Welcome to the Rajpurkar Lab

At Rajpurkar Lab, we are committed to pioneering the development of advanced medical artificial intelligence. Our mission is to scale the expertise of top medical professionals globally through innovative AI solutions. We approach this scientific challenge with innovation in algorithmic development, large scale data curation, and clinician impact studies to transform radiology, emergency medicine and beyond.

Lab Members
Pranav Rajpurkar PhD · Principal Investigator
Agustina Saenz MD MPH · Postgraduate Researcher
Julian Acosta · Research Scientist
Hongyu Zhou · Postdoctoral Researcher
Xiaoman Zhang · Postdoctoral Researcher
Luyang Luo · Postdoctoral Researcher
Emma Chen · PhD Student
Shreya Johri · PhD Student
Oishi Banerjee · PhD Student
Wendy Erselius · Partnership Manager, MAIDA
Heather Viana · Administrative Coordinator
+ Medical AI Bootcamp Members

Lab Alumni
Liyue Shen · Now Faculty at UMich
Kathy Yu · Former Masters Student; Now at Google
Ryan Han · Now MD/PhD at UCLA
Elaine Liu · Now at Meta
Xiaoli Yang · Former Masters Student
Henrik Marklund · Now PhD at Stanford
Jonathan Williams · Undergrad at Stanford
Martin Ma · Former Masters Student
Alyssa Huang · Former Undergrad Student
Yash Mehta· Now PhD Student at JHU
Caiwei Tian · Masters Student
Vignav Ramesh · Undergrad Student
Jaehwan Jeong · Undergrad Student

+ Medical AI Bootcamp Alumni

Research

Our group is at the forefront of pioneering the development of Generalist Medical AI systems, which can closely resemble doctors in their ability to reason through a wide range of medical tasks, incorporate multiple data modalities, and communicate in natural language.

Foundation Models

We develop self-supervision and pre-training techniques for adaptable medical (‘foundation’) models, reducing the need for extensive data annotation. For instance, we developed an innovative AI model capable of detecting diseases on chest X-rays without relying on explicit labels (Tiu, Nature BME 22). We successfully built and leveraged foundation models for medical domains including for chest X-rays (Sowrirajan, MIDL 21; Vu, PMLR 21; Iyer, preprint 23), electrocardiograms (Gopal, PMLR 21; Jin, JAMIA 22), lung and heart sounds (Soni, Patterns 22), and CTs (Ke, MIDL 23). Our recent review (Krishnan, Nature BME 22) further explores how self-supervised learning can free medical AI from its reliance on labeled data.

Multimodal Learning

We develop methods to combine diverse data sources, like images, sensors, and language, to improve decision-making and generalization in medicine. We developed models from physiological data to monitor high-risk patients in the emergency department (Sundrani, NPJ Digital Med 23). We also developed models capable of learning to interpret images by learning from paired medical images and radiology reports (Tiu, Nature BME 22). We established a benchmark for modality agnostic learning across medical image and sensor data (Wantlin, preprint 23). We discuss other opportunities for learning across modalities (Acosta, Nature Med, 2022) and across time (Acosta, Radiology, 22) in our recent reviews.

Generative AI

We build generative AI models where models can interpret medical images in natural language and enable interactive communication with clinicians (Endo et al., ML4H, 21). We recently introduced datasets to address some of the biggest challenges with automated report generation (Ramesh et al, ML4H, 22; Yu et al., preprint 23). Furthermore, we are pioneering a copilot approach to radiology report generation, where AI models provide initial drafts of reports that clinicians can edit (Jeong et al. MIDL 23). We investigate the implications of providing AI assistance to clinicians in terms of their behavior (Moehring, preprint 23), and trustworthiness of explainability methods (Saporta, Nature MI, 22).

Get Involved

We invite you to join our mission of advancing Al-driven solutions in medicine by joining the group, through collaboration, or supporting our work.

Students: We welcome applications from undergraduate, graduate, and post-doctoral students, as well as visiting researchers with a background in artificial intelligence, software engineering, or medicine. If you are a student at Harvard or Stanford or a medical doctor, we encourage you to apply through the Medical AI Bootcamp. Prospective postdocs, please apply using this link.

Collaborations: We actively seek collaborations with industry partners, academic institutions, and hospitals who share our passion for impact-driven medical AI. If you are interested in partnering with us to advance healthcare through AI, we invite you to reach out through the contact form.