Skip to main Communities My dashboard Log in Sign up Published April 9, 2026 | Version v1 Publication Open Thinking at the Edge: Neuromorphic Computing's Biomedical Moment Authors/Creators Pendleton, Michael (Editor) 1, 2 Alcoser, Corrina (Project leader) 1, 2 Suttin, Jacqueline (Project manager) 1, 2 Show affiliations 1. The University of Texas at San Antonio 2.
NSCC Description Abstract. Neuromorphic computing — event-driven, spiking neural network (SNN) inference on purpose-built silicon — offers a potentially transformative solution to the power and latency constraints of biomedical edge AI. Recent hardware demonstrations have achieved seizure detection at below 300 μW on wearable platforms, cardiac arrhythmia classification compatible with coin-cell operation, and neuroprosthetic control systems with sub-millisecond latency. Yet not one neuromorphic SNN-based medical device has received regulatory clearance anywhere in the world. This paper provides the first systematic analysis of that gap. We assign technology readiness level (TRL) estimates across three primary clinical domains — epilepsy monitoring (TRL 5–6), cardiac arrhythmia detection (TRL 4–5), and neuroprosthetics (TRL 3–4) — and assess hardware and algorithmic readiness across five dimensions: device variability, long-term stability, patient specificity, benchmark standardisation, and algorithm–hardware co-design. We then identify and characterise five structural regulatory gaps: absence of a cleared neuromorphic predicate; incompatibility of stochastic spike dynamics with deterministic verification standards; failure of the Predetermined Change Control Plan framework to accommodate continuous on-device learning; lack of standardised clinical benchmarks; and insufficient biocompatibility data for novel neuromorphic substrate materials. We propose a phased translational roadmap targeting first-in-human feasibility studies by 2028 and first regulatory clearance by 2030. The roadmap assigns specific actions to chip manufacturers, standards bodies, regulators, and clinical research teams. The analysis concludes with ethical, equity, and data governance considerations relevant to the deployment of adaptive neuromorphic inference in vulnerable patient populations. Keywords: neuromorphic computing, spiking neural networks, medical device regulation, epilepsy, brain-computer interfaces, edge AI, FDA, translational roadmap Files neuromorphic_biomedical.pdf Files (234.2 kB) Name Size Download all neuromorphic_biomedical.pdf md5:7514e83cf0b0e3e748ce867cc43cb944 234.2 kB Preview Download 489 Views 327 Downloads Show more details All versions This version Views Total views 489 489 Downloads Total downloads 327 327 Data volume Total data volume 84.6 MB 84.6 MB More info on how stats are collected.... Versions External resources Indexed in OpenAIRE Communities Keywords and subjects Keywords neuromorphic computing spiking neural networks medical device regulation epilepsy AI FDA Edge AI edge computing translational roadmap MeSH Brain-Computer Interfaces Brain-Computer Interfaces/standards Details DOI DOI Badge DOI 10.5281/zenodo.19478504 Markdown [](https://doi.org/10.5281/zenodo.19478504) reStructuredText .. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.19478504.svg :target: https://doi.org/10.5281/zenodo.19478504 HTML <a href="https://doi.org/10.5281/zenodo.19478504"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.19478504.svg" alt="DOI"></a> Image URL https://zenodo.org/badge/DOI/10.5281/zenodo.19478504.svg Target URL https://doi.org/10.5281/zenodo.19478504 Resource type Publication Publisher Zenodo Languages English Rights License Creative Commons Attribution 4.0 International The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited. Read more Citation Export Technical metadata Created April 13, 2026 Modified April 13, 2026 Jump up About About Policies Infrastructure Principles Projects Roadmap Contact Blog Blog Support Help FAQ Developers REST API OAI-PMH Contribute GitHub Donate Funded by Powered by CERN Data Centre & InvenioRDM Status Privacy policy Cookie policy Terms of Use This site uses cookies. Find out more on how we use cookies Accept all cookies Accept only essential cookies