Development and validation of a machine learning-based predictive model for chemotherapy-induced myelosuppression in colorectal cancer patients.
[OBJECTIVE] This study aimed to develop and validate a machine learning-based predictive model for individualized assessment and management of chemotherapy-induced myelosuppression (CIM) in patients w
- 95% CI 0.89-0.97
APA
Song X, Li S, et al. (2026). Development and validation of a machine learning-based predictive model for chemotherapy-induced myelosuppression in colorectal cancer patients.. Frontiers in medicine, 13, 1778951. https://doi.org/10.3389/fmed.2026.1778951
MLA
Song X, et al.. "Development and validation of a machine learning-based predictive model for chemotherapy-induced myelosuppression in colorectal cancer patients.." Frontiers in medicine, vol. 13, 2026, pp. 1778951.
PMID
41958593
Abstract
[OBJECTIVE] This study aimed to develop and validate a machine learning-based predictive model for individualized assessment and management of chemotherapy-induced myelosuppression (CIM) in patients with colorectal cancer (CRC).
[METHODS] A total of 450 patients with CRC undergoing chemotherapy were retrospectively enrolled in the training cohort, and an additional 150 patients were included for external validation. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. Three machine learning algorithms [Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)] were applied to construct predictive models. Model performance was assessed using multiple metrics, including accuracy, area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity. The SHapley Additive exPlanations (SHAP) method was employed to rank and interpret the importance of predictive features.
[RESULTS] In the training cohort, 52.4% of patients developed CIM. The feature selection process identified 19 significant variables that were incorporated into the predictive models. Both LR and RF demonstrated optimal performance, with an AUC of 0.83 and an accuracy of 0.76 in the training set. In the test set, RF continued to outperform other models, achieving an AUC of 0.77 and an accuracy of 0.71. External validation confirmed the robustness of the RF model, which achieved an AUC of 0.93 (95% CI: 0.89-0.97), an accuracy of 0.89, a sensitivity of 0.86, and a specificity of 0.92. SHAP analysis revealed that the most important predictors included hematological parameters, nutritional risk score (NRS2002), and a history of radiotherapy.
[CONCLUSION] The RF-based machine learning model demonstrated high accuracy and strong external validation capability for predicting the risk of CIM in CRC patients.
[METHODS] A total of 450 patients with CRC undergoing chemotherapy were retrospectively enrolled in the training cohort, and an additional 150 patients were included for external validation. Feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. Three machine learning algorithms [Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)] were applied to construct predictive models. Model performance was assessed using multiple metrics, including accuracy, area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity. The SHapley Additive exPlanations (SHAP) method was employed to rank and interpret the importance of predictive features.
[RESULTS] In the training cohort, 52.4% of patients developed CIM. The feature selection process identified 19 significant variables that were incorporated into the predictive models. Both LR and RF demonstrated optimal performance, with an AUC of 0.83 and an accuracy of 0.76 in the training set. In the test set, RF continued to outperform other models, achieving an AUC of 0.77 and an accuracy of 0.71. External validation confirmed the robustness of the RF model, which achieved an AUC of 0.93 (95% CI: 0.89-0.97), an accuracy of 0.89, a sensitivity of 0.86, and a specificity of 0.92. SHAP analysis revealed that the most important predictors included hematological parameters, nutritional risk score (NRS2002), and a history of radiotherapy.
[CONCLUSION] The RF-based machine learning model demonstrated high accuracy and strong external validation capability for predicting the risk of CIM in CRC patients.
같은 제1저자의 인용 많은 논문 (5)
- Pharmacokinetics and Customized Dosing of Vancomycin in Adult Patients With Hematological Malignancies: Status, Challenges, and Opportunities.
- METTL3 stabilizes FASN mRNA by mediating mA modification to promote malignant progression of diffuse large B-cell lymphoma.
- MHC-II-restricted neoantigen vaccine reverses immune microenvironment and overcomes resistance to immune-checkpoint inhibitors in cold tumors.
- Identification and Validation of Alkaliptosis Resistance-Associated Genes in Prostate Cancer Via Transcriptome Sequencing and Prediction of Biochemical Recurrence.
- Clinical characteristics of ground-glass opacities in young patients : a single-center retrospective study.