Objective To investigate the factors influencing quality of life in patients with chemotherapy-induced peripheral neuropathy (CIPN) and to construct a risk prediction model.

Methods Patients with CIPN admitted to our hospital from January 2022 to December 2024 were selected. Based on the mean score of the Functional Assessment of Cancer Therapy-General (FACT-G) scale, 262 patients were divided into good quality of life group and poor quality of life group. Clinical data were compared between the two groups. Binary logistic regression was used to identify factors influencing quality of life, and a nomogram prediction model was constructed. The predictive performance of the model was evaluated using receiver operating characteristic (ROC) curve, calibration curve, Hosmer-Lemeshow goodness-of-fit test, and decision curve analysis.

Results The 262 patients were divided into a good group (135 cases) and a poor group (127 cases) based on the mean FACT-G score of 84.65 ± 13.65. Multivariate analysis showed that marital status (odds ratio OR = 2.317, 95% CI: 1.037-5.176), renal dysfunction (OR = 2.635, 95% CI: 1.197-5.801), tumor TNM stage T2 (OR = 2.744, 95% CI: 1.095-6.878), stage T3 (OR = 0.301, 95% CI: 0.110-0.828), anxiety (OR = 2.763, 95% CI: 1.260-6.060), pain (OR = 4.651, 95% CI: 1.998-10.828), vomiting (OR = 3.459, 95% CI: 1.567-7.637), insomnia (OR = 5.215, 95% CI: 1.789-15.197), and somnolence (OR = 3.870, 95% CI: 1.387-10.795) were independent influencing factors for quality of life in CIPN patients (all P < 0.05).The nomogram prediction model was established based on the above factors. In the training cohort, the AUC of the ROC curve was 0.864 (95% CI: 0.813-0.915). The specificity and sensitivity corresponding to the optimal cut-off value were 0.827 (95% CI: 0.752-0.901) and 0.741 (95% CI: 0.648-0.834), respectively. In the validation cohort, the AUC was 0.803 (95% CI: 0.707-0.900), with a specificity of 0.703 (95% CI: 0.555-0.850) and a sensitivity of 0.738 (95% CI: 0.605-0.871) at the optimal cut-off value, suggesting good diagnostic efficacy of the model. The ideal curve aligns well with the calibration curve, and the Hosmer-Lemeshow test indicates that the model is well calibrated. Decision curve analysis demonstrated a high net benefit of the model within the range of 0.5 to 1.0.

Conclusion Marital status, renal dysfunction, tumor TNM staging, anxiety, pain, vomiting, insomnia, and somnolence are factors associated with a lower quality of life in patients with CIPN. The prediction model constructed based on these factors exhibits good discrimination and calibration, which can facilitate clinical assessment of quality of life in CIPN patients.