Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model
BackgroundColorectal cancer (CRC) is a highly frequent cancer worldwide, and early detection and risk stratification playing a critical role in reducing both incidence and mortality. we aimed to develop and validate a machine learning (ML) model using clinical data to improve CRC identification and...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2025.1575844/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839626738829623296 |
|---|---|
| author | Guinian Du Hui Lv Yishan Liang Jingyue Zhang Qiaoling Huang Guiming Xie Xian Wu Hao Zeng Lijuan Wu Jianbo Ye Wentan Xie Xia Li Yifan Sun |
| author_facet | Guinian Du Hui Lv Yishan Liang Jingyue Zhang Qiaoling Huang Guiming Xie Xian Wu Hao Zeng Lijuan Wu Jianbo Ye Wentan Xie Xia Li Yifan Sun |
| author_sort | Guinian Du |
| collection | DOAJ |
| description | BackgroundColorectal cancer (CRC) is a highly frequent cancer worldwide, and early detection and risk stratification playing a critical role in reducing both incidence and mortality. we aimed to develop and validate a machine learning (ML) model using clinical data to improve CRC identification and prognostic evaluation.MethodsWe analyzed multicenter datasets comprising 676 CRC patients and 410 controls from Guigang City People’s Hospital (2020-2024) for model training/internal validation, with 463 patients from Laibin City People’s Hospital for external validation. Seven ML algorithms were systematically compared, with Light Gradient Boosting Machine (LightGBM) ultimately selected as the optimal framework. Model performance was rigorously assessed through area under the receiver operating characteristic (AUROC) analysis, calibration curves, Brier scores, and decision curve analysis. SHAP (SHapley Additive exPlanations) methodology was employed for feature interpretation.ResultsThe LightGBM model demonstrated exceptional discrimination with AUROCs of 0.9931 (95% CI: 0.9883-0.998) in the training cohort and 0.9429 (95% CI: 0.9176-0.9682) in external validation. Calibration curves revealed strong prediction-actual outcome concordance (Brier score=0.139). SHAP analysis identified 13 key predictors, with age (mean SHAP value=0.216) and CA19-9 (mean SHAP value=0.198) as dominant contributors. Other significant variables included hematological parameters (WBC, RBC, HGB, PLT), biochemical markers (ALT, TP, ALB, UREA, uric acid), and gender. A clinically implementable web-based risk calculator was successfully developed for real-time probability estimation.ConclusionsOur LightGBM-based model achieves high predictive accuracy while maintaining clinical interpretability, effectively bridging the gap between complex ML systems and practical clinical decision-making. The identified biomarker panel provides biological insights into CRC pathogenesis. This tool shows significant potential for optimizing early diagnosis and personalized risk assessment in CRC management. |
| format | Article |
| id | doaj-art-7d1a1111f52b4ed19d74f70b22c43c0c |
| institution | Matheson Library |
| issn | 2234-943X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj-art-7d1a1111f52b4ed19d74f70b22c43c0c2025-07-17T04:10:20ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-07-011510.3389/fonc.2025.15758441575844Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM modelGuinian Du0Hui Lv1Yishan Liang2Jingyue Zhang3Qiaoling Huang4Guiming Xie5Xian Wu6Hao Zeng7Lijuan Wu8Jianbo Ye9Wentan Xie10Xia Li11Yifan Sun12Department of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, The People Hospital of Laibin, Laibin, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaDepartment of Endocrinology, The People Hospital of Guigang, Guigang, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaThe Office of Administration, Liuzhou Municipal Liutie Central Hospital, Liuzhou, Guangxi, ChinaDepartment of Laboratory Medicine, Eighth Affiliated Hospital of Guangxi Medical University, Guigang City People’s Hospital, Guigang, Guangxi, ChinaBackgroundColorectal cancer (CRC) is a highly frequent cancer worldwide, and early detection and risk stratification playing a critical role in reducing both incidence and mortality. we aimed to develop and validate a machine learning (ML) model using clinical data to improve CRC identification and prognostic evaluation.MethodsWe analyzed multicenter datasets comprising 676 CRC patients and 410 controls from Guigang City People’s Hospital (2020-2024) for model training/internal validation, with 463 patients from Laibin City People’s Hospital for external validation. Seven ML algorithms were systematically compared, with Light Gradient Boosting Machine (LightGBM) ultimately selected as the optimal framework. Model performance was rigorously assessed through area under the receiver operating characteristic (AUROC) analysis, calibration curves, Brier scores, and decision curve analysis. SHAP (SHapley Additive exPlanations) methodology was employed for feature interpretation.ResultsThe LightGBM model demonstrated exceptional discrimination with AUROCs of 0.9931 (95% CI: 0.9883-0.998) in the training cohort and 0.9429 (95% CI: 0.9176-0.9682) in external validation. Calibration curves revealed strong prediction-actual outcome concordance (Brier score=0.139). SHAP analysis identified 13 key predictors, with age (mean SHAP value=0.216) and CA19-9 (mean SHAP value=0.198) as dominant contributors. Other significant variables included hematological parameters (WBC, RBC, HGB, PLT), biochemical markers (ALT, TP, ALB, UREA, uric acid), and gender. A clinically implementable web-based risk calculator was successfully developed for real-time probability estimation.ConclusionsOur LightGBM-based model achieves high predictive accuracy while maintaining clinical interpretability, effectively bridging the gap between complex ML systems and practical clinical decision-making. The identified biomarker panel provides biological insights into CRC pathogenesis. This tool shows significant potential for optimizing early diagnosis and personalized risk assessment in CRC management.https://www.frontiersin.org/articles/10.3389/fonc.2025.1575844/fullColorectal cancerRisk predictionMachine learningLightGBM modelEarly diagnosis |
| spellingShingle | Guinian Du Hui Lv Yishan Liang Jingyue Zhang Qiaoling Huang Guiming Xie Xian Wu Hao Zeng Lijuan Wu Jianbo Ye Wentan Xie Xia Li Yifan Sun Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model Frontiers in Oncology Colorectal cancer Risk prediction Machine learning LightGBM model Early diagnosis |
| title | Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model |
| title_full | Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model |
| title_fullStr | Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model |
| title_full_unstemmed | Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model |
| title_short | Population-based colorectal cancer risk prediction using a SHAP-enhanced LightGBM model |
| title_sort | population based colorectal cancer risk prediction using a shap enhanced lightgbm model |
| topic | Colorectal cancer Risk prediction Machine learning LightGBM model Early diagnosis |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2025.1575844/full |
| work_keys_str_mv | AT guiniandu populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT huilv populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT yishanliang populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT jingyuezhang populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT qiaolinghuang populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT guimingxie populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT xianwu populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT haozeng populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT lijuanwu populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT jianboye populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT wentanxie populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT xiali populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel AT yifansun populationbasedcolorectalcancerriskpredictionusingashapenhancedlightgbmmodel |