Papers using MEDS

A Theoretical Framework for Understanding and Building"Any-task inference"Capable Foundation Models

Matthew B. A. McDermott, Florent Pollet, Payal Chandak, Gregory Kondas, Liat Antwarg, Noa Dagan et al.

2026

• 
  Columbia University
• 
  Harvard University
• 
  Clalit Health Services

MedJev: Evaluating Zero-Shot System-One Decision Making in Medicine

Simon A. Lee, Jia-Hang Sha, Moonseong Jeong, Yu Pan, Jeffrey N. Chiang

2026

• 
  University of California, Los Angeles
• 
  UCLA Health

Sequence Composition in EHR Foundation Model Pretraining

J. Placidi, Inigo Stibbe, A. Balston, Marek Rei, A. Faisal

2026

• 
  Imperial College London

Cross-continental generalizability of EHR foundation model: predicting length of stay in an Italian hospital using US-trained embeddings

G. Nicora, Francesca Negri, V. Tibollo, A. Malovini, A. Dagliati, L. Sacchi et al.

Frontiers in Digital Health · 2026

• 
  University of Pavia
• 
  Istituti Clinici Scientifici Maugeri

Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer

Qing-Yang Zhang

2026

• 
  Carnegie Mellon University

Expert-defined features remain competitive with foundation models in predicting Crohn’s-like disease of the pouch

J. Schmid, S. Ibing, Stefan Kalabakov, Katharina Alefs, R. P. van de Water, Arkadiusz Kwasigroch et al.

Scientific Reports · 2026

• 
  University of Potsdam
• 
  Charité – Universitätsmedizin Berlin
• 
  Icahn School of Medicine at Mount Sinai

EHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents

Xin-Ye Yang, Yu-Li Wang, Cheng-Ting Lin, Harrison X. Bai

arXiv · 2026

• 
  University of Colorado Anschutz
• 
  Johns Hopkins University
• 
  Johns Hopkins Medicine

Rethinking How We Evaluate Methodological Progress in Health AI

Florent Pollet, Matthew B. A. McDermott

arXiv · 2026

• 
  Columbia University

Digital Twins and Offline Reinforcement Learning for Mechanical Circulatory Support Decisions: What the Current Evidence Can and Cannot Support

O. Li, Yi-Jiang Li, Su-Jing Li

Cureus · 2026

• A
  Active Care and Education in Sports and Outreach (ACESO) Foundation

World models for biomedicine.

Ayush Noori, N. Fishman, Ada Fang, Lukas Fesser, M. Zitnik

Cell · 2026

• 
  Harvard University
• 
  University of Oxford
• 
  Broad Institute

DBToken: A Database Tokenizer for Medical Event Foundation Models

I. Shin, K. McCann, G. Marino, U. T. Siam, H. Li, E. Stutz et al.

medRxiv · 2026

• 
  Yale University
• 
  VA Connecticut Healthcare System

Forecasting Patient Trajectories from the Electronic Health Records with Action-Conditioned World Models

Simon A. Lee, Jia-Hang Sha, Soomin Chung, Kai Akamatsu, E. Halperin, Jeffrey N. Chiang

2026

• 
  University of California, Los Angeles
• 
  New York University
• 
  UCLA Health

Forecasting laboratory measurements from longitudinal electronic health records

F. Firoozbakht, J. Baumabach

medRxiv · 2026

• 
  Universität Hamburg
• 
  University of Southern Denmark

Longitudinal Clinical Foundation Models Augmented with Genomics for Early Detection and Risk Stratification of Inherited Cardiomyopathy

A. Zolensky, Colleen M. Kripke, Karl Keat, S. Damrauer, M. Levin, A. Verma

medRxiv · 2026

• 
  University of Pennsylvania

PORT: Generative EHR Pretraining for Pediatric Intraoperative Risk Prediction

Junseob Kim, Hao-Min Shi, Michael C. Fiedorek, Hannah D. Kilday, Henry P. Foote, C. Hornik et al.

