Risk prediction of severe chemotherapy-induced peripheral neuropathy in breast cancer patients receiving nab-paclitaxel: a clinical nomogram.

IMPORTANCE: Chemotherapy-induced peripheral neuropathy (CIPN) is a frequent and dose-limiting toxicity of nab-paclitaxel in breast cancer patients. Severe CIPN can impair quality of life, limit treatment adherence, and lacks validated prediction tools for early risk stratification. OBJECTIVE: To identify risk factors for grade ≥3 CIPN in breast cancer patients treated with nab-paclitaxel and to develop a predictive model for individualized risk assessment. DESIGN: Retrospective cohort study using clinical data from January 2021 to January 2025. Predictors were selected with least absolute shrinkage and selection operator (LASSO) regression and included in multivariable logistic regression. A nomogram was constructed, and model performance was evaluated using area under the curve (AUC), Hosmer-Lemeshow test, calibration curve, and decision curve analysis. Restricted cubic spline analysis examined nonlinear associations of body mass index (BMI) and total bilirubin (TBIL) with CIPN risk. SETTING: Mianyang Central Hospital, a tertiary referral center in China. PARTICIPANTS: A total of 403 breast cancer patients receiving nab-paclitaxel. Among them, 13.2% (53/403) developed CIPN ≥ Grade 3. Patients with severe CIPN more frequently had higher BMI, elevated TBIL, smoking or alcohol drinking, and diabetes, and lower platelet count, total protein, and hemoglobin (all P < 0.05). MAIN OUTCOMES AND MEASURES: Occurrence of CIPN ≥ Grade 3 according to Common Terminology Criteria for Adverse Events (CTCAE) v5.0. RESULTS: LASSO identified BMI, TBIL, smoking, alcohol drinking, and diabetes as key predictors. All were confirmed as independent risk factors in multivariable analysis, with diabetes showing the strongest association (adjusted OR = 4.01). The nomogram demonstrated good discrimination (AUC = 0.78), calibration (P = 0.898), and clinical utility. Restricted cubic spline analysis showed a linear association between TBIL and CIPN risk, and significantly increased risk with BMI ≥24 kg/m2. CONCLUSION AND RELEVANCE: Elevated BMI, smoking, Alcohol drinking, diabetes, and TBIL are independent risk factors for severe CIPN in patients with breast cancer treated with nab-paclitaxel. The proposed nomogram may support early identification of high-risk patients and guide individualized prevention and management strategies.