EUVIMEDEUVIMED entdecken
Open Access

Deep Learning‐Based Prediction of Heart Failure Readmission Using Longitudinal Cardiac Device Data

Veronica Ramos, Shantanu Sarkar, Jodi Koehler, Connie Ma, Daniel Joseph Gonzalez, Rahul Anand Devathu iD, Erick Godinez, Kushal Chatterjee iD, Muhammad Fazal, Tarek Haddad, Yong Cho, Javed Butler und 2 weitere

Journal of Cardiovascular Electrophysiology · 2026

DOI: 10.1111/jce.70406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Cardiovascular Electrophysiology, 2026. Verfasst von Veronica Ramos und 13 weiteren Autor:innen. Beteiligte Einrichtung: Medtronic Inc., Mounds View, Minnesota, USA. Hauptthemen laut MEDLINE: Patient Readmission, Deep Learning, Heart Failure, Defibrillators, Implantable. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Heart failure (HF) is a leading cause of hospitalization and readmission. Cardiac implantable electronic devices (CIEDs) continuously capture physiologic diagnostics that change during and after HF decompensation and may enable early post‐discharge risk stratification.

Objectives

To predict 60‐day HF readmission using deep learning models trained on post‐discharge temporal behavior of CIED diagnostic parameters.

Methods

We performed a retrospective analysis of patients with implantable cardioverter defibrillators (ICDs) or cardiac resynchronization therapy defibrillators (CRT‐Ds) devices enrolled in remote monitoring (2007–2021) with HF hospitalizations identified from linked electronic health record and remote monitoring databases. Five daily device diagnostics (activity, impedance, heart rate variability, and night/day heart rates) were aligned to the index HF discharge (day 0) and analyzed over the subsequent 30 days. Patients readmitted within 7 days and those with substantial missing device data were excluded; remaining recovery windows were labeled by the occurrence of HF readmission 8–60 days post‐discharge. We trained and evaluated two architectures of neural networks.

Results

The cohort included 5734 patients with 12 369 HF hospitalization events; 2489 index hospitalizations were followed by HF readmission within 60 days. Across the 30‐day recovery window of device parameters, temporal characteristics of CIED cardiac compass parameters differed significantly between readmitted and non‐readmitted patients ( p < 0.001), consistent with slower physiologic recovery among readmitted events. On an independent data set, the 1‐dimensional convolutional neural network architecture (1D CNN) achieved 0.77 sensitivity, 0.98 specificity, and area under the ROC curve (AUROC) of 0.89.

Conclusion

Deep learning models leveraging post‐discharge trajectories of routinely captured CIED diagnostics can identify patients at higher risk of 60‐day HF readmission and may support targeted early follow–up after HF hospitalization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient ReadmissionDeep LearningHeart FailureDefibrillators, ImplantableCardiac Resynchronization Therapy DevicesElectric CountershockHumansPredictive Learning ModelsRetrospective StudiesPredictive Value of TestsTime FactorsRisk AssessmentRisk FactorsFemaleAgedMalePrediction AlgorithmsRemote Patient MonitoringTreatment OutcomeHeart RateRemote Sensing TechnologyConvolutional Neural NetworksDatabases, FactualDecision Support Techniques

Stichwörter der Autor:innen

Neural Networks7heart failurehospital readmissionsimplantable devicesremote monitoring3

Autor:innen und Institutionen

  • Medtronic Inc., Mounds View, Minnesota, USA.
  • Stanford University School of Medicine, Stanford, California, USA.
  • Baylor Scott and White Research Institute, Dallas, Texas, USA.
  • University of Mississippi, Jackson, Mississippi, USA.
  • Veterans Affairs Palo Alto Health Care System, Palo Alto, California, USA.

ORCID-Profile: Rahul Anand Devathu, Kushal Chatterjee

Zitieren

APA

Ramos, V., Sarkar, S., Koehler, J., Ma, C., Gonzalez, D. J., Devathu, R. A., Godinez, E., Chatterjee, K., Fazal, M., Haddad, T., Cho, Y., Butler, J., Sandhu, A. T., & Baykaner, T. (2026). Deep Learning‐Based Prediction of Heart Failure Readmission Using Longitudinal Cardiac Device Data. Journal of Cardiovascular Electrophysiology. https://doi.org/10.1111/jce.70406

Vancouver

Ramos V, Sarkar S, Koehler J, Ma C, Gonzalez DJ, Devathu RA, et al. Deep Learning‐Based Prediction of Heart Failure Readmission Using Longitudinal Cardiac Device Data. Journal of Cardiovascular Electrophysiology. 2026. doi:10.1111/jce.70406

BibTeX
@article{Ramos2026,
  author = {Ramos, Veronica and Sarkar, Shantanu and Koehler, Jodi and Ma, Connie and Gonzalez, Daniel Joseph and Devathu, Rahul Anand and Godinez, Erick and Chatterjee, Kushal and Fazal, Muhammad and Haddad, Tarek and Cho, Yong and Butler, Javed and Sandhu, Alexander T and Baykaner, Tina},
  title = {Deep Learning‐Based Prediction of Heart Failure Readmission Using Longitudinal Cardiac Device Data},
  journal = {Journal of Cardiovascular Electrophysiology},
  year = {2026},
  doi = {10.1111/jce.70406}
}
Kostenlos starten →