Research Square · 2026

• 
  Duke University
• 
  Children's Healthcare of Atlanta
• 
  Duke Medical Center

OneEHR: Reproducible and AI Agent-Ready Longitudinal EHR Analysis Toolkit

Ying-Hao Zhu, Zi-Xiang Wang, Lei Gu, De-Hao Sui, Ya-Sha Wang, Ewen M. Harrison et al.

Knowledge Discovery and Data Mining · 2026

• 
  Peking University
• 
  University of Hong Kong
• 
  University of Edinburgh
• 
  Nanjing University
• 
  Health Data Research UK

Continuous Value Tokenization Improves Medical Event Foundation Models

K. McCann, I. Shin, Huan Li, D. White, E. Melnick, M. Iscoe et al.

medRxiv · 2026

• 
  Yale University
• 
  Epic Systems (United States)
• 
  Yale New Haven Health System

Autoregressive EHR Foundation Models with Multimodal Inputs

Yuxuan Liu, J. Placidi, Jinpei Han, A. Balston, Marek Rei, A. Faisal

arXiv · 2026

• 
  Imperial College London

LLM4EHR: Aligning Clinical Time Series with Medical Event Sequences via Large Language Models

Jing-Teng Li, A. Capstick, Louise Rigny, Iona Biggart, N. Sebire, P. Barnaghi

arXiv · 2026

• 
  Great Ormond Street Hospital
• 
  University College London
• 
  UK Dementia Research Institute
• 
  Imperial College London

How Should Transformers Encode Numeric Values in Electronic Health Records?

M. E. Montgomery, C. Igel, Mikkel Odgaard, Martin Sillesen, Mads Nielsen

arXiv · 2026

• 
  University of Copenhagen
• C
  Copenhagen University Hospital

The Verbose Context Problem in Medical Records

Shiva Kaul, Min-Gyu Kim, A. Khurshid, Sriram Vishwanath

arXiv · 2026

• 
  Ajou University
• 
  Harvard University
• 
  Harvard Pilgrim Health Care
• 
  Georgia Institute of Technology

PORTER: Language-Grounded Event Representations for Portable Structured EHR Foundation Models

L. Guo, A. P. Yan, E. Vettese, Lillian Sung

arXiv · 2026

• 
  Hospital for Sick Children

VISTA Architect: A graph database-oriented health AI system demonstrated in multidisciplinary tumor boards

T. Kiiskinen, J. A. Fries, P. Adamson, David J. H. Wu, T. Ellis-Caleo, A. Fanous et al.

arXiv · 2026

• 
  Stanford University

A multimodal generative model for structured and unstructured electronic health records

Sonish Sivarajkumar, Hang Zhang, Yuelyu Ji, Maneesh Bilalpur, Xi-Zhi Wu, Chen-Yu Li et al.

npj Health Systems · 2026

• 
  University of Pittsburgh
• 
  University of Pittsburgh Medical Center

Accelerating Reproducible Research in Synthetic EHR Generation

Jalen Jiang, Chu-Fan Gao, E. Rasmussen, Stephen Z. Xie, Ji-Meng Sun

arXiv · 2026

• 
  University of Illinois Urbana-Champaign

AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models

Yuanyu Zhang, Shi Li

arXiv · 2026

• 
  Chinese Academy of Sciences
• 
  Columbia University

Croissant Baker: Metadata Generation for Discoverable, Governable, and Reusable ML Datasets

Rafi Al Attrach, Rajna Fani, Sebastian Lobentanzer, J. Giner-Miguelez, Debanshu Das, K. VaruniH et al.

arXiv · 2026

• 
  Technical University of Munich
• 
  Massachusetts Institute of Technology
• 
  Helmholtz Munich
• 
  Barcelona Supercomputing Center
• 
  University of Maryland, Baltimore County
• 
  Nutanix (United States)
• 
  Sage Bionetworks
• 
  University of Göttingen
• 
  Harvard University
• 
  Bayer (Germany)
• 
  Eindhoven University of Technology
• 
  Massachusetts General Hospital
• 
  Columbia University

