Objective:

To construct and validate a predictive model for sleep disorders in older adults with coronary heart disease (CHD) using machine learning algorithms.

Approach:

• Study Design: A cross-sectional survey design was employed to collect clinical data from 338 older adult patients with CHD.
• Data Collection: Participants were divided into two groups based on the presence of sleep disorders, and data were collected from questionnaires and electronic medical records.
• Model Development: LASSO regression was used to screen risk factors, and Logistic regression, random forest (RF), and gradient boosting machine (GBM) models were built.
• Model Evaluation: Receiver operating characteristic (ROC) and calibration curves evaluated model performance, with a temporal validation cohort of 152 older CHD patients.

Key Findings:

• 24.26% of patients had sleep disorders, with 58 (24.07%) in the training group.
• LASSO identified five risk factors: sex, duration of CHD, chronic gastritis, anxiety, and depression.
• The RF model achieved the highest AUC (0.839) and accuracy (0.766) in the training set.
• In the validation set, the GBM model achieved the highest AUC (0.838) and accuracy (0.733).
• The Logistic regression model demonstrated the best specificity (0.875) and F1 score (0.825).

Interpretation:

The Logistic regression, GBM, and RF models based on identified risk factors demonstrated good predictive performance for sleep disorders in older adults with CHD.

Limitations:

• The study was conducted in a single hospital, which may limit generalizability.
• The sample size for the validation cohort was relatively small.

Conclusion:

The study provides a scientific basis for the early identification of sleep disorder risk and targeted intervention in older patients with CHD.