Related Experiment Videos
A fully automated machine learning assisted pipeline to predict disease progression for early-stage hypertrophic
Antoine Olivier1, Auriane Riou1, Thomas d'Humières2
1Owkin France, Paris, France.
Insights
Machine learning accurately predicts hypertrophic cardiomyopathy (HCM) progression using echocardiography. An automated pipeline identified the left atrioventricular coupling index (LACI) as a key predictor, improving risk stratification for pre-symptomatic patients.
Area of Science:
- Cardiology
- Medical Imaging
- Machine Learning
Background:
- Echocardiography is vital for hypertrophic cardiomyopathy (HCM) diagnosis and risk stratification.
- Predicting disease progression in pre-symptomatic HCM using echocardiography requires further exploration.
Purpose of the Study:
- To assess the prognostic value of echocardiography in pre-symptomatic HCM.
- To develop a machine learning (ML) pipeline for predicting disease progression in HCM patients.
Main Methods:
- Utilized echocardiographic data from 260 NYHA I HCM patients.
- Developed a fully automated deep learning segmentation and ML pipeline using radiomic features.
- Validated the ML model and derived echocardiographic marker on an external cohort.
Main Results:
- The ML model achieved good predictive performance in both discovery (C-index 0.66) and validation (C-index 0.67) cohorts.
- Derived left atrioventricular coupling index (LACI) showed strong prognostic value (C-index 0.67-0.72).
- High-risk group (LACI > 0.51) had a significantly higher 3-year risk of disease progression (19%) compared to the low-risk group (8%).
Conclusions:
- A fully automated ML model successfully identified area-derived LACI as a robust feature for predicting disease progression in pre-symptomatic HCM.
- This approach offers improved risk stratification for patients with pre-symptomatic HCM.
Introduction:
Echocardiography is critical for the diagnosis and risk stratification of hypertrophic cardiomyopathy (HCM). However, its value to predict disease progression in pre-symptomatic HCM remains to be fully explored. This study aims to assess the prognostic value of echocardiography in pre-symptomatic HCM using a fully automated machine learning (ML) pipeline to predict disease progression.
Methods:
Echocardiographic data (B-mode acquisitions of apical 4-chamber sequences) from 260 NYHA I HCM patients, collected retrospectively from two centers, was used. An ML pipeline was built on the discovery cohort ( patients) to predict disease progression, defined as a composite of NYHA class worsening and unplanned cardiovascular-related hospitalizations. A fully automated deep learning segmentation pipeline was used to delineate cardiac chambers in apical 4-chamber views and identify end-diastolic frames. Shape-based radiomic features extracted from these segmentations were used to train a survival model based on gradient-boosted trees. The ML model and a derived actionable echocardiographic marker were validated on an external cohort ( patients).
Results:
The 3-year risk of disease progression was 12% in the discovery cohort and 15% in the validation cohort. The ML model achieved a C-index of (95% CI [0.54, 0.77], nested cross-validation folds) in the discovery cohort and (95% CI [0.46, 0.88], 100 bootstrapped samples) in the validation cohort. Following model interpretation, the left atrioventricular coupling index (area-derived LACI) at end-diastole was derived, and used as a risk score, achieving a C-index of (95% CI [0.58, 0.77]) and (95% CI [0.56, 0.88]) in the discovery and validation cohorts, respectively (100 bootstrapped samples). The high-risk group, with , had a 3-year risk of disease progression of 19% (95% CI [13%, 36%]) compared to 8% (95% CI [5%, 15%]) for the low-risk group LACI in the discovery cohort.
Conclusion:
A fully automated ML model identifies area-derived LACI at end-diastole as a robust feature associated with disease progression, providing improved risk stratification for pre-symptomatic HCM.
