Machine Learning Analysis of Left Ventricular Function to Characterize Heart Failure With Preserved Ejection Fraction

Underpinnings of Heart Failure With Preserved Ejection Fraction in Women - From Prevention to Improving Function. A Co-publication With the American Journal of Preventive Cardiology and the Journal of Cardiac Failure

Heart failure with preserved ejection fraction (HFpEF) represents a major clinical challenge with rising global prevalence. Women have a nearly double lifetime risk of developing HFpEF compared to heart failure with reduced ejection fraction (HFrEF). In HFpEF, sex differences emerge both in how traditional cardiovascular risk factors (such as hypertension, obesity, and diabetes) affect cardiac function and through distinct pathophysiological mechanisms triggered by sex-specific events like menopause and adverse pregnancy outcomes. These patterns influence not only disease development, but also therapeutic responses, necessitating sex-specific approaches to treatment. This review aims to synthesize existing knowledge regarding HFpEF in women including traditional and sex-specific risk factors, pathophysiology, presentation, and therapies, while outlining important knowledge gaps that warrant further investigation. The impact of HFpEF spans a woman's entire lifespan, requiring prevention and management strategies tailored to different life stages. While understanding of sex-based differences in HFpEF has improved, significant knowledge gaps persist. Through examination of current evidence and challenges, this review highlights promising opportunities for innovative research, therapeutic development, and clinical care approaches that could transform the management of HFpEF in women.

Utilizing echocardiography and unsupervised machine learning for heart failure risk identification

BACKGROUND

Global longitudinal strain (GLS) is recognized as a powerful predictor of heart failure (HF). However, the entire strain curve may entail important prognostic information regarding HF risk that might be undiscovered by only focusing on the peak strain value.

OBJECTIVE

The hypothesis of the present study was, that analysis of the entire strain curve using unsupervised machine learning (uML) would reveal novel ventricular deformation patterns capable of predicting incident HF independently of GLS.

METHODS

Longitudinal strain curves from 3710 subjects from the general population without prevalent HF were analyzed using uML.

RESULTS

Mean age was 56 years and 43 % were male. During a median follow-up of 5.3 years, 92 subjects (2.5 %) developed HF. The uML algorithm generated a hierarchical clustering tree (HCT) resulting in 10 different clusters. Generally, the strain curves displayed reduced early diastolic strain to peak-strain ratio with an increasing incidence rate of HF. In multivariable Cox regressions, cluster 9 was significantly associated with increased risk of HF when compared to cluster 2-5, and 7-8 [For cluster 3: HR 8.95, 95 %CI: 2.08;38.48, P = 0.003] even though the subjects of cluster 9 were younger, displayed healthier clinical baseline characteristics, and only had slightly reduced GLS. The mean strain curve of cluster 9 displayed an early systolic lengthening followed by a late and reduced contraction specifically related to the basal lateral segment.

CONCLUSION

The unsupervised machine learning algorithm identified unknown strain patterns beyond GLS presumably related to increased risk of HF.

Exercise Stress Echocardiography-Based Phenotyping of Heart Failure With Preserved Ejection Fraction

BACKGROUND

Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous syndrome requiring improved phenotypic classification. Previous studies have identified subphenotypes of HFpEF, but the lack of exercise assessment is a major limitation. The aim of this study was to identify distinct pathophysiologic clusters of HFpEF based on clinical characteristics, and resting and exercise assessments.

METHODS

A total of 265 patients with HFpEF underwent ergometry exercise stress echocardiography with simultaneous expired gas analysis. Cluster analysis was performed by the K-prototype method with 21 variables (10 clinical and resting echocardiographic variables and 11 exercise echocardiographic parameters). Pathophysiologic features, exercise tolerance, and prognosis were compared among phenogroups.

RESULTS

Three distinct phenogroups were identified. Phenogroup 1 (n = 112 [42%]) was characterized by preserved biventricular systolic reserve and cardiac output augmentation. Phenogroup 2 (n = 58 [22%]) was characterized by a high prevalence of atrial fibrillation, increased pulmonary arterial and right atrial pressures, depressed right ventricular systolic functional reserve, and impaired right ventricular-pulmonary artery coupling during exercise. Phenogroup 3 (n = 95 [36%]) was characterized by the smallest body mass index, ventricular and vascular stiffening, impaired left ventricular diastolic reserve, and worse exercise capacity. Phenogroups 2 and 3 had higher rates of composite outcomes of all-cause mortality or heart failure events than phenogroup 1 (log-rank P = .02).

CONCLUSION

Exercise echocardiography-based cluster analysis identified three distinct phenogroups of HFpEF, with unique exercise pathophysiologic features, exercise capacity, and clinical outcomes.

Contrast-Enhanced Magnetic Resonance Imaging Based T1 Mapping and Extracellular Volume Fractions Are Associated with Peripheral Artery Disease

BACKGROUND

Extracellular volume fraction (ECV), measured with contrast-enhanced magnetic resonance imaging (CE-MRI), has been utilized to study myocardial fibrosis, but its role in peripheral artery disease (PAD) remains unknown. We hypothesized that T1 mapping and ECV differ between PAD patients and matched controls.

METHODS AND RESULTS

A total of 37 individuals (18 PAD patients and 19 matched controls) underwent 3.0T CE-MRI. Skeletal calf muscle T1 mapping was performed before and after gadolinium contrast with a motion-corrected modified look-locker inversion recovery (MOLLI) pulse sequence. T1 values were calculated with a three-parameter Levenberg-Marquardt curve fitting algorithm. ECV and T1 maps were quantified in five calf muscle compartments (anterior [AM], lateral [LM], and deep posterior [DM] muscle groups; soleus [SM] and gastrocnemius [GM] muscles). Averaged peak blood pool T1 values were obtained from the posterior and anterior tibialis and peroneal arteries. T1 values and ECV are heterogeneous across calf muscle compartments. Native peak T1 values of the AM, LM, and DM were significantly higher in PAD patients compared to controls (all p < 0.028). ECVs of the AM and SM were significantly higher in PAD patients compared to controls (AM: 26.4% (21.2, 31.6) vs. 17.3% (10.2, 25.1), p = 0.046; SM: 22.7% (19.5, 27.8) vs. 13.8% (10.2, 19.1), p = 0.020).

CONCLUSIONS

Native peak T1 values across all five calf muscle compartments, and ECV fractions of the anterior muscle group and the soleus muscle were significantly elevated in PAD patients compared with matched controls. Non-invasive T1 mapping and ECV quantification may be of interest for the study of PAD.

Artificial Intelligence and Its Role in Diagnosing Heart Failure: A Narrative Review

Heart failure (HF) is prevalent globally. It is a dynamic disease with varying definitions and classifications due to multiple pathophysiologies and etiologies. The diagnosis, clinical staging, and treatment of HF become complex and subjective, impacting patient prognosis and mortality. Technological advancements, like artificial intelligence (AI), have been significant roleplays in medicine and are increasingly used in cardiovascular medicine to transform drug discovery, clinical care, risk prediction, diagnosis, and treatment. Medical and surgical interventions specific to HF patients rely significantly on early identification of HF. Hospitalization and treatment costs for HF are high, with readmissions increasing the burden. AI can help improve diagnostic accuracy by recognizing patterns and using them in multiple areas of HF management. AI has shown promise in offering early detection and precise diagnoses with the help of ECG analysis, advanced cardiac imaging, leveraging biomarkers, and cardiopulmonary stress testing. However, its challenges include data access, model interpretability, ethical concerns, and generalizability across diverse populations. Despite these ongoing efforts to refine AI models, it suggests a promising future for HF diagnosis. After applying exclusion and inclusion criteria, we searched for data available on PubMed, Google Scholar, and the Cochrane Library and found 150 relevant papers. This review focuses on AI's significant contribution to HF diagnosis in recent years, drastically altering HF treatment and outcomes.

