Korean Circ J.
2024 Nov;54(11):743-756. 10.4070/kcj.2024.0060.
An Artificial Intelligence-Based Automated Echocardiographic Analysis: Enhancing Efficiency and Prognostic Evaluation in Patients With Revascularized STEMI
- Jang Y
1,2 - Choi H3,4
- Yoon YE2,3,4
- Jeon J1,2
- Kim H2
- Kim J1,5
- Jeong D1,5
- Ha S1,2,6
- Hong Y1,2
- Lee SA1,2
- Park J3,4
- Choi W4,7
- Choi HM3,4
- Hwang IC3,4
- Cho GY3,4
- Chang HJ1,2,8
- Affiliations
-
- 1CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, Korea
- 2Ontact Health Inc., Seoul, Korea
- 3Cardiovascular Center and Division of Cardiology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seongnam, Korea
- 4Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
- 5Department of Internal Medicine, Graduate School of Medical Science, Brain Korea 21 Project, Yonsei University College of Medicine, Seoul, Korea
- 6Graduate School of Biomedical Engineering, Yonsei University College of Medicine, Seoul, Korea
- 7Cardiovascular Center, Sheikh Khalifa Specialty Hospital, Ras Al Khaimah, United Arab Emirates
- 8Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Yonsei University Health System, Seoul, Korea
- KMID: 2560659
- DOI: http://doi.org/10.4070/kcj.2024.0060
Abstract
- Background and Objectives
Although various cardiac parameters on echocardiography have clinical importance, their measurement by conventional manual methods is time-consuming and subject to variability. We evaluated the feasibility, accuracy, and predictive value of an artificial intelligence (AI)-based automated system for echocardiographic analysis in patients with ST-segment elevation myocardial infarction (STEMI).
Methods
The AI-based system was developed using a nationwide echocardiographic dataset from five tertiary hospitals, and automatically identified views, then segmented and tracked the left ventricle (LV) and left atrium (LA) to produce volume and strain values. Both conventional manual measurements and AI-based fully automated measurements of the LV ejection fraction and global longitudinal strain, and LA volume index and reservoir strain were performed in 632 patients with STEMI.
Results
The AI-based system accurately identified necessary views (overall accuracy, 98.5%) and successfully measured LV and LA volumes and strains in all cases in which conventional methods were applicable. Inter-method analysis showed strong correlations between measurement methods, with Pearson coefficients ranging 0.81–0.92 and intraclass correlation coefficients ranging 0.74–0.90. For the prediction of clinical outcomes (composite of all-cause death, re-hospitalization due to heart failure, ventricular arrhythmia, and recurrent myocardial infarction), AI-derived measurements showed predictive value independent of clinical risk factors, comparable to those from conventional manual measurements.
Conclusions
Our fully automated AI-based approach for LV and LA analysis on echocardiography is feasible and provides accurate measurements, comparable to conventional methods, in patients with STEMI, offering a promising solution for comprehensive echocardiographic analysis, reduced workloads, and improved patient care.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Automated Bone Age Assessment Using Artificial Intelligence: The Future of Bone Age Assessment
- Development of a case-based nursing education program using generative artificial intelligence
- Artificial Intelligence in Pathology
- Application of Artificial Intelligence in the Area of Dysphagia
- Prognostication of Hepatocellular Carcinoma Using Artificial Intelligence
