Background: Psychological disorders, such as anxiety and depression, are considered to be one of the causes of noncardiac chest pain (NCCP). And these patients can be challenging to differentiate from coronary artery disease (CAD), leading to a considerable number of patients still undergoing angiography. We aim to develop a practical prediction model and nomogram using cardiopulmonary exercise testing (CPET), to help identify these patients.
Methods: 1,531 eligible patients' electronic medical record data were obtained from Guangdong Provincial People's Hospital. They were randomly divided into a training dataset (N = 918) and a testing dataset (N = 613) at a ratio of 6:4, and 595 cases without missing data were also selected from testing dataset to form a complete dataset. The training set is used to build the model, and the testing set and the complete set are used for internal validation. Eight machine learning (ML) methods are used to build the model and the best model is finally adopted.
Results: The model built by logistic regression performed the best, and among the 29 parameters, six parameters were determined to be valuable parameters for establishing the diagnostic equation and nomogram. The nomogram showed favorable calibration and discrimination with an area under the receiver operating characteristic curve (AUC) of 0.857 in the training set, 0.851 in the testing set, and 0.848 in the complete set. Meanwhile, decision curve analysis demonstrated the clinical utility of the nomogram.
Conclusions: A nomogram using CPET to distinguish anxiety/depression from CAD was developed. It may optimize the disease management and improve patient prognosis.
Keywords: Anxiety and depression; Cardiopulmonary exercise testing; Coronary artery disease; Diagnostic predictive models; Nomogram.
© 2024. The Author(s).