Artificial Intelligence in Cardiology and Atherosclerosis in the Context of Precision Medicine: A Scoping Review

Cardiovascular diseases remain the main cause of death worldwide which makes it essential to better understand, diagnose, and treat atherosclerosis. Artificial intelligence (AI) and novel technological solutions offer us new possibilities and enable the practice of individually tailored medicine. The study was performed using the PRISMA protocol. As of January 10, 2023, the analysis has been based on a review of 457 identified articles in PubMed and MEDLINE databases. The search covered reviews, original articles, meta-analyses, comments, and editorials published in the years 2009-2023. In total, 123 articles met inclusion criteria. The results were divided into the subsections presented in the review (genome-wide association studies, radiomics, and other studies). This paper presents actual knowledge concerning atherosclerosis, in silico, and big data analyses in cardiology that affect the way medicine is practiced in order to create an individual approach and adjust the therapy of atherosclerosis.

Value Creation Through Artificial Intelligence and Cardiovascular Imaging: A Scientific Statement From the American Heart Association

Multiple applications for machine learning and artificial intelligence (AI) in cardiovascular imaging are being proposed and developed. However, the processes involved in implementing AI in cardiovascular imaging are highly diverse, varying by imaging modality, patient subtype, features to be extracted and analyzed, and clinical application. This article establishes a framework that defines value from an organizational perspective, followed by value chain analysis to identify the activities in which AI might produce the greatest incremental value creation. The various perspectives that should be considered are highlighted, including clinicians, imagers, hospitals, patients, and payers. Integrating the perspectives of all health care stakeholders is critical for creating value and ensuring the successful deployment of AI tools in a real-world setting. Different AI tools are summarized, along with the unique aspects of AI applications to various cardiac imaging modalities, including cardiac computed tomography, magnetic resonance imaging, and positron emission tomography. AI is applicable and has the potential to add value to cardiovascular imaging at every step along the patient journey, from selecting the more appropriate test to optimizing image acquisition and analysis, interpreting the results for classification and diagnosis, and predicting the risk for major adverse cardiac events.

Feature-based clustering of the left ventricular strain curve for cardiovascular risk stratification in the general population

Objective

Identifying individuals with subclinical cardiovascular (CV) disease could improve monitoring and risk stratification. While peak left ventricular (LV) systolic strain has emerged as a strong prognostic factor, few studies have analyzed the whole temporal profiles of the deformation curves during the complete cardiac cycle. Therefore, in this longitudinal study, we applied an unsupervised machine learning approach based on time-series-derived features from the LV strain curve to identify distinct strain phenogroups that might be related to the risk of adverse cardiovascular events in the general population.

Method

We prospectively studied 1,185 community-dwelling individuals (mean age, 53.2 years; 51.3% women), in whom we acquired clinical and echocardiographic data including LV strain traces at baseline and collected adverse events on average 9.1 years later. A Gaussian Mixture Model (GMM) was applied to features derived from LV strain curves, including the slopes during systole, early and late diastole, peak strain, and the duration and height of diastasis. We evaluated the performance of the model using the clinical characteristics of the participants and the incidence of adverse events in the training dataset. To ascertain the validity of the trained model, we used an additional community-based cohort (n = 545) as external validation cohort.

Results

The most appropriate number of clusters to separate the LV strain curves was four. In clusters 1 and 2, we observed differences in age and heart rate distributions, but they had similarly low prevalence of CV risk factors. Cluster 4 had the worst combination of CV risk factors, and a higher prevalence of LV hypertrophy and diastolic dysfunction than in other clusters. In cluster 3, the reported values were in between those of strain clusters 2 and 4. Adjusting for traditional covariables, we observed that clusters 3 and 4 had a significantly higher risk for CV (28% and 20%, P ≤ 0.038) and cardiac (57% and 43%, P ≤ 0.024) adverse events. Using SHAP values we observed that the features that incorporate temporal information, such as the slope during systole and early diastole, had a higher impact on the model's decision than peak LV systolic strain.

Conclusion

Employing a GMM on features derived from the raw LV strain curves, we extracted clinically significant phenogroups which could provide additive prognostic information over the peak LV strain.

Unsupervised Time-Series Clustering of Left Atrial Strain for Cardiovascular Risk Assessment

BACKGROUND

Early identification of individuals at high risk for developing cardiovascular (CV) events is of paramount importance for efficient risk management. Here, the authors investigated whether using unsupervised machine learning methods on time-series data of left atrial (LA) strain could distinguish clinically meaningful phenogroups associated with the risk for developing adverse events.

METHODS

In 929 community-dwelling individuals (mean age, 51.6 years; 52.9% women), clinical and echocardiographic data were acquired, including LA strain traces, at baseline, and cardiac events were collected on average 6.3 years later. Two unsupervised learning techniques were used: (1) an ensemble of a deep convolutional neural network autoencoder with k-medoids and (2) a self-organizing map to cluster spatiotemporal patterns within LA strain curves. Clinical characteristics and cardiac outcome were used to evaluate the validity of the k clusters using the original cohort, while an external population cohort (n = 378) was used to validate the trained models.

RESULTS

In both approaches, the optimal number of clusters was five. The first three clusters had differences in sex distribution and heart rate but had a similar low CV risk profile. On the other hand, cluster 5 had the worst CV profile and a higher prevalence of left ventricular remodeling and diastolic dysfunction compared with the other clusters. The respective indexes of cluster 4 were between those of clusters 1 to 3 and 5. After adjustment for traditional risk factors, cluster 5 had the highest risk for cardiac events compared with clusters 1, 2, and 3 (hazard ratio, 1.36; 95% CI, 1.09-1.70; P = .0063). Similar LA strain patterns were obtained when the models were applied to the external validation cohort, and clinical characteristics revealed similar CV risk profiles across all clusters.

CONCLUSION

Unsupervised machine learning algorithms used in time-series LA strain curves identified clinically meaningful clusters of LA deformation and provide incremental prognostic information over traditional risk factors.

Machine Learning for Mortality Prediction in Patients With Heart Failure With Mildly Reduced Ejection Fraction

Background Machine-learning-based prediction models (MLBPMs) have shown satisfactory performance in predicting clinical outcomes in patients with heart failure with reduced and preserved ejection fraction. However, their usefulness has yet to be fully elucidated in patients with heart failure with mildly reduced ejection fraction. This pilot study aims to evaluate the prediction performance of MLBPMs in a heart failure with mildly reduced ejection fraction cohort with long-term follow-up data. Methods and Results A total of 424 patients with heart failure with mildly reduced ejection fraction were enrolled in our study. The primary outcome was all-cause mortality. Two feature selection strategies were introduced for MLBPM development. The "All-in" (67 features) strategy was based on feature correlation, multicollinearity, and clinical significance. The other strategy was the CoxBoost algorithm with 10-fold cross-validation (17 features), which was based on the selection result of the "All-in" strategy. Six MLBPMs with 5-fold cross-validation based on the "All-in" and the CoxBoost algorithm with 10-fold cross-validation strategy were developed by the eXtreme Gradient Boosting, random forest, and support vector machine algorithms. The logistic regression model with 14 benchmark predictors was used as a reference model. During a median follow-up of 1008 (750, 1937) days, 121 patients met the primary outcome. Overall, MLBPMs outperformed the logistic model. The "All-in" eXtreme Gradient Boosting model had the best performance, with an accuracy of 85.4% and a precision of 70.3%. The area under the receiver-operating characteristic curve was 0.916 (95% CI, 0.887-0.945). The Brier score was 0.12. Conclusions The MLBPMs could significantly improve outcome prediction in patients with heart failure with mildly reduced ejection fraction, which would further optimize the management of these patients.

HFrEF subphenotypes based on 4210 repeatedly measured circulating proteins are driven by different biological mechanisms

BACKGROUND

HFrEF is a heterogenous condition with high mortality. We used serial assessments of 4210 circulating proteins to identify distinct novel protein-based HFrEF subphenotypes and to investigate underlying dynamic biological mechanisms. Herewith we aimed to gain pathophysiological insights and fuel opportunities for personalised treatment.

METHODS

In 382 patients, we performed trimonthly blood sampling during a median follow-up of 2.1 [IQR:1.1-2.6] years. We selected all baseline samples and two samples closest to the primary endpoint (PEP; composite of cardiovascular mortality, HF hospitalization, LVAD implantation, and heart transplantation) or censoring, and applied an aptamer-based multiplex proteomic approach. Using unsupervised machine learning methods, we derived clusters from 4210 repeatedly measured proteomic biomarkers. Sets of proteins that drove cluster allocation were analysed via an enrichment analysis. Differences in clinical characteristics and PEP occurrence were evaluated.

FINDINGS

We identified four subphenotypes with different protein profiles, prognosis and clinical characteristics, including age (median [IQR] for subphenotypes 1-4, respectively:70 [64, 76], 68 [60, 79], 57 [47, 65], 59 [56, 66]years), EF (30 [26, 36], 26 [20, 38], 26 [22, 32], 33 [28, 37]%), and chronic renal failure (45%, 65%, 36%, 37%). Subphenotype allocation was driven by subsets of proteins associated with various biological functions, such as oxidative stress, inflammation and extracellular matrix organisation. Clinical characteristics of the subphenotypes were aligned with these associations. Subphenotypes 2 and 3 had the worst prognosis compared to subphenotype 1 (adjHR (95%CI):3.43 (1.76-6.69), and 2.88 (1.37-6.03), respectively).

INTERPRETATION

Four circulating-protein based subphenotypes are present in HFrEF, which are driven by varying combinations of protein subsets, and have different clinical characteristics and prognosis.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT01851538https://clinicaltrials.gov/ct2/show/NCT01851538.

FUNDING

EU/EFPIA IMI2JU BigData@Heart grant n°116074, Jaap Schouten Foundation and Noordwest Academie.

Exercise-induced B-lines for the diagnosis of heart failure with preserved ejection fraction: a two-centre study

BACKGROUND

Diagnosis of heart failure with preserved ejection fraction (HFpEF) remains challenging despite the use of scores/algorithms. This study intended to assess the diagnostic value of exercise lung ultrasound (LUS) for HFpEF diagnosis.

METHODS

We studied two independent case-control studies of HFpEF patients and control subjects undergoing different exercise protocols: (i) submaximal exercise stress echocardiography (ESE) with LUS performed by expert cardiologists (N = 116, HFpEF = 65.5%), and (ii) maximal cycle ergometer test (CET) (N = 54, HFpEF = 50%) with LUS performed by unexperienced physicians shortly trained for the study. B-line kinetics (i.e. peak values and their changes from rest) were assessed.

RESULTS

In the ESE cohort, the C-index (95% CI) of peak B-lines for HFpEF diagnosis was 0.985 (0.968-1.000), whereas the C-index of rest and exercise HFA-PEFF scores (i.e. including stress echo findings) were < 0.90 (CI 0.823-0.949), and that of H2FPEF score was < 0.70 (CI 0.558-0.764). The C-index increase of peak B-lines on top of the above-mentioned scores was significant (C-index increase > 0.090 and P-value < 0.001 for all). Similar results were observed for change B-lines. Peak B-lines > 5 (sensitivity = 93.4%, specificity = 97.5%) and change B-lines > 3 (sensitivity = 94.7%, specificity = 87.5%) were the best cutoffs for HFpEF diagnosis. Adding peak or change B-lines on top of HFpEF scores and BNP significantly improved diagnostic accuracy. Peak B-lines showed a good diagnostic accuracy in the LUS beginner-led CET cohort (C-index = 0.713, 0.588-0.838).

CONCLUSIONS

Exercise LUS showed excellent diagnostic value for HFpEF diagnosis regardless of different exercise protocols/level of expertise, with additive diagnostic accuracy on top of available scores and natriuretic peptides.

Personalized Management for Heart Failure with Preserved Ejection Fraction

Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous clinical syndrome with multiple underlying mechanisms and comorbidities that leads to a variety of clinical phenotypes. The identification and characterization of these phenotypes are essential for better understanding the precise pathophysiology of HFpEF, identifying appropriate treatment strategies, and improving patient outcomes. Despite accumulating data showing the potentiality of artificial intelligence (AI)-based phenotyping using clinical, biomarker, and imaging information from multiple dimensions in HFpEF management, contemporary guidelines and consensus do not incorporate these in daily practice. In the future, further studies are required to authenticate and substantiate these findings in order to establish a more standardized approach for clinical implementation.

Artificial Intelligence in Cardiology: Applications and Obstacles

Artificial intelligence (AI) technology is poised to alter the flow of daily life, and in particular, medicine, where it may eventually complement the physician's work in diagnosing and treating disease. Despite the recent frenzy and uptick in AI research over the past decade, the integration of AI into medical practice is in its early stages. Cardiology stands to benefit due to its many diagnostic modalities and diverse treatments. AI methods have been applied to various domains within cardiology: imaging, electrocardiography, wearable devices, risk prediction, and disease classification. While many AI-based approaches have been developed that perform equal to or better than the state-of-the-art, few prospective randomized studies have evaluated their use. Furthermore, obstacles at the intersection of medicine and AI remain unsolved, including model understanding, bias, model evaluation, relevance and reproducibility, and legal and ethical dilemmas. We summarize recent and current applications of AI in cardiology, followed by a discussion of the aforementioned complications.

Machine learning algorithms to automate differentiating cardiac amyloidosis from hypertrophic cardiomyopathy

Cardiac amyloidosis has a poor prognosis, and high mortality and is often misdiagnosed as hypertrophic cardiomyopathy, leading to delayed diagnosis. Machine learning combined with speckle tracking echocardiography was proposed to automate differentiating two conditions. A total of 74 patients with pathologically confirmed monoclonal immunoglobulin light chain cardiac amyloidosis and 64 patients with hypertrophic cardiomyopathy were enrolled from June 2015 to November 2018. Machine learning models utilizing traditional and advanced algorithms were established and determined the most significant predictors. The performance was evaluated by the receiver operating characteristic curve (ROC) and the area under the curve (AUC). With clinical and echocardiography data, all models showed great discriminative performance (AUC > 0.9). Compared with logistic regression (AUC 0.91), machine learning such as support vector machine (AUC 0.95, p = 0.477), random forest (AUC 0.97, p = 0.301) and gradient boosting machine (AUC 0.98, p = 0.230) demonstrated similar capability to distinguish cardiac amyloidosis and hypertrophic cardiomyopathy. With speckle tracking echocardiography, the predictive performance of the voting model was similar to that of LightGBM (AUC was 0.86 for both), while the AUC of XGBoost was slightly lower (AUC 0.84). In fivefold cross-validation, the voting model was more robust globally and superior to the single model in some test sets. Data-driven machine learning had shown admirable performance in differentiating two conditions and could automatically integrate abundant variables to identify the most discriminating predictors without making preassumptions. In the era of big data, automated machine learning will help to identify patients with cardiac amyloidosis and timely and effectively intervene, thus improving the outcome.

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

Application of AI in cardiovascular multimodality imaging

Technical advances in artificial intelligence (AI) in cardiac imaging are rapidly improving the reproducibility of this approach and the possibility to reduce time necessary to generate a report. In cardiac computed tomography angiography (CCTA) the main application of AI in clinical practice is focused on detection of stenosis, characterization of coronary plaques, and detection of myocardial ischemia. In cardiac magnetic resonance (CMR) the application of AI is focused on post-processing and particularly on the segmentation of cardiac chambers during late gadolinium enhancement. In echocardiography, the application of AI is focused on segmentation of cardiac chambers and is helpful for valvular function and wall motion abnormalities. The common thread represented by all of these techniques aims to shorten the time of interpretation without loss of information compared to the standard approach. In this review we provide an overview of AI applications in multimodality cardiac imaging.

