Developed a novel scalable monitoring framework for LLM juries evaluating LLM output to reduce burden on human clinicians

Co-authored 2 peer-reviewed abstracts accepted to international American Medical Informatics Association (AMIA) 2026 Annual Symposium

1st-author abstract selected for AMIA 2026 poster presentation; 2nd-author abstract accepted for oral presentation.

Selected as a participant for the 2026-2027 Stanford Neuroscience Journal Club [Stanford Medicine, Neurosurgery Department]

Processed electrocorticography data from multiple epilepsy patients; developed a pipeline to analyze data using CEBRA for emotion decoding

Conducted the lab's first test of Consistent EmBeddings of high-dimensional Recordings using Auxiliary variables (CEBRA) on a large-scale dataset (2.25 million timepoints, 600 channels)

Robust Pediatric Ejection Fraction Assessment Enabled Through Segmentation-Conditioned Two-Frame Deep Learning of Simulated Point of Care Echocardiograms

This project developed an AI system to assess heart function in children using just two frames from an echocardiogram, with the goal of making cardiac assessment more reliable with handheld point-of-care ultrasound

Presented clinical AI research poster at “Stanford AIMI Symposium + Summit Series 2026”

Improved performance via model architecture tests, report-level NLP, and data augmentation