Machine Learning Methods Improve Prognostication, Identify Clinically Distinct Phenotypes, and Detect Heterogeneity in Response to Therapy in a Large Cohort of Heart Failure Patients

Rationale and design of the artificial intelligence scalable solution for acute myocardial infarction (ASSIST) study

BACKGROUND

Acute coronary syndrome (ACS), specifically ST-segment elevation myocardial infarction is a major cause of morbidity and mortality throughout Europe. Diagnosis in the acute setting is mainly based on clinical symptoms and physician's interpretation of an electrocardiogram (ECG), which may be subject to errors. ST-segment elevation is the leading criteria to activate urgent reperfusion therapy, but a clear ST-elevation pattern might not be present in patients with coronary occlusion and ST-segment elevation might be seen in patients with normal coronary arteries.

METHODS

The ASSIST project is a retrospective observational study aiming to improve the ECG-assisted assessment of ACS patients in the acute setting by incorporating an artificial intelligence platform, Willem™ to analyze 12‑lead ECGs. Our aim is to improve diagnostic accuracy and reduce treatment delays. ECG and clinical data collected during this study will enable the optimization and validation of Willem™. A retrospective multicenter study will collect ECG, clinical, and coronary angiography data from 10,309 patients. The primary outcome is the performance of this tool in the correct identification of acute myocardial infarction with coronary artery occlusion. Model performance will be evaluated internally with patients recruited in this retrospective study while external validation will be performed in a second stage.

CONCLUSION

ASSIST will provide key data to optimize Willem™ platform to detect myocardial infarction based on ECG-assessment alone. Our hypothesis is that such a diagnostic approach may reduce time delays, enhance diagnostic accuracy, and improve clinical outcomes.

Role of Artificial Intelligence and Machine Learning to Create Predictors, Enhance Molecular Understanding, and Implement Purposeful Programs for Myocardial Recovery

Heart failure (HF) affects millions of individuals and causes hundreds of thousands of deaths each year in the United States. Despite the public health burden, medical and device therapies for HF significantly improve clinical outcomes and, in a subset of patients, can cause reversal of abnormalities in cardiac structure and function, termed "myocardial recovery." By identifying novel patterns in high-dimensional data, artificial intelligence (AI) and machine learning (ML) algorithms can enhance the identification of key predictors and molecular drivers of myocardial recovery. Emerging research in the area has begun to demonstrate exciting results that could advance the standard of care. Although major obstacles remain to translate this technology to clinical practice, AI and ML hold the potential to usher in a new era of purposeful myocardial recovery programs based on precision medicine. In this review, we discuss applications of ML to the prediction of myocardial recovery, potential roles of ML in elucidating the mechanistic basis underlying recovery, barriers to the implementation of ML in clinical practice, and areas for future research.

Detecting elevated left ventricular end diastolic pressure from simultaneously measured femoral pressure waveform and electrocardiogram

Objective.Instantaneous, non-invasive evaluation of left ventricular end-diastolic pressure (LVEDP) would have significant value in the diagnosis and treatment of heart failure. A new approach called cardiac triangle mapping (CTM) has been recently proposed, which can provide a non-invasive estimate of LVEDP. We hypothesized that a hybrid machine-learning (ML) method based on CTM can instantaneously identify an elevated LVEDP using simultaneously measured femoral pressure waveform and electrocardiogram (ECG).Approach.We studied 46 patients (Age: 39-90 (66.4 ± 9.9), BMI: 20.2-36.8 (27.6 ± 4.1), 12 females) scheduled for clinical left heart catheterizations or coronary angiograms at University of Southern California Keck Medical Center. Exclusion criteria included severe mitral/aortic valve disease; severe carotid stenosis; aortic abnormalities; ventricular paced rhythm; left bundle branch and anterior fascicular blocks; interventricular conduction delay; and atrial fibrillation. Invasive LVEDP and pressure waveforms at the iliac bifurcation were measured using transducer-tipped Millar catheters with simultaneous ECG. LVEDP range was 9.3-40.5 mmHg. LVEDP = 18 mmHg was used as cutoff. Random forest (RF) classifiers were trained using data from 36 patients and blindly tested on 10 patients.Main results.Our proposed ML classifier models accurately predict true LVEDP classes using appropriate physics-based features, where the most accurate demonstrates 100.0% (elevated) and 80.0% (normal) success in predicting true LVEDP classes on blind data.Significance.We demonstrated that physics-based ML models can instantaneously classify LVEDP using information from femoral waveforms and ECGs. Although an invasive validation, the required ML inputs can be potentially obtained non-invasively.