Prognostic Impact of the HFA-PEFF Score in Patients with Acute Myocardial Infarction and an Intermediate to High HFA-PEFF Score

This study aimed to investigate the efficacy of the HFA-PEFF score in predicting the long-term risks in patients with acute myocardial infarction (AMI) and an HFA-PEFF score ≥ 2. The subjects were divided according to their HFA-PEFF score into intermediate (2−3 points) and high (4−6 points) score groups. The primary outcome was all-cause mortality. Of 1018 patients with AMI and an HFA-PEFF score of ≥2, 712 (69.9%) and 306 (30.1%) were classified into the intermediate and high score groups, respectively. Over a median follow-up of 4.8 (3.2, 6.5) years, 114 (16.0%) and 87 (28.4%) patients died in each group. Multivariate Cox regression identified a high HFA-PEFF score as an independent predictor of all-cause mortality [hazard ratio (HR): 1.53, 95% CI: 1.15−2.04, p = 0.004]. The predictive accuracies for the discrimination and reclassification were significantly improved (C-index 0.750 [95% CI 0.712−0.789]; p = 0.049 and NRI 0.330 [95% CI 0.180−0.479]; p < 0.001) upon the addition of a high HFA-PEFF score to clinical risk factors. The model was better at predicting combined events of all-cause mortality and heart failure readmission (C-index 0.754 [95% CI 0.716−0.791]; p = 0.033, NRI 0.372 [95% CI 0.227−0.518]; p < 0.001). In the AMI cohort, the HFA-PEFF score can effectively predict the prognosis of patients with an HFA-PEFF score of ≥2.

The future of heart failure with preserved ejection fraction : Deep phenotyping for targeted therapeutics

Heart failure (HF) with preserved ejection fraction (HFpEF) is a multi-organ, systemic syndrome that involves multiple cardiac and extracardiac pathophysiologic abnormalities. Because HFpEF is a heterogeneous syndrome and resistant to a "one-size-fits-all" approach it has proven to be very difficult to treat. For this reason, several research groups have been working on methods for classifying HFpEF and testing targeted therapeutics for the HFpEF subtypes identified. Apart from conventional classification strategies based on comorbidity, etiology, left ventricular remodeling, and hemodynamic subtypes, researchers have been combining deep phenotyping with innovative analytical strategies (e.g., machine learning) to classify HFpEF into therapeutically homogeneous subtypes over the past few years. Despite the growing excitement for such approaches, there are several potential pitfalls to their use, and there is a pressing need to follow up on data-driven HFpEF subtypes in order to determine their underlying mechanisms and molecular basis. Here we provide a framework for understanding the phenotype-based approach to HFpEF by reviewing (1) the historical context of HFpEF; (2) the current HFpEF paradigm of comorbidity-induced inflammation and endothelial dysfunction; (3) various methods of sub-phenotyping HFpEF; (4) comorbidity-based classification and treatment of HFpEF; (5) machine learning approaches to classifying HFpEF; (6) examples from HFpEF clinical trials; and (7) the future of phenomapping (machine learning and other advanced analytics) for the classification of HFpEF.

Artificial Intelligence in Cardiovascular Medicine: Current Insights and Future Prospects

Cardiovascular disease (CVD) represents a significant and increasing burden on healthcare systems. Artificial intelligence (AI) is a rapidly evolving transdisciplinary field employing machine learning (ML) techniques, which aim to simulate human intuition to offer cost-effective and scalable solutions to better manage CVD. ML algorithms are increasingly being developed and applied in various facets of cardiovascular medicine, including and not limited to heart failure, electrophysiology, valvular heart disease and coronary artery disease. Within heart failure, AI algorithms can augment diagnostic capabilities and clinical decision-making through automated cardiac measurements. Occult cardiac disease is increasingly being identified using ML from diagnostic data. Improved diagnostic and prognostic capabilities using ML algorithms are enhancing clinical care of patients with valvular heart disease and coronary artery disease. The growth of AI techniques is not without inherent challenges, most important of which is the need for greater external validation through multicenter, prospective clinical trials.

Applications of Machine Learning in Cardiology

In this digital era, artificial intelligence (AI) is establishing a strong foothold in commercial industry and the field of technology. These effects are trickling into the healthcare industry, especially in the clinical arena of cardiology. Machine learning (ML) algorithms are making substantial progress in various subspecialties of cardiology. This will have a positive impact on patient care and move the field towards precision medicine. In this review article, we explore the progress of ML in cardiovascular imaging, electrophysiology, heart failure, and interventional cardiology.

Artificial intelligence in echocardiography: Review and limitations including epistemological concerns

BACKGROUND AND PURPOSE

In this review we describe the use of artificial intelligence in the field of echocardiography. Various aspects and terminologies used in artificial intelligence are explained in an easy-to-understand manner and supplemented with illustrations related to echocardiography. Limitations of artificial intelligence, including epistemologic concerns from a philosophical standpoint, are also discussed.

METHODS

A narrative review of relevant papers was conducted.

CONCLUSION

We provide an overview of the usefulness of artificial intelligence in echocardiography and focus on how it can supplement current day-to-day clinical practice in the assessment of various cardiovascular disease entities. On the other hand, there are significant limitations, including epistemological concerns, which need to be kept in perspective.

Análise Crítica e Limitações do Diagnóstico de Insuficiência Cardíaca com Fração de Ejeção Preservada (ICFEp)

Com o aumento da expectativa de vida da população e a maior frequência de fatores de risco como obesidade, hipertensão arterial e diabetes, espera-se um aumento na prevalência de insuficiência cardíaca com fração de ejeção preservada (ICFEp). Entretanto, no momento, o diagnóstico e o tratamento de pacientes com ICFEp permanecem desafiadores. O diagnóstico sindrômico de ICFEp inclui diversas etiologias e doenças com tratamentos específicos, mas que apresentam pontos em comum em relação à apresentação clínica e à avaliação laboratorial no que diz respeito aos biomarcadores como BNP e NT-ProBNP, à avaliação ecocardiográfica do remodelamento cardíaco e às pressões de enchimento diastólico ventricular esquerdo. Extensos ensaios clínicos randomizados envolvendo a terapia nesta síndrome falharam na demonstração de benefícios para o paciente, fazendo-se necessária uma reflexão acerca do diagnóstico, dos mecanismos de morbidade, da taxa de mortalidade e da reversibilidade. Na revisão, serão abordados os conceitos atuais, as controvérsias e, especialmente, os desafios no diagnóstico da ICFEp através de uma análise crítica do escore da European Heart Failure Association.

Artificial Intelligence in Cardiology-A Narrative Review of Current Status

Artificial intelligence (AI) is an integral part of clinical decision support systems (CDSS), offering methods to approximate human reasoning and computationally infer decisions. Such methods are generally based on medical knowledge, either directly encoded with rules or automatically extracted from medical data using machine learning (ML). ML techniques, such as Artificial Neural Networks (ANNs) and support vector machines (SVMs), are based on mathematical models with parameters that can be optimally tuned using appropriate algorithms. The ever-increasing computational capacity of today’s computer systems enables more complex ML systems with millions of parameters, bringing AI closer to human intelligence. With this objective, the term deep learning (DL) has been introduced to characterize ML based on deep ANN (DNN) architectures with multiple layers of artificial neurons. Despite all of these promises, the impact of AI in current clinical practice is still limited. However, this could change shortly, as the significantly increased papers in AI, machine learning and deep learning in cardiology show. We highlight the significant achievements of recent years in nearly all areas of cardiology and underscore the mounting evidence suggesting how AI will take a central stage in the field.

