Papers

2026

  1. Clinical Note Bloat Reduction for Efficient LLM Use
    Jordan L Cahoon , Chloe Stanwyck , Asad Aali , Rachel Madding , Emma Sun , Yixing Jiang , Renumathy Dhanasekaran , and Emily Alsentzer
    In arXiv preprint arXiv:2604.16364, 2026, 2026
    arXiv Scholar
  2. Clinician input steers frontier AI models toward both accurate and harmful decisions
    Ivan Lopez , Selin S Everett , Bryan J Bunning , April S Liang , Dong Han Yao , Shivam C Vedak , Kameron C Black , Sophie Ostmeier , Stephen P Ma , Emily Alsentzer , Jonathan H Chen , Akshay S Chaudhari , and Eric Horvitz
    In arXiv preprint arXiv:2603.14158, 2026, 2026
    arXiv Scholar
  3. Boards-style benchmarks overestimate prior-chat bias in large language models: a factorial evaluation study
    COC Stanwyck , A Adibi , P Dozie-Nnamah , and E Alsentzer
    medRxiv, 2026.02. 12.26346164, 2026, 2026
    HTML Scholar
  4. MedAgentBrief for Hospital Course Summarization: Safety, Use, and Discharge Documentation Burden
    François Grolleau , April S Liang , Timothy Keyes , Stephen P Ma , Thomas Lew , Tridu R Huynh , Natasha Steele , Philip Chung , Paige Qin , Gowri Chandra , Stephanie F Wang , Evan Mullen , Lauren Carpenter , Mita Hoppenfeld , Matthew Morrin , Baffour A Kyerematen , Nerissa Ambers , Nikesh Kotecha , Emily Alsentzer , Jason Hom , Nigam H Shah , Kevin Schulman , and Jonathan H Chen
    medRxiv, 2026.02. 05.26345607, 2026, 2026
    HTML Scholar
  5. Holistic evaluation of large language models for medical tasks with MedHELM
    Suhana Bedi , Hejie Cui , Miguel Fuentes , Alyssa Unell , Michael Wornow , Juan M Banda , Nikesh Kotecha , Timothy Keyes , Yifan Mai , Mert Oez , Hao Qiu , Shrey Jain , Leonardo Schettini , Mehr Kashyap , Jason Alan Fries , Akshay Swaminathan , Philip Chung , Fateme Nateghi Haredasht , Ivan Lopez , Asad Aali , Gabriel Tse , Ashwin Nayak , Shivam Vedak , Sneha S Jain , Birju Patel , Oluseyi Fayanju , Shreya Shah , Ethan Goh , Dong-han Yao , Brian Soetikno , Eduardo Reis , Sergios Gatidis , Vasu Divi , Robson Capasso , Rachna Saralkar , Chia-Chun Chiang , Jenelle Jindal , Tho Pham , Faraz Ghoddusi , Steven Lin , Albert S Chiou , Hyo Jung Hong , Mohana Roy , Michael F Gensheimer , Hinesh Patel , Kevin Schulman , Dev Dash , Danton Char , Lance Downing , Francois Grolleau , Kameron Black , Bethel Mieso , Aydin Zahedivash , Wen-wai Yim , Harshita Sharma , Tony Lee , Hannah Kirsch , Jennifer Lee , Nerissa Ambers , Carlene Lugtu , Aditya Sharma , Bilal Mawji , Alex Alekseyev , Vicky Zhou , Vikas Kakkar , Jarrod Helzer , Anurang Revri , Yair Bannett , Roxana Daneshjou , Jonathan Chen , Emily Alsentzer , Keith Morse , Nirmal Ravi , Nima Aghaeepour , Vanessa Kennedy , Akshay Chaudhari , Thomas Wang , Sanmi Koyejo , Matthew P Lungren , Eric Horvitz , Percy Liang , Michael A Pfeffer , and Nigam H Shah
    Nature Medicine, 1-9, 2026, 2026
    HTML Scholar
  6. AI-generated data contamination erodes pathological variability and diagnostic reliability
    Hongyu He , Shaowen Xiang , Ye Zhang , Yingtao Zhu , Jin Zhang , Hao Deng , Emily Alsentzer , Yun Liu , Qingyu Chen , Kun-Hsing Yu , Andrew Marshall , Tingting Chen , Srinivas Anumasa , Daniel Ebner , Dean Ho , Kee Yuan Ngiam , Ching-Yu Cheng , and Dianbo Liu
    In arXiv preprint arXiv:2601.12946, 2026, 2026
    arXiv Scholar
  7. Monitoring Deployed AI Systems in Health Care
    Timothy Keyes , Alison Callahan , Abby S Pandya , Nerissa Ambers , Juan M Banda , Miguel Fuentes , Carlene Lugtu , Pranav Masariya , Srikar Nallan , Connor O’Brien , Thomas Wang , Emily Alsentzer , Jonathan H Chen , Dev Dash , Matthew A Eisenberg , Patricia Garcia , Nikesh Kotecha , Anurang Revri , Michael A Pfeffer , Nigam H Shah , and Sneha S Jain
    In ArXiv, arXiv: 2512.09048 v2, 2026, 2026
    arXiv Scholar
  8. Bias and Equity in LLM Applications for Healthcare: A Scoping Review
    Jingchi Liao , Huitao Li , Rui Yang , Sabarinath Vinod Nair , Wentao Zhu , Jonathan Chong Kai Liew , Peiyu Zhang , Mingxuan Liu , Yilin Ning , Kabilan Elangovan , Yu He Ke , Chuan Hong , Jasmine Chiat Ling Ong , Qingyu Chen , Emily Alsentzer , Danielle Sara Bitterman , Daniel Shu Wei Ting , and Nan Liu
    2026
    HTML Scholar
  9. Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models
    Sasha Ronaghi , Chloe Stanwyck , Asad Aali , Amir Ronaghi , Miguel Fuentes , Tina Hernandez-Boussard , and Emily Alsentzer
    In arXiv preprint arXiv:2601.03423, 2026, 2026
    arXiv Scholar

2025

  1. APRIL: Annotations for Policy evaluation with Reliable Inference from LLMs
    A Mandyam , K Limaye , BE Engelhardt , and E Alsentzer
    In Proceedings of Machine Learning Research 297, Machine Learning for Health 2025, 2025
    HTML Scholar PDF
  2. Performance Benchmarking of Smaller Language Models Against GPT-4 for Predicting Reasons for Oral Anticoagulation Nonprescription in Atrial Fibrillation
    Sulaiman Somani , Dale Kim , Eduardo Perez Guerrero , Summer Ngo , Minh Nguyen , Alexander Sandhu , Emily Alsentzer , Tina Hernandez-Boussard , and Fatima Rodriguez
    Circulation 152 (Suppl_3), A4366575-A4366575, 2025, 2025
    HTML Scholar
  3. Large Language Models for Large-Scale, Rigorous Qualitative Analysis in Applied Health Services Research
    S Ronaghi , EL Aveling , M Levis , RL Ross , E Alsentzer , and S Singer
    Research Square, rs. 3. rs-7794878, 2025, 2025
    HTML Scholar
  4. Structured Prompting Enables More Robust, Holistic Evaluation of Language Models
    Asad Aali , Muhammad Ahmed Mohsin , Vasiliki Bikia , Arnav Singhvi , Richard Gaus , Suhana Bedi , Hejie Cui , Miguel Fuentes , Alyssa Unell , Yifan Mai , Jordan Cahoon , Michael Pfeffer , Roxana Daneshjou , Sanmi Koyejo , Emily Alsentzer , Percy Liang , Christopher Potts , Nigam H Shah , and Akshay S Chaudhari
    In arXiv e-prints, arXiv: 2511.20836, 2025, 2025
    arXiv Scholar
  5. The Moment AI Arrived in the Clinic: Insights from the SAIL 2025 Year in Review
    Pierre Elias , Kameron Collin Black , Payal Chandak , Elizabeth Healey , Rachit Kumar , Michelle M Li , Hugo Morales , Brett Beaulieu Jones , and Emily Alsentzer
    NEJM AI 2 (11), AIp2500788, 2025, 2025
    HTML Scholar
  6. Patient-Physician Messaging by Race, Ethnicity, Insurance Type, and Preferred Language
    Lisa S Rotenstein , Brianna Hardy , Mitchell Tang , Bryan Steitz , Robert W Turer , Emily Alsentzer , and Michael L Barnett
    JAMA Network Open 8 (10), e2534549, 2025, 2025
    HTML Scholar
  7. Predicting Postpartum Hemorrhage Using Clinical Features Extracted With Large Language Models
    Elizabeth G Woo , Israel Zighelboim , Tyler Gifford , Joseph G Bell , Hannah Milthorpe , Emily Alsentzer , Ryan E Longman , Jorge E Tolosa , and Brett K Beaulieu-Jones
    O&G Open 2 (5), e128, 2025, 2025
    HTML Scholar
  8. TIMER: temporal instruction modeling and evaluation for longitudinal clinical records
    H Cui , A Unell , B Chen , JA Fries , E Alsentzer , S Koyejo , and NH Shah
    npj Digital Medicine 8 (1), 577, 2025, 2025
    HTML Scholar
  9. Redefining bias audits for generative AI in health care
    IY Chen , and E Alsentzer
    NEJM AI 2 (9), AIp2500015, 2025, 2025
    HTML Scholar
  10. Medval: Toward expert-level medical text validation with language models
    Asad Aali , Vasiliki Bikia , Maya Varma , Nicole Chiou , Sophie Ostmeier , Arnav Singhvi , Magdalini Paschali , Ashwin Kumar , Andrew Johnston , Karimar Amador-Martinez , Eduardo Juan Perez Guerrero , Paola Naovi Cruz Rivera , Sergios Gatidis , Christian Bluethgen , Eduardo Pontes Reis , Eddy D Zandee Rilland , Poonam Laxmappa Hosamani , Kevin R Keet , Minjoung Go , Evelyn Ling , David B Larson , Curtis Langlotz , Roxana Daneshjou , Jason Hom , Sanmi Koyejo , Emily Alsentzer , and Akshay S Chaudhari
    In arXiv preprint arXiv:2507.03152, 2025, 2025
    arXiv Scholar
  11. Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases
    Emily Alsentzer , Michelle M Li , Shilpa N Kobren , Ayush Noori , Undiagnosed Diseases Network , Isaac S Kohane , and Marinka Zitnik
    npj Digital Medicine 8 (1), 380, 2025, 2025
    HTML Scholar PDF
  12. Verifiable Summarization of Electronic Health Records Using Large Language Models to Support Chart Review
    Ritchie Verma , Emily Alsentzer , Zachary Strasser , Leslie Chang , Kirollos Roman , Esteban Gershanik , Camellia Hernandez , Miguel Linares , Jorge Rodriguez , Durga Thakral , Ozan Unlu , Jacqueline You , Li Zhou , and David Bates
    medRxiv, 2025, 2025
    HTML Scholar
  13. Synthetic data distillation enables the extraction of clinical information at scale
    EG Woo , MC Burkhart , E Alsentzer , and BK Beaulieu-Jones
    npj Digital Medicine 8 (1), 267, 2025, 2025
    HTML Scholar
  14. BRIDGE: benchmarking large language models for understanding real-world clinical practice text
    Jiageng Wu , Bowen Gu , Ren Zhou , Kevin Xie , Doug Snyder , Yixing Jiang , Valentina Carducci , Richard Wyss , Rishi J Desai , Emily Alsentzer , Leo Anthony Celi , Adam Rodman , Sebastian Schneeweiss , Jonathan H Chen , Santiago Romero-Brufau , Kueiyu Joshua Lin , and Jie Yang
    In arXiv preprint arXiv:2504.19467, 2025, 2025
    arXiv Scholar
  15. Understanding contraceptive switching rationales from real world clinical notes using large language models
    Brenda Y Miao , Christopher YK Williams , Ebenezer Chinedu-Eneh , Travis Zack , Emily Alsentzer , Atul J Butte , and Irene Y Chen
    npj Digital Medicine 8 (1), 221, 2025, 2025
    HTML Scholar
  16. It’s time to bench the medical exam benchmark
    ID Raji , R Daneshjou , and E Alsentzer
    Nejm Ai 2 (2), AIe2401235, 2025, 2025
    HTML Scholar
  17. Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation
    Wenyuan Chen , Fateme Nateghi Haredasht , Kameron C Black , François Grolleau , Emily Alsentzer , Jonathan H Chen , and Stephen P Ma
    In Biocomputing 2026: Proceedings of the Pacific Symposium, 189-204, 2025, 2025
    HTML Scholar
  18. MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries
    Françcois Grolleau , Emily Alsentzer , Timothy Keyes , Philip Chung , Akshay Swaminathan , Asad Aali , Jason Hom , Tridu Huynh , Thomas Lew , April Liang , Weihan Chu , Natasha Steele , Christina Lin , Jingkun Yang , Kameron Black , Stephen Ma , Fateme N Haredasht , Nigam H Shah , Kevin Schulman , and Jonathan H Chen
    In Biocomputing 2026: Proceedings of the Pacific Symposium, 388-399, 2025, 2025
    HTML Scholar
  19. Best of Both Worlds: Combining General and Clinical Language Models for Classification and Text Generation
    Sasha Ronaghi , Asad Aali , Chloe O’Connell Stanwyck , Miguel Angel Fuentes Hernandez , Tina Hernandez-Boussard , and Emily Alsentzer
    Machine Learning for Health 2025, 2025
    HTML Scholar PDF
  20. Scalable Question Generation for Evaluating Longitudinal Reasoning in Electronic Health Records
    Jordan Li Cahoon , Chloe O’Connell Stanwyck , Sulaiman Somani , Kevin Keet , Alison Callahan , Jason Alan Fries , Nigam Shah , and Emily Alsentzer
    Machine Learning for Health 2025, 2025
    HTML Scholar PDF
  21. Prompt Optimization Improves Robustness of Language Model Benchmarks for Medical Tasks
    Asad Aali , Muhammad Ahmed Mohsin , Vasiliki Bikia , Arnav Singhvi , Suhana Bedi , Hejie Cui , Miguel Angel Fuentes Hernandez , Alyssa Unell , Yifan Mai , Michael Adam Pfeffer , Roxana Daneshjou , Sanmi Koyejo , Emily Alsentzer , Christopher Potts , Nigam Shah , and Akshay S Chaudhari
    Machine Learning for Health 2025, 2025
    HTML Scholar PDF

