Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study
Our findings demonstrate the potential of ML models leveraging electronic health record data to facilitate the early prediction of EOCRC in individuals under 45 years. By uncovering important risk factors and achieving promising predictive performance, this study provides preliminary insights that could inform future efforts toward earlier detection and prevention in younger populations.
Authors
- Michael B. Quillen
- Thomas J. George (ORCID: https://orcid.org/0000-0002-6249-9180)
- Jennifer N. Fishe (ORCID: https://orcid.org/0000-0001-9037-8143)
- Meghan Daly
- Jiang Bian (ORCID: https://orcid.org/0000-0002-2238-5429)
- Ziad T. Awad (ORCID: https://orcid.org/0000-0002-6555-6240)
- Alexander S. Parker (ORCID: https://orcid.org/0000-0001-6820-274X)
- Jie Xu (ORCID: https://orcid.org/0000-0001-5291-5198)
- Erin M. Mobley (ORCID: https://orcid.org/0000-0002-6278-6593)
- Rui Wang (ORCID: https://orcid.org/0000-0003-1130-8214)
- Chengkun Sun (ORCID: https://orcid.org/0000-0003-2095-9369)
- Max Parker
- Isabela Visintin
Institutions
- Florida Museum of Natural History (US)
- University of Florida Health (US)
- University of Florida (US)
- Jacksonville University (US)
- Indiana University Indianapolis (US)
- UF Health Cancer Center
- Indiana University – Purdue University Indianapolis (US)
- Florida College (US)
Publication Details
- Journal
- JMIR Cancer
- Published
- 2025-06-02
- DOI
- https://doi.org/10.2196/64506
- Citations
- 3
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 3.14