Machine learning-based phenogrouping in heart failure to identify responders to cardiac resynchronization therapy

Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility

BACKGROUND

Machine learning (ML) is increasingly used in research for subtype definition and risk prediction, particularly in cardiovascular diseases. No existing ML models are routinely used for cardiovascular disease management, and their phase of clinical utility is unknown, partly due to a lack of clear criteria. We evaluated ML for subtype definition and risk prediction in heart failure (HF), acute coronary syndromes (ACS) and atrial fibrillation (AF).

METHODS

For ML studies of subtype definition and risk prediction, we conducted a systematic review in HF, ACS and AF, using PubMed, MEDLINE and Web of Science from January 2000 until December 2019. By adapting published criteria for diagnostic and prognostic studies, we developed a seven-domain, ML-specific checklist.

RESULTS

Of 5918 studies identified, 97 were included. Across studies for subtype definition (n = 40) and risk prediction (n = 57), there was variation in data source, population size (median 606 and median 6769), clinical setting (outpatient, inpatient, different departments), number of covariates (median 19 and median 48) and ML methods. All studies were single disease, most were North American (n = 61/97) and only 14 studies combined definition and risk prediction. Subtype definition and risk prediction studies respectively had limitations in development (e.g. 15.0% and 78.9% of studies related to patient benefit; 15.0% and 15.8% had low patient selection bias), validation (12.5% and 5.3% externally validated) and impact (32.5% and 91.2% improved outcome prediction; no effectiveness or cost-effectiveness evaluations).

CONCLUSIONS

Studies of ML in HF, ACS and AF are limited by number and type of included covariates, ML methods, population size, country, clinical setting and focus on single diseases, not overlap or multimorbidity. Clinical utility and implementation rely on improvements in development, validation and impact, facilitated by simple checklists. We provide clear steps prior to safe implementation of machine learning in clinical practice for cardiovascular diseases and other disease areas.

Machine Learning in Arrhythmia and Electrophysiology

Machine learning (ML), a branch of artificial intelligence, where machines learn from big data, is at the crest of a technological wave of change sweeping society. Cardiovascular medicine is at the forefront of many ML applications, and there is a significant effort to bring them into mainstream clinical practice. In the field of cardiac electrophysiology, ML applications have also seen a rapid growth and popularity, particularly the use of ML in the automatic interpretation of ECGs, which has been extensively covered in the literature. Much lesser known are the other aspects of ML application in cardiac electrophysiology and arrhythmias, such as those in basic science research on arrhythmia mechanisms, both experimental and computational; in the development of better techniques for mapping of cardiac electrical function; and in translational research related to arrhythmia management. In the current review, we examine comprehensively such ML applications as they match the scope of this journal. The current review is organized in 3 parts. The first provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research. The basic information we provide can serve as a guide on how one might design and conduct an ML study. The second part is a review of arrhythmia and electrophysiology studies in which ML has been utilized, highlighting the broad potential of ML approaches. For each subject, we outline comprehensively the general topics, while reviewing some of the research advances utilizing ML under the subject. Finally, we discuss the main challenges and the perspectives for ML-driven cardiac electrophysiology and arrhythmia research.

[Artificial intelligence in cardiology : Relevance, current applications, and future developments]

Big data and applications of artificial intelligence (AI), such as machine learning or deep learning, will enrich healthcare in the future and become increasingly important. Among other things, they have the potential to avoid unnecessary examinations as well as diagnostic and therapeutic errors. They could enable improved, early and accelerated decision-making. In the article, the authors provide an overview of current AI-based applications in cardiology. The examples describe innovative solutions for risk assessment, diagnosis and therapy support up to patient self-management. Big data and AI serve as a basis for efficient, predictive, preventive and personalised medicine. However, the examples also show that research is needed to further develop the solutions for the benefit of the patient and the medical profession, to demonstrate the effectiveness and benefits in health care and to establish legal and ethical standards.

Identifying knowledge gaps in heart failure research among women using unsupervised machine-learning methods

Aim: To identify knowledge gaps in heart failure (HF) research among women, especially postmenopausal women. Materials & methods: We retrieved HF articles from PubMed. Natural language processing and text mining techniques were used to screen relevant articles and identify study objective(s) from abstracts. After text preprocessing, we performed topic modeling with non-negative matrix factorization to cluster articles based on the primary topic. Clusters were independently validated and labeled by three investigators familiar with HF research. Results: Our model yielded 15 topic clusters from articles on HF among women. Atrial fibrillation was found to be the most understudied topic. From articles specific to postmenopausal women, five clusters were identified. The smallest cluster was about stress-induced cardiomyopathy. Conclusion: Topic modeling can help identify understudied areas in medical research.

