholar ] [95]. Aravazhi PS, Gunasekaran P, Benjamin NZY, Thai A, Chandrasekar KK, Kolanu ND, et al. , The integration of artificial intelligence into clinical medicine: trends, challenges, and future directions. Disease-a-Month 2025:101882. [ DOI ] [ PubMed ] [ Google Scholar ] Articles from Saudi Medical Journal are provided here courtesy of Saudi Medical Journal ACTIONS View on publisher site PDF (7.2 MB) Cite Collections Permalink RESOURCES Similar articles Cited by other articles Links to NCBI Databases Follow NCBI NCBI on X (formerly known as Twitter) NCBI on Facebook NCBI on LinkedIn NCBI on GitHub NCBI RSS feed Connect with NLM NLM on X (formerly known as Twitter) NLM on Facebook NLM on YouTube National Library of Medicine 8600 Rockville Pike Bethesda, MD 20894 Web Policies FOIA HHS Vulnerability Disclosure Help Accessibility Careers NLM NIH HHS USA.gov Back to Top

Related documents

• Artificial intelligence for tuberculosis management in Africa: opportunities, challenges, and implementation.#258209
• Developing a Risk Assessment System of Multidrug-resistant Organisms Infection#141034
• The Role of Electronic Medical Record Systems and Pharmacovigilance Databases in the Surveillance of Antimicrobial Use and Resistance in Low- and Middle-Income Countries: Protocol for a Multistudy Project.#143217
• Evaluation of the American Thoracic Society Criteria for Predicting Multidrug-resistant Bacteria in Critically Ill Patients#160385
• Mastering Hospital Antimicrobial Resistance and Its Spread Into the Community#146230