New Study Reveals Insights into Chronic Coronary Disease Prediction with Machine Learning

Strategic Insights -

Researchers at Wannan Medical College, Anhui, People's Republic of China, have conducted a study to develop a machine learning model for predicting Chronic Coronary Disease (CCD) using text data and baseline characteristics. The study aimed to improve existing Pre-test Probability (PTP) models, which mainly rely on in-hospital data and clinician judgment. The researchers gathered text data from the internal medicine departments of two hospitals and employed machine learning algorithms to establish prediction models.

Key Takeaways:

  • The study enrolled a total of 21,855 patients, with 7,449 in the CCD group and 14,406 in the non-CCD group.
  • Patients in the CCD group were generally older and had a higher male proportion.
  • The Random Forest model achieved an area under the ROC curve (AUC) of 0.93 (95% CI, 0.93-0.94), demonstrating excellent performance.
  • The SHAP algorithm identified valuable text features like 'chest pain', 'chest tightness', and structured features such as age, which are crucial for CCD judgment.
  • Clinicians can leverage text data to construct a prediction model for CCD and apply the SHAP approach to pinpoint valuable text features and elucidate the model's decision-making mechanism.
  • The study has implications for improving the diagnosis and treatment of Chronic Coronary Disease.

Statistics:

  • Total patients enrolled in the study: 21,855
  • Patients in the CCD group: 7,449
  • Patients in the non-CCD group: 14,406
  • Age range of patients in the CCD group: older
  • Male proportion in the CCD group: higher
  • Area under the ROC curve (AUC) for the Random Forest model: 0.93 (95% CI, 0.93-0.94)

Sources:

  • Frontiers in Cardiovascular Medicine. Research Results from Wannan Medical College Update Knowledge of Heart Disease (An explainable machine learning model for predicting chronic coronary disease and identifying valuable text features). 2025;12:1559831
  • Frontiers Media Sa, Avenue Du Tribunal Federal 34, Lausanne, Ch-1015, Switzerland
  • NewsRx LLC. Research Results from Wannan Medical College Update Knowledge of Heart Disease (An explainable machine learning model for predicting chronic coronary disease and identifying valuable text features). Cardiovascular Week. October 20, 2025; p 124.