Machine Learning and Deep Learning for Predicting Response and Outcomes After Cardiac Resynchronization Therapy: A Systematic Review and Meta-Analysis of ECG-Based Models
Machine Learning und Deep Learning zur Vorhersage von Ansprechen und Outcomes nach kardialer Resynchronisationstherapie: systematische Übersicht und Metaanalyse von ECG-basierten Modellen
Medical Sciences · 01.11.2026 · 14 (7) · 738
DOI: 10.3390/medsci14070738 ↗Auf einen Blick
14 Studien zu ECG-basierten ML- und DL-Modellen zeigten eine moderate Trennschärfe zur Vorhersage von CRT-Outcomes. Die Heterogenität war hoch, und die meisten Modelle hatten ein hohes Verzerrungsrisiko.
Fragestellung
Wie gut sagen ML- und DL-Modelle auf Basis von ECG-Daten das Ansprechen und klinische Outcomes nach CRT voraus?
Methode
Systematische Übersicht und Metaanalyse; Suche in Scopus und Web of Science bis April 2026; Bewertung mit PROBAST+AI; Random-effects-Metaanalysen von AUROC und HRs.
Ergebnisse
14 Studien mit 34 Modellbewertungen. Gepoolter AUROC 0,710 (95 %-KI 0,660–0,759; I2=94,7 %). Gepoolter HR 1,75 (95 %-KI 1,42–2,15; I2=83,3 %). ML hatte höhere AUROC als DL (0,752 vs. 0,669).
Einschränkungen
Hohe Heterogenität, hohes Verzerrungsrisiko in 32 von 34 Modellen und nur 2 Studien mit unabhängiger externer Evaluation.
Schlussfolgerung der Autor:innen
ECG-basierte ML- und DL-Modelle zeigen eine moderate Diskrimination für CRT-Outcomes. Wegen Heterogenität, hohem Bias-Risiko und wenig externer Validierung ist eine Routineanwendung derzeit nicht möglich.
Kernaussagen
- 14 Studien, 34 Modellbewertungen
- Gepoolter AUROC 0,710 (95 %-KI 0,660–0,759)
- 32 von 34 Modellen mit hohem Verzerrungsrisiko
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Medical Sciences, online erschienen am 01.11.2026. Verfasst von Anton Kavaldzhiev und 1 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Up to 40% of patients receiving cardiac resynchronization therapy (CRT) do not experience significant clinical improvement, highlighting the limitations of conventional selection criteria. Artificial intelligence (AI) is increasingly being applied to electrocardiogram (ECG) and other clinical data to improve patient selection. This systematic review and meta-analysis evaluated the performance and methodological quality of machine learning (ML) and deep learning (DL) models using ECG-derived information to predict CRT response and clinical outcomes.
Methods
A systematic literature search was conducted in Scopus and Web of Science for studies published between January 2006 and April 2026. Eligible studies developed or evaluated ML or DL algorithms primarily using pre-implantation ECG data to predict CRT response, including changes in left ventricular ejection fraction (LVEF) or left ventricular end-systolic volume (LVESV), or mortality. Model performance and prognostic associations were synthesized using random-effects meta-analyses of the area under the receiver operating characteristic curve (AUROC) and hazard ratios (HRs), respectively. Methodological quality and risk of bias were assessed using the PROBAST+AI tool.
Results
We identified 14 eligible studies containing 34 distinct model evaluations. Most models utilized digital 12-lead ECG waveforms or single representative beats. Across 26 model-outcome estimates, the exploratory pooled AUROC was 0.710 (95% CI: 0.660–0.759), with substantial heterogeneity (I2 = 94.7%; p < 0.001). Across 10 heterogeneous model–outcome estimates, the exploratory pooled HR was 1.75 (95% CI: 1.42–2.15; I2 = 83.3%), although differences in prognostic constructs and endpoints precluded interpretation as a common effect. ML models had a higher pooled AUROC than DL models (0.752 vs. 0.669; exploratory Wald test: difference = 0.084; 95% CI: 0.002–0.165; p = 0.044). Pooled HR estimates also differed (ML: 2.22; DL: 1.46; ratio = 1.51; p < 0.001). These indirect subgroup comparisons were limited by clinical and methodological heterogeneity and potential dependence among estimates. PROBAST+AI assessment identified a high overall risk of bias in 32 of the 34 models, with concerns concentrated primarily in the participants and data sources and analysis domains. Independent geographic external evaluation was reported in only two studies, and these evaluations did not both constitute independent validation of fully specified CRT prediction models.
Conclusions
ECG-based ML and DL models demonstrate moderate discrimination for predicting CRT outcomes. However, substantial heterogeneity, high risk of bias and limited independent external validation currently preclude routine clinical implementation. Future research should prioritize standardized outcome definitions, independent external validation, and head-to-head comparisons within the same cohorts to establish incremental predictive and clinical utility. Registration: The review protocol was prospectively registered in PROSPERO (CRD420261448863).
Zitieren
APA
Kavaldzhiev, A., & Krasteva, V. (2026). Machine Learning and Deep Learning for Predicting Response and Outcomes After Cardiac Resynchronization Therapy: A Systematic Review and Meta-Analysis of ECG-Based Models. Medical Sciences, 14(7), 738. https://doi.org/10.3390/medsci14070738
Vancouver
Kavaldzhiev A, Krasteva V. Machine Learning and Deep Learning for Predicting Response and Outcomes After Cardiac Resynchronization Therapy: A Systematic Review and Meta-Analysis of ECG-Based Models. Medical Sciences. 2026;14(7):738. doi:10.3390/medsci14070738
BibTeX
@article{Kavaldzhiev2026,
author = {Kavaldzhiev, Anton and Krasteva, Vessela},
title = {Machine Learning and Deep Learning for Predicting Response and Outcomes After Cardiac Resynchronization Therapy: A Systematic Review and Meta-Analysis of ECG-Based Models},
journal = {Medical Sciences},
year = {2026},
volume = {14},
number = {7},
pages = {738},
doi = {10.3390/medsci14070738}
}
EUVIMED