Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units—A Novel Approach to the Early Identification of High-Risk Patients
Machine-Learning-Modelle zur frühen Echtzeit-Vorhersage von Verschlechterung auf Intensivstationen – ein neuer Ansatz zur frühen Identifikation von Hochrisikopatient:innen
Journal of Clinical Medicine · 08.01.2025 · 14 (2) · 350
DOI: 10.3390/jcm14020350 ↗Auf einen Blick
Eine intern validierte Modellierung mit 7.156 ICU-Patient:innen zeigte: Ein künstliches neuronales Netz sagte Verschlechterung am besten voraus. Das Modell nutzte nur 4 automatisch erfasste Vitalparameter.
Fragestellung
Lassen sich klinische Verschlechterungen auf Intensivstationen mit automatisch erzeugten Echtzeitdaten früh vorhersagen?
Methode
Routine-Monitoringdaten; ICU-Patient:innen mit mindestens 24 h Vitalzeichen-Aufzeichnungen; interne Aufteilung in Trainings- und Testdatensatz; Vergleich von 5 Modellen.
Ergebnisse
28.348 longitudinale Messungen. AUC: 0,81 für ANN gegenüber 0,78 (RF), 0,78 (SVM), 0,77 (LDA) und 0,76 (LR); Sensitivität höher als Spezifität.
Schlussfolgerung der Autor:innen
Das künstliche neuronale Netz mit 4 automatisch erfassten Vitalzeichen war am besten geeignet, eine Verschlechterung 10 h vor Dokumentation in den Akten vorherzusagen.
Kernaussagen
- ANN mit AUC 0,81 war das beste Modell
- Nur 4 automatisch erfasste Vitalparameter wurden verwendet
- Vorhersage der Verschlechterung 10 h vor Dokumentation
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 08.01.2025. Verfasst von Dominik Thiele und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology and Experimental Neurology, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Künstliche Intelligenz in der Pflege, Intensivpflege
Abstract (Originalsprache)
Background
Predictive machine learning models have made use of a variety of scoring systems to identify clinical deterioration in ICU patients. However, most of these scores include variables that are dependent on medical staff examining the patient. We present the development of a real-time prediction model using clinical variables that are digital and automatically generated for the early detection of patients at risk of deterioration.
Methods
Routine monitoring data were used in this analysis. ICU patients with at least 24 h of vital sign recordings were included. Deterioration was defined as qSOFA ≥ 2. Model development and validation were performed internally by splitting the cohort into training and test datasets and validating the results on the test dataset. Five different models were trained, tested, and compared against each other. The models were an artificial neural network (ANN), a random forest (RF), a support vector machine (SVM), a linear discriminant analysis (LDA), and a logistic regression (LR).
Results
In total, 7156 ICU patients were screened for inclusion in the study, which resulted in models trained from a total of 28,348 longitudinal measurements. The artificial neural network showed a superior predictive performance for deterioration, with an area under the curve of 0.81 over 0.78 (RF), 0.78 (SVM), 0.77 (LDA), and 0.76 (LR), by using only four vital parameters. The sensitivity was higher than the specificity for the artificial neural network.
Conclusions
The artificial neural network, only using four automatically recorded vital signs, was best able to predict deterioration, 10 h before documentation in clinical records. This real-time prediction model has the potential to flag at-risk patients to the healthcare providers treating them, for closer monitoring and further investigation.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurology and Experimental Neurology, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany.
- TCC Analytics, Telehealth Competence Center (TCC) GmbH, 22083 Hamburg, Germany.
- Netcare Limited, Johannesburg 2196, South Africa.
- Department of Anaesthesiology and Critical Care, University of KwaZulu-Natal, Durban 4001, South Africa.
- Department of Anesthesiology, Division of Critical Care Medicine, University of Minnesota School of Medicine, Minneapolis, MN 55455, USA.
- Department of Anesthesiology, Division of Critical Care Medicine, Emory University School of Medicine, Atlanta, GA 30322, USA.
ORCID-Profile: Reitze Rodseth, Chris Mathew, Caroline Maslo, Jens Nee
Zitieren
APA
Thiele, D., Rodseth, R., Friedland, R., Berger, F., Mathew, C., Maslo, C., Moll, V., Leithner, C., Storm, C., Krannich, A., & Nee, J. (2025). Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units—A Novel Approach to the Early Identification of High-Risk Patients. Journal of Clinical Medicine, 14(2), 350. https://doi.org/10.3390/jcm14020350
Vancouver
Thiele D, Rodseth R, Friedland R, Berger F, Mathew C, Maslo C, et al. Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units—A Novel Approach to the Early Identification of High-Risk Patients. Journal of Clinical Medicine. 2025;14(2):350. doi:10.3390/jcm14020350
BibTeX
@article{Thiele2025,
author = {Thiele, Dominik and Rodseth, Reitze and Friedland, Richard and Berger, Fabian and Mathew, Chris and Maslo, Caroline and Moll, Vanessa and Leithner, Christoph and Storm, Christian and Krannich, Alexander and Nee, Jens},
title = {Machine Learning Models for the Early Real-Time Prediction of Deterioration in Intensive Care Units—A Novel Approach to the Early Identification of High-Risk Patients},
journal = {Journal of Clinical Medicine},
year = {2025},
volume = {14},
number = {2},
pages = {350},
doi = {10.3390/jcm14020350}
}
EUVIMED