Digital health technologies in enhancing patient and caregiver engagement in heart failure management: Opportunities and challenges

The management of heart failure has undergone significant evolution, advancing from the initial utilization of digitalis and diuretics to the contemporary practice of personalized medicine and sophisticated device therapy. Despite these advancements, the persistent challenge of high hospitalization and readmission rates underscores an urgent need for innovative solutions. This manuscript explores how the integration of digital health technologies into interventional cardiology marks a paradigm shift in the management of heart failure. These technologies are no longer mere adjuncts but have become foundational to a modern approach, providing tools for continuous monitoring, patient education, and improved outcomes post-intervention. Through an examination of current trends, this perspective article highlights the transformative impact of wearable technologies, telehealth platforms, and advanced analytical tools in reshaping patient engagement and enabling proactive care strategies. Case studies illustrate the practical advantages, including enhanced medication adherence, early detection of heart failure signs, and a reduction in healthcare facility burdens. Central to this new digital health landscape is the Information Technology Management (ITM) system, a framework poised to revolutionize patient and caregiver engagement and pave the way for the future of interventional cardiology. This manuscript delineates the ITM system's innovative architecture and its consequential role in refining current and prospective cardiological interventions.

Characterisation of phenotypic patterns in equine exercise-associated myopathies

BACKGROUND

Equine exercise-associated myopathies are prevalent, clinically heterogeneous, generally idiopathic disorders characterised by episodes of myofibre damage that occur in association with exercise. Episodes are intermittent and vary within and between affected horses and across breeds. The aetiopathogenesis is often unclear; there might be multiple causes. Poor phenotypic characterisation hinders genetic and other disease analyses.

OBJECTIVES

The aim of this study was to characterise phenotypic patterns across exercise-associated myopathies in horses.

STUDY DESIGN

Historical cross-sectional study, with subsequent masked case-control validation study.

METHODS

Historical clinical and histological features from muscle samples (n = 109) were used for k-means clustering and validated using principal components analysis and hierarchical clustering. For further validation, a blinded histological study (69 horses) was conducted comparing two phenotypic groups with selected controls and horses with histopathological features characterised by myofibrillar disruption.

RESULTS

We identified two distinct broad phenotypes: a non-classic exercise-associated myopathy syndrome (EAMS) subtype was associated with practitioner-described signs of apparent muscle pain (p < 0.001), reluctance to move (10.85, p = 0.001), abnormal gait (p < 0.001), ataxia (p = 0.001) and paresis (p = 0.001); while a non-specific classic RER subtype was not uniquely associated with any particular variables. No histological differences were identified between subtypes in the validation study, and no identifying histopathological features for other equine myopathies identified in either subtype.

MAIN LIMITATIONS

Lack of an independent validation population; small sample size of smaller identified subtypes; lack of positive control myofibrillar myopathy cases; case descriptions derived from multiple independent and unblinded practitioners.

CONCLUSIONS

This is the first study using computational clustering methods to identify phenotypic patterns in equine exercise-associated myopathies, and suggests that differences in patterns of presenting clinical signs support multiple disease subtypes, with EAMS a novel subtype not previously described. Routine muscle histopathology was not helpful in sub-categorising the phenotypes in our population.

Artificial Intelligence-Based Electrocardiographic Biomarker for Outcome Prediction in Patients With Acute Heart Failure: Prospective Cohort Study

BACKGROUND

Although several biomarkers exist for patients with heart failure (HF), their use in routine clinical practice is often constrained by high costs and limited availability.

OBJECTIVE

We examined the utility of an artificial intelligence (AI) algorithm that analyzes printed electrocardiograms (ECGs) for outcome prediction in patients with acute HF.

METHODS

We retrospectively analyzed prospectively collected data of patients with acute HF at two tertiary centers in Korea. Baseline ECGs were analyzed using a deep-learning system called Quantitative ECG (QCG), which was trained to detect several urgent clinical conditions, including shock, cardiac arrest, and reduced left ventricular ejection fraction (LVEF).

RESULTS

Among the 1254 patients enrolled, in-hospital cardiac death occurred in 53 (4.2%) patients, and the QCG score for critical events (QCG-Critical) was significantly higher in these patients than in survivors (mean 0.57, SD 0.23 vs mean 0.29, SD 0.20; P<.001). The QCG-Critical score was an independent predictor of in-hospital cardiac death after adjustment for age, sex, comorbidities, HF etiology/type, atrial fibrillation, and QRS widening (adjusted odds ratio [OR] 1.68, 95% CI 1.47-1.92 per 0.1 increase; P<.001), and remained a significant predictor after additional adjustments for echocardiographic LVEF and N-terminal prohormone of brain natriuretic peptide level (adjusted OR 1.59, 95% CI 1.36-1.87 per 0.1 increase; P<.001). During long-term follow-up, patients with higher QCG-Critical scores (>0.5) had higher mortality rates than those with low QCG-Critical scores (<0.25) (adjusted hazard ratio 2.69, 95% CI 2.14-3.38; P<.001).

CONCLUSIONS

Predicting outcomes in patients with acute HF using the QCG-Critical score is feasible, indicating that this AI-based ECG score may be a novel biomarker for these patients.

TRIAL REGISTRATION

ClinicalTrials.gov NCT01389843; https://clinicaltrials.gov/study/NCT01389843.

