Related Experiment Video
Updated: Jun 25, 2026
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Atrial fibrillation prediction in patients with hypertrophic cardiomyopathy based on long-term follow-up data and
Wan-Xuan Ding1, Guo-Cao Li1, Hao-Yu Dong1
1Department of Cardiology, The First Affiliated Hospital of Dalian Medical University, Dalian, China.
Insights
Machine learning accurately predicts new-onset atrial fibrillation (AF) in hypertrophic cardiomyopathy (HCM) patients. This model identifies key risk factors, improving early detection and management of AF in HCM.
Area of Science:
- Cardiology
- Biomedical Engineering
- Data Science
Background:
- Hypertrophic cardiomyopathy (HCM) is a significant risk factor for new-onset atrial fibrillation (AF).
- Distinct pathogenic mechanisms link HCM and AF, necessitating improved prediction models.
- Early detection of AF in HCM patients is crucial for timely intervention and management.
Purpose of the Study:
- To develop and validate a machine learning (ML) model for predicting AF in patients with HCM.
- To identify electrophysiological abnormalities and non-traditional factors as preclinical predictors of AF.
- To enhance early warning systems and precision management strategies for AF in the HCM cohort.
Main Methods:
- Retrospective cohort study of HCM patients without prior AF (2014-2023).
- Two-step feature selection using Boruta algorithm and LASSO regression.
- Training and comparison of four ML algorithms against the HCM-AF score, utilizing SHAP for interpretability.
Main Results:
- New-onset AF developed in 3.42% of patients over a median follow-up of 6.50 years.
- The Random Forest model achieved an AUC of 0.770, outperforming the HCM-AF score (AUC 0.692).
- Key predictors identified include heart failure indices, age, left atrial size, and P-wave abnormalities.
Conclusions:
- The Random Forest model demonstrates robust predictive ability for AF in HCM patients.
- P-wave indices are validated as preclinical AF biomarkers using ML.
- The integrated model provides a practical tool for early AF risk stratification in HCM.
Background:
Hypertrophic cardiomyopathy (HCM) significantly increases the risk of new-onset atrial fibrillation (AF) through distinct pathogenic mechanisms. This study develops a machine learning (ML) model to improve AF prediction in patients with HCM and investigates electrophysiological abnormalities and non-traditional factors as preclinical predictors. The findings aim to inform early warning systems and precision management strategies for AF in this patient cohort.
Methods:
This retrospective cohort study consecutively enrolled patients diagnosed with HCM who had no prior history of AF from 2014 to 2023. A two-step feature selection procedure involving the Boruta algorithm and LASSO regression was implemented, and four machine-learning based algorithms were trained and compared against the reference model of the HCM-AF score. The Shapley Additive Explanations (SHAP) method was utilized for interpretability.
Results:
A total of 225 patients (annual incidence ratio 3.42%, 225/1014) developed new-onset AF during the median follow-up period of 6.50 years. Twelve clinical variables were identified through the feature selection process, with the random forest model demonstrating the best overall performance with area under the receiver-operating characteristic curve (AUC) 0.770 and 95% confidence interval (CI) of 0.699-0.840, outperforming the reference model (AUC 0.692, 95% CI 0.598-0.786) (Delong's P = 0.012). The SHAP analysis revealed that indices of heart failure, age, left atrial size, followed by a history of cardiac implantable electronic devices, frequent atrial premature contractions, P-wave terminal force in lead V1, P-wave duration, PR interval, and left ventricular remodeling were associated with a significantly higher model-predicted risk of AF.
Conclusions:
The Random Forest model outperformed the HCM-AF score with robust predictive ability, validating P-wave indices as preclinical AF biomarkers through ML model for the first time. This integrated model offers a practical tool for early AF risk stratification in HCM, highlighting the clinical value of early symptomatic monitoring. Future multicenter validation is needed.
Related Concept Videos
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:29Cardiomyopathy V: Interprofessional Care
01:30Cardiomyopathy II: Dilated Cardiomyopathy