Predicting the development of adverse cardiac events in patients with hypertrophic cardiomyopathy using machine
Stephanie M Kochav1, Yoshihiko Raita2, Michael A Fifer3
1Division of Cardiology, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA.
Insights
Machine learning models significantly improve prediction of adverse cardiac events in hypertrophic cardiomyopathy (HCM) patients, outperforming traditional methods for identifying high-risk individuals.
Area of Science:
- Cardiology
- Biomedical Informatics
- Machine Learning
Background:
- Hypertrophic cardiomyopathy (HCM) patients have varying risks for adverse cardiac events like heart failure and sudden death.
- Current risk stratification methods for HCM are insufficient for identifying high-risk individuals.
- There is a need for improved prediction models to guide clinical management in HCM.
Purpose of the Study:
- To enhance the prediction of adverse cardiac events in hypertrophic cardiomyopathy (HCM) patients.
- To develop and evaluate machine learning models for improved risk stratification in HCM.
- To identify high-risk HCM subpopulations more accurately.
Main Methods:
- Applied modern machine learning techniques to a prospective cohort of adult HCM patients.
- Developed four distinct machine learning models using 20 predictive characteristics.
- Compared machine learning model performance against a logistic regression reference model using known predictors.
Main Results:
- Machine learning models achieved a predictive accuracy of 85%, significantly outperforming the reference model's 73% accuracy.
- The elastic net regression model demonstrated superior performance with an area under the receiver-operating-characteristic curve of 0.93.
- Machine learning models showed improved sensitivity (88%) and specificity (84%) in predicting composite outcomes (heart failure death, transplant, sudden death).
Conclusions:
- Machine learning models offer superior predictive ability for adverse cardiac events in HCM compared to conventional risk stratification.
- These advanced methods can enhance the identification of high-risk HCM patient subpopulations.
- Improved risk stratification through machine learning may lead to more personalized and effective patient management.
Background:
Only a subset of patients with hypertrophic cardiomyopathy (HCM) develop adverse cardiac events - e.g., end-stage heart failure, cardiovascular death. Current risk stratification methods are imperfect, limiting identification of high-risk patients with HCM. Our aim was to improve the prediction of adverse cardiac events in patients with HCM using machine learning methods.
Methods:
We applied modern machine learning methods to a prospective cohort of adults with HCM. The outcome was a composite of death due to heart failure, heart transplant, and sudden death. As the reference model, we constructed logistic regression model using known predictors. We determined 20 predictive characteristics based on random forest classification and a priori knowledge, and developed 4 machine learning models. Results Of 183 patients in the cohort, the mean age was 53 (SD = 17) years and 45% were female. During the median follow-up of 2.2 years (interquartile range, 0.6-3.8), 33 subjects (18%) developed an outcome event, the majority of which (85%) was heart transplant. The predictive accuracy of the reference model was 73% (sensitivity 76%, specificity 72%) while that of the machine learning model was 85% (e.g., sensitivity 88%, specificity 84% with elastic net regression). All 4 machine learning models significantly outperformed the reference model - e.g., area under the receiver-operating-characteristic curve 0.79 with the reference model vs. 0.93 with elastic net regression (p < 0.001).
Conclusions:
Compared with conventional risk stratification, the machine learning models demonstrated a superior ability to predict adverse cardiac events. These modern machine learning methods may enhance identification of high-risk HCM subpopulations.
Related Concept Videos
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:29Cardiomyopathy V: Interprofessional Care
01:30Cardiomyopathy II: Dilated Cardiomyopathy
01:25Cardiomyopathy I: Introduction and Classification