The potential of artificial intelligence to revolutionize health care delivery, research, and education in cardiac electrophysiology

The field of electrophysiology (EP) has benefited from numerous seminal innovations and discoveries that have enabled clinicians to deliver therapies and interventions that save lives and promote quality of life. The rapid pace of innovation in EP may be hindered by several challenges including the aging population with increasing morbidity, the availability of multiple costly therapies that, in many instances, confer minor incremental benefit, the limitations of healthcare reimbursement, the lack of response to therapies by some patients, and the complications of the invasive procedures performed. To overcome these challenges and continue on a steadfast path of transformative innovation, the EP community must comprehensively explore how artificial intelligence (AI) can be applied to healthcare delivery, research, and education and consider all opportunities in which AI can catalyze innovation; create workflow, research, and education efficiencies; and improve patient outcomes at a lower cost. In this white paper, we define AI and discuss the potential of AI to revolutionize the EP field. We also address the requirements for implementing, maintaining, and enhancing quality when using AI and consider ethical, operational, and regulatory aspects of AI implementation. This manuscript will be followed by several perspective papers that will expand on some of these topics.

Revolutionizing Healthcare: Qure.AI's Innovations in Medical Diagnosis and Treatment

Qure.AI, a leading company in artificial intelligence (AI) applied to healthcare, has developed a suite of innovative solutions to revolutionize medical diagnosis and treatment. With a plethora of FDA-approved tools for clinical use, Qure.AI continually strives for innovation in integrating AI into healthcare systems. This article delves into the efficacy of Qure.AI's chest X-ray interpretation tool, "qXR," in medicine, drawing from a comprehensive review of clinical trials conducted by various institutions. Key applications of AI in healthcare include machine learning, deep learning, and natural language processing (NLP), all of which contribute to enhanced diagnostic accuracy, efficiency, and speed. Through the analysis of vast datasets, AI algorithms assist physicians in interpreting medical data and making informed decisions, thereby improving patient care outcomes. Illustrative examples highlight AI's impact on medical imaging, particularly in the diagnosis of conditions such as breast cancer, heart failure, and pulmonary nodules. AI can significantly reduce diagnostic errors and expedite the interpretation of medical images, leading to more timely interventions and treatments. Furthermore, AI-powered predictive analytics enable early detection of diseases and facilitate personalized treatment plans, thereby reducing healthcare costs and improving patient outcomes. The efficacy of AI in healthcare is underscored by its ability to complement traditional diagnostic methods, providing physicians with valuable insights and support in clinical decision-making. As AI continues to evolve, its role in patient care and medical research is poised to expand, promising further advancements in diagnostic accuracy and treatment efficacy.

Long-Term Mortality Predictors Using a Machine-Learning Approach in Patients With Chronic Limb-Threatening Ischemia After Peripheral Vascular Intervention

BACKGROUND

Patients with chronic limb-threatening ischemia (CLTI) face a high long-term mortality risk. Identifying novel mortality predictors and risk profiles would enable individual health care plan design and improved survival. We aimed to leverage a random survival forest machine-learning algorithm to identify long-term all-cause mortality predictors in patients with CLTI undergoing peripheral vascular intervention.

METHODS AND RESULTS

Patients with CLTI undergoing peripheral vascular intervention from 2017 to 2018 were derived from the Medicare-linked VQI (Vascular Quality Initiative) registry. We constructed a random survival forest to rank 66 preprocedural variables according to their relative importance and mean minimal depth for 3-year all-cause mortality. A random survival forest of 2000 trees was built using a training sample (80% of the cohort). Accuracy was assessed in a testing sample (20%) using continuous ranked probability score, Harrell C-index, and out-of-bag error rate. A total of 10 114 patients were included (mean±SD age, 72.0±11.0 years; 59% men). The 3-year mortality rate was 39.1%, with a median survival of 1.4 years (interquartile range, 0.7-2.0 years). The most predictive variables were chronic kidney disease, age, congestive heart failure, dementia, arrhythmias, requiring assisted care, living at home, and body mass index. A total of 41 variables spanning all domains of the biopsychosocial model were ranked as mortality predictors. The accuracy of the model was excellent (continuous ranked probability score, 0.172; Harrell C-index, 0.70; out-of-bag error rate, 29.7%).

CONCLUSIONS

Our random survival forest accurately predicts long-term CLTI mortality, which is driven by demographic, functional, behavioral, and medical comorbidities. Broadening frameworks of risk and refining health care plans to include multidimensional risk factors could improve individualized care for CLTI.

Heart Failure with Mildly Reduced Ejection Fraction-A Phenotype Waiting to Be Explored

Heart failure (HF) presents a significant global health challenge recognised by frequent hospitalisation and high mortality rates. The assessment of left ventricular (LV) ejection fraction (EF) plays a crucial role in diagnosing and predicting outcomes in HF, leading to its classification into preserved (HFpEF), reduced (HFrEF), and mildly reduced (HFmrEF) EF. HFmrEF shares features of both HFrEF and HFpEF but also exhibits distinct characteristics. Despite advancements, managing HFmrEF remains challenging due to its diverse presentation. Large-scale studies are needed to identify the predictors of clinical outcomes and treatment responses. Utilising biomarkers for phenotyping holds the potential for discovering new treatment targets. Given the uncertainty surrounding optimal management, individualised approaches are imperative for HFmrEF patients. This chapter examines HFmrEF, discusses the rationale for its re-classification, and elucidates HFmrEF's key attributes. Furthermore, it provides a comprehensive review of current treatment strategies for HFmrEF patients.

