Automated machine learning of echocardiographic strain enables identification of early myocardial changes in pre-symptomatic TTR carriers

Authors:
Preprint
Publisher website
Google Scholar
Abstract
Objectives: To identify unique echocardiographic signatures associated with TTR + carrier status preceding onset of cardiac amyloidosis. Background: Carrier status for the most common pathogenic TTR variant in the United States, Val142Ile (V142I), found in 4% of African Americans (AA) and 1% of Hispanic/Latino (H/L) individuals, confers a 40-60% lifetime risk of developing variant transthyretin amyloidosis (ATTRv), including cardiac amyloidosis (CA) and heart failure (HF). Myocardial amyloid deposition is believed to progress over many years. Genomic screening programs and familial cascade genetic testing are increasingly uncovering pre-symptomatic TTR + carriers, yet no guidelines exist to pragmatically risk stratify these individuals for CA. Methods: V142I+ carriers (cases) without prior diagnoses of amyloidosis or HF were identified among Bio Me biobank participants with available exome sequencing data linked to electronic health records (EHRs) including at least one available echocardiogram. Controls were biobank participants with normal TTR sequencing who were age-, sex- and ancestry-matched to cases. Speckle-tracking echocardiography (STE) was applied to images and conventional and strain measurements were evaluated by univariate analyses. A random forest model was trained using a minimal redundancy maximal relevance (mRMR, applied to mitigate overfitting) feature set and evaluated by 5-fold cross-validation to minimize optimism bias. Discriminatory performance was assessed using the area under the receiver operating characteristic curve (AUC). Results: 49 TTR + (100% V142I, median age 61 years, 69.4% female) and 45 matched TTR -biobank participants were included in the model development cohort. STE generated approximately 200 features. Univariate analyses revealed no significant differences between carriers and controls on any individual strain or conventional echocardiographic measurements including global longitudinal, right ventricular and left atrial strain. mRMR feature selection resulted in a set of 15 features retained for all downstream modeling, integrating global amyloid signatures, regional inferolateral strain abnormalities, layer-specific deformation, and mechanical timing heterogeneity. Using this feature set, the model achieved good discrimination (AUC=0.76). Feature importance analysis highlighted relative apical sparing, inferolateral strain reduction, and basal-apical timing gradients as key contributors to model performance. External validation (n=115) confirmed good model discrimination (AUC=0.781, 95% CI: 0.688-0.869, sensitivity 0.983). Conclusions: Machine learning applied to routinely acquired echocardiographic data can identify subtle myocardial abnormalities associated with TTR V142I carrier status prior to development of CA. Key model features are physiologically relevant to known echocardiographic characteristics of overt CA. Genotype-guided echocardiographic surveillance may be a scalable strategy for early detection of CA risk.

This publication has 36 references indexed in Scilit: