EUVIMEDEUVIMED entdecken
Crossref

Calibration of ECG-Based Deep-Learning Algorithm Scores for Patients Flagged as High Risk for Hypertrophic Cardiomyopathy

Joshua Lampert iD, Deepak L Bhatt iD, Akhil Vaid iD, Katia Kon iD, Jason Feinman iD, Stephanie Jou iD, Justin Kauffman iD, Girish Nadkarni iD, Vivek Y Reddy iD

NEJM AI · 24.04.2025 · 2 (5)

DOI: 10.1056/aioa2400421 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NEJM AI, erschienen am 24.04.2025. Verfasst von Joshua Lampert und 8 weiteren Autor:innen. Beteiligte Einrichtung: Mount Sinai Fuster Heart Hospital, Icahn School of Medicine at Mount Sinai, New York. Hauptthemen laut MEDLINE: Cardiomyopathy, Hypertrophic, Electrocardiography, Deep Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 46 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Despite optimism for the incorporation of deep-learning (DL) algorithms into clinical practice, there is a lack of prospective data on how U.S. Food and Drug Administration (FDA)-cleared algorithms function out of the box and clinicians' interpretations of model predictions. This study illustrates how model calibration, which rescales model outputs to represent probabilities of disease among those flagged, enables improved interpretability of the scores by end users. METHODS: Using data from patients flagged as being at high risk for hypertrophic cardiomyopathy (HCM), patients 18 years of age and over were screened from a single health system using a DL electrocardiogram (ECG)-based algorithm for HCM detection. Cardiologists manually reviewed medical records and imaging of patients flagged as being suggestive of HCM to classify individuals as HCM positive (HCM+) or HCM negative (HCM-). Logistic regression was used for calibration to transform model outputs to probabilities in the flagged sample. We compare calibrated probabilities with the estimated probability of disease in the flagged sample and estimated positive predictive value (PPV) at different thresholds of the calibrated score. RESULTS: Among 1522 patients were flagged as being high risk, 166 were classified as HCM+ and 1356 as HCM-. Being flagged as being at high risk on the initial screening has a PPV of 10.9% for HCM patients. Recalibrated model scores in the flagged sample closely approximated the probability of HCM among those who were initially flagged, lending improved interpretability. Setting a cutoff value that corresponds to the top 5 and 10 ranked values yields PPVs of 80% and 70%, respectively. As the ranks of the model outputs and the recalibrated scores are equivalent, PPVs derived from this approach do not depend on which score is used, but the calibrated scores have context-relevant interpretability as the probability of HCM. CONCLUSIONS: Using the raw scores from an out-of-the-box-FDA-cleared algorithm for the identification of HCM from ECGs may have low PPV for identifying patients who truly have HCM. Calibration of scores for those flagged can improve the interpretability of the scores in terms of disease probability. (Funded by Viz.ai.).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiomyopathy, HypertrophicElectrocardiographyDeep LearningHumansAlgorithmsFemaleMiddle AgedCalibrationMaleAdultPrediction AlgorithmsAgedRisk AssessmentPredictive Value of Tests

Autor:innen und Institutionen

  • Mount Sinai Fuster Heart Hospital, Icahn School of Medicine at Mount Sinai, New York.
  • Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York.
  • Division of Data-Driven and Digital Medicine, Icahn School of Medicine at Mount Sinai, New York.
  • Viz.ai, San Francisco.

ORCID-Profile: Joshua Lampert, Deepak L Bhatt, Akhil Vaid, Katia Kon, Jason Feinman, Stephanie Jou, Justin Kauffman, Girish Nadkarni, Vivek Y Reddy

Zitieren

APA

Lampert, J., Bhatt, D. L., Vaid, A., Kon, K., Feinman, J., Jou, S., Kauffman, J., Nadkarni, G., & Reddy, V. Y. (2025). Calibration of ECG-Based Deep-Learning Algorithm Scores for Patients Flagged as High Risk for Hypertrophic Cardiomyopathy. NEJM AI, 2(5). https://doi.org/10.1056/aioa2400421

Vancouver

Lampert J, Bhatt DL, Vaid A, Kon K, Feinman J, Jou S, et al. Calibration of ECG-Based Deep-Learning Algorithm Scores for Patients Flagged as High Risk for Hypertrophic Cardiomyopathy. NEJM AI. 2025;2(5). doi:10.1056/aioa2400421

BibTeX
@article{Lampert2025,
  author = {Lampert, Joshua and Bhatt, Deepak L and Vaid, Akhil and Kon, Katia and Feinman, Jason and Jou, Stephanie and Kauffman, Justin and Nadkarni, Girish and Reddy, Vivek Y},
  title = {Calibration of ECG-Based Deep-Learning Algorithm Scores for Patients Flagged as High Risk for Hypertrophic Cardiomyopathy},
  journal = {NEJM AI},
  year = {2025},
  volume = {2},
  number = {5},
  doi = {10.1056/aioa2400421}
}
Kostenlos starten →