The Efficacy of Machine Learning Models for Predicting the Prognosis of Heart Failure: A Systematic Review and Meta-Analysis

INTRODUCTION

Heart failure (HF) is a major global public health concern. The application of machine learning (ML) to identify individuals at high risk and enable early intervention is a promising approach for improving HF prognosis. We aim to systematically evaluate the performance and value of ML models for predicting HF prognosis.

METHODS

PubMed, Web of Science, Scopus, and Embase online databases were searched up to April 30, 2023, to identify studies on the use of ML models to predict HF prognosis. HF prognosis primarily encompasses readmission and mortality. The meta-analysis was conducted by MedCalc software. Subgroup analyses include grouping based on types of ML models, time intervals, sample sizes, the number of predictive variables, validation methods, whether to conduct hyperparameter optimization and calibration, data set partitioning methods.

RESULTS

A total of 31 studies were included. The most common ML models were random forest, boosting, support vector machine, neural network. The area under the receiver operating characteristic curve (AUC) for predicting HF readmission was 0.675 (95% CI: 0.651-0.699, p < 0.001), and the AUC for predicting HF mortality was 0.790 (95% CI: 0.765-0.816, p < 0.001). Subgroup analyses revealed that models with the prediction time interval of 1 year, sample sizes ≥10,000, the number of predictive variables ≥100, external validation, hyperparameter tuning, calibration adjustment, and data set partitioning using 10-fold cross-validation exhibited favorable performance within their respective subgroups.

CONCLUSION

The performance of ML models in predicting HF readmission is relatively poor, while its performance in predicting HF mortality is moderate. The quality of the relevant studies is generally low, it is essential to enhance the predictive capabilities of ML models through targeted improvements in practical applications.

Identifying subgroups in heart failure patients with multimorbidity by clustering and network analysis

This study presents a workflow for identifying and characterizing patients with Heart Failure (HF) and multimorbidity utilizing data from Electronic Health Records. Multimorbidity, the co-occurrence of two or more chronic conditions, poses a significant challenge on healthcare systems. Nonetheless, understanding of patients with multimorbidity, including the most common disease interactions, risk factors, and treatment responses, remains limited, particularly for complex and heterogeneous conditions like HF. We conducted a clustering analysis of 3745 HF patients using demographics, comorbidities, laboratory values, and drug prescriptions. Our analysis revealed four distinct clusters with significant differences in multimorbidity profiles showing differential prognostic implications regarding unplanned hospital admissions. These findings underscore the considerable disease heterogeneity within HF patients and emphasize the potential for improved characterization of patient subgroups for clinical risk stratification through the use of EHR data.

Integrating clinical pharmacology and artificial intelligence: potential benefits, challenges, and role of clinical pharmacologists

INTRODUCTION

The integration of artificial intelligence (AI) into clinical pharmacology could be a potential approach for accelerating drug discovery and development, improving patient care, and streamlining medical research processes.

AREAS COVERED

We reviewed the current state of AI applications in clinical pharmacology, focusing on drug discovery and development, precision medicine, pharmacovigilance, and other ventures. Key AI applications in clinical pharmacology are examined, including machine learning, natural language processing, deep learning, and reinforcement learning etc. Additionally, the evolving role of clinical pharmacologists, ethical considerations, and challenges in implementing AI in clinical pharmacology are discussed.

EXPERT OPINION

The AI could be instrumental in accelerating drug discovery, predicting drug safety and efficacy, and optimizing clinical trial designs. It can play a vital role in precision medicine by helping in personalized drug dosing, treatment selection, and predicting drug response based on genetic, clinical, and environmental factors. The role of AI in pharmacovigilance, such as signal detection and adverse event prediction, is also promising. The collaboration between clinical pharmacologists and AI experts also poses certain ethical and practical challenges. Clinical pharmacologists can be instrumental in shaping the future of AI-driven clinical pharmacology and contribute to the improvement of healthcare systems.

Patient phenotype profiling using echocardiography and natriuretic peptides to personalise heart failure therapy

Heart failure (HF) is a progressive condition with a clinical picture resulting from reduced cardiac output (CO) and/or elevated left ventricular (LV) filling pressures (LVFP). The original Diamond-Forrester classification, based on haemodynamic data reflecting CO and pulmonary congestion, was introduced to grade severity, manage, and risk stratify advanced HF patients, providing evidence that survival progressively worsened for those classified as warm/dry, cold/dry, warm/wet, and cold/wet. Invasive haemodynamic evaluation in critically ill patients has been replaced by non-invasive haemodynamic phenotype profiling using echocardiography. Decreased CO is not infrequent among ambulatory HF patients with reduced ejection fraction, ranging from 23 to 45%. The Diamond-Forrester classification may be used in combination with the evaluation of natriuretic peptides (NPs) in ambulatory HF patients to pursue the goal of early identification of those at high risk of adverse events and personalise therapy to antagonise neurohormonal systems, reduce congestion, and preserve tissue/renal perfusion. The most benefit of the Guideline-directed medical treatment is to be expected in stable patients with the warm/dry profile, who more often respond with LV reverse remodelling, while more selective individualised treatments guided by echocardiography and NPs are necessary for patients with persisting congestion and/or tissue/renal hypoperfusion (cold/dry, warm/wet, and cold/wet phenotypes) to achieve stabilization and to avoid further neurohormonal activation, as a result of inappropriate use of vasodilating or negative chronotropic drugs, thus pursuing the therapeutic objectives. Therefore, tracking the haemodynamic status over time by clinical, imaging, and laboratory indicators helps implement therapy by individualising drug regimens and interventions according to patients' phenotypes even in an ambulatory setting.