EHR-RAGp: Prototype-Guided Retrieval of Longitudinal Electronic Health Records for Clinical Prediction Models

Saeed Shurrab, M. Alomari, Dana El Samad, Farah E. Shamout

2026

• 
  New York University

From Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical Prediction

Mingcheng Zhu, Zhi-Yao Luo, Yu Liu, Tingting Zhu

arXiv · 2026

• 
  University of Oxford

WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records

R. Dong, Yuanyu Zhang, Shi Li

arXiv · 2026

• 
  Chinese Academy of Sciences
• 
  Columbia University

Event Fields: Learning Latent Event Structure for Waveform Foundation Models

Li Na, Yuanyu Zhang, Shi Li

arXiv · 2026

• 
  Chinese Academy of Sciences
• 
  Columbia University

Representation Before Training: A Practical Benchmark for Generative Medical Event Model Tokenization

Inhyeok Lee, Luke Solo, Michael C. Burkhart, B. Ramadan, Sahil Sethi, Sarah Jabbour et al.

2026

• 
  University of Chicago

Uncertainty-Aware Foundation Models for Clinical Data

Qian Zhou, Yuanyu Zhang, Shi Li

arXiv · 2026

• 
  Chinese Academy of Sciences
• 
  Columbia University

Discriminative Representation Learning for Clinical Prediction

Yang Zhang, Lianyi Fan, Sam Lawrence, Shi Li

arXiv · 2026

• 
  University of Hong Kong
• 
  Columbia University

EveryQuery: A Promptable Foundation Model for Clinical Prediction Tasks over Electronic Health Records

Payal Chandak, Gregory Kondas, Liat Antwarg Friedman, I. Kohane, Matthew B. A. McDermott

2026

• 
  Harvard–MIT Division of Health Sciences and Technology
• 
  Columbia University
• 
  Harvard University

Learning Clinical Representations Under Systematic Distribution Shift

Yuanyu Zhang, Shi Li

arXiv · 2026

• 
  Chinese Academy of Sciences
• 
  Columbia University

Tokenization Tradeoffs in Structured EHR Foundation Models

L. Guo, S. Arciniegas, Joseph Lee, A. P. Yan, G. Tomlinson, J. A. Fries et al.

arXiv · 2026

• 
  Hospital for Sick Children
• 
  University Health Network

Dense Feature Learning via Linear Structure Preservation in Medical Data

Yuanyu Zhang, Mingxuan Zhang, Si-Yuan Li, Zihan Wang, Hao-Ran Chen, Wenbo Zhou et al.

arXiv · 2026

• 
  Chinese University of Hong Kong
• 
  Columbia University

EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation

Lang Cao, Qing-Yu Chen, Yue Guo

arXiv · 2026

• 
  University of Illinois Urbana-Champaign
• 
  Yale University

TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins

Nikita Makarov, Maria Bordukova, Lena Voith von Voithenberg, Estrella Pivel-Villanueva, Sabrina Mielke, Jonathan Wickes et al.

arXiv · 2026

• 
  F. Hoffmann-La Roche AG
• 
  Stanford University
• 
  New York University

Developing a multi-domain EHR foundation model for predicting Hepatitis B liver disease: a clinical perspective

C. Weis, F. Grazioli, G. Visonà, A. Kania, M. Burg, M. Horn et al.

medRxiv · 2026

• 
  GSK plc

PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning

John Wu, Yong Fan, Zhenbang Wu, Paul Landes, Eric Schrock, Sayeed Sajjad Razin et al.

arXiv · 2026

• 
  University of Illinois Urbana-Champaign
• 
  University of Illinois Chicago
• 
  Bangladesh University of Engineering and Technology
• 
  Health Data Research UK
• 
  University of Edinburgh

Large language models improve transferability of electronic health record-based predictions across countries and coding systems

M. Kirchler, M. Ferro, Veronica Lorenzini, R. P. van de Water, FinnGen, C. Lippert et al.

npj Digital Medicine · 2026

• 
  University of Helsinki
• 
  University of Potsdam
• 
  Icahn School of Medicine at Mount Sinai
• 
  Massachusetts General Hospital

Clinically-guided models or foundation models? predicting cervical spondylotic myelopathy from electronic health records

S. Yakdan, Benjamin C. Warner, Z. Ghogawala, Wilson Z. Ray, M. Bydon, M. Steinmetz et al.

npj Digital Medicine · 2026

• 
  Washington University in St. Louis
• 
  Tufts University
• 
  University of Chicago
• 
  Cleveland Clinic
• 
  University of Missouri

Learning Longitudinal Health Representations from EHR and Wearable Data

Yuanyu Zhang, Han Zhou, Li Feng, Yilin Hong, Shi Li

arXiv · 2026

• 
  Chinese Academy of Sciences
• 
  Columbia University

Clinical Data Goes MEDS? Let's OWL make sense of it

A. Marfoglia, J. Jhee, Adrien Coulet

arXiv · 2026

• 
  Inria
• 
  Inserm
• 
  Université Paris Cité
• 
  University of Bologna

Benchmark to bedside: Building modular multimodal machine learning infrastructure for healthcare at scale

Robin P. van de Water

PhD thesis, University of Potsdam · 2026

• 
  University of Potsdam

Sparse Foundation Models for Continous-Time EHRs

William Ferrel, Timothy S. Chang, Samuel Lawrence

Research Square · 2026

• 
  Carnegie Mellon University
• 
  Columbia University

Coefficient of Variation Masking: A Volatility-Aware Strategy for EHR Foundation Models

Rajna Fani, Rafi Al Attrach, David Restrepo, Yu-Gang Jia, L. Celi, P. Schüffler

arXiv · 2025

• 
  Massachusetts Institute of Technology
• 
  Technical University of Munich
• 
  Université Paris-Saclay

Rethinking Tokenization for Clinical Time Series: When Less is More

Rafi Al Attrach, Rajna Fani, David Restrepo, Yu-Gang Jia, P. Schüffler

arXiv · 2025

• 
  Technical University of Munich
• 
  Université Paris-Saclay
• 
  Massachusetts Institute of Technology

TempoQL: A Readable, Precise, and Portable Query System for Electronic Health Record Data

Ziyong Ma, R. Boyce, Adam Perer, Venkatesh Sivaraman

arXiv · 2025

• 
  Carnegie Mellon University
• 
  University of Pittsburgh

HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series

Simon A. Lee, Cyrus Tanade, Hao Zhou, Juhyeon Lee, Megha Thukral, Minji Han et al.

arXiv · 2025

• 
  Samsung Research America
• 
  University of California, Los Angeles

BONSAI: A framework for processing and analysing Electronic Health Records (EHR) data using transformer-based models

M. E. Montgomery, K. Klein, Mikkel Odgaard, Stephan Sloth Lorenzen, Zahra Sobhaninia

Journal of Open Source Software · 2025

• 
  University of Copenhagen

Learning-To-Measure: In-context Active Feature Acquisition

Y. Kobayashi, Zi-Lin Jing, Jiayu Yao, Hongseok Namkoong, Shalmali Joshi

arXiv · 2025

• 
  Columbia University

Serialized EHR make for good text representations

Zhirong Chou, Quan Qin, Shi Li

arXiv · 2025

• 
  Southern University of Science and Technology
• 
  Columbia University

EMR-AGENT: Automating Cohort and Feature Extraction from EMR Databases

Kwanhyung Lee, S. Hong, Joonhyung Park, J. Lim, Juhwan Choi, Donghwee Yoon et al.

arXiv · 2025

• 
  Korea Advanced Institute of Science and Technology

Predicting Hospital Admissions Using Pretrained EHR Embeddings: External Evaluation and Insights on Local Vocabulary Adaptation

B. Neves, J. Cerejo, S. Gonçalves, I. Mota, J. Moreira, N. Silva et al.

medRxiv · 2025

• 
  Hospital da Luz
• 
  Stanford University
• 
  University of Lisbon

CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records

Chao Pang, Jiheum Park, Xin-Zhuo Jiang, N. Pavinkurve, Krishna S. Kalluri, Shalmali Joshi et al.