Importance of Systematic Right Ventricular Assessment in Cardiac Resynchronization Therapy Candidates: A Machine Learning Approach

BACKGROUND

Despite all having systolic heart failure and broad QRS intervals, patients screened for cardiac resynchronization therapy (CRT) are highly heterogeneous, and it remains extremely challenging to predict the impact of CRT devices on left ventricular function and outcomes. The aim of this study was to evaluate the relative impact of clinical, electrocardiographic, and echocardiographic data on the left ventricular remodeling and prognosis of CRT candidates by the application of machine learning approaches.

METHODS

One hundred ninety-three patients with systolic heart failure receiving CRT according to current recommendations were prospectively included in this multicenter study. A combination of the Boruta algorithm and random forest methods was used to identify features predicting both CRT volumetric response and prognosis. Model performance was tested using the area under the receiver operating characteristic curve. The k-medoid method was also applied to identify clusters of phenotypically similar patients.

RESULTS

From 28 clinical, electrocardiographic, and echocardiographic variables, 16 features were predictive of CRT response, and 11 features were predictive of prognosis. Among the predictors of CRT response, eight variables (50%) pertained to right ventricular size or function. Tricuspid annular plane systolic excursion was the main feature associated with prognosis. The selected features were associated with particularly good prediction of both CRT response (area under the curve, 0.81; 95% CI, 0.74-0.87) and outcomes (area under the curve, 0.84; 95% CI, 0.75-0.93). An unsupervised machine learning approach allowed the identification of two phenogroups of patients who differed significantly in clinical variables and parameters of biventricular size and right ventricular function. The two phenogroups had significantly different prognosis (hazard ratio, 4.70; 95% CI, 2.1-10.0; P < .0001; log-rank P < .0001).

CONCLUSIONS

Machine learning can reliably identify clinical and echocardiographic features associated with CRT response and prognosis. The evaluation of both right ventricular size and functional parameters has pivotal importance for the risk stratification of CRT candidates and should be systematically performed in patients undergoing CRT.

Clinical and prognostic implications of phenomapping in patients with heart failure receiving cardiac resynchronization therapy

BACKGROUND

Despite having an indication for cardiac resynchronization therapy according to current guidelines, patients with heart failure with reduced ejection fraction who receive cardiac resynchronization therapy do not consistently derive benefit from it.

AIM

To determine whether unsupervised clustering analysis (phenomapping) can identify distinct phenogroups of patients with differential outcomes among cardiac resynchronization therapy recipients from routine clinical practice.

METHODS

We used unsupervised hierarchical cluster analysis of phenotypic data after data reduction (55 clinical, biological and echocardiographic variables) to define new phenogroups among 328 patients with heart failure with reduced ejection fraction from routine clinical practice enrolled before cardiac resynchronization therapy. Clinical outcomes and cardiac resynchronization therapy response rate were studied according to phenogroups.

RESULTS

Although all patients met the recommended criteria for cardiac resynchronization therapy implantation, phenomapping analysis classified study participants into four phenogroups that differed distinctively in clinical, biological, electrocardiographic and echocardiographic characteristics and outcomes. Patients from phenogroups 1 and 2 had the most improved outcome in terms of mortality, associated with cardiac resynchronization therapy response rates of 81% and 78%, respectively. In contrast, patients from phenogroups 3 and 4 had cardiac resynchronization therapy response rates of 39% and 59%, respectively, and the worst outcome, with a considerably increased risk of mortality compared with patients from phenogroup 1 (hazard ratio 3.23, 95% confidence interval 1.9-5.5 and hazard ratio 2.49, 95% confidence interval 1.38-4.50, respectively).

CONCLUSIONS

Among patients with heart failure with reduced ejection fraction with an indication for cardiac resynchronization therapy from routine clinical practice, phenomapping identifies subgroups of patients with differential clinical, biological and echocardiographic features strongly linked to divergent outcomes and responses to cardiac resynchronization therapy. This approach may help to identify patients who will derive most benefit from cardiac resynchronization therapy in "individualized" clinical practice.

