Systematic Review and Meta-Analysis of AI Prediction Models for Prostate Cancer Outcomes

85 studies were included in a meta-analysis of artificial intelligence models for predicting prostate cancer outcomes. The review, authored by Emmanuel Nsedu Israel and last updated in May 2026, examined pooled predictive performances across five endpoints using area under the curve (AUC) metrics. It is a CC-BY-4.0 licensed document summarizing findings from a systematic review registered with PROSPERO.

Use Cases

• Benchmarking new prostate cancer prediction models based on reported AUC performance metrics.
• Assessing methodological quality of clinical AI studies based on the Prediction Model Quality Score (PMQS) framework.
• Identifying research gaps in model validation for endpoints like overall survival (OS) or progression-free survival (PFS).
• Informing clinical translation efforts based on the review's conclusions about reproducibility and external validation needs.

Strengths

• The meta-analysis provides a quantitative summary of model performance, reporting pooled AUC values for five distinct clinical endpoints.
• Methodological rigor is indicated by adherence to PRISMA criteria and a registered PROSPERO protocol (CRD42025611480).
• Publication bias was assessed using funnel plots, Egger’s regression test, and the trim-and-fill method.

Limitations

• The dataset is a 188.9 KB DOCX document summarizing results; the underlying study-level data or model outputs are not provided.
• Column-level documentation is absent; field semantics must be inferred from the review text after download.
• Row count is unknown, which may limit suitability assessment for direct data analysis.

Provenance

Source

figshare

Collection Method

Systematic review and meta-analysis of studies from PubMed and Scopus.

Freshness

Last updated 2026-05-01 05:28:15; freshness should be verified.