Tandem deep learning and logistic regression models to optimize hypertrophic cardiomyopathy detection in routine

Related Experiment Video

Updated: Aug 15, 2025

Investigating the Pathogenesis of MYH7 Mutation Gly823Glu in Familial Hypertrophic Cardiomyopathy using a Mouse Model
03:45

Investigating the Pathogenesis of MYH7 Mutation Gly823Glu in Familial Hypertrophic Cardiomyopathy using a Mouse Model

Published on: August 8, 2022

3.3K

Maren Maanja1,2, Peter A Noseworthy2, Jeffrey B Geske2

  • 1Department of Clinical Physiology, Karolinska University Hospital, and Karolinska Institutet, Stockholm, Sweden.

Cardiovascular Digital Health Journal
|January 2, 2023
PubMed

Insights

An AI algorithm for hypertrophic cardiomyopathy (HCM) detection using ECGs can be improved. A new clinical score (HCM-DETECT) significantly reduces false positives, enhancing diagnostic accuracy for this heart condition.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Electrocardiogram (ECG)-based artificial intelligence (AI) algorithms show promise for detecting hypertrophic cardiomyopathy (HCM).
  • Clinical implementation faces challenges due to low disease prevalence and high false-positive rates.
  • Improving the accuracy of AI-ECG in identifying true HCM cases is crucial.

Purpose of the Study:

  • To identify clinical characteristics that distinguish true-positive from false-positive HCM AI-ECG results.
  • To develop a clinical scoring system to enhance the application of AI-ECG for HCM detection.
  • To reduce the rate of false-positive diagnoses in AI-ECG screening for HCM.

Main Methods:

  • Retrospective review of 200 patients with high HCM AI-ECG scores (2021 cohort).
  • Development of the HCM-DETECT clinical score using logistic regression.
  • Validation of the HCM-DETECT score in an independent cohort of 200 patients (2022 cohort).

Main Results:

  • In the 2021 cohort, true-positive, false-positive, and indeterminate AI-ECG results were 36%, 48%, and 16%.
  • The HCM-DETECT score, incorporating age and prior cardiac history, achieved an AUC of 0.81 for differentiating true vs. false positives.
  • Applying the HCM-DETECT score in the 2022 cohort reduced the AI-ECG false-positive rate from 47% to 13.5%.

Conclusions:

  • A clinical scoring system (HCM-DETECT) effectively improves the diagnostic yield of AI-ECG for HCM.
  • Integrating clinical data with AI-ECG significantly reduces false-positive results, aiding clinical decision-making.
  • The HCM-DETECT score enhances the practical utility of AI-ECG in hypertrophic cardiomyopathy screening.
Abstract

Keywords:
Artificial intelligenceDiagnostic performanceEchocardiographyElectrocardiographyHypertrophic cardiomyopathy

More Related Videos

In Silico Clinical Trials for Cardiovascular Disease09:09

In Silico Clinical Trials for Cardiovascular Disease

Published on: May 27, 2022

1.8K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Related Concept Videos

Cardiomyopathy III: Hypertrophic Cardiomyopathy01:29

Cardiomyopathy III: Hypertrophic Cardiomyopathy

Hypertrophic cardiomyopathy, or HCM, is an autosomal dominant genetic disorder characterized by asymmetric left ventricular hypertrophy without ventricular dilation. It is more common in men and is typically diagnosed in young, athletic adults.EtiologyHCM is primarily genetic and is caused by mutations in genes encoding sarcomeric proteins. Researchers have identified over 1400 mutations across at least 11 different genes. Among these, the most frequently occurring mutations are found in the...
30
Cardiomyopathy V: Interprofessional Care01:29

Cardiomyopathy V: Interprofessional Care

Managing cardiomyopathy involves addressing underlying or precipitating causes, treating heart failure with medications, and implementing dietary changes and a balanced exercise and rest regimen.Lifestyle ModificationsCardiomyopathy patients should adopt a low-sodium diet to reduce fluid retention and manage heart failure. A personalized exercise and rest plan helps maintain physical fitness without overstraining the heart. Avoiding alcohol and tobacco is essential to prevent further damage to...
25
Cardiomyopathy II: Dilated Cardiomyopathy01:30

Cardiomyopathy II: Dilated Cardiomyopathy

Dilated cardiomyopathy, or DCM, is a progressive myocardial disorder characterized by ventricular chamber dilation and contractile dysfunction.EtiologyVarious factors can cause DCM, including hypertension and heavy alcohol intake, which contribute to the weakening and enlargement of the heart muscle. Viral infections, such as Coxsackievirus B, adenoviruses, and influenza, can lead to DCM by causing inflammation and damage to heart tissue. Certain chemotherapeutic agents, including daunorubicin,...
19
Cardiomyopathy I: Introduction and Classification01:25

Cardiomyopathy I: Introduction and Classification

Cardiomyopathy, or CMP, is a group of diseases affecting the myocardial structure, impairing its ability to pump blood effectively. This condition can lead to arrhythmias, heart failure, or sudden cardiac death.Cardiomyopathies are classified into primary and secondary categories:Primary Cardiomyopathy refers to conditions involving only the heart muscle that are often idiopathic (of unknown cause) or genetic. They primarily affect the myocardium without the involvement of other systemic...
36
Cardiomyopathy IV: Restrictive Cardiomyopathy01:29

Cardiomyopathy IV: Restrictive Cardiomyopathy

Restrictive cardiomyopathy (RCM) is a rare heart muscle disease characterized by impaired ventricular filling due to stiffened ventricular walls, leading to significant diastolic dysfunction.EtiologyRestrictive cardiomyopathy can arise from both inherited and acquired diseases, many of which are systemic. It is categorized into four main types: infiltrative, storage, non-infiltrative, and endomyocardial diseases.Infiltrative diseases, such as amyloidosis, lead to RCM by depositing amyloid...
17