arXiv · 2025

• 
  Columbia University Irving Medical Center

Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing

Eunbyeol Cho, Jiyoun Kim, Minjae Lee, Sungjin Park, Edward Choi

Neural Information Processing Systems · 2025

• 
  Korea Advanced Institute of Science and Technology

PMOA-TTS: Introducing the PubMed Open Access Textual Times Series Corpus

Shahriar Noroozizadeh, Sayantan Kumar, George H. Chen, Jeremy C. Weiss

arXiv · 2025

• 
  Carnegie Mellon University
• 
  National Institutes of Health

FoMoH: A clinically meaningful foundation model evaluation for structured electronic health records

Chao Pang, V. Jeanselme, Young-Sang Choi, Xin-Zhuo Jiang, Zi-Lin Jing, Aparajita Kashyap et al.

arXiv · 2025

• 
  Columbia University

Temporal Entailment Pretraining for Clinical Language Models over EHR Data

Tatsunori Tanaka, Fi Zheng, Kai Sato, Zhifeng Li, Yuanyu Zhang, Shi Li

arXiv · 2025

A Case Study Exploring the Current Landscape of Synthetic Medical Record Generation with Commercial LLMs

Yihan Lin, Zhi-Rong Yu, Simon A. Lee

ACM Conference on Health, Inference, and Learning · 2025

• 
  University of California, Los Angeles

ChronoFormer: Time-Aware Transformer Architectures for Structured Clinical Event Modeling

Yuanyu Zhang, Shi Li

arXiv · 2025

• 
  Chinese Academy of Sciences
• 
  Columbia University

Clinical ModernBERT: An efficient and long context encoder for biomedical text

Simon A. Lee, A. Wu, Jeffrey N. Chiang

arXiv · 2025

• 
  University of California, Los Angeles

A Collection of Innovations in Medical AI for patient records in 2024

Yuanyu Zhang, Shi Li

arXiv · 2025

• 
  Chinese Academy of Sciences
• 
  Columbia University

Large language models are powerful electronic health record encoders

Stefan Hegselmann, Georg von Arnim, Tillmann Rheude, Noel Kronenberg, David A. Sontag, G. Hindricks et al.

npj Digital Medicine · 2025

• 
  Charité – Universitätsmedizin Berlin
• 
  Freie Universität Berlin
• 
  Massachusetts Institute of Technology
• 
  Fudan University

Foundation model of electronic medical records for adaptive risk estimation

Pawel Renc, Michal K. Grzeszczyk, Nassim Oufattole, Deirdre Goode, Yugang Jia, S. Biegański et al.

GigaScience · 2025

• 
  Harvard University
• 
  Massachusetts General Hospital
• 
  AGH University of Krakow
• 
  Massachusetts Institute of Technology
• 
  Newton Wellesley Hospital
• 
  Medical University of Lodz
• 
  Columbia University
• 
  Brigham and Women's Hospital

EHRs Enable Robust Lung Cancer Risk Stratification with Transformer-based Models: A Retrospective Multi-center Validation Study

Eduardo Alonso, Naroa Mendez, Teresa García-Navarro, Eunate Arana-Arri, Jon Eneko Idoyaga Uribarrena, Miguel Giraldez-Álvarez et al.

Research Square · 2025

• 
  Vicomtech
• 
  Osakidetza
• 
  Instituto de Biomedicina de Sevilla
• 
  Hospital Universitario Virgen Macarena
• 
  Centre Hospitalier Universitaire de Liège
• 
  University of Ulster
• 
  University of the Basque Country

Mind the data gap: Missingness Still Shapes Large Language Model Prognoses

Y. Kobayashi, V. Jeanselme, Shalmali Joshi

arXiv · 2025

• 
  Columbia University

Resilient Systems for Capturing Tacit Knowledge: The next generation of healthcare foundation models

J. A. Fries