Predicting Chemotherapy-Induced Peripheral Neuropathy: Development and Internal Validation of the Novel Foresight Neuro-Wing Model.

BACKGROUND: Chemotherapy-induced peripheral neuropathy (CIPN) is a frequent and debilitating side effect that significantly reduces cancer patients' quality of life, limits treatment tolerance, and can compromise treatment efficacy. Accurate prediction of CIPN risk is crucial for targeted interventions. OBJECTIVE: To develop and validate a risk prediction model, Foresight Neuro-Wing, for identifying patients at increased risk of CIPN during chemotherapy with common cytotoxic agents. METHODS: A retrospective cohort study was used to analyze the electronic medical records of patients receiving chemotherapy at a single institution. Potential risk factors (demographic characteristics, as well as cancer-related and chemotherapy-related factors) were assessed using logistic regression. Model performance was evaluated using area under the receiver operating characteristic curve and calibration plots. Internal validation involved bootstrapping and cross-validation. A classified score model stratified patients into 4 risk groups. RESULTS: A total of 346 patients met the inclusion criteria. The incidence of CIPN was 33.5% (n = 116). Significant predictors included sex, underlying disease, cancer type, previous and current chemotherapy regimens, and number of chemotherapy cycles. The scoring model achieved a predictive performance of 87.33%, and the classified score model had a predictive performance of 85.93%. Decision curve analysis demonstrated that using the model to guide intervention decisions provided a greater net benefit than treating all or treating none. CONCLUSIONS: The Foresight Neuro-Wing model effectively identified patients at increased risk of CIPN. This tool has the potential to inform clinical decision-making, enabling targeted monitoring and preventive strategies, ultimately improving patient outcomes and quality of life.