EUVIMEDEUVIMED entdecken
Crossref

An explainable predictive machine learning model of oxaliplatin induced peripheral neuropathy based on clinical data: a retrospective single center

Juan Lv, Fen Xie, Ruirong Wu, Ying Zhang, Hehe Tang, Wenxiu Tian, Yongjuan Ding, Yujiao Hua

Supportive Care in Cancer · 2026-07 · 34 (7)

DOI: 10.1007/s00520-026-10877-7 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Supportive Care in Cancer, online erschienen am 08.06.2026. Verfasst von Juan Lv und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Pharmacy, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu Province, 214122, China. Hauptthemen laut MEDLINE: Antineoplastic Agents, Colorectal Neoplasms, Oxaliplatin, Peripheral Nervous System Diseases. Die Arbeit nennt 51 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Oxaliplatin (OXA) is widely used in the treatment of gastrointestinal malignancies such as colorectal cancer. However, oxaliplatin-induced peripheral neuropathy (OIPN) is a common and distinctive adverse effect, with a high incidence rate. Characterized by numbness and paresthesia in the extremities, OIPN is dose-limiting, often irreversible, and significantly impacts patients' quality of life. Current assessment relies primarily on subjective symptoms, and effective predictive models are lacking. This single-center retrospective cohort study included 829 colorectal cancer patients receiving oxaliplatin chemotherapy. Fourteen core features were screened from 104 potential variables using Lasso regression, Boruta algorithm, Recursive Elimination Feature with Cross-Validation (REFCV), and Gradient Boosting Decision Trees (GBDT). Five machine learning models were developed and evaluated. Model optimization was performed using fivefold cross-validation, and performance was assessed via metrics including the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA). SHAP (SHapley Additive exPlanations) analysis was employed to interpret the model, and an online risk calculator was developed. The GBDT model demonstrated the best performance, with an AUC of 0.997 (95% CI: 0.994–1.000) in the training set, 0.908 (0.854–0.962) in the validation folds, and 0.892 (0.837–0.947) in the internal test set. High calibration accuracy was observed, and DCA showed significant net benefit. SHAP analysis identified cumulative oxaliplatin dose (Total OXA), body mass index (BMI), carcinoembryonic antigen (CEA), apolipoprotein A1 (APOA-1), Sex, and cold exposure (ETCO) as the top six core predictors for OIPN, with total OXA exhibiting the most significant and dose-dependent impact. This study demonstrates that the GBDT machine learning model effectively predicts OIPN risk in colorectal cancer patients. Combined with SHAP analysis, the model's interpretability is enhanced. The developed online calculator provides a reliable tool for early clinical identification of high-risk patients and personalized intervention strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Antineoplastic AgentsColorectal NeoplasmsOxaliplatinPeripheral Nervous System DiseasesPredictive Learning ModelsAdultAgedFemaleHumansMaleMiddle AgedBoosting Machine Learning AlgorithmsCohort StudiesMachine LearningQuality of LifeRetrospective StudiesROC Curve

Stichwörter der Autor:innen

Colorectal cancerInterpretable machine learningOxaliplatin induced peripheral neuropathyRisk prediction mode

Substanzen

Antineoplastic AgentsOxaliplatin

Autor:innen und Institutionen

  • Department of Clinical Pharmacy, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu Province, 214122, China.
  • Department of Medical Oncology, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu Province, 214122, China.
  • Department of Clinical Pharmacy, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu Province, 214122, China. dingyongjuan2021@163.com.
  • Department of Clinical Pharmacy, Affiliated Hospital of Jiangnan University, Wuxi, Jiangsu Province, 214122, China. huayujiao1020@163.com.
  • School of Life Sciences and Health Engineering, Jiangnan University, Wuxi, Jiangsu Province, 214122, China. huayujiao1020@163.com.

Zitieren

APA

Lv, J., Xie, F., Wu, R., Zhang, Y., Tang, H., Tian, W., Ding, Y., & Hua, Y. (2026). An explainable predictive machine learning model of oxaliplatin induced peripheral neuropathy based on clinical data: a retrospective single center. Supportive Care in Cancer, 34(7). https://doi.org/10.1007/s00520-026-10877-7

Vancouver

Lv J, Xie F, Wu R, Zhang Y, Tang H, Tian W, et al. An explainable predictive machine learning model of oxaliplatin induced peripheral neuropathy based on clinical data: a retrospective single center. Supportive Care in Cancer. 2026;34(7). doi:10.1007/s00520-026-10877-7

BibTeX
@article{Lv2026,
  author = {Lv, Juan and Xie, Fen and Wu, Ruirong and Zhang, Ying and Tang, Hehe and Tian, Wenxiu and Ding, Yongjuan and Hua, Yujiao},
  title = {An explainable predictive machine learning model of oxaliplatin induced peripheral neuropathy based on clinical data: a retrospective single center},
  journal = {Supportive Care in Cancer},
  year = {2026},
  volume = {34},
  number = {7},
  doi = {10.1007/s00520-026-10877-7}
}
Kostenlos starten →