Early detection of non-small cell lung cancer: an electronic health record data-driven approach
This study identified EHR-derived features which are predictive of early NSCLC diagnosis. The developed risk prediction model exhibits superior performance for early detection of NSCLC compared to a baseline model that only relies on demographic and smoking information, demonstrating the potential of incorporating EHR-derived features for personalized cancer screening recommendations and early detection.
Authors
- Stephen Kuperberg (ORCID: https://orcid.org/0000-0002-6819-4425)
- Melissa L. Santorelli (ORCID: https://orcid.org/0000-0002-2964-7292)
- Katherine P. Liao (ORCID: https://orcid.org/0000-0002-4797-3200)
- Rui Yuan (ORCID: https://orcid.org/0000-0002-6603-6423)
- Xiudi Li
- Tianrun Cai (ORCID: https://orcid.org/0000-0001-5772-7460)
- Raquel Aguiar‐Ibáñez (ORCID: https://orcid.org/0000-0002-3839-6966)
- Yu-Han Kao (ORCID: https://orcid.org/0000-0003-2416-4395)
- Mary Jeffway
- Clara-Lea Bonzel (ORCID: https://orcid.org/0000-0001-5238-1413)
- Tianxi Cai (ORCID: https://orcid.org/0000-0002-5379-2502)
- Rui Duan (ORCID: https://orcid.org/0000-0002-9261-4864)
- David C. Christiani
Institutions
- Brigham and Women's Hospital (US)
- Merck & Co., Inc., Rahway, NJ, USA (United States) (US)
- Harvard University (US)
- Merck Canada Inc. (Canada) (CA)
- Cancer Research And Biostatistics (US)
- Harvard College Observatory (US)
- New York University (US)
Publication Details
- Journal
- BMC Medicine
- Published
- 2025-10-10
- DOI
- https://doi.org/10.1186/s12916-025-04289-3
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institutes of Health
- National Cancer Institute