Xia Y, Zhang M, Yao Y, Cai T, Mo H, Shen J, Lou J. Epidemiology and reporting characteristics of systematic reviews of clinical prediction models: a scoping review.
J Clin Epidemiol 2025;
182:111763. [PMID:
40122153 DOI:
10.1016/j.jclinepi.2025.111763]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2024] [Revised: 03/09/2025] [Accepted: 03/17/2025] [Indexed: 03/25/2025]
Abstract
OBJECTIVES
This study aimed to explore research trends and areas of interest in systematic reviews (SRs) and meta-analysis of clinical prediction models (CPMs), while summarizing their conduct and reporting characteristics.
STUDY DESIGN AND SETTING
A scoping review was conducted, with searches performed in PubMed, Embase, and Cochrane Library from inception to January 7, 2023. Pairs of reviewers independently screened potentially eligible studies. Data on bibliographic and methodological characteristics were collected and analyzed descriptively.
RESULTS
A total of 1004 SRs published between 2001 and 2023 were included. The number of SRs increased significantly after 2020, with the majority originating from Europe (44.1%) and Asia (26.7%). Populations and outcomes were categorized into 19 and 34 classifications, respectively. The general population was the most frequently targeted (38.7%), and mortality was the most common outcome (18.9%). The prediction or diagnosis of neoplasms in the general population was the most prevalent focus (7.2%). Prognostic models were included only in 69.6% of SRs, while diagnostic models were included in 16.8%; 13.6% included both. The number of primary studies included in SRs ranged from 1 to 495, and the models ranged from 1 to 731. Most SRs lacked standardized reporting: 88.3% did not frame their review questions using established frameworks, and 79.8% did not follow standardized checklists for data extraction. Quality and risk of bias assessments were reported in 76.5% of SRs, with the Prediction model Risk of Bias Assessment Tool (27.9%) and the Quality Assessment of Diagnostic Accuracy Studies-2 tool (17.0%) being the most common. Narrative synthesis was the predominant method for evidence summarization (63.5%), while meta-analysis was conducted in 36.5%. Measures of model performance were summarized in 80.5% of SRs, with discrimination being the most frequently reported (67.7%). Only 5.2% assessed the certainty of evidence. Moreover, 42.2% of SRs published a protocol, 76.0% clearly stated support, and 91.1% stated competing interests.
CONCLUSION
The number of SRs of CPMs has grown substantially, with increasing diversity in populations and outcomes. However, significant variability in conduct and reporting was observed. Future SRs should strictly follow well-developed guidelines, and a dedicated study assessing the reporting quality and risk of bias in SRs of CPMs is warranted.
Collapse