Search

AIMS: We tested the hypothesis that a machine learning (ML) algorithm utilizing both complex echocardiographic data and clinical parameters could be used to phenogroup a heart failure (HF) cohort and identify patients with beneficial response to cardiac resynchronization therapy (CRT). METHODS AND RESULTS: We studied 1106 HF patients from the Multicenter Automatic Defibrillator Implantation Trial with Cardiac Resynchronization Therapy (MADIT-CRT) (left ventricular ejection fraction ≤ 30%, QRS ≥ 130 ms, New York Heart Association class ≤ II) randomized to CRT with a defibrillator (CRT-D, n = 677) or an implantable cardioverter defibrillator (ICD, n = 429). An unsupervised ML algorithm (Multiple Kernel Learning and K-means clustering) was used to categorize subjects by similarities in clinical parameters, and left ventricular volume and deformation traces at baseline into mutually exclusive groups. The treatment effect of CRT-D on the primary outcome (all-cause death or HF event) and on volume response was compared among these groups. Our analysis identified four phenogroups, significantly different in the majority of baseline clinical characteristics, biomarker values, measures of left and right ventricular structure and function and the primary outcome occurrence. Two phenogroups included a higher proportion of known clinical characteristics predictive of CRT response, and were associated with a substantially better treatment effect of CRT-D on the primary outcome [hazard ratio (HR) 0.35; 95% confidence interval (CI) 0.19-0.64; P = 0.0005 and HR 0.36; 95% CI 0.19-0.68; P = 0.001] than observed in the other groups (interaction P = 0.02). CONCLUSIONS: Our results serve as a proof-of-concept that, by integrating clinical parameters and full heart cycle imaging data, unsupervised ML can provide a clinically meaningful classification of a phenotypically heterogeneous HF cohort and might aid in optimizing the rate of responders to specific therapies. ispartof: EUROPEAN JOURNAL OF HEART FAILURE vol:21 issue:1 pages:74-85 ispartof: location:England status: published

International audience; Electroanatomical maps (EAMs) are commonly acquired in clinical routine for guiding ablation therapies. They provide voltage and activation time information on a 3D anatomical mesh representation, making them useful for analyzing the electrical activation patterns in specific pathologies. However, they are extremely acquisition dependent and complex, and therefore difficult to quantify and compare with other EAMs acquired at different times or from different patients. In this paper, we introduce a set of tools for the quantitative analysis of EAMs, going beyond the methods currently used in clinical practice. They are based on the quantitative estimation of simple biomarkers relevant to disease and therapies. Notably, we develop global indices (total activation time), local indices (local activation time, surrogates of conduction velocity, inter-ventricular and transmural delays), and therapy-based indices (lead position) to better characterize EAM data. Furthermore we propose 2D and 3D representations of the activation patterns –for their enhanced visualization and comparison in a common reference system. After verification and validation experiments on synthetically generated data, the proposed analysis tools are applied to EAM data obtained in an experimental swine model of induced Left Bundle Branch Block (LBBB) with an implanted Cardiac Resynchronization (CRT) device. Specifically, we have analyzed and compared electrical activation patterns at baseline, LBBB and CRT stages in 4 animals: two without any structural disease; and two with an induced infarction. The proposed tools automatically relate the ventricular lead location with electrical dyssynchrony, which allows evaluating the current hypothesis about lead placement in CRT.

We tested the hypothesis that a machine learning (ML) algorithm utilizing both complex echocardiographic data and clinical parameters could be used to phenogroup a heart failure (HF) cohort and identify patients with beneficial response to cardiac resynchronization therapy (CRT). The work of S. Sanchez‐Martinez was supported by a fellowship from ‘la Caixa’ Banking Foundation. C. Butakoff was supported by a grant from the Fundació La Marató de TV3 (n. 20154031), Spain. N. Duchateau was supported by ‘Programme Avenir Lyon Saint‐Etienne’ (PALSE‐IMPULSION‐2016, Lyon, France). MADIT‐CRT was sponsored by Boston Scientific, while no additional funding was provided for this analysis. This study was also partially supported by the Spanish Ministry of Economy and Competitiveness (grant TIN2014‐52923‐R; Maria de Maeztu Units of Excellence Programme ‐ MDM‐2015‐0502) and FEDER.