Model-based analysis of myocardial strain data acquired by tissue Doppler imaging

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.

Chromatin Immunoprecipitation Experiments from Drosophila Ovaries

Chromatin is composed of DNA and its associated proteins, and has an essential role in all cellular processes, including those taking place during Drosophila oogenesis. In order to understand the molecular basis of chromatin-based processes, such as transcription, it is essential to be able to study how and when different proteins, such as transcription factors, histones and RNA polymerases, interact with chromatin. One of the most popular methods to study this is chromatin immunoprecipitation followed by next generation sequencing (ChIP-seq). Here, we describe a ChIP-seq protocol that has been optimized for Drosophila ovaries, focusing on sample preparation through preliminary data processing.

How myocardial work could be relevant in patients with an aortic valve stenosis?

AIMS

Myocardial work (MW) calculation is an attractive method to assess left ventricular (LV) myocardial function. In case of aortic stenosis (AS), assessment of work indices is challenging because it requires an accurate evaluation of LV-pressure curves. We sought to evaluate the performances of two distinct methods and to provide a quantitative comparison with invasive data.

METHODS AND RESULTS

Model-based and template-based methods were defined and applied for the evaluation of LV-pressures on 67 AS-patient. Global Constructive (GCW), Wasted (GWW), Positive (GPW), Negative (GNW) MW and Global Work Efficiency (GWE), and Index (GWI) parameters were calculated using the available software computing the indices using brachial blood-pressure and trans-aortic mean pressure gradient (MPG) for estimating the LV-pressures vs. using a model-based and homemade software. A complete comparison was performed with invasive measurements. Patients were characterized by MPG of 49.8 ± 14.8 mmHg, the global longitudinal strain (GLS) was -15.0 ± 4.04%, GCW was 2107 ± 800 mmHg.% (model-based) and 2483 ± 1068 mmHg.% (template-based). The root mean square error (RMSE) and correlation were calculated for each patient and pressure estimation methods. The mean RMSE are 33.9 mmHg and 40.4 mmHg and the mean correlation coefficients are 0.81 and 0.72 for the model-based and template-based methods, respectively. The two methods present correlation coefficient r2 >0.75 for all the indices.

CONCLUSION

The two non-invasive methods of LV pressure estimation and work indices computation correlate with invasive measurements. Although the model-based approach requires less information and is associated with slightly better performances, the implementation of template-based method is easier and is appropriate for clinical practice.

Desynchronization Strain Patterns and Contractility in Left Bundle Branch Block through Computer Model Simulation

Left bundle branch block (LBBB) is associated with specific septal-to-lateral wall activation patterns which are strongly influenced by the intrinsic left ventricular (LV) contractility and myocardial scar localization. The objective of this study was to propose a computational-model-based interpretation of the different patterns of LV contraction observed in the case of LBBB and preserved contractility or myocardial scarring. Two-dimensional transthoracic echocardiography was used to obtain LV volumes and deformation patterns in three patients with LBBB: (1) a patient with non-ischemic dilated cardiomyopathy, (2) a patient with antero-septal myocardial scar, and (3) a patient with lateral myocardial scar. Scar was confirmed by the distribution of late gadolinium enhancement with cardiac magnetic resonance imaging (cMRI). Model parameters were evaluated manually to reproduce patient-derived data such as strain curves obtained from echocardiographic apical views. The model was able to reproduce the specific strain patterns observed in patients. A typical septal flash with pre-ejection shortening, rebound stretch, and delayed lateral wall activation was observed in the case of non-ischemic cardiomyopathy. In the case of lateral scar, the contractility of the lateral wall was significantly impaired and septal flash was absent. In the case of septal scar, septal flash and rebound stretch were also present as previously described in the literature. Interestingly, the model was also able to simulate the specific contractile properties of the myocardium, providing an excellent localization of LV scar in ischemic patients. The model was able to simulate the electromechanical delay and specific contractility patterns observed in patients with LBBB of ischemic and non-ischemic etiology. With further improvement and validation, this technique might be a useful tool for the diagnosis and treatment planning of heart failure patients needing CRT.

Modeling patient-specific desaturation patterns in sleep apnea

OBJECTIVE

The physiological mechanisms involved in cardio-respiratory responses to sleep apnea events are not yet fully elucidated. A model-based approach is proposed to analyse the acute desaturation response to obstructive apneas.