Early Diagnosis of Cardiovascular Diseases in the Era of Artificial Intelligence: An In-Depth Review

Cardiovascular diseases (CVDs) are significant health issues that result in high death rates globally. Early detection of cardiovascular events may lower the occurrence of acute myocardial infarction and reduce death rates in people with CVDs. Traditional data analysis is inadequate for managing multidimensional data related to the risk prediction of CVDs, heart attacks, medical image interpretations, therapeutic decision-making, and disease prognosis due to the complex pathological mechanisms and multiple factors involved. Artificial intelligence (AI) is a technology that utilizes advanced computer algorithms to extract information from large databases, and it has been integrated into the medical industry. AI methods have shown the ability to speed up the advancement of diagnosing and treating CVDs such as heart failure, atrial fibrillation, valvular heart disease, hypertrophic cardiomyopathy, congenital heart disease, and more. In clinical settings, AI has shown usefulness in diagnosing cardiovascular illness, improving the efficiency of supporting tools, stratifying and categorizing diseases, and predicting outcomes. Advanced AI algorithms have been intricately designed to analyze intricate relationships within extensive healthcare data, enabling them to tackle more intricate jobs compared to conventional approaches.

Artificial intelligence and machine learning for clinical pharmacology

Artificial intelligence (AI) will impact many aspects of clinical pharmacology, including drug discovery and development, clinical trials, personalized medicine, pharmacogenomics, pharmacovigilance and clinical toxicology. The rapid progress of AI in healthcare means clinical pharmacologists should have an understanding of AI and its implementation in clinical practice. As with any new therapy or health technology, it is imperative that AI tools are subject to robust and stringent evaluation to ensure that they enhance clinical practice in a safe and equitable manner. This review serves as an introduction to AI for the clinical pharmacologist, highlighting current applications, aspects of model development and issues surrounding evaluation and deployment. The aim of this article is to empower clinical pharmacologists to embrace and lead on the safe and effective use of AI within healthcare.

Heart failure registries - Future directions

Heart failure (HF) is a growing, global public health issue. Despite advances in HF care, many challenges remain and HF outcomes are poor. Some of the major reasons for this are the lack of understanding and treatment for certain HF sub-types as well as the lack of implementation of treatment in areas where effective treatment exists. HF registries provide the opportunity to transform clinical research and patient care. Recently the registry-based randomized clinical trial has emerged as a pragmatic and inexpensive alternative to the gold standard in clinical trial design, the randomized controlled trial. Registries may also provide platforms for strategy trials, implementation trials, and screening. Using examples from the Swedish Heart Failure Registry and others, the present review provides insights into how registry-based research can address many of the unmet needs in HF.

Heartfelt Breakthroughs: Elevating Quality of Life with Cutting-Edge Advances in Heart Failure Treatment

Heart failure is a cardiovascular condition, leading to fatigue, breathlessness, and fluid retention. It affects around 56 million people globally and is a leading cause of hospitalization and mortality. Its prevalence is rising due to aging populations and lifestyle factors. Managing heart failure demands a multidisciplinary approach, encompassing medications, lifestyle modifications, and often medical devices or surgeries. The treatment burden is substantial, impacting patients' daily lives and straining healthcare systems. Improving early detection, novel therapies, and patient education are crucial for alleviating the burden and enhancing the quality of life. There are notable advancements in the field of heart failure treatment and prevention. We will discuss significant pharmacological and device advances related to heart failure, including angiotensin receptor-neprilysin inhibitor, sodium-glucose co-transporter inhibition, glucagon-like peptide-1 agonist, cardiac resynchronization therapy, cardiac contractility modulation, mechanical circulatory support devices, and transcatheter valve interventions. We will also review novel therapies on the horizon, emerging technologies like CRISPR-based treatments for genetic anomalies, and the involvement of artificial intelligence in heart failure detection and management.

Unsupervised cluster analysis reveals different phenotypes in patients after transcatheter aortic valve replacement

Aims

The aim of this study was to identify phenotypes with potential prognostic significance in aortic stenosis (AS) patients after transcatheter aortic valve replacement (TAVR) through a clustering approach.