2024

  1. Leveraging large language models to foster equity in healthcare
    JA Rodriguez , E Alsentzer , and DW Bates
    Journal of the American Medical Informatics Association 31 (9), 2147-2150, 2024, 2024
    HTML Scholar
  2. GENERATIVE AI IN PRIMARY CARE: LESSONS FROM AMBIENT LISTENING DOCUMENTATION AND DRAFTING PATIENT PORTAL REPLIES
    Jacqueline G You , Amanda J Centi , Emily Alsentzer , David Y Ting , Lydia C Siegel , Elaine Goodman , Sayon Dutta , Anne Stanislaus , Dustin S McEvoy , Jackson Olin , and Rebecca G Mishuris
    JOURNAL OF GENERAL INTERNAL MEDICINE 39, S450-S450, 2024, 2024
    Scholar
  3. Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study
    Travis Zack , Eric Lehman , Mirac Suzgun , Jorge A Rodriguez , Leo Anthony Celi , Judy Gichoya , Dan Jurafsky , Peter Szolovits , David W Bates , Raja-Elie E Abdulnour , Atul J Butte , and Emily Alsentzer
    The Lancet Digital Health 6 (1), e12-e22, 2024, 2024
    HTML Scholar

2023

  1. Predicting seizure recurrence after an initial seizure-like episode from routine clinical notes using large language models: a retrospective cohort study
    Brett K Beaulieu-Jones , Mauricio F Villamar , Phil Scordis , Ana Paula Bartmann , Waqar Ali , Benjamin D Wissel , Emily Alsentzer , Johann Jong , Arijit Patra , and Isaac Kohane
    The Lancet Digital Health 5 (12), e882-e894, 2023, 2023
    HTML Scholar
  2. Zero-shot interpretable phenotyping of postpartum hemorrhage using large language models
    Emily Alsentzer , Matthew J Rasmussen , Romy Fontoura , Alexis L Cull , Brett Beaulieu-Jones , Kathryn J Gray , David W Bates , and Vesela P Kovacheva
    NPJ digital medicine 6 (1), 212, 2023, 2023
    HTML Scholar
  3. Simulation of undiagnosed patients with novel genetic conditions
    Emily Alsentzer , Samuel G Finlayson , Michelle M Li , Undiagnosed Diseases Network , Shilpa N Kobren , and Isaac S Kohane
    Nature Communications 14 (1), 6403, 2023, 2023
    HTML Scholar
  4. Towards medical billing automation: NLP for outpatient clinician note classification
    MG Crowson , E Alsentzer , J Fiskio , and DW Bates
    medRxiv, 2023.07. 07.23292367, 2023, 2023
    HTML Scholar
  5. Do we still need clinical language models?
    Eric Lehman , Evan Hernandez , Diwakar Mahajan , Jonas Wulff , Micah J Smith , Zachary Ziegler , Daniel Nadler , Peter Szolovits , Alistair Johnson , and Emily Alsentzer
    In Conference on health, inference, and learning, 578-597, 2023, 2023
    arXiv HTML Scholar PDF Code

