EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Early prediction of sepsis associated encephalopathy in elderly ICU patients using machine learning models: a retrospective study based on the MIMIC-IV database

Frühe Vorhersage von Sepsis-assoziierter Enzephalopathie bei älteren ICU-Patient:innen mit Machine-Learning-Modellen: retrospektive Studie auf Basis der MIMIC-IV-Datenbank

Yupeng Han, Xiyuan Xie, Jiapeng Qiu, Yijie Tang, Zhiwei Song, Wangyu Li, Xiaodan Wu

Frontiers in Cellular and Infection Microbiology · 17.04.2025 · 15

DOI: 10.3389/fcimb.2025.1545979 ↗

Auf einen Blick

Bei 3.156 älteren Sepsis-Patient:innen in der ICU sagte ein XGBoost-Modell das Auftreten einer sepsisassoziierten Enzephalopathie am besten voraus. Die AUC betrug 0,898.

Fragestellung

Lässt sich eine sepsisassoziierte Enzephalopathie (SAE) bei älteren ICU-Patient:innen mit Machine-Learning-Modellen früh vorhersagen?

Methode

Retrospektive Studie mit Daten aus MIMIC-IV (Version 3.1); Aufteilung in Trainings- und Testset 7:3; Entwicklung von 5 ML-Modellen nach LASSO-Boruta-Auswahl; Bewertung u. a. mit AUC, Kalibrierung und DCA.

Ergebnisse

3.156 ältere Sepsis-Patient:innen; SAE-Inzidenz 48,7 %. Mortalität bei SAE 28,78 % vs. 12,59 % ohne SAE (P < 0,001). XGBoost: AUC 0,898; Genauigkeit 0,830; Recall 0,819; F1-Score 0,820; Spezifität 0,840; Precision 0,821.

Schlussfolgerung der Autor:innen

Das XGBoost-Modell sagte SAE bei älteren ICU-Patient:innen wirksam voraus und könnte Ärzt:innen helfen, Hochrisikopatient:innen zu identifizieren.

Kernaussagen

  • SAE-Inzidenz bei 3.156 älteren Sepsis-Patient:innen: 48,7 %
  • XGBoost schnitt besser ab als 4 weitere ML-Modelle und Scores
  • Vereinfachtes XGBoost-Modell: AUC 0,858

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 Frontiers in Cellular and Infection Microbiology, online erschienen am 17.04.2025. Verfasst von Yupeng Han und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou University Affiliated…. Hauptthemen laut MEDLINE: Sepsis-Associated Encephalopathy, Machine Learning, Intensive Care Units, Sepsis. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Sepsis associated encephalopathy (SAE) is prevalent among elderly patients in the ICU and significantly affects patient prognosis. Due to the symptom similarity with other neurological disorders and the absence of specific biomarkers, early clinical diagnosis remains challenging. This study aimed to develop a predictive model for SAE in elderly ICU patients.

Methods

The data of elderly sepsis patients were extracted from the MIMIC IV database (version 3.1) and divided into training and test sets in a 7:3 ratio. Feature variables were selected using the LASSO-Boruta combined algorithm, and five machine learning (ML) models, including Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost),Light Gradient Boosting Machine(LGBM), Multilayer Perceptron (MLP), and Support Vector Machines (SVM), were subsequently developed using these variables. A comprehensive set of performance metrics was used to assess the predictive accuracy, calibration, and clinical applicability of these models. For the machine learning model with the best performance, we employed the SHapley Additive Explanations(SHAP) method to visualize the model.

Results

Based on strict inclusion and exclusion criteria, a total of 3,156 elderly sepsis patients were enrolled in the study, with an SAE incidence rate of 48.7%. The mortality rate of elderly sepsis patients who developed SAE was significantly higher than that of patients in the non-SAE group (28.78% vs. 12.59%, P < 0.001). A total of 18 feature variables were selected for the construction of the ML model using the LASSO-Boruta combined algorithm. Compared to the other four models and traditional scoring systems, the XGBoost model demonstrated the best overall predictive performance, with Area Under the Curve(AUC)=0.898, accuracy=0.830, recall=0.819, F1-Score=0.820, specificity=0.840, and Precision=0.821. Furthermore, the results from the Decision Curve Analysis (DCA) and calibration curves demonstrated that the XGBoost model has significant clinical value and stable predictive performance. The ten-fold cross-validation method further confirmed the robustness and generalizability of the model. In addition, we simplified the model based on the SHAP feature importance ranking, and the results indicated that the simplified XGBoost model retains excellent predictive ability (AUC=0.858).

Conclusions

The XGBoost model effectively predicts SAE in elderly ICU patients and may serve as a reliable tool for clinicians to identify high-risk patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sepsis-Associated EncephalopathyMachine LearningIntensive Care UnitsSepsisHumansAgedRetrospective StudiesMaleFemaleAged, 80 and overDatabases, FactualPrognosisAlgorithmsEarly Diagnosis

Stichwörter der Autor:innen

MIMIC-IVearly predictionelderlymachine learningsepsis associated encephalopathy

Autor:innen und Institutionen

  • Department of Anesthesiology, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou University Affiliated Provincial Hospital, Fuzhou, Fujian, China.
  • Department of Neurology, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou University Affiliated Provincial Hospital, Fuzhou, Fujian, China.
  • Department of Pain Management, The First Affiliated Hospital of Fujian Medical University, Fuzhou, Fujian, China.
  • Fujian Provincial Key Laboratory of Critical care Medicine, Fujian Provincial Hospital, Fuzhou University Affiliated Provincial Hospital, Fuzhou, Fujian, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Han, Y., Xie, X., Qiu, J., Tang, Y., Song, Z., Li, W., & Wu, X. (2025). Early prediction of sepsis associated encephalopathy in elderly ICU patients using machine learning models: a retrospective study based on the MIMIC-IV database. Frontiers in Cellular and Infection Microbiology, 15. https://doi.org/10.3389/fcimb.2025.1545979

Vancouver

Han Y, Xie X, Qiu J, Tang Y, Song Z, Li W, et al. Early prediction of sepsis associated encephalopathy in elderly ICU patients using machine learning models: a retrospective study based on the MIMIC-IV database. Frontiers in Cellular and Infection Microbiology. 2025;15. doi:10.3389/fcimb.2025.1545979

BibTeX
@article{Han2025,
  author = {Han, Yupeng and Xie, Xiyuan and Qiu, Jiapeng and Tang, Yijie and Song, Zhiwei and Li, Wangyu and Wu, Xiaodan},
  title = {Early prediction of sepsis associated encephalopathy in elderly ICU patients using machine learning models: a retrospective study based on the MIMIC-IV database},
  journal = {Frontiers in Cellular and Infection Microbiology},
  year = {2025},
  volume = {15},
  doi = {10.3389/fcimb.2025.1545979}
}
Kostenlos starten →