Characterization of cardiac resynchronization therapy response through machine learning and personalized models.

INTRODUCTION: The characterization and selection of heart failure (HF) patients for cardiac resynchronization therapy (CRT) remain challenging, with around 30% non-responder rate despite following current guidelines. This study aims to propose a novel hybrid approach, integrating machine-learning and personalized models, to identify explainable phenogroups of HF patients and predict their CRT response. METHODS: The paper proposes the creation of a complete personalized model population based on preoperative CRT patient strain curves. Based on the parameters and features extracted from these personalized models, phenotypes of patients are identified thanks to a clustering algorithm and a random forest classification is provided. RESULTS: A close match was observed between the 162 experimental and simulated myocardial strain curves, with a mean RMSE of 4.48% (±1.08) for the 162 patients. Five phenogroups of personalized models were identified from the clustering, with response rates ranging from 52% to 94%. The classification results show a mean area under the curves (AUC) of 0.86 ± 0.06 and provided a feature importance analysis with 22 features selected. Results show both regional myocardial contractility (from 22.5% to 33.0%), tissue viability and electrical activation delays importance on CRT response for each HF patient (from 55.8 ms to 88.4 ms). DISCUSSION: The patient-specific model parameters' analysis provides an explainable interpretation of HF patient phenogroups in relation to physiological mechanisms that seem predictive of the CRT response. These novel combined approaches appear as promising tools to improve understanding of LV mechanical dyssynchrony for HF patient characterization and CRT selection.

Model-based estimation of left ventricular pressure and myocardial work in aortic stenosis.

This paper proposes a model-based estimation of left ventricular (LV) pressure for the evaluation of constructive and wasted myocardial work of patients with aortic stenosis (AS). A model of the cardiovascular system is proposed, including descriptions of i) cardiac electrical activity, ii) elastance-based cardiac cavities, iii) systemic and pulmonary circulations and iv) heart valves. After a sensitivity analysis of model parameters, an identification strategy was implemented using a Monte-Carlo cross-validation approach. Parameter identification procedure consists in two steps for the estimation of LV pressures: step 1) from invasive, intraventricular measurements and step 2) from non-invasive data. The proposed approach was validated on data obtained from 12 patients with AS. The total relative errors between estimated and measured pressures were on average 11.9% and 12.27% and mean R2 were equal to 0.96 and 0.91, respectively for steps 1 and 2 of parameter identification strategy. Using LV pressures obtained from non-invasive measurements (step 2) and patient-specific simulations, Global Constructive (GCW), Wasted (GWW) myocardial Work and Global Work Efficiency (GWE) parameters were calculated. Correlations between measures and model-based estimations were 0.88, 0.80, 0.91 respectively for GCW, GWW and GWE. The main contributions concern the proposal of the parameter identification procedure, applied on an integrated cardiovascular model, able to reproduce LV pressure specifically to each AS patient, by non-invasive procedures, as well as a new method for the non-invasive estimation of constructive, wasted myocardial work and work efficiency in AS.