ObjectiveTo systematically evaluate prediction models for in-hospital mortality risk in patients with acute myocardial infarction (AMI). MethodsA comprehensive search was conducted in PubMed, Embase, Web of Science, Cochrane Library, and CNKI databases from inception to May 30, 2025, to identify studies related to AMI in-hospital mortality prediction models. Risk of bias and applicability were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Relevant data were extracted for model quality assessment. ResultsA total of 29 studies involving 75 AMI in-hospital mortality prediction models were included. Key predictive factors identified included Killip classification, neutrophil count, renal insufficiency, age, systolic blood pressure, and left ventricular ejection fraction. The area under the receiver operating characteristic curve (AUC) ranged from 0.580 to 0.998. Internal validation was reported in 21 studies, external validation in 4, and both in 4 studies. Model calibration was evaluated in 23 studies. Most models were presented as nomograms. All studies demonstrated good applicability, though 25 were rated as high risk of bias overall. ConclusionCurrent AMI in-hospital mortality prediction models show generally good predictive performance, with some variables exhibiting stable predictive effects. However, the lack of external validation and high risk of bias remain prevalent issues. Future studies should focus on prospective, multicenter, high-quality designs to enhance the practical and clinical value of these models.