Bigdata Analysis of Pesticide Poisoning in Rural Worker Using Machine Learning Algorithm

It is in recent times that the working conditions of the rural and farm workers have drawn special attention on account of escalating exposure to toxins like pesticides. Detection and diagnosis of pesticide poisonings at the initial stages become crucial to save the patient at the earliest stage of medical interventions and to forestall longterm complications. Even so, few rural communities still lack access to high-tech equipment and techniques in diagnostics. To resolve this problem, this project introduces a data-driven methodology using Supervised Machine Learning (SML) methods for the efficient and accurate diagnosis of pesticide poisoning using clinical and biochemical markers. The main contribution of this research is the development and application of a systematic methodology called Data Refinement Cycle with Supervised Machine Learning (DRC–SML). This model was created to offer a complete, applicable, and reproducible methodology that directs a Data Science project from start to finish. It consists of phases like data collection, data preprocessing, missing value handling, encoding and scaling, model selection, performance metrics, and preparation for deployment. In contrast to most current methodologies, which only deal with isolated phases of the data pipeline, DRC–SML guarantees an overall workflow that facilitates a smooth transition between the steps and uniform results.