Table 2_Machine learning approaches for risk prediction in aortic dissection: a systematic

A systematic review and meta-analysis of 40 studies evaluating machine learning models for predicting adverse outcomes in aortic dissection, published up to September 2025. The analysis, conducted by Yijun Mao and following PRISMA guidelines, synthesized performance metrics like C-statistics for outcomes including early mortality and acute kidney injury. The document was last updated on March 26, 2026.

Use Cases

• Benchmarking machine learning model performance for aortic dissection risk prediction based on the reported pooled C-statistics.
• Identifying methodological gaps in clinical ML studies based on the reported PROBAST risk-of-bias assessment.
• Informing the design of future prediction models based on the analysis of common algorithms like random forest and XGBoost.
• Assessing reporting standards adherence in medical AI research based on the TRIPOD compliance metrics.

Strengths

• Analysis is based on 40 included studies, providing a substantial evidence base.
• Reports specific pooled performance metrics, such as a C-statistic of 0.891 for early mortality prediction.
• Follows established methodological guidelines including PRISMA, CHARMS, and TRIPOD.
• Includes detailed subgroup and sensitivity analyses as mentioned in the description.

Limitations

• The 17.7 KB file size suggests the document is a summary or table, not the underlying dataset.
• Column-level documentation and sample data are unavailable, limiting understanding of the raw data structure.
• The description notes significant methodological heterogeneity and high risk of bias across the reviewed studies.

Provenance

Source

Yijun Mao via figshare

Collection Method

Systematic review and meta-analysis of six major databases (PubMed, Web of Science, Cochrane Library, Embase, CNKI, Wanfang).

Time Range

Studies from database inception to September 30, 2025.

Freshness

Last updated 2026-03-26 06:23:34