EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Prediction of 90 Day Mortality in Elderly Patients with Acute HF from e-Health Records Using Artificial Intelligence

Joconde Weller, Johann Gutton, Guillaume Hocquet, Leïla Pellet, Marie-José Aroulanda, Amélie Bruandet, Didier Theis, Fabio Boudis, Romain Cador, Pierre Zweigenbaum, Anne Buronfosse, Pascal de Groote iD und 1 weitere

ESC Heart Failure · 2025

DOI: 10.1002/ehf2.15244 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ESC Heart Failure, 2025. Verfasst von Joconde Weller und 12 weiteren Autor:innen. Beteiligte Einrichtung: Direction of Medical Information, Prospects and Data Sciences, Hôpitaux Paris Saint-Joseph and Marie-Lannelongue, Paris, France. Hauptthemen laut MEDLINE: Artificial Intelligence, Electronic Health Records, Heart Failure. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: French National Research Agency, Agence Nationale de la Recherche.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims

Mortality risk after hospitalization for heart failure (HF) is high, especially in the first 90 days. This study aimed to construct a model automatically predicting 90 day post-discharge mortality using electronic health record (EHR) data 48 h after admission and artificial intelligence.

Methods

All HF-related admissions from 2015 to 2020 in a single hospital were included in the model training. Comprehensive EHR data were collected 48 h after admission. Natural language processing was applied to textual information. Deaths were identified from the French national database. After variable selection with least absolute shrinkage and selection operator, a logistic regression model was trained. Model performance [area under the receiver operating characteristic curve (AUC)] was tested in two independent cohorts of patients admitted to two hospitals between March and December 2021.

Results

The derivation cohort included 2257 admissions (248 deaths after hospitalization). The evaluation cohorts included 348 and 388 admissions (34 and 38 deaths, respectively). Forty-two independent variables were selected. The model performed well in the derivation cohort [AUC: 0.817; 95% confidence interval (CI) (0.789–0.845)] and in both evaluation cohorts [AUC: 0.750; 95% CI (0.672–0.829) and AUC: 0.723; 95% CI (0.644–0.803]), with better performance than previous models in the literature. Calibration was good: ‘low-risk’ (predicted mortality ≤8%), ‘intermediate-risk’ (8–12.5%) and ‘high-risk’ (>12.5%) patients had an observed 90 day mortality rate of 3.8%, 8.4% and 19.4%, respectively.

Conclusions

The study proposed a robust model for the automatic prediction of 90 day mortality risk 48 h after hospitalization for decompensated HF. This could be used to identify high-risk patients for intensification of therapeutic management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceElectronic Health RecordsHeart FailureAgedAged, 80 and overFemaleHumansMaleAcute DiseaseFollow-Up StudiesFranceHospitalizationPrognosisRetrospective StudiesRisk AssessmentROC CurveSurvival RateTime Factors

Stichwörter der Autor:innen

heart failuremachine learningmortalitynatural language processingrisk prediction

Autor:innen und Institutionen

  • Direction of Medical Information, Prospects and Data Sciences, Hôpitaux Paris Saint-Joseph and Marie-Lannelongue, Paris, France.
  • Department of Cardiology, Hôpital Paris Saint-Joseph, Paris, France.
  • Department of Medical Information, CHU Lille, Lille, France.
  • LISN Research Center, Université Paris-Saclay, Paris, France.
  • Department of Cardiology, CHU Lille, Lille, France.
  • Inserm U1167, Institut Pasteur de Lille, Lille, France.

ORCID-Profile: Pascal de Groote

Förderung

  • French National Research Agency
  • Agence Nationale de la Recherche

Zitieren

APA

Weller, J., Gutton, J., Hocquet, G., Pellet, L., Aroulanda, M. J., Bruandet, A., Theis, D., Boudis, F., Cador, R., Zweigenbaum, P., Buronfosse, A., de Groote, P., & Komajda, M. (2025). Prediction of 90 Day Mortality in Elderly Patients with Acute HF from e-Health Records Using Artificial Intelligence. ESC Heart Failure. https://doi.org/10.1002/ehf2.15244

Vancouver

Weller J, Gutton J, Hocquet G, Pellet L, Aroulanda MJ, Bruandet A, et al. Prediction of 90 Day Mortality in Elderly Patients with Acute HF from e-Health Records Using Artificial Intelligence. ESC Heart Failure. 2025. doi:10.1002/ehf2.15244

BibTeX
@article{Weller2025,
  author = {Weller, Joconde and Gutton, Johann and Hocquet, Guillaume and Pellet, Leïla and Aroulanda, Marie-José and Bruandet, Amélie and Theis, Didier and Boudis, Fabio and Cador, Romain and Zweigenbaum, Pierre and Buronfosse, Anne and de Groote, Pascal and Komajda, Michel},
  title = {Prediction of 90 Day Mortality in Elderly Patients with Acute HF from e-Health Records Using Artificial Intelligence},
  journal = {ESC Heart Failure},
  year = {2025},
  doi = {10.1002/ehf2.15244}
}
Kostenlos starten →