Estimating pulse wave velocity from the radial pressure wave using machine learning algorithms

One of the European gold standard measurement of vascular ageing, a risk factor for cardiovascular disease, is the carotid-femoral pulse wave velocity (cfPWV), which requires an experienced operator to measure pulse waves at two sites. In this work, two machine learning pipelines were proposed to estimate cfPWV from the peripheral pulse wave measured at a single site, the radial pressure wave measured by applanation tonometry. The study populations were the Twins UK cohort containing 3,082 subjects aged from 18 to 110 years, and a database containing 4,374 virtual subjects aged from 25 to 75 years. The first pipeline uses Gaussian process regression to estimate cfPWV from features extracted from the radial pressure wave using pulse wave analysis. The mean difference and upper and lower limits of agreement (LOA) of the estimation on the 924 hold-out test subjects from the Twins UK cohort were 0.2 m/s, and 3.75 m/s & -3.34 m/s, respectively. The second pipeline uses a recurrent neural network (RNN) to estimate cfPWV from the entire radial pressure wave. The mean difference and upper and lower LOA of the estimation on the 924 hold-out test subjects from the Twins UK cohort were 0.05 m/s, and 3.21 m/s & -3.11m/s, respectively. The percentage error of the RNN estimates on the virtual subjects increased by less than 2% when adding 20% of random noise to the pressure waveform. These results show the possibility of assessing the vascular ageing using a single peripheral pulse wave (e.g. the radial pressure wave), instead of cfPWV. The proposed code for the machine learning pipelines is available from the following online depository (https://github.com/WeiweiJin/Estimate-Cardiovascular-Risk-from-Pulse-Wave-Signal).

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.

Clinical applications of machine learning in the diagnosis, classification, and prediction of heart failure

Machine learning and artificial intelligence are generating significant attention in the scientific community and media. Such algorithms have great potential in medicine for personalizing and improving patient care, including in the diagnosis and management of heart failure. Many physicians are familiar with these terms and the excitement surrounding them, but many are unfamiliar with the basics of these algorithms and how they are applied to medicine. Within heart failure research, current applications of machine learning include creating new approaches to diagnosis, classifying patients into novel phenotypic groups, and improving prediction capabilities. In this paper, we provide an overview of machine learning targeted for the practicing clinician and evaluate current applications of machine learning in the diagnosis, classification, and prediction of heart failure.

Deep phenotype unsupervised machine learning revealed the significance of pachychoroid features in etiology and visual prognosis of age-related macular degeneration

Unsupervised machine learning has received increased attention in clinical research because it allows researchers to identify novel and objective viewpoints for diseases with complex clinical characteristics. In this study, we applied a deep phenotyping method to classify Japanese patients with age-related macular degeneration (AMD), the leading cause of blindness in developed countries, showing high phenotypic heterogeneity. By applying unsupervised deep phenotype clustering, patients with AMD were classified into two groups. One of the groups had typical AMD features, whereas the other one showed the pachychoroid-related features that were recently identified as a potentially important factor in AMD pathogenesis. Based on these results, a scoring system for classification was established; a higher score was significantly associated with a rapid improvement in visual acuity after specific treatment. This needs to be validated in other datasets in the future. In conclusion, the current study demonstrates the usefulness of unsupervised classification and provides important knowledge for future AMD studies.

Machine Learning in Electrocardiography and Echocardiography: Technological Advances in Clinical Cardiology

PURPOSE OF REVIEW

Electrocardiography (ECG) and echocardiography are the most widely used diagnostic tools in clinical cardiology. This review focuses on recent advancements in applying machine learning (ML) in ECG and echocardiography and potential synergistic ML integration of ECG and echocardiography.

RECENT FINDINGS

ML algorithms have been used in ECG for technical quality assurance, arrhythmia identification, and prognostic predictions, and in echocardiography to recognize image views, quantify measurements, and identify pathologic patterns. Synergistic application of ML in ECG and echocardiograph has demonstrated the potential to optimize therapeutic response, improve risk stratification, and generate new disease classification. There is mounting evidence that ML potentially outperforms in disease diagnoses and outcome prediction with ECG and echocardiography when compared with trained healthcare professionals. The applications of ML in ECG and echocardiography are playing increasingly greater roles in medical research and clinical practice, particularly for their contributions to developing novel diagnostic/prognostic prediction models. The automation in data acquisition, processing, and interpretation help streamline the workflows of ECG and echocardiography in contemporary cardiology practice.

Big Data Approaches in Heart Failure Research

PURPOSE OF REVIEW

The goal of this review is to summarize the state of big data analyses in the study of heart failure (HF). We discuss the use of big data in the HF space, focusing on "omics" and clinical data. We address some limitations of this data, as well as their future potential.

RECENT FINDINGS

Omics are providing insight into plasmal and myocardial molecular profiles in HF patients. The introduction of single cell and spatial technologies is a major advance that will reshape our understanding of cell heterogeneity and function as well as tissue architecture. Clinical data analysis focuses on HF phenotyping and prognostic modeling. Big data approaches are increasingly common in HF research. The use of methods designed for big data, such as machine learning, may help elucidate the biology underlying HF. However, important challenges remain in the translation of this knowledge into improvements in clinical care.

Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction

Advances in deep learning (DL) have resulted in impressive accuracy in some medical image classification tasks, but often deep models lack interpretability. The ability of these models to explain their decisions is important for fostering clinical trust and facilitating clinical translation. Furthermore, for many problems in medicine there is a wealth of existing clinical knowledge to draw upon, which may be useful in generating explanations, but it is not obvious how this knowledge can be encoded into DL models - most models are learnt either from scratch or using transfer learning from a different domain. In this paper we address both of these issues. We propose a novel DL framework for image-based classification based on a variational autoencoder (VAE). The framework allows prediction of the output of interest from the latent space of the autoencoder, as well as visualisation (in the image domain) of the effects of crossing the decision boundary, thus enhancing the interpretability of the classifier. Our key contribution is that the VAE disentangles the latent space based on 'explanations' drawn from existing clinical knowledge. The framework can predict outputs as well as explanations for these outputs, and also raises the possibility of discovering new biomarkers that are separate (or disentangled) from the existing knowledge. We demonstrate our framework on the problem of predicting response of patients with cardiomyopathy to cardiac resynchronization therapy (CRT) from cine cardiac magnetic resonance images. The sensitivity and specificity of the proposed model on the task of CRT response prediction are 88.43% and 84.39% respectively, and we showcase the potential of our model in enhancing understanding of the factors contributing to CRT response.

Integration of artificial intelligence into clinical patient management: focus on cardiac imaging

Cardiac imaging is a crucial component in the management of patients with heart disease, and as such it influences multiple, inter-related parts of the clinical workflow: physician-patient contact, image acquisition, image pre- and postprocessing, study reporting, diagnostics and outcome predictions, medical interventions, and, finally, knowledge-building through clinical research. With the gradual and ubiquitous infiltration of artificial intelligence into cardiology, it has become clear that, when used appropriately, it will influence and potentially improve-through automation, standardization and data integration-all components of the clinical workflow. This review aims to present a comprehensive view of full integration of artificial intelligence into the standard clinical patient management-with a focus on cardiac imaging, but applicable to all information handling-and to discuss current barriers that remain to be overcome before its widespread implementation and integration.

Applications of Machine Learning in Cardiac Electrophysiology

Artificial intelligence through machine learning (ML) methods is becoming prevalent throughout the world, with increasing adoption in healthcare. Improvements in technology have allowed early applications of machine learning to assist physician efficiency and diagnostic accuracy. In electrophysiology, ML has applications for use in every stage of patient care. However, its use is still in infancy. This article will introduce the potential of ML, before discussing the concept of big data and its pitfalls. The authors review some common ML methods including supervised and unsupervised learning, then examine applications in cardiac electrophysiology. This will focus on surface electrocardiography, intracardiac mapping and cardiac implantable electronic devices. Finally, the article concludes with an overview of how ML may impact on electrophysiology in the future.

Artificial Intelligence and Machine Learning in Arrhythmias and Cardiac Electrophysiology

Artificial intelligence (AI) and machine learning (ML) in medicine are currently areas of intense exploration, showing potential to automate human tasks and even perform tasks beyond human capabilities. Literacy and understanding of AI/ML methods are becoming increasingly important to researchers and clinicians. The first objective of this review is to provide the novice reader with literacy of AI/ML methods and provide a foundation for how one might conduct an ML study. We provide a technical overview of some of the most commonly used terms, techniques, and challenges in AI/ML studies, with reference to recent studies in cardiac electrophysiology to illustrate key points. The second objective of this review is to use examples from recent literature to discuss how AI and ML are changing clinical practice and research in cardiac electrophysiology, with emphasis on disease detection and diagnosis, prediction of patient outcomes, and novel characterization of disease. The final objective is to highlight important considerations and challenges for appropriate validation, adoption, and deployment of AI technologies into clinical practice.

Patient-specific heart simulation can identify non-responders to cardiac resynchronization therapy

To identify non-responders to cardiac resynchronization therapy (CRT), various biomarkers have been proposed, but these attempts have not been successful to date. We tested the clinical applicability of computer simulation of CRT for the identification of non-responders. We used the multi-scale heart simulator “UT-Heart,” which can reproduce the electrophysiology and mechanics of the heart based on a molecular model of the excitation–contraction mechanism. Patient-specific heart models were created for eight heart failure patients who were treated with CRT, based on the clinical data recorded before treatment. Using these heart models, bi-ventricular pacing simulations were performed at multiple pacing sites adopted in clinical practice. Improvement in pumping function measured by the relative change of maximum positive derivative of left ventricular pressure (%ΔdP/dt_max) was compared with the clinical outcome. The operators of the simulation were blinded to the clinical outcome. In six patients, the relative reduction in end-systolic volume exceeded 15% in the follow-up echocardiogram at 3 months (responders) and the remaining two patients were judged as non-responders. The simulated %ΔdP/dt_max at the best lead position could identify responders and non-responders successfully. With further refinement of the model, patient-specific simulation could be a useful tool for identifying non-responders to CRT.

