About
I'm a Ph.D. candidate at MIT EECS in the Computational Cardiovascular Research Group, where I build machine learning models for cardiovascular health monitoring from multimodal clinical data — waveform, imaging, text, and EHR. My work centers on self-supervised and representation learning methods for phenotyping, disease prediction, and patient stratification at scale.
Before MIT, I worked in the Trayanova Lab at Johns Hopkins — part-time throughout undergrad, then full-time for a year after graduating — while earning my B.S. and M.S.E. in Biomedical Engineering.
News
- June 2026 MIT jClinic covered MEDS: "Health AI Has a Standards Problem. Researchers Want to Fix It."
- May 2026 Columbia DBMI covered MEDS: "Columbia-Led Team Develops Open-Source Framework to Accelerate Health AI Research."
- May 2026 MEDS is now published in NEJM AI.
- March 2026 MIT News covered our PULSE-HF paper: "Can AI help predict which heart-failure patients will worsen within a year?"
- February 2026 Our paper introducing PULSE-HF, forecasting left ventricular systolic dysfunction with AI, was published in eClinicalMedicine.
- December 2025 Organized ML4H.
- 2025 Started as a Graduate Teaching Fellow for AI in Healthcare at Harvard Medical School.
- December 2024 Attended ML4H as an author and organizer.
- December 2024 Attended NeurIPS and presented work at the Time Series in the Age of Large Models workshop.
- October 2024 Gave a talk at IEEE BSN.
Publications
Journal Articles
Forecasting left ventricular systolic dysfunction in heart failure with artificial intelligence
eClinicalMedicine, 92, 2026
MEDS — An Emerging Data Standard and Ecosystem for Health AI Research
NEJM AI, 3(6), 2026
Agent-based large language model system for extracting structured data from breast cancer synoptic reports: a dual-validation study
JAMIA Open, 9(1), 2026
Predicting intensive care delirium with machine learning: model development and external validation
Anesthesiology, 138(3), 299–311, 2023
Customized gaming system engages young children in reaching and balance training
Journal of Rehabilitation and Assistive Technologies Engineering, 10, 2023
Characterization of the electrophysiologic remodeling of patients with ischemic cardiomyopathy by clinical measurements and computer simulations coupled with machine learning
Frontiers in Physiology, 12, 684149, 2021
Conference Papers
MEDS: Building models and tools in a reproducible health AI ecosystem
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Vol. 2, 6243–6244, 2025
Continuity Contrastive Representations of ECG for Heart Block Detection from Only Lead-I
Machine Learning for Health (ML4H) @ NeurIPS, 130–142, 2024
Heart Block Identification from 12-Lead ECG: Exploring the Generalizability of Self-Supervised AI
IEEE 20th International Conference on Body Sensor Networks (BSN), 1–4, 2024
MEDS-Torch: An ML Pipeline for Inductive Experiments for EHR Medical Foundation Models
NeurIPS Workshop on Time Series in the Age of Large Models, 2024
Preprints
Subtyping with ConCEPT: Contrastive clinical embeddings from patient trajectories
Under review, 2026
Bridging the Diagnostic Gap in Transthyretin Cardiac Amyloidosis (ATTR-CM): Enhancing ATTR-CM Detection at the Time of Heart Failure Diagnosis in Women Through Sex-Specific ATTR Models (SS-ATTR-CMs)
Under review, 2026
Clinical Abstracts & Posters
Longitudinal changes in amyloid burden as assessed by extracellular volume (ECV) on cardiac magnetic resonance (CMR) for patients with transthyretin amyloidosis with cardiomyopathy (ATTR-CM) on tafamidis and contemporary guideline-directed medical therapy
European Society of Cardiology (ESC) Congress, 2026
Novel blood-based biomarkers for transthyretin amyloidosis with cardiomyopathy (ATTR-CM) in patients with heart failure with preserved ejection fraction
European Society of Cardiology (ESC) Congress, 2026
743: Computational Endotypes of ICU Delirium
Critical Care Medicine, 49(1), 368 — SCCM Congress, 2021
27: Machine Learning Prediction of Intensive Care Unit Delirium
Critical Care Medicine, 49(1), 14 — SCCM Congress, 2021
Projects & Tools
A PyTorch-based ML pipeline for inductive experiments for EHR medical foundation models.
The MEDS Decentralized Extensible Validation benchmarking project — establishing reproducibility and comparability in ML for health.
Tools for evaluating MEDS models on electronic health record binary classification tasks.
An easy-to-use Python package for efficient tabularization and featurization of MEDS-format datasets for ML baseline generation.
Tutorial and start-up guide for how the MEDS tools fit together.
Talks
Heart Block Identification from 12-Lead ECG: Exploring the Generalizability of Self-Supervised AI
MEDS-DEV: Baselining MEDS datasets
Deep Learning for Diagnostics
27: Machine Learning Prediction of Intensive Care Unit Delirium
Teaching & Service
Teaching
- Graduate Teaching Fellow, AI in Healthcare I & IIHarvard Medical School · 2025–2026
- Graduate Teaching Assistant, Quantitative Methods for NLPMIT · 2023
- UROP Mentor, Computational Cardiology Research GroupMIT · 2022–present
Service
- Outreach Chair, Machine Learning for Health Symposium (ML4H)June 2026–present
- Outreach Subchair, Machine Learning for Health Symposium (ML4H)July 2025–January 2026
- Demonstrations and Perspectives Subchair, Machine Learning for Health Symposium (ML4H)July 2024–January 2025
- Mentor, Science Club for Girls2025–present
- Conference reviewerML4H, MLHC, NeurIPS TS4H, MICCAI MLLMs
Awards
- Lemelson Presidential Scholar, MIT
- MIT-Sloan University Center for Exemplary Mentoring Scholar
- Star Research Achievement Award, Society of Critical Care Medicine