Key result
The XGBoost machine learning algorithm predicted major bleeding better than RIETE and VTE-BLEED scores in prospective validation (F1 15.4% vs 8.6% and 6.4%), but failed in external validation.
Why the study?
Predictive tools for major bleeding using machine learning might offer advantages over traditional methods in patients with venous thromboembolism receiving anticoagulation.
Does a machine learning algorithm (XGBoost) improve the prediction of major bleeding compared to traditional scores in patients with VTE on anticoagulation?
Observational (n=49,587)
Does a machine learning algorithm (XGBoost) improve the prediction of major bleeding compared to traditional scores in patients with VTE on anticoagulation?
Answers are grounded in this paper and cite their sources.
Machine learning algorithms for predicting major bleeding in VTE patients showed poor generalizability in external validation compared to traditional risk scores.
Predictive tools for major bleeding (MB) using machine learning (ML) might be advantageous over traditional methods. We used data from the Registro Informatizado de Enfermedad TromboEmbólica (RIETE) to develop ML algorithms to identify patients with venous thromboembolism (VTE) at increased risk of MB during the first 3 months of anticoagulation. A total of 55 baseline variables were used as predictors. New data prospectively collected from the RIETE were used for further validation. The RIETE and VTE-BLEED scores were used for comparisons. External validation was performed with the COMMAND-VTE database. Learning was carried out with data from 49 587 patients, of whom 873 (1.8%) had MB. The best performing ML method was XGBoost. In the prospective validation cohort the sensitivity, specificity, positive predictive value and F1 score were: 33.2%, 93%, 10%, and 15.4% respectively. F1 value for the RIETE and VTE-BLEED scores were 8.6% and 6.4% respectively. In the external validation cohort the metrics were 10.3%, 87.6%, 3.5% and 5.2% respectively. In that cohort, the F1 value for the RIETE score was 17.3% and for the VTE-BLEED score 9.75%. The performance of the XGBoost algorithm was better than that from the RIETE and VTE-BLEED scores only in the prospective validation cohort, but not in the external validation cohort.
No takes yet. Share an insight, caveat, or question.
Mora et al. (2023) conducted an observational in Venous thromboembolism (n=49,587). XGBoost machine learning algorithm vs. RIETE and VTE-BLEED scores was evaluated on Major bleeding prediction (F1 score in prospective validation). The XGBoost machine learning algorithm predicted major bleeding better than RIETE and VTE-BLEED scores in prospective validation (F1 15.4% vs 8.6% and 6.4%), but failed in external validation.
Synapse has enriched 10 related papers. Consider them for comparative context: