Anton Alyakin medical student and ai scientist

Status Quo
I am a medical student at Washington University in Saint Louis School of Medicine. I am currently applying for the 2026 Neurological Surgery Match. My research is in applying statistical and computational approachces to neuroscience, neurosurgery, and medicine at large.
Road So Far
I graduated from Johns Hopkins University with a BS in Computer Science in May 2019 and an MSE in Applied Mathematics & Statistics in December 2019. While a student there I was fortunate to be advised by Suchi Saria and Avanti Athreya. During my gap year I worked as an Assistant Research Engineer at my alma mater’s Department of Applied Mathematics & Statistics. I was a part of the NeuroData lab and primarily worked with Carey Priebe on various problems in statistical graph inference and with Joshua Vogelstein on causal inference from observational health data.
I started medical school at WashU in 2021. In 2024, I took a research gap year during which I was a CNS AI fellow at NYU OLAB under the supervision of Dr. Eric Oermann. I was co-advised by Dr. Eric Leuthardt at my home institution. During that time I worked on intersections of vision-language models with neurosurgery.
Research Interests
I have worked on various topics spanning connectome statistics, causal decision support, clinical artificial intelligence, and computational safety. Some notable papers are listed below.
Connectome Statistics
- Valid Two-Sample Graph Testing via Optimal Transport Procrustes and Multiscale Graph Correlation with Applications in Connectomics (Stat, 2021)
- Correcting a Nonparametric Two-sample Graph Hypothesis Test for Graphs with Different Numbers of Vertices with Applications to Connectomics (Applied Network Science, 2024)
Causal Decision Support
- Using Machine Learning for Early Prediction of Cardiogenic Shock in Patients with Acute Heart Failure (Journal of the Society for Cardiovascular Angiography & Interventions, 2022)
- Exploration of Residual Confounding in Analyses of Associations of Metformin Use and Outcomes in Adults With Type 2 Diabetes (JAMA Network Open, 2022)
- Clinical Prediction for Surgical versus Nonsurgical Interventions in Patients with Vertebral Osteomyelitis and Discitis (Journal of Spine Surgery, 2024)
Clinical Artificial Intelligence
- CNS-CLIP: Transforming a Neurosurgical Journal into a Multimodal Medical Model (Neurosurgery, 2025)
- MedMobile: A mobile-sized language model with clinical capabilities (BMJ Digital Health and AI, 2025)
- Repurposing the Scientific Literature with Vision-Language Models (preprint, 2025)
Computational Safety
- Medical Large Language Models are Vulnerable to Data-poisoning Attacks (Nature Medicine, 2025)
- Medical Large Language Models are Easily Distracted (preprint, 2025)
- It is Too Many Options: Pitfalls of Multiple-Choice Questions in Generative AI and Medical Education (preprint, 2025)