Machine Learning of 12-Lead QRS Waveforms to Identify Cardiac Resynchronization Therapy Patients With Differential Outcomes

BACKGROUND

Cardiac resynchronization therapy (CRT) improves heart failure outcomes but has significant nonresponse rates, highlighting limitations in ECG selection criteria: QRS duration (QRSd) ≥150 ms and subjective labeling of left bundle branch block (LBBB). We explored unsupervised machine learning of ECG waveforms to identify CRT subgroups that may differentiate outcomes beyond QRSd and LBBB.

METHODS

We retrospectively analyzed 946 CRT patients with conduction delay. Principal component analysis (PCA) dimensionality reduction obtained a 2-dimensional representation of preCRT 12-lead QRS waveforms. k-means clustering of the 2-dimensional PCA representation of 12-lead QRS waveforms identified 2 patient subgroups (QRS PCA groups). Vectorcardiographic QRS area was also calculated. We examined following 2 primary outcomes: (1) composite end point of death, left ventricular assist device, or heart transplant, and (2) degree of echocardiographic left ventricular ejection fraction (LVEF) change after CRT.

RESULTS

Compared with QRS PCA Group 2 (n=425), Group 1 (n=521) had lower risk for reaching the composite end point (HR, 0.44 [95% CI, 0.38-0.53]; P<0.001) and experienced greater mean LVEF improvement (11.1±11.7% versus 4.8±9.7%; P<0.001), even among patients with LBBB with QRSd ≥150 ms (HR, 0.42 [95% CI, 0.30-0.57]; P<0.001; mean LVEF change 12.5±11.8% versus 7.3±8.1%; P=0.001). QRS area also stratified outcomes but had significant differences from QRS PCA groups. A stratification scheme combining QRS area and QRS PCA group identified patients with LBBB with similar outcomes to non-LBBB patients (HR, 1.32 [95% CI, 0.93-1.62]; difference in mean LVEF change: 0.8% [95% CI, -2.1% to 3.7%]). The stratification scheme also identified patients with LBBB with QRSd <150 ms with comparable outcomes to patients with LBBB with QRSd ≥150 ms (HR, 0.93 [95% CI, 0.67-1.29]; difference in mean LVEF change: -0.2% [95% CI, -2.7% to 3.0%]).

CONCLUSIONS

Unsupervised machine learning of ECG waveforms identified CRT subgroups with relevance beyond LBBB and QRSd. This method may assist in objective classification of bundle branch block morphology in CRT.

Artificial Intelligence (AI) and Cardiovascular Diseases: An Unexpected Alliance

Cardiovascular disease (CVD), despite the significant advances in the diagnosis and treatments, still represents the leading cause of morbidity and mortality worldwide. In order to improve and optimize CVD outcomes, artificial intelligence techniques have the potential to radically change the way we practice cardiology, especially in imaging, offering us novel tools to interpret data and make clinical decisions. AI techniques such as machine learning and deep learning can also improve medical knowledge due to the increase of the volume and complexity of the data, unlocking clinically relevant information. Likewise, the use of emerging communication and information technologies is becoming pivotal to create a pervasive healthcare service through which elderly and chronic disease patients can receive medical care at their home, reducing hospitalizations and improving quality of life. The aim of this review is to describe the contemporary state of artificial intelligence and digital health applied to cardiovascular medicine as well as to provide physicians with their potential not only in cardiac imaging but most of all in clinical practice.

Comprehensive data integration-Toward a more personalized assessment of diastolic function

BACKGROUND AND AIM

The main challenge of assessing diastolic function is the balance between clinical utility, in the sense of usability and time-efficiency, and overall applicability, in the sense of precision for the patient under investigation. In this review, we aim to explore the challenges of integrating data in the assessment of diastolic function and discuss the perspectives of a more comprehensive data integration approach.

METHODS

Review of traditional and novel approaches regarding data integration in the assessment of diastolic function.

RESULTS

Comprehensive data integration can lead to improved understanding of disease phenotypes and better relation of these phenotypes to underlying pathophysiological processes-which may help affirm diagnostic reasoning, guide treatment options, and reduce limitations related to previously unaddressed confounders. The optimal assessment of diastolic function should ideally integrate all relevant clinical information with all available structural and functional whole cardiac cycle echocardiographic data-envisioning a personalized approach to patient care, a high-reaching future goal in medicine.

