Comparison of machine learning methods for prediction of venous thromboembolism among hospitalized adults
Vergleich von Machine-Learning-Methoden zur Vorhersage venöser Thromboembolien bei hospitalisierten Erwachsenen
Journal of Hospital Medicine · 2026-11 · 21 (11) · 1218-1226
DOI: 10.1002/jhm.70342 ↗Auf einen Blick
Mehrere Prognosemodelle für HA-VTE auf Basis von EHR-Daten zeigten ähnlich hohe Diskriminierung. Die logistische Regression war in Kalibrierung und Gesamtleistung mindestens ebenso gut wie Machine-Learning-Methoden.
Fragestellung
Welche Methode ist für die Vorhersage von HA-VTE anhand von EHR-Daten am praktikabelsten?
Methode
Vergleich von Prognosemodellen mit logistischer Regression, Random Forest, XGBoost, tiefen neuronalen Netzen und Ensemble; zeitliche externe Validierung in einem akademischen Zentrum.
Ergebnisse
Alle Modelle hatten hohe Diskriminierung mit C-Statistiken von 0.886 bis 0.900. Logistische Regression, Random Forest und XGBoost kalibrierten gut; tiefe neuronale Netze schlechter. Logistische Regression schnitt insgesamt vergleichbar gut oder besser ab.
Schlussfolgerung der Autor:innen
Die Autor:innen schließen, dass die logistische Regression ein hoch wirksames Werkzeug für die EHR-basierte Vorhersage von HA-VTE ist.
Kernaussagen
- C-Statistiken aller Modelle: 0.886 bis 0.900
- Logistische Regression zeigte gute Kalibrierung
- Tiefe neuronale Netze kalibrierten schlechter
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Vergleichsstudie in der Zeitschrift Journal of Hospital Medicine, online erschienen am 14.05.2026. Verfasst von Yeji Ko und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA. Hauptthemen laut MEDLINE: Venous Thromboembolism, Machine Learning, Hospitalization. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHLBI NIH HHS, National Heart, Lung, and Blood Institute.
Themen: Thromboseprophylaxe, Künstliche Intelligenz in der Pflege
Abstract (Originalsprache)
Background
Hospital‐acquired venous thromboembolism (HA‐VTE) is a significant cause of morbidity and mortality among hospitalized adults. Accurate prediction of HA‐VTE is crucial for timely intervention and prevention. While logistic regression is widely used for the development of clinical prediction models, there is ongoing interest in the potential for machine learning methods to enhance prediction performance.
Objectives
This study aimed to identify the most practical method for the prediction of HA‐VTE based on electronic health record (EHR) data.
Methods
We evaluated and compared the performance of prognostic models developed using logistic regression, random forest, extreme gradient boosting (XGBoost), deep neural networks, and an ensemble method to predict HA‐VTE using EHR data from a large academic medical center. Models were evaluated in a temporal external validation cohort based on discrimination and calibration metrics, overall and among key patient subgroups.
Results
All models demonstrated similarly high discrimination, with C statistics ranging from 0.886 to 0.900. Logistic regression, random forest, and XGBoost showed excellent calibration, whereas deep neural networks exhibited poorer calibration. Additionally, prediction accuracy at a probability cut‐off of 0.02 and correlations between models indicated that logistic regression performed comparably well, if not better, compared with machine learning methods. Subgroup analyses further confirmed that the logistic regression model demonstrated strong discrimination and calibration among patient subpopulations.
Conclusions
Our findings suggest that logistic regression is a highly effective tool for EHR‐based prediction of HA‐VTE.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biostatistics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
- Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
- Department of Medicine, Division of Hematology and Oncology, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
- Geriatric Research, Education and Clinical Center, VA Tennessee Valley Healthcare System, Nashville, TN, USA.
- Department of Medicine, Division of General Internal Medicine and Public Health, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
ORCID-Profile: Benjamin French, Amanda S Mixon
Förderung
- NHLBI NIH HHS
- National Heart, Lung, and Blood Institute
Zitieren
APA
Ko, Y., French, B., Schildcrout, J. S., El-Rifai, M., Wright, A., Tillman, B. F., Mixon, A. S., & Domenico, H. J. (2026). Comparison of machine learning methods for prediction of venous thromboembolism among hospitalized adults. Journal of Hospital Medicine, 21(11), 1218-1226. https://doi.org/10.1002/jhm.70342
Vancouver
Ko Y, French B, Schildcrout JS, El-Rifai M, Wright A, Tillman BF, et al. Comparison of machine learning methods for prediction of venous thromboembolism among hospitalized adults. Journal of Hospital Medicine. 2026;21(11):1218-1226. doi:10.1002/jhm.70342
BibTeX
@article{Ko2026,
author = {Ko, Yeji and French, Benjamin and Schildcrout, Jonathan S and El-Rifai, Merna and Wright, Adam and Tillman, Benjamin F and Mixon, Amanda S and Domenico, Henry J},
title = {Comparison of machine learning methods for prediction of venous thromboembolism among hospitalized adults},
journal = {Journal of Hospital Medicine},
year = {2026},
volume = {21},
number = {11},
pages = {1218--1226},
doi = {10.1002/jhm.70342}
}
EUVIMED