About

Tianxi Cai, ScD, is a Professor of Biomedical Informatics at Harvard Medical School and the Director of the Translational Data Science Center for a Learning Health System (CELEHS). His research focuses on the development and application of statistical and computational methods for analyzing large-scale biomedical data, with an emphasis on translational and population health sciences. He holds a joint appointment as the John Rock Professor of Population and Translational Data Sciences at Harvard T.H. Chan School of Public Health. Dr. Cai's work involves leveraging data science to improve health outcomes through innovative approaches in biomedical discovery, infrastructure, and clinical decision making. His contributions include advancing methodologies for analyzing complex biomedical data and fostering translational research that bridges data science and clinical practice.

Research topics

• Internal medicine
• Medicine
• Emergency medicine
• Pediatrics
• Genetics
• Pathology
• Intensive care medicine

Selected publications

• Tu1495 MACHINE-LEARNING BASED STRATIFICATION IDENTIFIES TREATMENT TRAJECTORY SUBTYPES AND UNMET NEED IN INFLAMMATORY BOWEL DISEASES

  Gastroenterology · 2026-05-01

  article
  PublisherDOI

• Tu1588 COMPARATIVE RISK OF CANCER WITH IL-12/23 OR IL-23 INHIBITORS AND ANTI-TNFS IN INFLAMMATORY BOWEL DISEASES

  Gastrointestinal Endoscopy · 2026-05-01

  article
  PublisherDOI

• Nonparametric estimation of the total treatment effect with multiple outcomes in the presence of terminal events

  Biometrics · 2026-04-03

  preprintOpen access

  As standards of care advance, patients are living longer and once-fatal diseases are becoming manageable. Clinical trials increasingly focus on reducing disease burden, which can be quantified by the timing and occurrence of multiple non-fatal clinical events. Most existing methods for the analysis of multiple event-time data require stringent modeling assumptions that can be difficult to verify empirically, leading to treatment efficacy estimates that forego interpretability when the underlying assumptions are not met. Moreover, many methods do not appropriately account for informative terminal events, such as premature treatment discontinuation or death, which prevent the occurrence of subsequent events. To address these limitations, we derive and validate estimation and inference procedures for the area under the mean cumulative function (AUMCF), an extension of the restricted mean survival time to the multiple event-time setting. The AUMCF is clinically interpretable, properly accounts for terminal competing risks, and can be estimated nonparametrically. To enable covariate adjustment, we also develop an augmentation estimator that provides efficiency at least equaling, and often exceeding, the unadjusted estimator. The utility and interpretability of the AUMCF are illustrated with extensive simulation studies and through an analysis of multiple heart-failure-related endpoints using data from the Beta-Blocker Evaluation of Survival Trial. Our open-source R package MCC makes conducting AUMCF analyses straightforward and accessible.

  PublisherOA PDFDOI

• Tu1592 CANCER RISK ASSOCIATED WITH COMBINATION METHOTREXATE AND ANTI-TNF THERAPY VERSUS ANTI-TNF MONOTHERAPY FOR INFLAMMATORY BOWEL DISEASE: A RETROSPECTIVE COHORT STUDY.

  Gastrointestinal Endoscopy · 2026-05-01

  article
  PublisherDOI

• Tu1592 CANCER RISK ASSOCIATED WITH COMBINATION METHOTREXATE AND ANTI-TNF THERAPY VERSUS ANTI-TNF MONOTHERAPY FOR INFLAMMATORY BOWEL DISEASE: A RETROSPECTIVE COHORT STUDY.

  Gastroenterology · 2026-05-01

  article
  PublisherDOI

• Phenotypic prediction of missense variants via deep contrastive learning

  Nature Biomedical Engineering · 2026-04-14

  articleSenior authorCorresponding
  PublisherDOI

• Tu1494 MACHINE LEARNING-BASED STRATIFICATION TO DEFINE DISTINCT DISEASE TRAJECTORIES FOLLOWING ADVANCED THERAPY INITIATION IN CROHN’S DISEASE AND ULCERATIVE COLITIS

  Gastroenterology · 2026-05-01

  article
  PublisherDOI

• Tu1588 COMPARATIVE RISK OF CANCER WITH IL-12/23 OR IL-23 INHIBITORS AND ANTI-TNFS IN INFLAMMATORY BOWEL DISEASES

  Gastroenterology · 2026-05-01

  article
  PublisherDOI

• Tu1494 MACHINE LEARNING-BASED STRATIFICATION TO DEFINE DISTINCT DISEASE TRAJECTORIES FOLLOWING ADVANCED THERAPY INITIATION IN CROHN’S DISEASE AND ULCERATIVE COLITIS

  Gastrointestinal Endoscopy · 2026-05-01

  article
  PublisherDOI

• Tu1495 MACHINE-LEARNING BASED STRATIFICATION IDENTIFIES TREATMENT TRAJECTORY SUBTYPES AND UNMET NEED IN INFLAMMATORY BOWEL DISEASES

  Gastrointestinal Endoscopy · 2026-05-01

  article
  PublisherDOI

Recent grants

• Theory and Methods for Estimation of Nonsmooth Functionals and Detection of Simultaneous Signals

  NSF · $486k · 2014–2017

• FRG: Collaborative Research: Statistical Inference for High-Dimensional Data: Theory, Methodology and Applications

  NSF · $143k · 2009–2013

• Random Matrix Theory and High Dimensional Statistics

  NSF · $255k · 2012–2016

• Studying exceptional treatment non-responders and genetics to predict treatment response in rheumatoid arthritis

  NIH · $444k · 2021–2024

• Collaborative Research: Transfer Learning for Large-Scale Inference: General Framework and Data-Driven Algorithms

  NSF · $250k · 2020–2023

Frequent coauthors

• Shawn N. Murphy

  381 shared

• Vivian S. Gainer

  281 shared

• Katherine P. Liao

  Harvard University

  266 shared

• Víctor M. Castro

  Mass General Brigham

  242 shared

• Isaac S. Kohane

  Harvard University

  226 shared

• Guergana Savova

  Harvard University

  220 shared

• Sheng Yu

  Tsinghua University

  219 shared

• Anil Can

  Brigham and Women's Hospital

  214 shared

Labs

• Cai LabPI