About me
Dr. Linying Zhang is an Assistant Professor of Biostatistics at the Institute for Informatics, Data Science and Biostatistics at Washington University School of Medicine in St. Louis. She leads the CausAI Lab, which advances methods at the intersection of causality and machine learning/artificial intelligence (ML/AI) to enhance the explainability, generalizability, and fairness of models trained on electronic health records (EHRs), with applications in real-world evidence generation and clinical risk prediction.
Lab mission
ML/AI has the potential to revolutionize healthcare if developed and deployed thoughtfully. In healthcare, AI models are frequently trained on real-world data (RWD), which are inherently imperfect – frequently missing not at random, irregularly sampled, subject to measurement error, and reflective of existing health disparities. To realize AI’s promise, it is essential to design methodologies that correct these biases and limitations.
The CausAI Lab is dedicated to tackling these challenges by integrating causality with machine learning/AI to produce reliable real-world evidence and build equitable clinical AI models that benefit all patient populations.
For the most up-to-date information, please visit the CausAI Lab website.
Join us
Post-doc Fellows We are looking for one postdoctoral fellow to work on causal AI for health care.
PhD Students We are looking for 1-2 PhD students starting Fall 2026. Please apply directly to the Biomedical Informatics and Data Science (BIDS) PhD program at Washington University School of Medicine. In your PhD application, please explicitly mention your interest in working with Professor Linying Zhang. Existing BIDS and Computational & Systems Biology (CSB) PhD students interested in rotating through the lab should email Dr. Zhang directly.
Undergraduates or Master’s Students Undergraduates and Master’s students looking for research opportunities are encouraged to apply through the BIDS@I2 Summer Research Internship. We are looking for students who have taken at least one machine learning course and received a good grade. For masters students, we typically expect students to have taken a graduate-level machine learning course and a graduate-level probability or statistical inference course, or have had significant related research experience. WashU students interested in research assistantship should email Dr. Zhang directly.
You can reach me at linyingz [at] wustl [dot] edu or on Twitter.
Selected Publications & Preprints
Causal machine earning for reliable real-world evidence generation in healthcare.
Linying Zhang
PhD thesis, Columbia University, 2023.
[URL]
Explaining treatment disparities from a causal perspective with EHRs.
Zhang L, Jiang X, Natarajan K, and Hripcsak G.
AMIA Symposium, 2023.
[Abs]
Causal fairness assessment of treatment allocation with electronic health records.
Zhang L, Richter LR, Wang Y, Ostropolets A, Elhadad N, Blei DM, and Hripcsak G.
JBI (to appear), 2023.
[PDF]
Adjusting for indirectly measured confounding using large-scale propensity score.
Zhang L, Wang Y, Schuemie MJ, Blei DM, and Hripcsak G.
Journal of Biomedical Informatics, 2022.
[PDF]
Evaluating and Improving the Performance and Racial Fairness of Algorithms for GFR Estimation.
Zhang L, Richter LR, Kim T, and Hripcsak G.
IEEE International Conference on Artificial Intelligence x Medicine, Health, and Care (AIMHC), 2024.
[PDF]
The Medical Deconfounder: Assessing Treatment Effects with Electronic Health Records.
Zhang L, Wang Y, Ostropolets A, Mulgrave JJ, Blei DM, and Hripcsak G.
Machine Learning for Healthcare Conference, 2019.
[PDF][code]
Data assimilation on mechanistic models of glucose metabolism predicts glycemic states in adolescents following bariatric surgery.
Richter LR, Albert BI, Zhang L, Ostropolets A, Zitsman JL, Fennoy I, Albers D, and Hripcsak G.
Frontiers in Physiology, 2022.
[PDF]
Predicting hospitalization of COVID-19 positive patients using clinician-guided machine learning methods.
Song W, Zhang L, Liu L, Sainlaire M, Karvar M, Kang M, Pullman A, Lipsitz S, Massaro A, Patil N, Jasuja R, and Dykes PC.
Journal of the American Medical Informatics Association, 2022.
[PDF]
Predicting pressure injury using nursing assessment phenotypes and machine learning methods.
Song W, Kang M, Zhang L, Jung W, Song J, Bates D, and Dykes PC.
Journal of the American Medical Informatics Association, 2021.
[PDF]