METHODS

An integrated model of cardio-respiratory interactions was proposed and parameters were identified, using an evolutionary algorithm, on a database composed of 107 obstructive apneas acquired from 10 patients (HYPNOS clinical study). Unsupervised clustering was applied to the identified parameters in order to characterize the phenotype of each response to obstructive apneas.

RESULTS

A close match was observed between simulated oxygen saturation (SaO2) and experimental SaO2 in all identifications (median RMSE = 1.3892%). Two clusters of parameters, associated with different dynamics related to sleep apnea and periodic breathing were obtained.

CONCLUSION AND SIGNIFICANCE

The proposed patient and event-specific model-based analysis provides understanding on specific desaturation patterns, consequent to apnea events, with potential applications for personalized diagnosis and treatment.

Prediction of response to cardiac resynchronization therapy using a multi-feature learning method

We hypothesized that a multiparametric evaluation, based on the combination of electrocardiographic and echocardiographic parameters, could enhance the appraisal of the likelihood of reverse remodeling and prognosis of favorable clinical evolution to improve the response of cardiac resynchronization therapy (CRT). Three hundred and twenty-three heart failure patients were retrospectively included in this multicenter study. 221 patients (68%) were responders, defined by a decrease in left ventricle end-systolic volume ≥15% at the 6-month follow-up. In addition, strain data coming from echocardiography were analyzed with custom-made signal processing methods. Integrals of regional longitudinal strain signals from the beginning of the cardiac cycle to strain peak and to the instant of aortic valve closure were analyzed. QRS duration, septal flash and different other features manually extracted were also included in the analysis. The random forest (RF) method was applied to analyze the relative feature importance, to select the most significant features and to build an ensemble classifier with the objective of predicting response to CRT. The set of most significant features was composed of Septal Flash, E, E/A, E/EA, QRS, left ventricular end-diastolic volume and eight features extracted from strain curves. A Monte Carlo cross-validation method with 100 runs was applied, using, in each run, different random sets of 80% of patients for training and 20% for testing. Results show a mean area under the curve (AUC) of 0.809 with a standard deviation of 0.05. A multiparametric approach using a combination of echo-based parameters of left ventricular dyssynchrony and QRS duration helped to improve the prediction of the response to cardiac resynchronization therapy.

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.

Sensitivity Analysis of a Left Ventricle Model in the Context of Intraventricular Dyssynchrony

The objective of the current study was to propose a sensitivity analysis of a 3D left ventricle model in order to assess the influence of parameters on myocardial mechanical dispersion. A finite element model of LV electro-mechanical activity was proposed and a screening method was used to evaluate the sensitivity of model parameters on the standard deviation of time to peak strain. Results highlight the importance of propagation parameters associated with septal and lateral segments activation. Simulated curves were compared to myocardial strains, obtained from echocardiography of one healthy subject and one patient diagnosed with intraventricular dyssynchrony and coronary artery disease. Results show a close match between simulation and clinical strains and illustrate the model ability to reproduce myocardial strains in the context of intraventricular dyssynchrony.

Visualization of Myocardial Strain Pattern Uniqueness with Respect to Activation Time and Contractility: A Computational Study

Speckle tracking echography is used to measure myocardial strain patterns in order to assess the state of myocardial tissue. Because electro-mechanical coupling in myocardial tissue is complex and nonlinear, and because of the measurement errors the uniqueness of strain patterns is questionable. In this study, the uniqueness of strain patterns was visualized in order to revel characteristics that may improve their interpretation. A computational model of sarcomere mechanics was used to generate a database of 1681 strain patterns, each simulated with a different set of sarcomere parameters: time of activation (TA) and contractility (Con). TA and Con ranged from −100 ms to 100 ms and 2% to 202% in 41 steps respectively, thus forming a two-dimensional 41 × 41 parameter space. Uniqueness of the strain pattern was assessed by using a cohort of similar strain patterns defined by a measurement error. The cohort members were then visualized in the parameter space. Each cohort formed one connected component (or blob) in the parameter space; however, large differences in the shape, size, and eccentricity of the blobs were found for different regions in the parameter space. The blobs were elongated along the TA direction (±50 ms) when contractility was low, and along the Con direction (±50%) when contractility was high. The uniqueness of the strain patterns can be assessed and visualized in the parameter space. The strain patterns in the studied database are not degenerated because a cohort of similar strain patterns forms only one connected blob in the parameter space. However, the elongation of the blobs means that estimations of TA when contractility is low and of Con when contractility is high have high uncertainty.