Methods and results

This multi-centre retrospective study included 1365 patients with severe AS who underwent TAVR between January 2015 and March 2019. Among demographics, laboratory, and echocardiography parameters, 20 variables were selected through dimension reduction and used for unsupervised clustering. Phenotypes and outcomes were compared between clusters. Patients were randomly divided into a derivation cohort (n = 1092: 80%) and a validation cohort (n = 273: 20%). Three clusters with markedly different features were identified. Cluster 1 was associated predominantly with elderly age, a high aortic valve gradient, and left ventricular (LV) hypertrophy; Cluster 2 consisted of preserved LV ejection fraction, larger aortic valve area, and high blood pressure; and Cluster 3 demonstrated tachycardia and low flow/low gradient AS. Adverse outcomes differed significantly among clusters during a median of 2.2 years of follow-up (P < 0.001). After adjustment for clinical and echocardiographic data in a Cox proportional hazards model, Cluster 3 (hazard ratio, 4.18; 95% confidence interval, 1.76-9.94; P = 0.001) was associated with increased risk of adverse outcomes. In sequential Cox models, a model based on clinical data and echocardiographic variables (χ2 = 18.4) was improved by Cluster 3 (χ2 = 31.5; P = 0.001) in the validation cohort.

Conclusion

Unsupervised cluster analysis of patients after TAVR revealed three different groups for assessment of prognosis. This provides a new perspective in the categorization of patients after TAVR that considers comorbidities and extravalvular cardiac dysfunction.

Application and Potential of Artificial Intelligence in Heart Failure: Past, Present, and Future

The prevalence of heart failure (HF) is increasing, necessitating accurate diagnosis and tailored treatment. The accumulation of clinical information from patients with HF generates big data, which poses challenges for traditional analytical methods. To address this, big data approaches and artificial intelligence (AI) have been developed that can effectively predict future observations and outcomes, enabling precise diagnoses and personalized treatments of patients with HF. Machine learning (ML) is a subfield of AI that allows computers to analyze data, find patterns, and make predictions without explicit instructions. ML can be supervised, unsupervised, or semi-supervised. Deep learning is a branch of ML that uses artificial neural networks with multiple layers to find complex patterns. These AI technologies have shown significant potential in various aspects of HF research, including diagnosis, outcome prediction, classification of HF phenotypes, and optimization of treatment strategies. In addition, integrating multiple data sources, such as electrocardiography, electronic health records, and imaging data, can enhance the diagnostic accuracy of AI algorithms. Currently, wearable devices and remote monitoring aided by AI enable the earlier detection of HF and improved patient care. This review focuses on the rationale behind utilizing AI in HF and explores its various applications.

Development and Validation of a Protein Risk Score for Mortality in Heart Failure : A Community Cohort Study

BACKGROUND

Heart failure (HF) is a complex clinical syndrome with high mortality. Current risk stratification approaches lack precision. High-throughput proteomics could improve risk prediction. Its use in clinical practice to guide the management of patients with HF depends on validation and evidence of clinical benefit.

OBJECTIVE

To develop and validate a protein risk score for mortality in patients with HF.

DESIGN

Community-based cohort.

SETTING

Southeast Minnesota.

PARTICIPANTS

Patients with HF enrolled between 2003 and 2012 and followed through 2021.

MEASUREMENTS

A total of 7289 plasma proteins in 1351 patients with HF were measured using the SomaScan Assay (SomaLogic). A protein risk score was derived using least absolute shrinkage and selection operator regression and temporal validation in patients enrolled between 2003 and 2007 (development cohort) and 2008 and 2012 (validation cohort). Multivariable Cox regression was used to examine the association between the protein risk score and mortality. The performance of the protein risk score to predict 5-year mortality risk was assessed using calibration plots, decision curves, and relative utility analyses and compared with a clinical model, including the Meta-Analysis Global Group in Chronic Heart Failure mortality risk score and N-terminal pro-B-type natriuretic peptide.

RESULTS

The development (n = 855; median age, 78 years; 50% women; 29% with ejection fraction <40%) and validation cohorts (n = 496; median age, 76 years; 45% women; 33% with ejection fraction <40%) were mostly similar. In the development cohort, 38 unique proteins were selected for the protein risk score. Independent of ejection fraction, the protein risk score demonstrated good calibration, reclassified mortality risk particularly at the extremes of the risk distribution, and showed greater clinical utility compared with the clinical model.

LIMITATION

Participants were predominantly of European ancestry, potentially limiting the generalizability of the findings to different patient populations.

CONCLUSION

Validation of the protein risk score demonstrated good calibration and evidence of predicted benefits to stratify the risk for death in HF superior to that of clinical methods. Further studies are needed to prospectively evaluate the score's performance in diverse populations and determine risk thresholds for interventions.

PRIMARY FUNDING SOURCE

Division of Intramural Research at the National Heart, Lung, and Blood Institute of the National Institutes of Health.

Unsupervised clustering identifies sub-phenotypes and reveals novel outcome predictors in patients with dialysis-requiring sepsis-associated acute kidney injury

INTRODUCTION

Heterogeneity exists in sepsis-associated acute kidney injury (SA-AKI). This study aimed to perform unsupervised consensus clustering in critically ill patients with dialysis-requiring SA-AKI.

PATIENTS AND METHODS

This prospective observational cohort study included all septic patients, defined by the Sepsis-3 criteria, with dialysis-requiring SA-AKI in surgical intensive care units in Taiwan between 2009 and 2018. We employed unsupervised consensus clustering based on 23 clinical variables upon initializing renal replacement therapy. Multivariate-adjusted Cox regression models and Fine-Gray sub-distribution hazard models were built to test associations between cluster memberships with mortality and being free of dialysis at 90 days after hospital discharge, respectively.

