Pranav Rajpurkar

Computer scientist · Medical artificial intelligence

Pranav Rajpurkar

Associate Professor of Biomedical Informatics
Harvard Medical School
Co-founder of a2z Radiology AI

Pranav Rajpurkar develops and evaluates artificial intelligence for medicine. He leads the Rajpurkar Lab at Harvard and co-founded a2z Radiology AI.

He works on medical imaging, multimodal learning, clinical agents, and clinician–AI collaboration.

Pranav Rajpurkar
Computer scientist working on artificial intelligence for medicine
Position
Associate Professor of Biomedical Informatics, Harvard Medical School
Lab
Rajpurkar Lab at Harvard Medical School
Industry
Co-founder of a2z Radiology AI
Training
BS, MS, and PhD in computer science, Stanford University
Teaching
90,000+ learners in AI for Medicine
Record
201 research publications · 58,040 citations per Google Scholar

About

Research

At Stanford, Dr. Rajpurkar worked on SQuAD and early AI systems for arrhythmias and chest X-rays. He now leads the Rajpurkar Lab at Harvard Medical School, where his group works on multimodal medical AI, clinical agents, clinician–AI collaboration, and embodied AI.

The lab is especially interested in what happens outside a benchmark: at a different hospital, with changing patient context, and alongside clinicians.

Expert medical care should reach everyone.

Getting there will take AI doctors: systems that can carry real clinical work, not only answer questions about it.

2016–present

Selected work

2016 · Machine comprehension

SQuAD: a benchmark for question answering

SQuAD introduced more than 100,000 questions grounded in Wikipedia passages and made extractive question answering easier to measure.

SQuAD paper

2017–2020 · Medical signals and images

Arrhythmias and chest X-rays

Research on arrhythmias and chest radiographs compared deep-learning systems with physicians on retrospective tasks. CheXpert also made a large labeled chest X-ray dataset available for research.

Arrhythmia detection CheXNet CheXpert

2021–2024 · Broader medical AI

Generalist medical AI and clinician–AI collaboration

Projects included generalist medical AI, systems that use several kinds of medical information, and studies of how clinicians and AI make decisions together.

Generalist medical AI

2025–present · Imaging AI translation

a2z Radiology AI

Dr. Rajpurkar co-founded a2z Radiology AI, whose first product, a2z-Unified-Triage, received FDA clearance to prioritize adult abdomen and pelvis CT studies with suspected findings across seven conditions.

a2z Radiology AI FDA clearance

Rajpurkar Lab

Current work

The Rajpurkar Lab builds models, datasets, evaluation methods, and simulation environments for medical AI.

01Multimodal medical AI

Can one system understand the whole medical picture?

A clinician combines images, language, video, laboratory results, and physiological signals. We are studying how a single system can reason across them without losing the context that connects them.

02Clinical agents and evaluation

Can clinical AI reason over time?

Care is a sequence of decisions, not a single answer. We build agents that gather information, revise their view, and work through clinical tasks—and environments that test those abilities dynamically.

03Clinician–AI collaboration

When does AI actually help a clinician?

Putting a clinician and an AI system together does not automatically improve a decision. We study when the combination helps, when it fails, and how responsibility should be shared.

04Medical imaging and embodied AI

Can perception lead safely to action?

Interpreting an image is only one part of care. We are connecting medical perception to action, including procedural and robotic settings where mistakes have immediate consequences.

Outside the lab

Company and teaching

01

Clinical translation

a2z-Unified-Triage is FDA-cleared to prioritize adult abdomen and pelvis CT studies with suspected findings across seven conditions. Dr. Rajpurkar co-founded a2z Radiology AI.

Google Scholar

Recent publications

The five newest research publications in the public Google Scholar record, last synced August 8, 2026.

  1. 2026

    Toward a test of medical AI superintelligence

    Nature Medicine, 1-3, 2026

  2. 2026

    Humanoid robots in the operating room: a framework for staged integration of embodied AI in surgery

    npj Digital Medicine, 2026

  3. 2026

    Open-Ended Clinical Text Generation for Acute Care: Applying Reinforcement Learning with Clinically Grounded Rewards

    Conference on Health, Inference, and Learning, 966-984, 2026

  4. 2026

    Large reasoning models as thinking machines for medicine

    Nature Biomedical Engineering, 1-10, 2026

  5. 2026

    Rexgroundingct: A 3d chest ct dataset for segmentation of findings from free-text reports

    NEJM AI, AIdbp2501220, 2026

Full publication record (201 research publications)