CONCLUSION

Complete data integration seems to be a long-lasting goal, the way forward in diastology, and machine learning seems to be one of the tools suited for the challenge. With perpetual evidence that traditional approaches to complex problems may not the optimal solution, there is room for a steady and cautious, and inherently very exciting paradigm shift toward novel diagnostic tools and workflows to reach a more personalized, comprehensive, and integrated assessment of cardiac function.

Collaborative AI and Laboratory Medicine integration in precision cardiovascular medicine

Artificial Intelligence (AI) is a broad term that combines computation with sophisticated mathematical models and in turn allows the development of complex algorithms which are capable to simulate human intelligence such as problem solving and learning. It is devised to promote a significant paradigm shift in the most diverse areas of medical knowledge. On the other hand, Cardiology is a vast field dealing with diseases relating to the heart, the circulatory system, and includes coronary heart disease, cerebrovascular disease, rheumatic heart disease and other conditions. AI has emerged as a promising tool in cardiovascular medicine which is aimed in augmenting the effectiveness of the cardiologist and to extend better quality to patients. It has the ability to support decision‑making and improve diagnostic and prognostic performance. Attempt has also been made to explore novel genotypes and phenotypes in existing cardiovascular diseases, improve the quality of patient care, to enablecost-effectiveness with reducereadmissionand mortality rates. Our review addresses the integration of AI and laboratory medicine as an accelerator of personalization care associated with the precision and the need of value creation services in cardiovascular medicine.

Machine learning-based mortality prediction of patients undergoing cardiac resynchronization therapy: the SEMMELWEIS-CRT score

AIMS

Our aim was to develop a machine learning (ML)-based risk stratification system to predict 1-, 2-, 3-, 4-, and 5-year all-cause mortality from pre-implant parameters of patients undergoing cardiac resynchronization therapy (CRT).

METHODS AND RESULTS

Multiple ML models were trained on a retrospective database of 1510 patients undergoing CRT implantation to predict 1- to 5-year all-cause mortality. Thirty-three pre-implant clinical features were selected to train the models. The best performing model [SEMMELWEIS-CRT score (perSonalizEd assessMent of estiMatEd risk of mortaLity With machinE learnIng in patientS undergoing CRT implantation)], along with pre-existing scores (Seattle Heart Failure Model, VALID-CRT, EAARN, ScREEN, and CRT-score), was tested on an independent cohort of 158 patients. There were 805 (53%) deaths in the training cohort and 80 (51%) deaths in the test cohort during the 5-year follow-up period. Among the trained classifiers, random forest demonstrated the best performance. For the prediction of 1-, 2-, 3-, 4-, and 5-year mortality, the areas under the receiver operating characteristic curves of the SEMMELWEIS-CRT score were 0.768 (95% CI: 0.674-0.861; P < 0.001), 0.793 (95% CI: 0.718-0.867; P < 0.001), 0.785 (95% CI: 0.711-0.859; P < 0.001), 0.776 (95% CI: 0.703-0.849; P < 0.001), and 0.803 (95% CI: 0.733-0.872; P < 0.001), respectively. The discriminative ability of our model was superior to other evaluated scores.

CONCLUSION

The SEMMELWEIS-CRT score (available at semmelweiscrtscore.com) exhibited good discriminative capabilities for the prediction of all-cause death in CRT patients and outperformed the already existing risk scores. By capturing the non-linear association of predictors, the utilization of ML approaches may facilitate optimal candidate selection and prognostication of patients undergoing CRT implantation.

Artificial Intelligence in Cardiology: Present and Future

Artificial intelligence (AI) is a nontechnical, popular term that refers to machine learning of various types but most often to deep neural networks. Cardiology is at the forefront of AI in medicine. For this review, we searched PubMed and MEDLINE databases with no date restriction using search terms related to AI and cardiology. Articles were selected for inclusion on the basis of relevance. We highlight the major achievements in recent years in nearly all areas of cardiology and underscore the mounting evidence suggesting how AI will take center stage in the field. Artificial intelligence requires a close collaboration among computer scientists, clinical investigators, clinicians, and other users in order to identify the most relevant problems to be solved. Best practices in the generation and implementation of AI include the selection of ideal data sources, taking into account common challenges during the interpretation, validation, and generalizability of findings, and addressing safety and ethical concerns before final implementation. The future of AI in cardiology and in medicine in general is bright as the collaboration between investigators and clinicians continues to excel.