A model-based approach for the evaluation of vagal and sympathetic activities in a newborn lamb

This paper proposes a baroreflex model and a recursive identification method to estimate the time-varying vagal and sympathetic contributions to heart rate variability during autonomic maneuvers. The baroreflex model includes baroreceptors, cardiovascular control center, parasympathetic and sympathetic pathways. The gains of the global afferent sympathetic and vagal pathways are identified recursively. The method has been validated on data from newborn lambs, which have been acquired during the application of an autonomic maneuver, without medication and under beta-blockers. Results show a close match between experimental and simulated signals under both conditions. The vagal and sympathetic contributions have been simulated and, as expected, it is possible to observe different baroreflex responses under beta-blockers compared to baseline conditions.

An inverse finite element method for determining the tissue compressibility of human left ventricular wall during the cardiac cycle

The determination of the myocardium's tissue properties is important in constructing functional finite element (FE) models of the human heart. To obtain accurate properties especially for functional modeling of a heart, tissue properties have to be determined in vivo. At present, there are only few in vivo methods that can be applied to characterize the internal myocardium tissue mechanics. This work introduced and evaluated an FE inverse method to determine the myocardial tissue compressibility. Specifically, it combined an inverse FE method with the experimentally-measured left ventricular (LV) internal cavity pressure and volume versus time curves. Results indicated that the FE inverse method showed good correlation between LV repolarization and the variations in the myocardium tissue bulk modulus K (K = 1/compressibility), as well as provided an ability to describe in vivo human myocardium material behavior. The myocardium bulk modulus can be effectively used as a diagnostic tool of the heart ejection fraction. The model developed is proved to be robust and efficient. It offers a new perspective and means to the study of living-myocardium tissue properties, as it shows the variation of the bulk modulus throughout the cardiac cycle.

Embedding a cardiac pulsatile model into an integrated model of the cardiovascular regulation for heart failure followup

The analysis of followup data from patients suffering from heart failure is a difficult task, due to the complex and multifactorial nature of this pathology. In this paper, we present a coupled model, integrating a pulsatile heart into a model of the short to long-term regulations of the cardiovascular system. An interface method is proposed to couple these models, which present significantly different time scales. Results from a sensitivity analysis of the original and integrated models are proposed with simulations reproducing the main effects of the short- and long-term responses of an acute decompensated heart failure episode on a patient undergoing cardiac resynchronization therapy.

Current progress in patient-specific modeling

We present a survey of recent advancements in the emerging field of patient-specific modeling (PSM). Researchers in this field are currently simulating a wide variety of tissue and organ dynamics to address challenges in various clinical domains. The majority of this research employs three-dimensional, image-based modeling techniques. Recent PSM publications mostly represent feasibility or preliminary validation studies on modeling technologies, and these systems will require further clinical validation and usability testing before they can become a standard of care. We anticipate that with further testing and research, PSM-derived technologies will eventually become valuable, versatile clinical tools.

A multiformalism and multiresolution modelling environment: application to the cardiovascular system and its regulation

The role of modelling and simulation in the systemic analysis of living systems is now clearly established. Emerging disciplines, such as systems biology, and worldwide research actions, such as the Physiome Project or the Virtual Physiological Human, are based on an intensive use of modelling and simulation methodologies and tools. One of the key aspects in this context is to perform an efficient integration of various models representing different biological or physiological functions, at different resolutions, spanning through different scales. This paper presents a multiformalism modelling and simulation environment (M2SL) that has been conceived to ease model integration. A given model is represented as a set of coupled and atomic model components that may be based on different mathematical formalisms with heterogeneous structural and dynamical properties. A co-simulation approach is used to solve these hybrid systems. The pioneering model of the overall regulation of the cardiovascular system proposed by Guyton and co-workers in 1972 has been implemented under M2SL and a pulsatile ventricular model based on a time-varying elastance has been integrated in a multi-resolution approach. Simulations reproducing physiological conditions and using different coupling methods show the benefits of the proposed environment.