SaMD & SaaS clinical AI
Audit of cloud-based decision-support, diagnostic, prognostic, triage, RAG/LLM, and multimodal clinical AI systems.
Medical AI Audit · Regulatory-Facing Evidence · Explainable AI · SaMD · On-Device AI · Biomarkers
Biomedical AI researcher and independent AI/ML model auditor for medical applications. I help MedTech, digital health, clinical AI, pharma, and biomedical research teams evaluate whether their models are scientifically valid, reproducible, explainable, bias-aware, and ready for regulatory-facing evidence generation.
I help teams and investors distinguish promising medical AI from models that are not yet reproducible, clinically meaningful, or deployment-ready.
Independent audit, validation, advisory, and seminars available globally in English and Greek - online, onsite, or hybrid.
Postdoctoral Researcher, AI & Biometrics Security
BioML Lab, CODE Research Institute, Universität der Bundeswehr München, Munich, Germany
Affiliated Researcher / Sr. AI Data Scientist
Amsterdam UMC, Amsterdam, The Netherlands
Core theme
Compact, explainable, train-from-scratch AI for low-data medicine - when data are limited, labels are expensive, and massive GPU workflows are not realistic.
Independent AI/ML medical model audit
I provide scientific and technical review of medical AI/ML systems before clinical, regulatory-facing, investor due diligence, or production use. The focus is on evidence quality: data provenance, intended use, leakage, confounding, validation design, calibration, subgroup performance, reproducibility, explainability, deployment assumptions, and lifecycle risks.
I also support angel investors, VC funds, family offices, and corporate innovation teams with independent technical due diligence on medical AI, SaMD, digital health, biomarker, LLM/CDSS, and on-device AI startups.
Audit of cloud-based decision-support, diagnostic, prognostic, triage, RAG/LLM, and multimodal clinical AI systems.
Validation of embedded, low-resource, ultrasound, imaging, wearable, biomarker, and edge-deployed AI models.
Technical evidence-gap review for model documentation, validation claims, and clinical performance reporting.
Independent review of data splits, leakage, confounding, batch effects, metrics, thresholds, XAI, and reproducibility.
Useful AI for small cohorts, rare diseases, ultrasound, omics, biomarkers, and early diagnostic/prognostic tests.
ZACH-ViT, hZACH-ViT, and s-DNNs: compact models designed to be trained, audited, and reproduced without massive compute.
Trustworthy AI for biomedical and biometric high-stakes systems: tabular, imaging, omics, text, video, and multimodal data.
Compact vision transformers for low-data medical imaging, trained from scratch and stress-tested for robustness.
Small neural networks for tabular clinical data, non-invasive tests, biomarkers, and prognostic modeling.
Machine-learning-enhanced clinical scores and non-invasive tests, including MASLD fibrosis applications.
Feature-selection methodology for biomarker discovery, biological signal retrieval, and potential drug-target identification.
ZACH-ViT: compact medical imaging AI.
github.com/Bluesman79/ZACH-ViT
pip install zachvit
Reviewer for International Journal of Computer Vision, Knowledge-Based Systems, Journal of Hepatology, Scientific Reports, CSBJ, IEEE Access, Nutrition & Metabolism, and JMIR.
I am a biomedical AI researcher and consultant working across academia, clinical research, and industry, with more than 10 years of production AI experience in the biomedical domain. My work focuses on compact, explainable, and auditable AI for high-stakes biomedical and biometric systems - from low-data medical imaging and biomarker discovery to diagnostic/prognostic tests, MLE-NITs, and privacy-aware biometric security.
A. Angelakis. arXiv, 2026.
arXiv:2606.00906A. Angelakis, G. De Vito, E.-M. Trifylli, F. Ferrucci. arXiv, 2026.
arXiv:2605.20523A. Angelakis, M. Gomez Barrero. CVPR Workshops / PHAROS AIF-MIH Workshop, accepted, 2026.
arXiv:2604.06099A. Angelakis. arXiv, 2026.
doi.org/10.48550/arXiv.2602.17929A. Angelakis et al. arXiv, 2025.
doi.org/10.48550/arXiv.2510.17650E. Stamatelou, N. Nijland, N. Su, B. G. Loos, A. Angelakis. Scientific Reports, 2026.
doi.org/10.1038/s41598-026-43934-6G. De Vito, F. Ferrucci, A. Angelakis. Knowledge-Based Systems, 2026.
doi.org/10.1016/j.knosys.2026.115486G. De Vito, F. Ferrucci, A. Angelakis. Knowledge-Based Systems, 2025.
doi.org/10.1016/j.knosys.2025.114184Trifylli EM, Angelakis A, et al. World Journal of Gastroenterology, 2025.
doi.org/10.3748/wjg.v31.i22.106937A. Angelakis, I. Soulioti, M. Filippakis. Heliyon, 2023.
doi.org/10.1016/j.heliyon.2023.e20530A. Angelakis, P. Stevenhagen. Acta Arithmetica, 2021.
doi.org/10.4064/aa171025-27-3Education & Seminars
I offer seminar and workshop formats for physicians, residents, clinical researchers, and pharmaceutical partners who need practical, clinically grounded education on responsible AI, multimodal biomedical AI, clinical decision support, and preparation for the agentic AI era in medicine.
From FAIR clinical data and nonlinear diagnostic models to explainable AI, computer vision, LLMs, and safe clinical integration.
Independent, scientifically rigorous AI seminars for collaborating MDs and clinical teams, adapted to oncology, hepatology, radiology, ultrasound, omics, or broader clinical AI literacy.
Email: ath.angelakis@gmail.com
GitHub: @Bluesman79
X: @AthAngelakis
LinkedIn: Athanasios (Thanos) Angelakis
Website: bluesman79.github.io