The emerging role of cardiovascular MRI for risk stratification in hypertrophic cardiomyopathy

Machine learning and physical based modeling for cardiac hypertrophy

Background and objective

Predicting the long-term expansion and remodeling of the left ventricle in patients is challenging task but it has the potential to be clinically very useful.

Methods

In our study, we present machine learning models based on random forests, gradient boosting, and neural networks, used to track cardiac hypertrophy. We collected data from multiple patients, and then the model was trained using the patient's medical history and present level of cardiac health. We also demonstrate a physical-based model, using the finite element procedure to simulate the development of cardiac hypertrophy.

Results

Our models were used to forecast the evolution of hypertrophy over six years. The machine learning model and finite element model provided similar results.

Conclusions

The finite element model is much slower, but it's more accurate compared to the machine learning model since it's based on physical laws guiding the hypertrophy process. On the other hand, the machine learning model is fast but the results can be less trustworthy in some cases. Both of our models, enable us to monitor the development of the disease. Because of its speed machine learning model is more likely to be used in clinical practice. Further improvements to our machine learning model could be achieved by collecting data from finite element simulations, adding them to the dataset, and retraining the model. This can result in a fast and more accurate model combining the advantages of physical-based and machine learning modeling.

Disease Progression of Hypertrophic Cardiomyopathy: Modeling Using Machine Learning

BACKGROUND

Cardiovascular disorders in general are responsible for 30% of deaths worldwide. Among them, hypertrophic cardiomyopathy (HCM) is a genetic cardiac disease that is present in about 1 of 500 young adults and can cause sudden cardiac death (SCD).

OBJECTIVE

Although the current state-of-the-art methods model the risk of SCD for patients, to the best of our knowledge, no methods are available for modeling the patient's clinical status up to 10 years ahead. In this paper, we propose a novel machine learning (ML)-based tool for predicting disease progression for patients diagnosed with HCM in terms of adverse remodeling of the heart during a 10-year period.

METHODS

The method consisted of 6 predictive regression models that independently predict future values of 6 clinical characteristics: left atrial size, left atrial volume, left ventricular ejection fraction, New York Heart Association functional classification, left ventricular internal diastolic diameter, and left ventricular internal systolic diameter. We supplemented each prediction with the explanation that is generated using the Shapley additive explanation method.

RESULTS

The final experiments showed that predictive error is lower on 5 of the 6 constructed models in comparison to experts (on average, by 0.34) or a consortium of experts (on average, by 0.22). The experiments revealed that semisupervised learning and the artificial data from virtual patients help improve predictive accuracies. The best-performing random forest model improved R² from 0.3 to 0.6.

CONCLUSIONS

By engaging medical experts to provide interpretation and validation of the results, we determined the models' favorable performance compared to the performance of experts for 5 of 6 targets.

A machine learning-based risk stratification model for ventricular tachycardia and heart failure in hypertrophic cardiomyopathy

BACKGROUND

Machine learning (ML) and artificial intelligence are emerging as important components of precision medicine that enhance diagnosis and risk stratification. Risk stratification tools for hypertrophic cardiomyopathy (HCM) exist, but they are based on traditional statistical methods. The aim was to develop a novel machine learning risk stratification tool for the prediction of 5-year risk in HCM. The goal was to determine if its predictive accuracy is higher than the accuracy of the state-of-the-art tools.

METHOD

Data from a total of 2302 patients were used. The data were comprised of demographic characteristics, genetic data, clinical investigations, medications, and disease-related events. Four classification models were applied to model the risk level, and their decisions were explained using the SHAP (SHapley Additive exPlanations) method. Unwanted cardiac events were defined as sustained ventricular tachycardia occurrence (VT), heart failure (HF), ICD activation, sudden cardiac death (SCD), cardiac death, and all-cause death.

RESULTS

The proposed machine learning approach outperformed the similar existing risk-stratification models for SCD, cardiac death, and all-cause death risk-stratification: it achieved higher AUC by 17%, 9%, and 1%, respectively. The boosted trees achieved the best performing AUC of 0.82. The resulting model most accurately predicts VT, HF, and ICD with AUCs of 0.90, 0.88, and 0.87, respectively.

CONCLUSIONS

The proposed risk-stratification model demonstrates high accuracy in predicting events in patients with hypertrophic cardiomyopathy. The use of a machine-learning risk stratification model may improve patient management, clinical practice, and outcomes in general.

Clinics in diagnostic imaging (189). Acute phase cardiac sarcoidosis (CS)

A 44-year-old man presented with breathlessness and episodes of palpitations for the last one year. The imaging diagnosis of cardiac sarcoidosis was made based on chest radiography and cardiac magnetic resonance (MR) imaging findings, and was further confirmed by biopsy. Cardiac sarcoidosis is an uncommon entity, yet is potentially fatal with nonspecific clinical manifestations, including sudden cardiac death. Hence, it is important to diagnose and treat this entity at an early stage to improve morbidity and mortality. Cardiac MR imaging plays a pivotal role in facilitating diagnosis and monitoring therapeutic response. We describe the MR imaging features of cardiac sarcoidosis and discuss imaging features of other cardiomyopathies that may mimic cardiac sarcoidosis.