Machine Learning-Based Systems for the Anticipation of Adverse Events After Pediatric Cardiac Surgery

Pediatric congenital heart disease (CHD) patients are at higher risk of postoperative complications and clinical deterioration either due to their underlying pathology or due to the cardiac surgery, contributing significantly to mortality, morbidity, hospital and family costs, and poor quality of life. In current clinical practice, clinical deterioration is detected, in most of the cases, when it has already occurred. Several early warning scores (EWS) have been proposed to assess children at risk of clinical deterioration using vital signs and risk indicators, in order to intervene in a timely manner to reduce the impact of deterioration and risk of death among children. However, EWS are based on measurements performed at a single time point without incorporating trends nor providing information about patient's risk trajectory. Moreover, some of these measurements rely on subjective assessment making them susceptible to different interpretations. All these limitations could explain why the implementation of EWS in high-resource settings failed to show a significant decrease in hospital mortality. By means of machine learning (ML) based algorithms we could integrate heterogeneous and complex data to predict patient's risk of deterioration. In this perspective article, we provide a brief overview of the potential of ML technologies to improve the identification of pediatric CHD patients at high-risk for clinical deterioration after cardiac surgery, and present the CORTEX traffic light, a ML-based predictive system that Sant Joan de Déu Barcelona Children's Hospital is implementing, as an illustration of the application of an ML-based risk stratification system in a relevant hospital setting.

Characterization of motion patterns by a spatio-temporal saliency descriptor in cardiac cine MRI

BACKGROUND AND OBJECTIVE

Abnormalities of the heart motion reveal the presence of a disease. However, a quantitative interpretation of the motion is still a challenge due to the complex dynamics of the heart. This work proposes a quantitative characterization of regional cardiac motion patterns in cine magnetic resonance imaging (MRI) by a novel spatio-temporal saliency descriptor.

METHOD

The strategy starts by dividing the cardiac sequence into a progression of scales which are in due turn mapped to a feature space of regional orientation changes, mimicking the multi-resolution decomposition of oriented primitive changes of visual systems. These changes are estimated as the difference between a particular time and the rest of the sequence. This decomposition is then temporarily and regionally integrated for a particular orientation and then for the set of different orientations. A final spatio-temporal 4D saliency map is obtained as the summation of the previously integrated information for the available scales. The saliency dispersion of this map was computed in standard cardiac locations as a measure of the regional motion pattern and was applied to discriminate control and hypertrophic cardiomyopathy (HCM) subjects during the diastolic phase.

RESULTS

Salient motion patterns were estimated from an experimental set, which consisted of 3D sequences acquired by MRI from 108 subjects (33 control, 35 HCM, 20 dilated cardiomyopathy (DCM), and 20 myocardial infarction (MINF) from heterogeneous datasets). HCM and control subjects were classified by an SVM that learned the salient motion patterns estimated from the presented strategy, by achieving a 94% AUC. In addition, statistical differences (test t-student, p<0.05) were found among groups of disease in the septal and anterior ventricular segments at both the ED and ES, with salient motion characteristics aligned with existing knowledge on the diseases.

CONCLUSIONS

Regional wall motion abnormality in the apical, anterior, basal, and inferior segments was associated with the saliency dispersion in HCM, DCM, and MINF compared to healthy controls during the systolic and diastolic phases. This saliency analysis may be used to detect subtle changes in heart function.

Assessment of Artificial Intelligence in Echocardiography Diagnostics in Differentiating Takotsubo Syndrome From Myocardial Infarction

Importance

Machine learning algorithms enable the automatic classification of cardiovascular diseases based on raw cardiac ultrasound imaging data. However, the utility of machine learning in distinguishing between takotsubo syndrome (TTS) and acute myocardial infarction (AMI) has not been studied.

Objectives

To assess the utility of machine learning systems for automatic discrimination of TTS and AMI.

Design, Settings, and Participants

This cohort study included clinical data and transthoracic echocardiogram results of patients with AMI from the Zurich Acute Coronary Syndrome Registry and patients with TTS obtained from 7 cardiovascular centers in the International Takotsubo Registry. Data from the validation cohort were obtained from April 2011 to February 2017. Data from the training cohort were obtained from March 2017 to May 2019. Data were analyzed from September 2019 to June 2021.

Exposure

Transthoracic echocardiograms of 224 patients with TTS and 224 patients with AMI were analyzed.

Main Outcomes and Measures

Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the machine learning system evaluated on an independent data set and 4 practicing cardiologists for comparison. Echocardiography videos of 228 patients were used in the development and training of a deep learning model. The performance of the automated echocardiogram video analysis method was evaluated on an independent data set consisting of 220 patients. Data were matched according to age, sex, and ST-segment elevation/non-ST-segment elevation (1 patient with AMI for each patient with TTS). Predictions were compared with echocardiographic-based interpretations from 4 practicing cardiologists in terms of sensitivity, specificity, and AUC calculated from confidence scores concerning their binary diagnosis.

Results

In this cohort study, apical 2-chamber and 4-chamber echocardiographic views of 110 patients with TTS (mean [SD] age, 68.4 [12.1] years; 103 [90.4%] were female) and 110 patients with AMI (mean [SD] age, 69.1 [12.2] years; 103 [90.4%] were female) from an independent data set were evaluated. This approach achieved a mean (SD) AUC of 0.79 (0.01) with an overall accuracy of 74.8 (0.7%). In comparison, cardiologists achieved a mean (SD) AUC of 0.71 (0.03) and accuracy of 64.4 (3.5%) on the same data set. In a subanalysis based on 61 patients with apical TTS and 56 patients with AMI due to occlusion of the left anterior descending coronary artery, the model achieved a mean (SD) AUC score of 0.84 (0.01) and an accuracy of 78.6 (1.6%), outperforming the 4 practicing cardiologists (mean [SD] AUC, 0.72 [0.02]) and accuracy of 66.9 (2.8%).

Conclusions and Relevance

In this cohort study, a real-time system for fully automated interpretation of echocardiogram videos was established and trained to differentiate TTS from AMI. While this system was more accurate than cardiologists in echocardiography-based disease classification, further studies are warranted for clinical application.

Review of applications and challenges of quantitative systems pharmacology modeling and machine learning for heart failure

Quantitative systems pharmacology (QSP) is an important approach in pharmaceutical research and development that facilitates in silico generation of quantitative mechanistic hypotheses and enables in silico trials. As demonstrated by applications from numerous industry groups and interest from regulatory authorities, QSP is becoming an increasingly critical component in clinical drug development. With rapidly evolving computational tools and methods, QSP modeling has achieved important progress in pharmaceutical research and development, including for heart failure (HF). However, various challenges exist in the QSP modeling and clinical characterization of HF. Machine/deep learning (ML/DL) methods have had success in a wide variety of fields and disciplines. They provide data-driven approaches in HF diagnosis and modeling, and offer a novel strategy to inform QSP model development and calibration. The combination of ML/DL and QSP modeling becomes an emergent direction in the understanding of HF and clinical development new therapies. In this work, we review the current status and achievement in QSP and ML/DL for HF, and discuss remaining challenges and future perspectives in the field.

A Phenotyping of Diastolic Function by Machine Learning Improves Prediction of Clinical Outcomes in Heart Failure

Background: Discriminating between different patterns of diastolic dysfunction in heart failure (HF) is still challenging. We tested the hypothesis that an unsupervised machine learning algorithm would detect heterogeneity in diastolic function and improve risk stratification compared with recommended consensus criteria.

Methods: This study included 279 consecutive patients aged 24–97 years old with clinically stable HF referred for echocardiographic assessment, in whom diastolic variables were measured according to the current guidelines. Cluster analysis was undertaken to identify homogeneous groups of patients with similar profiles of the variables. Sequential Cox models were used to compare cluster-based classification with guidelines-based classification for predicting clinical outcomes. The primary endpoint was hospitalization for worsening HF.

