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.
Aims:
Although left ventricular hypertrophy (LVH) has a high incidence and clinical importance, the conventional diagnosis criteria for detecting LVH using electrocardiography (ECG) has not been satisfied. We aimed to develop an artificial intelligence (AI) algorithm for detecting LVH.
Methods And Results:
This retrospective cohort study involved the review of 21 286 patients who were admitted to two hospitals between October 2016 and July 2018 and underwent 12-lead ECG and echocardiography within 4 weeks. The patients in one hospital were divided into a derivation and internal validation dataset, while the patients in the other hospital were included in only an external validation dataset. An AI algorithm based on an ensemble neural network (ENN) combining convolutional and deep neural network was developed using the derivation dataset. And we visualized the ECG area that the AI algorithm used to make the decision. The area under the receiver operating characteristic curve of the AI algorithm based on ENN was 0.880 (95% confidence interval 0.877-0.883) and 0.868 (0.865-0.871) during the internal and external validations. These results significantly outperformed the cardiologist's clinical assessment with Romhilt-Estes point system and Cornell voltage criteria, Sokolov-Lyon criteria, and interpretation of ECG machine. At the same specificity, the AI algorithm based on ENN achieved 159.9%, 177.7%, and 143.8% higher sensitivities than those of the cardiologist's assessment, Sokolov-Lyon criteria, and interpretation of ECG machine.
Conclusion:
An AI algorithm based on ENN was highly able to detect LVH and outperformed cardiologists, conventional methods, and other machine learning techniques.