The follow-up of progressive hypertrophic cardiomyopathy using magnetic resonance rotating frame relaxation times

Magnetic resonance rotating frame relaxation times are an alternative non-contrast agent choice for the diagnosis of chronic myocardial infarct. Fibrosis typically occurs in progressive hypertrophic cardiomyopathy. Fibrosis has been imaged in myocardial infarcted tissue using rotating frame relaxation times, which provides the possibility to follow up progressive cardiomyopathy without contrast agents. Mild and severe left ventricular hypertrophy were induced in mice by transverse aortic constriction, and the longitudinal rotating frame relaxation times (T_1ρ ) and relaxation along the fictitious field (T_RAFF2 , T_RAFF3 ) were measured at 5, 10, 24, 62 and 89 days after transverse aortic constriction in vivo. Myocardial fibrosis was verified using Masson's trichrome staining. Increases in the relative relaxation time differences of T_1ρ , together with T_RAFF2 and T_RAFF3 , between fibrotic and remote tissues over time were observed. Furthermore, T_RAFF2 and T_RAFF3 showed higher relaxation times overall in fibrotic tissue than T_1ρ . Relaxation time differences were highly correlated with an excess of histologically verified fibrosis. We found that T_RAFF2 and T_RAFF3 are more sensitive than T_1ρ to hypertrophic cardiomyopathy-related tissue changes and can serve as non-invasive diagnostic magnetic resonance imaging markers to follow up the mouse model of progressive hypertrophic cardiomyopathy.

Cardiac Magnetic Resonance and Computed Tomography in Hypertrophic Cardiomyopathy: an Update

Hypertrophic cardiomyopathy (HCM) is the most common genetic cardiovascular disease and represents the main cause of sudden death in young patients. Cardiac magnetic resonance (CMR) and cardiac computed tomography (CCT) are noninvasive imaging methods with high sensitivity and specificity, useful for the establishment of diagnosis and prognosis of HCM, and for the screening of patients with subclinical phenotypes. The improvement of image analysis by CMR and CCT offers the potential to promote interventions aiming at stopping the natural course of the disease. This study aims to describe the role of RCM and CCT in the diagnosis and prognosis of HCM, and how these methods can be used in the management of these patients.

Unexpectedly low left ventricular voltage on ECG in hypertrophic cardiomyopathy

OBJECTIVE

While late gadolinium enhancement (LGE) in paediatric patients with hypertrophic cardiomyopathy (HCM) is reported as similar to adults, the relationship between LGE and ECG findings in paediatric patients is unknown. We sought to evaluate the relationship between LGE on cardiac MRI and LV precordial voltage on ECG.

METHODS

This was a retrospective analysis of paediatric patients with HCM aged 9-21 years with cardiac MRI and ECG completed within 60 days of each other. Demographic, MRI and ECG data were compared between patients with and without LGE. Maximal diastolic septal thickness, septal to free wall ratio and LGE presence were compared with LV precordial voltage (SV1, RV6 and SV1+RV6).

RESULTS

This study included 37 patients (33 male). Mean age was 15.8±2.8 years. Mean maximal LV diastolic septal thickness was 22.1±7.9 mm. Mean septal to free wall ratio was 2.4±1.6 mm. LGE was present in 18 patients, with 16 isolated to the ventricular septum. Comparing patients with and without LGE, there was no difference in age (p=0.2) or body surface area (p=0.9). However, the presence of LGE was associated with significantly increased septal thickness (p=0.03), yet decreased voltages in SV1 (p=0.005), RV6 (p=0.005) and SV1+RV6 (p=0.002) despite increased septal dimensions.

CONCLUSIONS

A significant inverse relationship exists between LGE presence and LV precordial voltage in this population. Unexpectedly low LV precordial voltages in patients with HCM may serve as a clinical surrogate marker for myocardial fibrosis and potential loss of viable myocardial tissue.

Advanced Imaging of Athletes: Added Value of Coronary Computed Tomography and Cardiac Magnetic Resonance Imaging

Cardiac magnetic resonance imaging and cardiac computed tomographic angiography have become important parts of the armamentarium for noninvasive diagnosis of cardiovascular disease. Emerging technologies have produced faster imaging, lower radiation dose, improved spatial and temporal resolution, as well as a wealth of prognostic data to support usage. Investigating true pathologic disease as well as distinguishing normal from potentially dangerous is now increasingly more routine for the cardiologist in practice. This article investigates how advanced imaging technologies can assist the clinician when evaluating all athletes for pathologic disease that may put them at risk.