Results: The analysis identified three clusters with distinct properties of diastolic function that shared similarities with guidelines-based classification. The clusters were associated with brain natriuretic peptide level (p < 0.001), hemoglobin concentration (p = 0.017) and estimated glomerular filtration rate (p = 0.001). During a mean follow-up period of 2.6 ± 2.0 years, 62 patients (22%) experienced the primary endpoint. Cluster-based classification predicted events with a hazard ratio 1.68 (p = 0.019) that was independent from and incremental to the Meta-analysis Global Group in Chronic Heart Failure (MAGGIC) risk score for HF, and from left ventricular end-diastolic volume and global longitudinal strain, whereas guidelines-based classification did not retain its independent prognostic value (hazard ratio = 1.25, p = 0.202).

Conclusion: Machine learning can identify patterns of diastolic function that better stratify the risk for decompensation than the current consensus recommendations in HF. Integrating this data-driven phenotyping may help in refining prognostication and optimizing treatment.

A Novel Composite Indicator of Predicting Mortality Risk for Heart Failure Patients With Diabetes Admitted to Intensive Care Unit Based on Machine Learning

BACKGROUND

Patients with heart failure (HF) with diabetes may face a poorer prognosis and higher mortality than patients with either disease alone, especially for those in intensive care unit. So far, there is no precise mortality risk prediction indicator for this kind of patient.

METHOD

Two high-quality critically ill databases, the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and the Telehealth Intensive Care Unit (eICU) Collaborative Research Database (eICU-CRD) Collaborative Research Database, were used for study participants' screening as well as internal and external validation. Nine machine learning models were compared, and the best one was selected to define indicators associated with hospital mortality for patients with HF with diabetes. Existing attributes most related to hospital mortality were identified using a visualization method developed for machine learning, namely, Shapley Additive Explanations (SHAP) method. A new composite indicator ASL was established using logistics regression for patients with HF with diabetes based on major existing indicators. Then, the new index was compared with existing indicators to confirm its discrimination ability and clinical value using the receiver operating characteristic (ROC) curve, decision curve, and calibration curve.

RESULTS

The random forest model outperformed among nine models with the area under the ROC curve (AUC) = 0.92 after hyper-parameter optimization. By using this model, the top 20 attributes associated with hospital mortality in these patients were identified among all the attributes based on SHAP method. Acute Physiology Score (APS) III, Sepsis-related Organ Failure Assessment (SOFA), and Max lactate were selected as major attributes related to mortality risk, and a new composite indicator was developed by combining these three indicators, which was named as ASL. Both in the initial and external cohort, the new indicator, ASL, had greater risk discrimination ability with AUC higher than 0.80 in both low- and high-risk groups compared with existing attributes. The decision curve and calibration curve indicated that this indicator also had a respectable clinical value compared with APS III and SOFA. In addition, this indicator had a good risk stratification ability when the patients were divided into three risk levels.

CONCLUSION

A new composite indicator for predicting mortality risk in patients with HF with diabetes admitted to intensive care unit was developed on the basis of attributes identified by the random forest model. Compared with existing attributes such as APS III and SOFA, the new indicator had better discrimination ability and clinical value, which had potential value in reducing the mortality risk of these patients.

Artificial Intelligence: A Shifting Paradigm in Cardio-Cerebrovascular Medicine

The future of healthcare is an organic blend of technology, innovation, and human connection. As artificial intelligence (AI) is gradually becoming a go-to technology in healthcare to improve efficiency and outcomes, we must understand our limitations. We should realize that our goal is not only to provide faster and more efficient care, but also to deliver an integrated solution to ensure that the care is fair and not biased to a group of sub-population. In this context, the field of cardio-cerebrovascular diseases, which encompasses a wide range of conditions-from heart failure to stroke-has made some advances to provide assistive tools to care providers. This article aimed to provide an overall thematic review of recent development focusing on various AI applications in cardio-cerebrovascular diseases to identify gaps and potential areas of improvement. If well designed, technological engines have the potential to improve healthcare access and equitability while reducing overall costs, diagnostic errors, and disparity in a system that affects patients and providers and strives for efficiency.

Deep Learning Predicts Heart Failure With Preserved, Mid-Range, and Reduced Left Ventricular Ejection Fraction From Patient Clinical Profiles

Background: Left ventricular ejection fraction (LVEF) is the gold standard for evaluating heart failure (HF) in coronary artery disease (CAD) patients. It is an essential metric in categorizing HF patients as preserved (HFpEF), mid-range (HFmEF), and reduced (HFrEF) ejection fraction but differs, depending on whether the ASE/EACVI or ESC guidelines are used to classify HF. Objectives: We sought to investigate the effectiveness of using deep learning as an automated tool to predict LVEF from patient clinical profiles using regression and classification trained models. We further investigate the effect of utilizing other LVEF-based thresholds to examine the discrimination ability of deep learning between HF categories grouped with narrower ranges. Methods: Data from 303 CAD patients were obtained from American and Greek patient databases and categorized based on the American Society of Echocardiography and the European Association of Cardiovascular Imaging (ASE/EACVI) guidelines into HFpEF (EF > 55%), HFmEF (50% ≤ EF ≤ 55%), and HFrEF (EF < 50%). Clinical profiles included 13 demographical and clinical markers grouped as cardiovascular risk factors, medication, and history. The most significant and important markers were determined using linear regression fitting and Chi-squared test combined with a novel dimensionality reduction algorithm based on arc radial visualization (ArcViz). Two deep learning-based models were then developed and trained using convolutional neural networks (CNN) to estimate LVEF levels from the clinical information and for classification into one of three LVEF-based HF categories. Results: A total of seven clinical markers were found important for discriminating between the three HF categories. Using statistical analysis, diabetes, diuretics medication, and prior myocardial infarction were found statistically significant (p < 0.001). Furthermore, age, body mass index (BMI), anti-arrhythmics medication, and previous ventricular tachycardia were found important after projections on the ArcViz convex hull with an average nearest centroid (NC) accuracy of 94%. The regression model estimated LVEF levels successfully with an overall accuracy of 90%, average root mean square error (RMSE) of 4.13, and correlation coefficient of 0.85. A significant improvement was then obtained with the classification model, which predicted HF categories with an accuracy ≥93%, sensitivity ≥89%, 1-specificity <5%, and average area under the receiver operating characteristics curve (AUROC) of 0.98. Conclusions: Our study suggests the potential of implementing deep learning-based models clinically to ensure faster, yet accurate, automatic prediction of HF based on the ASE/EACVI LVEF guidelines with only clinical profiles and corresponding information as input to the models. Invasive, expensive, and time-consuming clinical testing could thus be avoided, enabling reduced stress in patients and simpler triage for further intervention.

Data-driven clustering supports adaptive remodeling of athlete's hearts: An echocardiographic study from the Taipei Summer Universiade

BACKGROUND/PURPOSE

Sport-specific adaptations of athlete's hearts are still under investigation. This study sought to 1) identify athlete groups with similar characteristics by clustering echocardiographic data; 2) externally validate the data-driven clusters with sport classifications of various dynamic or static loads to support the conventional hypothesis-driven approach in delineating the athlete's heart.

METHODS

Anthropometric, echocardiographic and electrocardiographic assessments were collected during the 2017 Summer Universiade in Taiwan. Besides standard echocardiography and strain measurements, ventricular-arterial coupling (VAC) was assessed by the ratio of effective arterial elastance (Ea) to left ventricular end-systolic elastance (Ees) as calculated by a modified single-beat algorithm.

RESULTS

We grouped 598 elite athletes (348 male, age 23 ± 2.5 years, across 24 disciplines) using Mitchell's classification. The hypothesis-driven analysis showed dynamic training-related adaptations in heart rate and morphology, including ventricular size, mass, and stroke volume. In comparison, the unsupervised approach found two clusters for each sex. Male athletes participating in high dynamic-load exercises had larger chambers, supranormal diastolic functions, depressed Ees, lower Ea and preserved optimal VAC implicating the resting status of a reservoir-rich pump, which affirmed sport-specific adaptation. The female athletes could be clustered with more noticeable functional alterations, such as depressed biventricular strain. However, the imbalanced number between clusters impeded the validation of load-related remodeling.

