Heart failure (HF) is a major chronic condition that significantly impacts humanl health. Coronary heart disease (CHD) is the leading cause of HF. Developing risk prediction models for HF in patients with CHD is crucial for enabling healthcare professionals to identify high-risk populations and implement timely interventions.

To systematically evaluate risk prediction models for HF with CHD in Chinese patients, serving as a reference for the development, selection, and dissemination of relevant predictive models.

CNKI, Wanfang Data, VIP, SinoMed, PubMed, Embase, Web of Science and the Cochrane Library were searched for relevant studies on risk prediction models for HF with CHD in Chinese patients up to October 2024. Two reviewers independently screened the literature, extracted data, and assessed the risk of bias and applicability of the included studies using the Prediction Model Risk of Bias Assessment Tool (PROBAST).

A total of 27 studies were included, reporting 64 risk prediction models. The area under the receiver operating characteristic (ROC) curve (AUC) or these models ranged from 0.511 to 0.989, with 63 models achieving an AUC>0.7, indicating good predictive performance. However, PROBAST assessment revealed that all 27 studies had a high risk of bias and low applicability. Key predictive factors included age, left ventricular ejection fraction, history of diabetes, history of hypertension, N-terminal pro-B-type natriuretic peptide, and Gensini score.

The stability and external validity of existing risk prediction models for HF with CHD in Chinese patients require further validation through prospective, large-scale studies. Future model development should adhere strictly to PROBAST guidelines to ensure the design and implementation of high-quality, generalizable predictive models.