Image-Based Cardiac Diagnosis With Machine Learning: A Review

Cardiac imaging plays an important role in the diagnosis of cardiovascular disease (CVD). Until now, its role has been limited to visual and quantitative assessment of cardiac structure and function. However, with the advent of big data and machine learning, new opportunities are emerging to build artificial intelligence tools that will directly assist the clinician in the diagnosis of CVDs. This paper presents a thorough review of recent works in this field and provide the reader with a detailed presentation of the machine learning methods that can be further exploited to enable more automated, precise and early diagnosis of most CVDs.

Artificial Intelligence for Cardiac Imaging-Genetics Research

Cardiovascular conditions remain the leading cause of mortality and morbidity worldwide, with genotype being a significant influence on disease risk. Cardiac imaging-genetics aims to identify and characterize the genetic variants that influence functional, physiological, and anatomical phenotypes derived from cardiovascular imaging. High-throughput DNA sequencing and genotyping have greatly accelerated genetic discovery, making variant interpretation one of the key challenges in contemporary clinical genetics. Heterogeneous, low-fidelity phenotyping and difficulties integrating and then analyzing large-scale genetic, imaging and clinical datasets using traditional statistical approaches have impeded process. Artificial intelligence (AI) methods, such as deep learning, are particularly suited to tackle the challenges of scalability and high dimensionality of data and show promise in the field of cardiac imaging-genetics. Here we review the current state of AI as applied to imaging-genetics research and discuss outstanding methodological challenges, as the field moves from pilot studies to mainstream applications, from one dimensional global descriptors to high-resolution models of whole-organ shape and function, from univariate to multivariate analysis and from candidate gene to genome-wide approaches. Finally, we consider the future directions and prospects of AI imaging-genetics for ultimately helping understand the genetic and environmental underpinnings of cardiovascular health and disease.

Association of Machine Learning-Derived Phenogroupings of Echocardiographic Variables with Heart Failure in Stable Coronary Artery Disease: The Heart and Soul Study

BACKGROUND

Many individual echocardiographic variables have been associated with heart failure (HF) in patients with stable coronary artery disease (CAD), but their combined utility for prediction has not been well studied.

METHODS

Unsupervised model-based cluster analysis was performed by researchers blinded to the study outcome in 1,000 patients with stable CAD on 15 transthoracic echocardiographic variables. We evaluated associations of cluster membership with HF hospitalization using Cox proportional hazards regression analysis.

RESULTS

The echo-derived clusters partitioned subjects into four phenogroupings: phenogroup 1 (n = 85) had the highest levels, phenogroups 2 (n = 314) and 3 (n = 205) displayed intermediate levels, and phenogroup 4 (n = 396) had the lowest levels of cardiopulmonary structural and functional abnormalities. Over 7.1 ± 3.2 years of follow-up, there were 198 HF hospitalizations. After multivariable adjustment for traditional cardiovascular risk factors, phenogroup 1 was associated with a nearly fivefold increased risk (hazard ratio [HR] = 4.8; 95% CI, 2.4-9.5), phenogroup 2 was associated with a nearly threefold increased risk (HR = 2.7; 95% CI, 1.4-5.0), and phenogroup 3 was associated with a nearly twofold increased risk (HR = 1.9; 95% CI, 1.0-3.8) of HF hospitalization, relative to phenogroup 4.

CONCLUSIONS

Transthoracic echocardiographic variables can be used to classify stable CAD patients into separate phenogroupings that differentiate cardiopulmonary structural and functional abnormalities and can predict HF hospitalization, independent of traditional cardiovascular risk factors.

Machine Learning Approaches for Myocardial Motion and Deformation Analysis

Information about myocardial motion and deformation is key to differentiate normal and abnormal conditions. With the advent of approaches relying on data rather than pre-conceived models, machine learning could either improve the robustness of motion quantification or reveal patterns of motion and deformation (rather than single parameters) that differentiate pathologies. We review machine learning strategies for extracting motion-related descriptors and analyzing such features among populations, keeping in mind constraints specific to the cardiac application.

Machine Learning in Fetal Cardiology: What to Expect

In fetal cardiology, imaging (especially echocardiography) has demonstrated to help in the diagnosis and monitoring of fetuses with a compromised cardiovascular system potentially associated with several fetal conditions. Different ultrasound approaches are currently used to evaluate fetal cardiac structure and function, including conventional 2-D imaging and M-mode and tissue Doppler imaging among others. However, assessment of the fetal heart is still challenging mainly due to involuntary movements of the fetus, the small size of the heart, and the lack of expertise in fetal echocardiography of some sonographers. Therefore, the use of new technologies to improve the primary acquired images, to help extract measurements, or to aid in the diagnosis of cardiac abnormalities is of great importance for optimal assessment of the fetal heart. Machine leaning (ML) is a computer science discipline focused on teaching a computer to perform tasks with specific goals without explicitly programming the rules on how to perform this task. In this review we provide a brief overview on the potential of ML techniques to improve the evaluation of fetal cardiac function by optimizing image acquisition and quantification/segmentation, as well as aid in improving the prenatal diagnoses of fetal cardiac remodeling and abnormalities.