RESULTS

Consensus clustering among 999 enrolled patients identified three sub-phenotypes characterized with distinct clinical manifestations upon renal replacement therapy initiation (n = 352, 396 and 251 in cluster 1, 2 and 3, respectively). They were followed for a median of 48 (interquartile range 9.5-128.5) days. Phenotypic cluster 1, featured by younger age, lower Charlson Comorbidity Index, higher baseline estimated glomerular filtration rate but with higher severity of acute illness was associated with an increased risk of death (adjusted hazard ratio of 3.05 [95% CI, 2.35-3.97]) and less probability to become free of dialysis (adjusted sub-distribution hazard ratio of 0.55 [95% CI, 0.38-0.8]) than cluster 3. By examining distinct features of the sub-phenotypes, we discovered that pre-dialysis hyperlactatemia ≥3.3 mmol/L was an independent outcome predictor. A clinical model developed to determine high-risk sub-phenotype 1 in this cohort (C-static 0.99) can identify a sub-phenotype with high in-hospital mortality risk (adjusted hazard ratio of 1.48 [95% CI, 1.25-1.74]) in another independent multi-centre SA-AKI cohort.

CONCLUSIONS

Our data-driven approach suggests sub-phenotypes with clinical relevance in dialysis-requiring SA-AKI and serves an outcome predictor. This strategy represents further development toward precision medicine in the definition of high-risk sub-phenotype in patients with SA-AKI.Key messagesUnsupervised consensus clustering can identify sub-phenotypes of patients with SA-AKI and provide a risk prediction.Examining the features of patient heterogeneity contributes to the discovery of serum lactate levels ≥ 3.3 mmol/L upon initializing RRT as an independent outcome predictor.This data-driven approach can be useful for prognostication and lead to a better understanding of therapeutic strategies in heterogeneous clinical syndromes.

Rationale and design of the ESC Heart Failure III Registry - Implementation and discovery

AIMS

Heart failure outcomes remain poor despite advances in therapy. The European Society of Cardiology Heart Failure III Registry (ESC HF III Registry) aims to characterize HF clinical features and outcomes and to assess implementation of guideline-recommended therapy in Europe and other ESC affiliated countries.

METHODS

Between 1 November 2018 and 31 December 2020, 10 162 patients with chronic or acute/worsening HF with reduced, mildly reduced, or preserved ejection fraction were enrolled from 220 centres in 41 European or ESC affiliated countries. The ESC HF III Registry collected data on baseline characteristics (hospital or clinic presentation), hospital course, diagnostic and therapeutic decisions in hospital and at the clinic visit; and on outcomes at 12-month follow-up. These data include demographics, medical history, physical examination, biomarkers and imaging, quality of life, treatments, and interventions - including drug doses and reasons for non-use, and cause-specific outcomes.

CONCLUSION

The ESC HF III Registry will provide comprehensive and unique insight into contemporary HF characteristics, treatment implementation, and outcomes, and may impact implementation strategies, clinical discovery, trial design, and public policy.

Predicting incident cardiovascular disease among African-American adults: A deep learning approach to evaluate social determinants of health in the Jackson heart study

The present study sought to leverage machine learning approaches to determine whether social determinants of health improve prediction of incident cardiovascular disease (CVD). Participants in the Jackson Heart study with no history of CVD at baseline were followed over a 10-year period to determine first CVD events (i.e., coronary heart disease, stroke, heart failure). Three modeling algorithms (i.e., Deep Neural Network, Random Survival Forest, Penalized Cox Proportional Hazards) were used to evaluate three feature sets (i.e., demographics and standard/biobehavioral CVD risk factors [FS1], FS1 combined with psychosocial and socioeconomic CVD risk factors [FS2], and FS2 combined with environmental features [FS3]) as predictors of 10-year CVD risk. Contrary to hypothesis, overall predictive accuracy did not improve when adding social determinants of health. However, social determinants of health comprised eight of the top 15 predictors of first CVD events. The social determinates of health indicators included four socioeconomic factors (insurance status and types), one psychosocial factor (discrimination burden), and three environmental factors (density of outdoor physical activity resources, including instructional and water activities; modified retail food environment index excluding alcohol; and favorable food stores). Findings suggest that whereas understanding biological determinants may identify who is currently at risk for developing CVD and in need of secondary prevention, understanding upstream social determinants of CVD risk could guide primary prevention efforts by identifying where and how policy and community-level interventions could be targeted to facilitate changes in individual health behaviors.

Discovering Distinct Phenotypical Clusters in Heart Failure Across the Ejection Fraction Spectrum: a Systematic Review

REVIEW PURPOSE

This systematic review aims to summarise clustering studies in heart failure (HF) and guide future clinical trial design and implementation in routine clinical practice.

