Key result
Machine learning models predict DVT in hospitalized patients with 0.85 AUC.
Why the study?
To evaluate the methodological quality, predictive performance, and clinical applicability of machine learning-based prediction models for deep vein thrombosis in hospitalized patients.
Do machine learning-based prediction models accurately predict deep vein thrombosis in hospitalized adults?
Meta-Analysis
Do machine learning-based prediction models accurately predict deep vein thrombosis in hospitalized adults?
Machine learning models show promising discrimination for predicting DVT in hospitalized patients (pooled AUC 0.85), but clinical applicability is currently limited by methodological weaknesses and lack of external validation.
Answers are grounded in this paper and cite their sources.
Supports ML DVT prediction model development; leaves open routine use pending external validation and heterogeneity reduction.
Objectives To systematically review machine learning–based prediction models for deep vein thrombosis (DVT) in hospitalized patients and to evaluate their methodological quality, predictive performance, and clinical applicability. Methods This systematic review was conducted in accordance with PRISMA and registered in PROSPERO (CRD420251069584). PubMed, Embase, Web of Science, and CINAHL were searched from November 1, 2015, to November 1, 2025. Studies developing, validating, or updating machine learning–based prediction models for DVT in hospitalized adults were included. Data were extracted on study characteristics, data sources, predictors, modeling methods, validation strategies, and model performance. Risk of bias and applicability were assessed using PROBAST. A meta-analysis of validation AUCs was performed in R, and heterogeneity was explored using the Cochrane Q test, I 2 statistic, subgroup analysis, and sensitivity analysis. Results A total of 983 studies were initially identified through database searches. Following screening, 17 studies met the inclusion criteria, of which 10 were included in the meta-analysis. D-dimer, surgery, and age emerged as the most frequently reported predictors across models. Six studies were judged to be at high risk of bias, mainly because of limitations in the analysis domain, including inadequate reporting of missing-data handling, calibration, and validation procedures. The pooled AUC of the 10 validated models was 0.85 (95% CI: 0.81–0.90), indicating good overall discrimination; however, heterogeneity was substantial and remained high in subgroup and sensitivity analyses. Conclusion Machine learning–based models for predicting DVT in hospitalized patients show promising discriminative performance, but their clinical applicability remains limited by methodological weaknesses, poor reporting, substantial heterogeneity, and insufficient external validation. Future studies should prioritize multicenter external validation, transparent reporting, and head-to-head comparison with established clinical risk assessment tools.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2026) conducted a meta-analysis in Deep vein thrombosis (DVT). Machine learning prediction models was evaluated on Validation Area Under the Curve (AUC) (AUC 0.85, 95% CI 0.81-0.90). Machine learning-based prediction models for deep vein thrombosis in hospitalized patients showed good discriminative performance with a pooled AUC of 0.85.
Synapse has enriched 10 related papers. Consider them for comparative context: