A Dataset for Understanding Radiologist-Artificial Intelligence Collaboration
This dataset, Collab-CXR, provides a unique resource to study human-AI collaboration in chest X-ray interpretation. We present experimentally generated data from 227 professional radiologists who assessed 324 historical cases under varying information conditions: with and without AI assistance, and with and without clinical history. Using a custom-designed interface, we collected probabilistic assessments for 104 thoracic pathologies using a comprehensive hierarchical reporting structure. This dataset is the largest known comparison of human-AI collaborative performance to either AI or humans alone in radiology, offering assessments across an extensive range of pathologies with rich metadata on radiologist characteristics and decision-making processes. Multiple experimental designs enable both within-subject and between-subject analyses. Researchers can leverage this dataset to investigate how radiologists incorporate AI assistance, factors influencing collaborative effectiveness, and impacts on diagnostic accuracy, speed, and confidence across different cases and pathologies. By enabling rigorous study of human-AI integration in clinical workflows, this dataset can inform AI tool development, implementation strategies, and ultimately improve patient care through optimized collaboration in medical imaging.
Authors
- Pranav Rajpurkar (ORCID: https://orcid.org/0000-0002-8030-3727)
- Dexter P. Mendoza (ORCID: https://orcid.org/0000-0001-7571-740X)
- Tobias Salz
- Yogesh Gupta (ORCID: https://orcid.org/0000-0002-4561-7210)
- Matthew P. Lungren (ORCID: https://orcid.org/0000-0002-8591-5861)
- Nikhil Agarwal (ORCID: https://orcid.org/0000-0003-2106-6175)
- Oishi Banerjee (ORCID: https://orcid.org/0009-0004-0097-3555)
- Tan Bui
- Anuj Pareek (ORCID: https://orcid.org/0000-0002-1526-3685)
- Corey Eber (ORCID: https://orcid.org/0000-0003-3290-420X)
- Adam Jacobi (ORCID: https://orcid.org/0000-0002-9057-9129)
- Alex Moehring (ORCID: https://orcid.org/0000-0001-6822-6354)
- Curtis P. Langlotz (ORCID: https://orcid.org/0000-0002-8972-8051)
- Etan Dayan (ORCID: https://orcid.org/0000-0002-6435-6458)
- Ray Huang
- Mike Chung
- Steven Q. H. Truong
- Manasi Kutwal
Institutions
- Microsoft (United States) (US)
- Harvard University (US)
- Purdue University West Lafayette (US)
- Copenhagen University Hospital (DK)
- Blueprint Medicines (United States) (US)
- Mount Sinai Hospital (US)
- IIT@MIT (US)
- Temple University Health System (US)
- VinUniversity (VN)
- Artificial Intelligence in Medicine (Canada) (CA)
- University of San Francisco (US)
- Temple University (US)
- Stanford University (US)
Publication Details
- Journal
- Scientific Data
- Published
- 2025-05-03
- DOI
- https://doi.org/10.1038/s41597-025-05054-0
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65
Funders
- Alfred P. Sloan Foundation