Related Experiment Videos

Comparing the performance of artificial intelligence and conventional diagnosis criteria for detecting left

Joon-Myoung Kwon1,2, Ki-Hyun Jeon2,3, Hyue Mee Kim3

  • 1Department of Emergency Medicine, Mediplex Sejong Hospital, 20, Gyeyangmunhwa-ro, Gyeyang-gu, Incheon, Republic of Korea.

Insights

An artificial intelligence (AI) algorithm effectively detects left ventricular hypertrophy (LVH) using electrocardiography (ECG). This AI tool significantly outperforms cardiologists and traditional diagnostic methods in identifying LVH.

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Left ventricular hypertrophy (LVH) is a common condition with significant clinical implications.
  • Conventional electrocardiography (ECG) diagnostic criteria for LVH often fall short in accuracy.
  • There is a need for improved diagnostic tools for LVH detection.

Purpose of the Study:

  • To develop and validate an artificial intelligence (AI) algorithm for detecting LVH using ECG.
  • To compare the AI algorithm's performance against cardiologists and established diagnostic criteria.

Main Methods:

  • A retrospective cohort study of 21,286 patients was conducted.
  • An AI algorithm utilizing an ensemble neural network (ENN) was developed and trained on a derivation dataset.
  • Internal and external validation datasets were used to assess the AI algorithm's performance.

Main Results:

  • The AI algorithm achieved an area under the receiver operating characteristic curve of 0.880 (internal) and 0.868 (external).
  • The AI algorithm demonstrated significantly higher sensitivity compared to cardiologists and conventional criteria at similar specificity.
  • The ENN-based AI algorithm outperformed existing machine learning techniques.

Conclusions:

  • An AI algorithm based on ENN shows high efficacy in detecting LVH from ECG data.
  • The developed AI algorithm surpasses the diagnostic capabilities of cardiologists and traditional methods for LVH detection.
  • This AI approach represents a promising advancement in the diagnosis of left ventricular hypertrophy.
Abstract

Related Concept Videos