CONCLUSION

Hierarchical clustering could analyze complicated multiparametric interactions among numerous echocardiography-derived phenotypes to discern the adaptive propensity of the athlete's heart. The endorsement or generation of hypotheses by a data-driven approach can be applied to various domains.

Exercise-induced B-lines in heart failure with preserved ejection fraction occur along with diastolic function worsening

Aims

Pulmonary congestion during exercise assessed by lung ultrasound predicts negative outcome in patients with heart failure with preserved ejection fraction (HFpEF). We aimed at assessing predictors of exercise‐induced pulmonary B‐lines in HFpEF patients.

Methods and results

Eighty‐one I–II NYHA class HFpEF patients (65.0  ± 8.2 y/o, 56.8% females) underwent standard and strain echocardiography, lung ultrasound, and natriuretic peptide assessment during supine exercise echocardiography (baseline and peak exercise). Peak values and their changes were compared in subgroups according to exercise lung congestion grading (peak B‐lines >10 or ≤10). Exercise elicited significant changes for all echocardiographic parameters in both subgroups [39/81 (48.1%) with peak B‐lines >10; 42/81 (51.9%) with B‐lines ≤10]. Peak values and changes of E‐wave (and its derived indices) were significantly higher in patients with >10 peak B‐lines compared with those with ≤10 B‐line (all P‐values <0.03), showing significant correlation with peak B‐lines for all parameters; concomitantly, global longitudinal strain (GLS) and global strain rate (GSR) during systole (GSRs), early (GSRe) and late (GSRa) diastole, and isovolumic relaxation (GSRivr) were reduced in patients with B‐lines >10 (all P‐values <0.05), showing a negative correlation with peak B‐lines. By adjusted linear regression analysis, peak and change diastolic parameters (E‐wave, E/e′, GSRivr, and E/GSRivr) and peak GLS were individually significantly associated with peak B‐lines. By covariate‐adjusted multivariable model, E/e′ and GSRa at peak exercise were retained as independent predictors of peak B‐lines, with substantial goodness of fit of model (adjusted R² 0.776).

Conclusions

In HFpEF, development of pulmonary congestion upon exercise is mostly concomitant with exercise‐induced worsening of diastolic function.

The evolving role of artificial intelligence in cardiac image analysis

Research in artificial intelligence (AI) have progressed over the last decade. The field of cardiac imaging has seen significant developments using newly developed deep learning methods for automated image analysis and AI tools for disease detection and prognostication. This review article is aimed at those without special background in AI. We review AI concepts and we survey the growing contemporary applications of AI for image analysis in echocardiography, nuclear cardiology, cardiac computed tomography, cardiac magnetic resonance, and invasive angiography.

Machine Learning Augmented Echocardiography for Diastolic Function Assessment

Cardiac diastolic dysfunction is prevalent and is a diagnostic criterion for heart failure with preserved ejection fraction—a burgeoning global health issue. As gold-standard invasive haemodynamic assessment of diastolic function is not routinely performed, clinical guidelines advise using echocardiography measures to determine the grade of diastolic function. However, the current process has suboptimal accuracy, regular indeterminate classifications and is susceptible to confounding from comorbidities. Advances in artificial intelligence in recent years have created revolutionary ways to evaluate and integrate large quantities of cardiology data. Imaging is an area of particular strength for the sub-field of machine-learning, with evidence that trained algorithms can accurately discern cardiac structures, reliably estimate chamber volumes, and output systolic function metrics from echocardiographic images. In this review, we present the emerging field of machine-learning based echocardiographic diastolic function assessment. We summarise how machine-learning has made use of diastolic parameters to accurately differentiate pathology, to identify novel phenotypes within diastolic disease, and to grade diastolic function. Perspectives are given about how these innovations could be used to augment clinical practice, whilst areas for future investigation are identified.

Left atrial conduit flow rate at baseline and during exercise: an index of impaired relaxation in HFpEF patients

Aims

In healthy subjects, adrenergic stimulation augments left ventricular (LV) long‐axis shortening and lengthening, and increases left atrial (LA) to LV intracavitary pressure gradients in early diastole. Lower increments are observed in patients with heart failure with preserved ejection fraction (HFpEF). We hypothesized that exercise in HFpEF would further impair passive LV filling in early‐mid diastole, during conduit flow from pulmonary veins.

Methods and results

Twenty HFpEF patients (67.8 ± 9.8 years; 11 women), diagnosed using 2007 ESC recommendations, underwent ramped semi‐supine bicycle exercise to submaximal target heart rate (∼100 bpm) or symptoms. Seventeen asymptomatic subjects (64.3 ± 8.9 years; 7 women) were controls. Simultaneous LA and LV volumes were measured from pyramidal 3D‐echocardiographic full‐volume datasets acquired from an apical window at baseline and during stress, together with brachial arterial pressure. LA conduit flow was computed from the increase in LV volume from its minimum at end‐systole to the last frame before atrial contraction (onset of the P wave), minus the reduction in LA volume during the same time interval; the difference was integrated and expressed as average flow rate, according to a published formula. The slope of single‐beat preload recruitable stroke work (PRSW) quantified LV inotropic state. 3D LV torsion (rotation of the apex minus rotation of the base divided by LV length) was also measurable, both at rest and during stress, in 10 HFpEF patients and 4 controls. There were divergent responses in conduit flow rate, which increased by 40% during exercise in controls (+17.8 ± 37.3 mL/s) but decreased by 18% in patients with HFpEF (−9.6 ± 42.3 mL/s) (P = 0.046), along with congruent changes (+1.77 ± 1.13°/cm vs. −1.94 ± 2.73°/cm) in apical torsion (P = 0.032). Increments of conduit flow rate and apical torsion during stress correlated with changes in PRSW slope (P = 0.003 and P = 0.006, respectively).

Conclusions

In HFpEF, conduit flow rate decreases when diastolic dysfunction develops during exercise, in parallel with changes in LV inotropic state and torsion, contributing to impaired stroke volume reserve. Conduit flow is measurable using 3D‐echocardiographic full‐volume atrio‐ventricular datasets, and as a marker of LV relaxation can contribute to the diagnosis of HFpEF.

Automated Pattern Recognition in Whole-Cardiac Cycle Echocardiographic Data: Capturing Functional Phenotypes with Machine Learning

BACKGROUND

Echocardiography provides complex data on cardiac function that can be integrated into patterns of dysfunction related to the severity of cardiac disease. The aim of this study was to demonstrate the feasibility of applying machine learning (ML) to automate the integration of echocardiographic data from the whole cardiac cycle and to automatically recognize patterns in velocity profiles and deformation curves, allowing the identification of functional phenotypes.

METHODS

Echocardiography was performed in 189 clinically managed patients with hypertension and 97 healthy individuals without hypertension. Speckle-tracking analysis of the left ventricle and atrium was performed, and deformation curves were extracted. Aortic and mitral blood pool pulsed-wave Doppler and mitral annular tissue pulsed-wave Doppler velocity profiles were obtained. These whole-cardiac cycle deformation and velocity curves were used as ML input. Unsupervised ML was used to create a representation of patients with hypertension in a virtual space in which patients are positioned on the basis of the similarity of their integrated whole-cardiac cycle echocardiography data. Regression methods were used to explore patterns of echocardiographic traces within this virtual ML-derived space, while clustering was used to define phenogroups.

RESULTS

The algorithm captured different patterns in tissue and blood-pool velocity and deformation profiles and integrated the findings, yielding phenotypes related to normal cardiac function and others to advanced remodeling associated with pressure overload in hypertension. The addition of individuals without hypertension into the ML-derived space confirmed the interpretation of normal and remodeled phenotypes.

