Abstract
OBJECTIVES: This study aimed to identify risk factors for sleep disorders in gastrointestinal cancer patients undergoing chemotherapy and to construct a predictive nomogram model, validated both internally and externally. METHODS: A prospective study was conducted (ChiCTR2400085854), involving 308 patients from Jiangnan University Affiliated Central Hospital (Oct 2023-Aug 2024) for model development. Sleep quality and symptom burden were assessed using the Pittsburgh Sleep Quality Index (PSQI) and the Memorial Symptom Assessment Scale-Chinese version (MSAS-Ch). Independent risk factors were identified by multivariate logistic regression. A nomogram was constructed using R software and validated internally with 1000 bootstrap resamples and externally with 103 patients (Aug-Dec 2024). Model performance was evaluated by AUC, calibration curves, and decision curve analysis (DCA). RESULTS: The incidence of sleep disorders was 53.8%. Significant influencing factors included longer disease duration, more severe depression, pain, fatigue, and diarrhea, as well as lower social support and physical activity (all P < 0.05). Internal validation showed good discrimination (AUC = 0.897, 95% CI: 0.862-0.931) and calibration. External validation confirmed robust performance (AUC = 0.896, 95% CI: 0.837-0.954) with consistent calibration. DCA demonstrated favorable clinical value. CONCLUSIONS: Sleep disorders are prevalent among gastrointestinal cancer patients undergoing chemotherapy. The developed nomogram demonstrates high predictive accuracy and is a practical tool to identify high-risk patients.