Related Experiment Video
Updated: Jan 8, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Construction and validation of a cognitive frailty risk prediction model for elderly patients with colorectal cancer
Yu Wang1, Li Wang2, Yunhong Du2
1School of Nursing, Hunan University of Chinese Medicine, Changsha, China.
Background:
Elderly patients with colorectal cancer (CRC) are a high-risk population for cognitive frailty (CF). This study aims to develop and validate a risk prediction model for CF in this specific patient group, so as to facilitate early identification and intervention.
Methods:
This study collected cross-sectional data from 528 elderly patients with CRC who were treated in multiple Grade A Class 3 hospitals in Shandong Province from July 2024 to July 2025. A total of 22 indicators were included. Logistic regression was employed to identify factors associated with CF in elderly patients with colorectal cancer, and R software (version 4.4.3) was used to develop a risk prediction model. The predictive performance and clinical utility of the model were evaluated using metrics including the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA).
Results:
The regression analysis showed that age, chemotherapy history, tumor stage, whether engaging in intellectual activities, social support level, and educational level were independent risk factors for CF in elderly patients with CRC (p < 0.05). The AUC of the modeling group and the validation group was 0.819 and 0.802, respectively; the Hosmer-Lemeshow test results indicated good model fit; the consistency between the actual values and the predicted values of the calibration curve was also high.
Conclusion:
The risk of CF in elderly patients with colorectal cancer is relatively high, and it is related to factors such as age, chemotherapy history, tumor stage, whether engaging in intellectual activities, social support level, and educational level. The risk prediction model for CF in elderly patients with CRC developed in this study exhibits good predictive performance in both internal and external validations. The prediction model constructed in this study can provide a reference for healthcare providers to early identify high-risk individuals and implement targeted intervention measures.