A primer in artificial intelligence in cardiovascular medicine

Driven by recent developments in computational power, algorithms and web-based storage resources, machine learning (ML)-based artificial intelligence (AI) has quickly gained ground as the solution for many technological and societal challenges. AI education has become very popular and is oversubscribed at Dutch universities. Major investments were made in 2018 to develop and build the first AI-driven hospitals to improve patient care and reduce healthcare costs. AI has the potential to greatly enhance traditional statistical analyses in many domains and has been demonstrated to allow the discovery of 'hidden' information in highly complex datasets. As such, AI can also be of significant value in the diagnosis and treatment of cardiovascular disease, and the first applications of AI in the cardiovascular field are promising. However, many professionals in the cardiovascular field involved in patient care, education or science are unaware of the basics behind AI and the existing and expected applications in their field. In this review, we aim to introduce the broad cardiovascular community to the basics of modern ML-based AI and explain several of the commonly used algorithms. We also summarise their initial and future applications relevant to the cardiovascular field.

Artificial intelligence in cardiovascular imaging: state of the art and implications for the imaging cardiologist

Healthcare, conceivably more than any other area of human endeavour, has the greatest potential to be affected by artificial intelligence (AI). This potential has been shown by several reports that demonstrate equal or superhuman performance in medical tasks that aim to improve efficiency, diagnosis and prognosis. This review focuses on the state of the art of AI applications in cardiovascular imaging. It provides an overview of the current applications and studies performed, including the potential value, implications, limitations and future directions of AI in cardiovascular imaging.It is envisioned that AI will dramatically change the way doctors practise medicine. In the short term, it will assist physicians with easy tasks, such as automating measurements, making predictions based on big data, and putting clinical findings into an evidence-based context. In the long term, AI will not only assist doctors, it has the potential to significantly improve access to health and well-being data for patients and their caretakers. This empowers patients. From a physician's perspective, reliable AI assistance will be available to support clinical decision-making. Although cardiovascular studies implementing AI are increasing in number, the applications have only just started to penetrate contemporary clinical care.

Machine Learning Prediction of Response to Cardiac Resynchronization Therapy: Improvement Versus Current Guidelines

BACKGROUND

Cardiac resynchronization therapy (CRT) has significant nonresponse rates. We assessed whether machine learning (ML) could predict CRT response beyond current guidelines.

METHODS

We analyzed CRT patients from Cleveland Clinic and Johns Hopkins. A training cohort was created from all Johns Hopkins patients and an equal number of randomly sampled Cleveland Clinic patients. All remaining patients comprised the testing cohort. Response was defined as ≥10% increase in left ventricular ejection fraction. ML models were developed to predict CRT response using different combinations of classification algorithms and clinical variable sets on the training cohort. The model with the highest area under the curve was evaluated on the testing cohort. Probability of response was used to predict survival free from a composite end point of death, heart transplant, or placement of left ventricular assist device. Predictions were compared with current guidelines.

RESULTS

Nine hundred twenty-five patients were included. On the training cohort (n=470: 235, Johns Hopkins; 235, Cleveland Clinic), the best ML model was a naive Bayes classifier including 9 variables (QRS morphology, QRS duration, New York Heart Association classification, left ventricular ejection fraction and end-diastolic diameter, sex, ischemic cardiomyopathy, atrial fibrillation, and epicardial left ventricular lead). On the testing cohort (n=455, Cleveland Clinic), ML demonstrated better response prediction than guidelines (area under the curve, 0.70 versus 0.65; P=0.012) and greater discrimination of event-free survival (concordance index, 0.61 versus 0.56; P<0.001). The fourth quartile of the ML model had the greatest risk of reaching the composite end point, whereas the first quartile had the least (hazard ratio, 0.34; P<0.001).

CONCLUSIONS

ML with 9 variables incrementally improved prediction of echocardiographic CRT response and survival beyond guidelines. Performance was not improved by incorporating more variables. The model offers potential for improved shared decision-making in CRT (online calculator: http://riskcalc.org:3838/CRTResponseScore ). Significant remaining limitations confirm the need to identify better variables to predict CRT response.