CONCLUSIONS

ML-based pattern recognition is feasible from echocardiographic data obtained during the whole cardiac cycle. Automated algorithms can consistently capture patterns in velocity and deformation data and, on the basis of these patterns, group patients into interpretable, clinically comprehensive phenogroups that describe structural and functional remodeling. Automated pattern recognition may potentially aid interpretation of imaging data and diagnostic accuracy.

Phenomapping Heart Failure with Preserved Ejection Fraction Using Machine Learning Cluster Analysis: Prognostic and Therapeutic Implications

Heart failure with preserved ejection fraction (HFpEF) is characterized by a high rate of hospitalization and mortality (up to 84% at 5 years), which are similar to those observed for heart failure with reduced ejection fraction (HFrEF). These epidemiologic data claim for the development of specific and innovative therapies to reduce the burden of morbidity and mortality associated with this disease. Compared with HFrEF, which is due to a primary myocardial damage (eg ischemia, cardiomyopathies, toxicity), a heterogeneous etiologic background characterizes HFpEF. The authors discuss these phenotypes and specificities for defining therapeutic strategies that could be proposed according to phenotypes.

Utility of a Deep-Learning Algorithm to Guide Novices to Acquire Echocardiograms for Limited Diagnostic Use

Importance

Artificial intelligence (AI) has been applied to analysis of medical imaging in recent years, but AI to guide the acquisition of ultrasonography images is a novel area of investigation. A novel deep-learning (DL) algorithm, trained on more than 5 million examples of the outcome of ultrasonographic probe movement on image quality, can provide real-time prescriptive guidance for novice operators to obtain limited diagnostic transthoracic echocardiographic images.

Objective

To test whether novice users could obtain 10-view transthoracic echocardiographic studies of diagnostic quality using this DL-based software.

Design, Setting, and Participants

This prospective, multicenter diagnostic study was conducted in 2 academic hospitals. A cohort of 8 nurses who had not previously conducted echocardiograms was recruited and trained with AI. Each nurse scanned 30 patients aged at least 18 years who were scheduled to undergo a clinically indicated echocardiogram at Northwestern Memorial Hospital or Minneapolis Heart Institute between March and May 2019. These scans were compared with those of sonographers using the same echocardiographic hardware but without AI guidance.

Interventions

Each patient underwent paired limited echocardiograms: one from a nurse without prior echocardiography experience using the DL algorithm and the other from a sonographer without the DL algorithm. Five level 3-trained echocardiographers independently and blindly evaluated each acquisition.

Main Outcomes and Measures

Four primary end points were sequentially assessed: qualitative judgement about left ventricular size and function, right ventricular size, and the presence of a pericardial effusion. Secondary end points included 6 other clinical parameters and comparison of scans by nurses vs sonographers.

Results

A total of 240 patients (mean [SD] age, 61 [16] years old; 139 men [57.9%]; 79 [32.9%] with body mass indexes >30) completed the study. Eight nurses each scanned 30 patients using the DL algorithm, producing studies judged to be of diagnostic quality for left ventricular size, function, and pericardial effusion in 237 of 240 cases (98.8%) and right ventricular size in 222 of 240 cases (92.5%). For the secondary end points, nurse and sonographer scans were not significantly different for most parameters.

Conclusions and Relevance

This DL algorithm allows novices without experience in ultrasonography to obtain diagnostic transthoracic echocardiographic studies for evaluation of left ventricular size and function, right ventricular size, and presence of a nontrivial pericardial effusion, expanding the reach of echocardiography to clinical settings in which immediate interrogation of anatomy and cardiac function is needed and settings with limited resources.

Risk stratification of ST-segment elevation myocardial infarction (STEMI) patients using machine learning based on lipid profiles

BACKGROUND

Numerous studies have revealed the relationship between lipid expression and increased cardiovascular risk in ST-segment elevation myocardial infarction (STEMI) patients. Nevertheless, few investigations have focused on the risk stratification of STEMI patients using machine learning algorithms.

METHODS

A total of 1355 STEMI patients who underwent percutaneous coronary intervention were enrolled in this study during 2015-2018. Unsupervised machine learning (consensus clustering) was applied to the present cohort to classify patients into different lipid expression phenogroups, without the guidance of clinical outcomes. Kaplan-Meier curves were implemented to show prognosis during a 904-day median follow-up (interquartile range: 587-1316). In the adjusted Cox model, the association of cluster membership with all adverse events including all-cause mortality, all-cause rehospitalization, and cardiac rehospitalization was evaluated.

RESULTS

All patients were classified into three phenogroups, 1, 2, and 3. Patients in phenogroup 1 with the highest Lp(a) and the lowest HDL-C and apoA1 were recognized as the statin-modified cardiovascular risk group. Patients in phenogroup 2 had the highest HDL-C and apoA1 and the lowest TG, TC, LDL-C and apoB. Conversely, patients in phenogroup 3 had the highest TG, TC, LDL-C and apoB and the lowest Lp(a). Additionally, phenogroup 1 had the worst prognosis. Furthermore, a multivariate Cox analysis revealed that patients in phenogroup 1 were at significantly higher risk for all adverse outcomes.

CONCLUSION

Machine learning-based cluster analysis indicated that STEMI patients with increased concentrations of Lp(a) and decreased concentrations of HDL-C and apoA1 are likely to have adverse clinical outcomes due to statin-modified cardiovascular risks.

TRIAL REGISTRATION

ChiCTR1900028516 ( http://www.chictr.org.cn/index.aspx ).

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: at the heart of failure diagnosis

PURPOSE OF REVIEW

Refinement in machine learning (ML) techniques and approaches has rapidly expanded artificial intelligence applications for the diagnosis and classification of heart failure (HF). This review is designed to provide the clinician with the basics of ML, as well as this technologies future utility in HF diagnosis and the potential impact on patient outcomes.

RECENT FINDINGS

Recent studies applying ML methods to unique data sets available from electrocardiography, vectorcardiography, echocardiography, and electronic health records show significant promise for improving diagnosis, enhancing detection, and advancing treatment of HF. Innovations in both supervised and unsupervised methods have heightened the diagnostic accuracy of models developed to identify the presence of HF and further augmentation of model capabilities are likely utilizing ensembles of ML algorithms derived from different techniques.

SUMMARY

This article is an overview of recent applications of ML to achieve improved diagnosis of HF and the resultant implications for patient management.

Routine Echocardiography and Artificial Intelligence Solutions

Introduction: Echocardiography is widely used because of its portability, high temporal resolution, absence of radiation, and due to the low-costs. Over the past years, echocardiography has been recommended by the European Society of Cardiology in most cardiac diseases for both diagnostic and prognostic purposes. These recommendations have led to an increase in number of performed studies each requiring diligent processing and reviewing. The standard work pattern of image analysis including quantification and reporting has become highly resource intensive and time consuming. Existence of a large number of datasets with digital echocardiography images and recent advent of AI technology have created an environment in which artificial intelligence (AI) solutions can be developed successfully to automate current manual workflow. Methods and Results: We report on published AI solutions for echocardiography analysis on methods' performance, characteristics of the used data and imaged population. Contemporary AI applications are available for automation and advent in the image acquisition, analysis, reporting and education. AI solutions have been developed for both diagnostic and predictive tasks in echocardiography. Left ventricular function assessment and quantification have been most often performed. Performance of automated image view classification, image quality enhancement, cardiac function assessment, disease classification, and cardiac event prediction was overall good but most studies lack external evaluation. Conclusion: Contemporary AI solutions for image acquisition, analysis, reporting and education are developed for relevant tasks with promising performance. In the future major benefit of AI in echocardiography is expected from improvements in automated analysis and interpretation to reduce workload and improve clinical outcome. Some of the challenges have yet to be overcome, however, none of them are insurmountable.