Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study
Abstract BackgroundColorectal cancer is now the leading cause of cancer-related deaths among young Americans. Accurate early prediction and a thorough understanding of the risk factors for early-onset colorectal cancer (EOCRC) are vital for effective prevention and treatment,...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-06-01
|
| Series: | JMIR Cancer |
| Online Access: | https://cancer.jmir.org/2025/1/e64506 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849430505468985344 |
|---|---|
| author | Chengkun Sun Erin Mobley Michael Quillen Max Parker Meghan Daly Rui Wang Isabela Visintin Ziad Awad Jennifer Fishe Alexander Parker Thomas George Jiang Bian Jie Xu |
| author_facet | Chengkun Sun Erin Mobley Michael Quillen Max Parker Meghan Daly Rui Wang Isabela Visintin Ziad Awad Jennifer Fishe Alexander Parker Thomas George Jiang Bian Jie Xu |
| author_sort | Chengkun Sun |
| collection | DOAJ |
| description |
Abstract
BackgroundColorectal cancer is now the leading cause of cancer-related deaths among young Americans. Accurate early prediction and a thorough understanding of the risk factors for early-onset colorectal cancer (EOCRC) are vital for effective prevention and treatment, particularly for patients below the recommended screening age.
ObjectiveOur study aims to predict EOCRC using machine learning (ML) and structured electronic health record data for individuals under the screening age of 45 years, with the aim of exploring potential risk and protective factors that could support early diagnosis.
MethodsWe identified a cohort of patients under the age of 45 years from the OneFlorida+ Clinical Research Consortium. Given the distinct pathology of colon cancer (CC) and rectal cancer (RC), we created separate prediction models for each cancer type with various ML algorithms. We assessed multiple prediction time windows (ie, 0, 1, 3, and 5 y) and ensured robustness through propensity score matching to account for confounding variables including sex, race, ethnicity, and birth year. We conducted a comprehensive performance evaluation using metrics including area under the curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and F1
ResultsThe final cohort included 1358 CC cases with 6790 matched controls, and 560 RC cases with 2800 matched controls. The RC group had a more balanced sex distribution (2:3 male-to-female) compared to the CC group (2:5 male-to-female), and both groups showed diverse racial and ethnic representation. Our predictive models demonstrated reasonable results, with AUC scores for CC prediction of 0.811, 0.748, 0.689, and 0.686 at 0, 1, 3, and 5 years before diagnosis, respectively. For RC prediction, AUC scores were 0.829, 0.771, 0.727, and 0.721 across the same time windows. Key predictive features across both cancer types included immune and digestive system disorders, secondary malignancies, and underweight status. In addition, blood diseases emerged as prominent indicators specifically for CC.
ConclusionsOur 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. |
| format | Article |
| id | doaj-art-2b48754b76e540f1bf7b855604cefc33 |
| institution | Kabale University |
| issn | 2369-1999 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Cancer |
| spelling | doaj-art-2b48754b76e540f1bf7b855604cefc332025-08-20T03:27:58ZengJMIR PublicationsJMIR Cancer2369-19992025-06-0111e64506e6450610.2196/64506Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control StudyChengkun Sunhttp://orcid.org/0000-0003-2095-9369Erin Mobleyhttp://orcid.org/0000-0002-6278-6593Michael Quillenhttp://orcid.org/0009-0006-6657-1748Max Parkerhttp://orcid.org/0009-0006-7873-9480Meghan Dalyhttp://orcid.org/0009-0002-3445-250XRui Wanghttp://orcid.org/0000-0002-8320-6500Isabela Visintinhttp://orcid.org/0009-0004-7991-2391Ziad Awadhttp://orcid.org/0000-0002-6555-6240Jennifer Fishehttp://orcid.org/0000-0001-9037-8143Alexander Parkerhttp://orcid.org/0000-0001-6820-274XThomas Georgehttp://orcid.org/0000-0002-6249-9180Jiang Bianhttp://orcid.org/0000-0002-2238-5429Jie Xuhttp://orcid.org/0000-0001-5291-5198 Abstract BackgroundColorectal cancer is now the leading cause of cancer-related deaths among young Americans. Accurate early prediction and a thorough understanding of the risk factors for early-onset colorectal cancer (EOCRC) are vital for effective prevention and treatment, particularly for patients below the recommended screening age. ObjectiveOur study aims to predict EOCRC using machine learning (ML) and structured electronic health record data for individuals under the screening age of 45 years, with the aim of exploring potential risk and protective factors that could support early diagnosis. MethodsWe identified a cohort of patients under the age of 45 years from the OneFlorida+ Clinical Research Consortium. Given the distinct pathology of colon cancer (CC) and rectal cancer (RC), we created separate prediction models for each cancer type with various ML algorithms. We assessed multiple prediction time windows (ie, 0, 1, 3, and 5 y) and ensured robustness through propensity score matching to account for confounding variables including sex, race, ethnicity, and birth year. We conducted a comprehensive performance evaluation using metrics including area under the curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and F1 ResultsThe final cohort included 1358 CC cases with 6790 matched controls, and 560 RC cases with 2800 matched controls. The RC group had a more balanced sex distribution (2:3 male-to-female) compared to the CC group (2:5 male-to-female), and both groups showed diverse racial and ethnic representation. Our predictive models demonstrated reasonable results, with AUC scores for CC prediction of 0.811, 0.748, 0.689, and 0.686 at 0, 1, 3, and 5 years before diagnosis, respectively. For RC prediction, AUC scores were 0.829, 0.771, 0.727, and 0.721 across the same time windows. Key predictive features across both cancer types included immune and digestive system disorders, secondary malignancies, and underweight status. In addition, blood diseases emerged as prominent indicators specifically for CC. ConclusionsOur 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.https://cancer.jmir.org/2025/1/e64506 |
| spellingShingle | Chengkun Sun Erin Mobley Michael Quillen Max Parker Meghan Daly Rui Wang Isabela Visintin Ziad Awad Jennifer Fishe Alexander Parker Thomas George Jiang Bian Jie Xu Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study JMIR Cancer |
| title | Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study |
| title_full | Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study |
| title_fullStr | Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study |
| title_full_unstemmed | Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study |
| title_short | Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study |
| title_sort | predicting early onset colorectal cancer in individuals below screening age using machine learning and real world data case control study |
| url | https://cancer.jmir.org/2025/1/e64506 |
| work_keys_str_mv | AT chengkunsun predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT erinmobley predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT michaelquillen predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT maxparker predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT meghandaly predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT ruiwang predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT isabelavisintin predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT ziadawad predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT jenniferfishe predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT alexanderparker predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT thomasgeorge predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT jiangbian predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy AT jiexu predictingearlyonsetcolorectalcancerinindividualsbelowscreeningageusingmachinelearningandrealworlddatacasecontrolstudy |