Related Experiment Video
Updated: Jun 25, 2026
Ultrasonic Assessment of Myocardial Microstructure
Published on: January 14, 2014
Detection of late gadolinium enhancement in patients with hypertrophic cardiomyopathy using machine learning
Keitaro Akita1, Kenichiro Suwa2, Kazuto Ohno2
1Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA; Division of Cardiology, Internal Medicine III, Hamamatsu University School of Medicine, Hamamatsu, Shizuoka, Japan.
Insights
Machine learning models can predict late gadolinium enhancement (LGE) in hypertrophic cardiomyopathy (HCM) using clinical data, potentially reducing the need for cardiac magnetic resonance (CMR) imaging. This approach aids physicians in identifying patients likely to have LGE.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Late gadolinium enhancement (LGE) on cardiac magnetic resonance (CMR) indicates myocardial fibrosis in hypertrophic cardiomyopathy (HCM), a risk factor for fatal arrhythmias.
- CMR is resource-intensive and sometimes contraindicated, necessitating alternative diagnostic methods.
Purpose of the Study:
- To develop and validate a machine learning (ML) algorithm for detecting LGE in HCM patients using clinical parameters.
- To assess the utility of ML in identifying HCM patients with a high pre-test probability of LGE.
Main Methods:
- A ridge classification ML model was trained on 22 clinical parameters (including echocardiographic data) from 554 HCM patients in the US.
- The model was validated on a separate cohort of 188 HCM patients from Japan.
- Performance was evaluated using the area under the receiver-operating-characteristic curve (AUC).
Main Results:
- The ML model achieved an AUC of 0.77 in the test set (95% CI 0.70-0.84).
- The ML model significantly outperformed a reference model based on 3 conventional risk factors (AUC 0.69, P=0.01).
- LGE was present in 54% of the training set and 40% of the test set.
Conclusions:
- ML analysis of clinical parameters can effectively distinguish the presence of LGE on CMR in HCM patients.
- This ML model can assist physicians in identifying HCM patients who would benefit most from CMR.
- The findings support the use of ML as a tool to optimize CMR utility in HCM management.
Background:
Late gadolinium enhancement (LGE) on cardiac magnetic resonance (CMR) in hypertrophic cardiomyopathy (HCM) typically represents myocardial fibrosis and may lead to fatal ventricular arrhythmias. However, CMR is resource-intensive and sometimes contraindicated. Thus, in patients with HCM, we aimed to detect LGE on CMR by applying machine learning (ML) algorithm to clinical parameters.
Methods And Results:
In this trans-Pacific multicenter study of HCM, a ML model was developed to distinguish the presence or absence of LGE on CMR by ridge classification method using 22 clinical parameters including 9 echocardiographic data. Among 742 patients in this cohort, the ML model was constructed in 2 institutions in the United States (training set, n = 554) and tested using data from an institution in Japan (test set, n = 188). LGE was detected in 299 patients (54%) in the training set and 76 patients (40%) in the test set. In the test set, the area under the receiver-operating-characteristic curve (AUC) of the ML model derived from the training set was 0.77 (95% confidence interval [CI] 0.70-0.84). When compared with a reference model constructed with 3 conventional risk factors for LGE on CMR (AUC 0.69 [95% CI 0.61-0.77]), the ML model outperformed the reference model (DeLong's test P = 0.01).
Conclusions:
This trans-Pacific study demonstrates that ML analysis of clinical parameters can distinguish the presence of LGE on CMR in patients with HCM. Our ML model would help physicians identify patients with HCM in whom the pre-test probability of LGE is high, and therefore CMR will have higher utility.
More Related Videos
12:24Noninvasive Assessment of Cardiac Abnormalities in Experimental Autoimmune Myocarditis by Magnetic Resonance Microscopy Imaging in the Mouse
Published on: June 20, 2014
12:15Tissue Preparation Techniques for Contrast-Enhanced Micro Computed Tomography Imaging of Large Mammalian Cardiac Models with Chronic Disease
Published on: February 8, 2022
