Construction and verification of a prediction model for sleep disorders in older patients with coronary heart disease based on machine learning algorithms - Report - MDSpire

Construction and verification of a prediction model for sleep disorders in older patients with coronary heart disease based on machine learning algorithms

  • By

  • Dali Dong

  • Xiang Peng

  • Siling Tan

  • Hua He

  • June 30, 2026

  • 0 min

Share

Clinical Report: Predictive Model for Sleep Disorders in Elderly with CHD

Overview

This study developed and validated a machine learning-based predictive model for sleep disorders in older adults with coronary heart disease (CHD). The model identified key risk factors such as sex, duration of CHD, chronic gastritis, anxiety, and depression.

Background

Coronary heart disease (CHD) is a leading cause of morbidity and mortality, particularly among older adults. Sleep disorders are prevalent in this population and can significantly impact recovery and long-term outcomes.

Data Highlights

ModelAUCAccuracySensitivitySpecificityF1 Score
Random Forest (Training Set)0.8390.7660.812N/A0.818
Gradient Boosting Machine (Validation Set)0.8380.733N/AN/A0.825
Logistic Regression (Validation Set)0.785N/A0.7980.8750.825

Key Findings

  • 24.26% of older adults with CHD experienced sleep disorders.
  • LASSO regression identified five key risk factors: sex, duration of CHD, chronic gastritis, anxiety, and depression.
  • The Random Forest model achieved the highest AUC of 0.839 in the training set.
  • The Gradient Boosting Machine model showed an AUC of 0.838 in the validation set.
  • Logistic regression demonstrated the best specificity (0.875) in the validation cohort.
  • External validation of the Logistic regression model yielded an AUC of 0.785.

Clinical Implications

The predictive models developed in this study can assist clinicians in identifying older CHD patients at risk for sleep disorders.

Conclusion

The study developed machine learning models that predict sleep disorders in older adults with CHD.

Related Resources & Content

  1. BMC Psychiatry, Springer, 2025 -- Creation, assessment, and illustration of a machine learning-driven model to predict depression risk among patients with sleep disorders
  2. DIGITAL HEALTH, 2026 -- Development of a machine learning-based depression risk prediction model for middle-aged and elderly Chinese heart disease patients: Evidence from CHARLS data
  3. Frontiers in Cardiovascular Medicine, 2026 -- Evaluation of coronary heart disease risk prediction based on simple physical examination parameters by machine learning model: a retrospective cohort model development and validation study
  4. conexiant — One Night's Sleep May Predict 130 Diseases
  5. Sleep matters: duration, timing, quality and more may affect cardiovascular disease risk | American Heart Association
  6. Recommendation: Obstructive Sleep Apnea in Adults: Screening | United States Preventive Services Taskforce
  7. Polysomnography for OSA should include arousal-based scoring
  8. https://aasm.org/wp-content/uploads/2026/02/inpatient-sleep-apnea-guideline-AASM-2025.pdf
  9. Sleep Apnea Cardiovascular Endpoints - American College of Cardiology
  10. Effect of obstructive sleep apnoea and its treatment with continuous positive airway pressure on the prevalence of cardiovascular events in patients with acute coronary syndrome (ISAACC study): a randomised controlled trial - ScienceDirect
  11. Obstructive sleep apnea and the risk of sudden cardiac death: a systematic review and meta-analysis | BMC Cardiovascular Disorders | Springer Nature Link
  12. Frontiers | Prevalence and influencing factors of insomnia in patients with coronary heart disease: a systematic review and meta-analysis
  13. Frontiers | Gender correlation between sleep duration and risk of coronary heart disease: a systematic review and meta-analysis
  14. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods | The BMJ

Original Source(s)

Construction and verification of a prediction model for sleep disorders in older patients with coronary heart disease based on machine learning algorithms

  • by Dali Dong, Xiang Peng, Siling Tan, Hua He

  • June 30, 2026

Related Content

Echo AI: From Innovation to Adoption

Experts examined the evidence, practical applications, and barriers shaping AI integration in echocardiography.

Prehypertension in young physically active adults: early vascular alterations and implications for exercise-intensity prescription

Metabolic Health Tied to Dementia

In two population-based cohorts, metabolically unhealthy status generally showed higher dementia risk estimates, while metabolically healthy obesity was not associated with increased risk in primary analyses.