Integrating liquid biopsies and artificial intelligence for early cancer detection: A systematic review and meta-analysis

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Sensitivity: 72-92% (stages I-III), Specificity: 94-99%

• Primary Outcome: Diagnostic accuracy for early cancer detection using ML-integrated cfDNA analysis

• Nnt Or Sensitivity: Best performing approaches: Neural networks (90%), Random forest (86%), Ensemble learning (85%)

• Confidence Interval: Neural networks: 90% sensitivity (95% CI: 81%-95%)

Clinical Application

Currently limited by technology availability, cost, and need for specialized laboratory infrastructure Would require TGA approval for diagnostic use, PBS consideration for funding, and integration with existing cancer screening programs (BreastScreen, National Bowel Cancer Screening Program) Patients at risk for multiple cancer types, particularly suitable for population screening programs

Abstract

INTRODUCTION: The latest generation of liquid biopsies incorporates multi-omic features, including genomics, methylomics, and fragmentomics. Machine learning (ML) approaches have been proposed to synthesize these complex biological data for the development of diagnostic classifiers. This study aims to evaluate the integration of ML with circulating cell-free DNA (cfDNA) analysis for early cancer detection. METHODS: Medline, Embase, Cochrane, and Web of Science were searched in July 2025. Eligible studies combined ML and cfDNA features to distinguish cancer patients (stages I-III) from non-cancer controls. Summary diagnostic performance metrics and their 95% confidence intervals (CI) were calculated. RESULTS: The study included 109 articles permitting analyses for lung (n = 34), liver (n = 29), colorectal (n = 28), pancreatic (n = 16), breast (n = 17), esophageal (n = 12), ovarian (n = 13), gastric (n = 9), head and neck (n = 4), and mixed (n = 27) cancer types. Specificity was consistently high across all tumor types and stages (94%-99%). Sensitivity ranged from 72% to 92% for stage I-III, 44-91% for stage I, 71-98% for stage II and 83-99% for stage III. In the pooled study population, neural networks (90%, 95% CI: 81%-95%), random forest (86%, 95% CI: 77%-92%) and heterogeneous ensemble learning (85%, 95% CI: 79%-89%) demonstrated the highest sensitivity. The stratified analysis by classifier feature revealed 86% (95% CI: 80%-90%) sensitivity for fragmentation and 81% (95% CI: 76%-85%) for methylation, with 92%-96% specificity. CONCLUSION: ML and cfDNA profiling show potential for early cancer detection, with ensemble methods, neural networks and random forests achieving the best overall performance. Fragmentomic features provide the highest sensitivity.

References

1. 1.Filis, P., Markozannes, G., Salgkamis, D., Tsiknakis, N., Zerdes, I., Pagkalidou, E., Manou, M., Filis, N., Papakonstantinou, A., Mavroudis, D., Matikas, A., Tsilidis, K. K., & Foukakis, T. (2026). Integrating liquid biopsies and artificial intelligence for early cancer detection: A systematic review and meta-analysis. European Journal of Cancer, 116699. https://doi.org/10.1016/j.ejca.2026.116699