2022

  1. Mitigating the impact of biased artificial intelligence in emergency decision-making
    H Adam , A Balagopalan , E Alsentzer , F Christia , and M Ghassemi
    Communications Medicine 2 (1), 149, 2022, 2022
    HTML Scholar
  2. Knowledge-based systems in medicine
    P Szolovits , and E Alsentzer
    Intelligent Systems in Medicine and Health: The Role of AI, 75-108, 2022, 2022
    HTML Scholar
  3. Just following ai orders: When unbiased people are influenced by biased ai
    H Adam , A Balagopalan , E Alsentzer , F Christia , and M Ghassemi
    In Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022, 2022, 2022
    HTML Scholar PDF

2021

  1. What’s in a summary? laying the groundwork for advances in hospital-course summarization
    G Adams , E Alsentzer , M Ketenci , J Zucker , and N Elhadad
    In Proceedings of the 2021 Conference of the North American Chapter of the …, 2021, 2021
    HTML Scholar

2020

  1. Assessing 3 outbreak detection algorithms in an electronic syndromic surveillance system in a resource-limited setting
    Emily Alsentzer , Sarah-Blythe Ballard , Joan Neyra , Delphis M Vera , Victor B Osorio , Jose Quispe , David L Blazes , and Luis Loayza
    Emerging Infectious Diseases 26 (9), 2196, 2020, 2020
    HTML Scholar
  2. Baselines for chest x-ray report generation
    W Boag , TMH Hsu , M McDermott , G Berner , E Alsentzer , and P Szolovits
    In Machine learning for health workshop, 126-140, 2020, 2020
    HTML Scholar PDF
  3. Intimate partner violence and injury prediction from radiology reports
    Irene Y Chen , Emily Alsentzer , Hyesun Park , Richard Thomas , Babina Gosangi , Rahul Gujrathi , and Bharti Khurana
    In BIOCOMPUTING 2021: Proceedings of the Pacific Symposium, 55-66, 2020, 2020
    HTML Scholar
  4. Subgraph neural networks
    E Alsentzer , S Finlayson , M Li , and M Zitnik
    Advances in Neural Information Processing Systems 33, 8017-8029, 2020, 2020
    HTML Scholar PDF

2019

  1. Publicly available clinical BERT embeddings
    Emily Alsentzer , John Murphy , William Boag , Wei-Hung Weng , Di Jindi , Tristan Naumann , and Matthew McDermott
    In Proceedings of the 2nd clinical natural language processing workshop, 72-78, 2019, 2019
    HTML Scholar PDF

2018

  1. Scalable Electronic Phenotyping For Studying Patient Comorbidities
    AY Ling , E Alsentzer , J Chen , JM Banda , S Tamang , and E Minty
    In AMIA Annual Symposium Proceedings 2018, 740, 2018, 2018
    HTML Scholar Website
  2. Extractive summarization of ehr discharge notes
    E Alsentzer , and A Kim
    In arXiv preprint arXiv:1810.12085, 2018, 2018
    arXiv Scholar
  3. Investigating inequities in hospital care among lesbian, gay, bisexual, and transgender (LGBT) individuals using social media
    Y Hswen , KC Sewalk , E Alsentzer , G Tuli , JS Brownstein , and JB Hawkins
    Social science & medicine 215, 92-97, 2018, 2018
    HTML Scholar

2016

  1. The effect of microbial colonization on the host proteome varies by gastrointestinal location
    Joshua S Lichtman , Emily Alsentzer , Mia Jaffe , Daniel Sprockett , Evan Masutani , Elvis Ikwa , Gabriela K Fragiadakis , David Clifford , Bevan Emma Huang , Justin L Sonnenburg , Kerwyn Casey Huang , and Joshua E Elias
    The ISME journal 10 (5), 1170-1181, 2016, 2016
    HTML Scholar

2015

  1. Monitoring acute diarrhea via an electronic surveillance system in the Peruvian Navy
    Emily Alsentzer , Delphis M Vera , Joan Neyra , Luis Loayza , Ricardo A Hora , Victor B Osorio , Jose Quispe , Sarah-Blythe Ballard , and David Blazes
    Online Journal of Public Health Informatics 7 (1), 2015, 2015
    HTML Scholar

2014

  1. An algorithm developed using the Brighton Collaboration case definitions is more efficient for determining diagnostic certainty
    D Joshi , E Alsentzer , K Edwards , A Norton , and SE Williams
    Vaccine 32 (28), 3469-3472, 2014, 2014
    HTML Scholar