Key result
Super learner machine learning models improved VTE prediction compared to the IMPROVE score, identifying a highest-risk tertile with an 11.4% event rate and a 5-fold increased odds of VTE.
Why the study?
Integer-based scoring systems for identifying acutely ill patients at high risk for VTE have demonstrated modest performance in external data sets.
Do machine learning models improve the prediction of venous thromboembolism compared to the IMPROVE score in acutely medically ill patients?
Observational (n=7,513)
Do machine learning models improve the prediction of venous thromboembolism compared to the IMPROVE score in acutely medically ill patients?
Machine learning models, including a reduced 16-variable model, offer improved discrimination and calibration over the standard IMPROVE score for predicting VTE in acutely ill medical patients.
Answers are grounded in this paper and cite their sources.
May refine VTE stratification in medical inpatients; hypothesis-generating and requires prospective validation before practice change.
BACKGROUND: The identification of acutely ill patients at high risk for venous thromboembolism (VTE) may be determined clinically or by use of integer-based scoring systems. These scores demonstrated modest performance in external data sets. OBJECTIVES: To evaluate the performance of machine learning models compared to the IMPROVE score. METHODS: The APEX trial randomized 7513 acutely medically ill patients to extended duration betrixaban vs. enoxaparin. Including 68 variables, a super learner model (ML) was built to predict VTE by combining estimates from 5 families of candidate models. A "reduced" model (rML) was also developed using 16 variables that were thought, a priori, to be associated with VTE. The IMPROVE score was calculated for each patient. Model performance was assessed by discrimination and calibration to predict a composite VTE end point. The frequency of predicted risks of VTE were plotted and divided into tertiles. VTE risks were compared across tertiles. The observed event rate in the lowest tertile was 2.5%, 4.8% in tertile 2, and 11.4% in the highest tertile. Patients in the highest tertile of VTE risk had a 5-fold increase in odds of VTE compared to the lowest tertile. CONCLUSION: The super learner algorithms improved discrimination and calibration compared to the IMPROVE score for predicting VTE in acute medically ill patients.
No takes yet. Share an insight, caveat, or question.
Nafee et al. (2020) conducted an observational in Venous thromboembolism in acutely medically ill patients (n=7,513). Super learner machine learning models (ML and rML) vs. IMPROVE score was evaluated on Composite VTE end point (OR 5). Super learner machine learning models improved VTE prediction compared to the IMPROVE score, identifying a highest-risk tertile with an 11.4% event rate and a 5-fold increased odds of VTE.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: