Objective To systematically evaluate the research quality and efficacy of prediction models for acute kidney injury (AKI) after heart valve surgery, screen key predictive factors, and provide evidence-based basis for clinical risk assessment. Methods Computer search was carried out in PubMed, Web of Science, EMBASE, Cochrane Library, Medline, China Biology Medicine Database, China National Knowledge Infrastructure, Wanfang Database, and VIP Database to collect studies on AKI prediction models after heart valve surgery published from January 2015 to July 2025. The PROBAST tool was used to evaluate the bias risk and applicability of the models, and the TRIPOD was used to assess the reporting quality. Meta-analysis was performed to integrate the effect sizes of high-frequency (≥3 times) predictive factors. Results A total of 24 studies (39 models) were included. Area under the curve (AUC) of the receiver operational characteristic curve was between 0.551 and 0.928, and the combined AUC was 0.77 (95%CI 0.72-0.82). The overall bias risk of the models was relatively high (100% of the studies had a high bias risk), only 2 studies conducted external validation, and the models in 10 studies were not validated. In terms of TRIPOD reporting quality, the overall reporting quality of 24 studies was low, with a compliance percentage (number of items) ranging from 36.36% to 77.27%. Meta-analysis showed that age (OR=1.041, P=0.006), diabetes (OR=1.64, P=0.001), hypertension (OR=2.529, P <0.001), blood transfusion (OR=1.49, P=0.001), cystatin C (OR=2.408, P=0.018), history of cardiac surgery (OR=2.585, P <0.001), atrial fibrillation (OR=1.33, P <0.001), and vascular complications (OR=1.22, P=0.008) were independent risk factors for postoperative AKI. Conclusion The clinical applicability of existing prediction models is limited, with high bias risk and low reporting quality, and the methodology needs to be optimized. Eight factors such as age and hypertension can be used as core indicators for postoperative AKI risk assessment. In the future, multicenter prospective studies should be carried out to develop more reliable prediction tools.