就医延迟风险预测模型的范围综述OA

Objective:To conduct a scoping review of risk prediction models for delayed medical care,in order to provide reference for clinical practice and related research.Methods:Literature related to risk prediction models for delayed medical care was retrieved from both Chinese and English databases,including CNKI,Wanfang,VIP,SinoMed,PubMed,Embase,Web of Science,CINAHL,and the Cochrane Library,covering all records up to June 2025.Two researchers independently screened the literature,extracted data,and performed quality assessment and content analysis of the included studies.Results:A total of 14 studies were included,encompassing 34 predictive models for delayed medical care.The area under the ROC curve(AUC)of these models ranged from 0.530 to 0.979.Four studies underwent external validation.The most commonly identified predictors included age,health insurance status,gender,place of residence,ethnicity,and lack of regular physical examinations.Conclusion:Research on prediction models for medical treatment delay is still in the early exploratory stage.Although the models demonstrate relatively good predictive performance,they carry a high risk of bias.Future studies need to standardize the model development and validation processes to create predictive tools that combine high accuracy with clinical utility,thereby providing high-quality decision-making support for healthcare professionals and patients.