FINDINGS

34 studies were identified (n = 19 in HF with preserved ejection fraction (HFpEF)). There was significant heterogeneity invariables and techniques used. However, 149/165 described clusters could be assigned to one of nine phenotypes: 1) young, low comorbidity burden; 2) metabolic; 3) cardio-renal; 4) atrial fibrillation (AF); 5) elderly female AF; 6) hypertensive-comorbidity; 7) ischaemic-male; 8) valvular disease; and 9) devices. There was room for improvement on important methodological topics for all clustering studies such as external validation and transparency of the modelling process. The large overlap between the phenotypes of the clustering studies shows that clustering is a robust approach for discovering clinically distinct phenotypes. However, future studies should invest in a phenotype model that can be implemented in routine clinical practice and future clinical trial design. HF = heart failure, EF = ejection fraction, HFpEF = heart failure with preserved ejection fraction, HFrEF = heart failure with reduced ejection fraction, CKD = chronic kidney disease, AF = atrial fibrillation, IHD = ischaemic heart disease, CAD = coronary artery disease, ICD = implantable cardioverter-defibrillator, CRT = cardiac resynchronization therapy, NT-proBNP = N-terminal pro b-type natriuretic peptide, BMI = Body Mass Index, COPD = Chronic obstructive pulmonary disease.

Multimorbidity in Heart Failure: Leveraging Cluster Analysis to Guide Tailored Treatment Strategies

REVIEW PURPOSE

This review summarises key findings on treatment effects within phenotypical clusters of patients with heart failure (HF), making a distinction between patients with preserved ejection fraction (HFpEF) and reduced ejection fraction (HFrEF).

FINDINGS

Treatment response differed among clusters; ACE inhibitors were beneficial in all HFrEF phenotypes, while only some studies show similar beneficial prognostic effects in HFpEF patients. Beta-blockers had favourable effects in all HFrEF patients but not in HFpEF phenotypes and tended to worsen prognosis in older, cardiorenal patients. Mineralocorticoid receptor antagonists had more favourable prognostic effects in young, obese males and metabolic HFpEF patients. While a phenotype-guided approach is a promising solution for individualised treatment strategies, there are several aspects that still require improvements before such an approach could be implemented in clinical practice. Stronger evidence from clinical trials and real-world data may assist in establishing a phenotype-guided treatment approach for patient with HF in the future.

Phenotyping left ventricular systolic dysfunction in asymptomatic individuals for improved risk stratification

AIMS

Left ventricular systolic dysfunction (LSVD) is a heterogeneous condition with several factors influencing prognosis. Better phenotyping of asymptomatic individuals can inform preventative strategies. This study aims to explore the clinical phenotypes of LVSD in initially asymptomatic subjects and their association with clinical outcomes and cardiovascular abnormalities through multi-dimensional data clustering.

METHODS AND RESULTS

Clustering analysis was performed on 60 clinically available variables from 1563 UK Biobank participants without pre-existing heart failure (HF) and with left ventricular ejection fraction (LVEF) < 50% on cardiovascular magnetic resonance (CMR) assessment. Risks of developing HF, other cardiovascular events, death, and a composite of major adverse cardiovascular events (MACE) associated with clusters were investigated. Cardiovascular imaging characteristics, not included in the clustering analysis, were also evaluated. Three distinct clusters were identified, differing considerably in lifestyle habits, cardiovascular risk factors, electrocardiographic parameters, and cardiometabolic profiles. A stepwise increase in risk profile was observed from Cluster 1 to Cluster 3, independent of traditional risk factors and LVEF. Compared with Cluster 1, the lowest risk subset, the risk of MACE ranged from 1.42 [95% confidence interval (CI): 1.03-1.96; P < 0.05] for Cluster 2 to 1.72 (95% CI: 1.36-2.35; P < 0.001) for Cluster 3. Cluster 3, the highest risk profile, had features of adverse cardiovascular imaging with the greatest LV re-modelling, myocardial dysfunction, and decrease in arterial compliance.

CONCLUSIONS

Clustering of clinical variables identified three distinct risk profiles and clinical trajectories of LVSD amongst initially asymptomatic subjects. Improved characterization may facilitate tailored interventions based on the LVSD sub-type and improve clinical outcomes.

Virtual healthcare solutions in heart failure: a literature review

The widespread adoption of mobile technologies offers an opportunity for a new approach to post-discharge care for patients with heart failure (HF). By enabling non-invasive remote monitoring and two-way, real-time communication between the clinic and home-based patients, as well as a host of other capabilities, mobile technologies have a potential to significantly improve remote patient care. This literature review summarizes clinical evidence related to virtual healthcare (VHC), defined as a care team + connected devices + a digital solution in post-release care of patients with HF. Searches were conducted on Embase (06/12/2020). A total of 171 studies were included for data extraction and evidence synthesis: 96 studies related to VHC efficacy, and 75 studies related to AI in HF. In addition, 15 publications were included from the search on studies scaling up VHC solutions in HF within the real-world setting. The most successful VHC interventions, as measured by the number of reported significant results, were those targeting reduction in rehospitalization rates. In terms of relative success rate, the two most effective interventions targeted patient self-care and all-cause hospital visits in their primary endpoint. Among the three categories of VHC identified in this review (telemonitoring, remote patient management, and patient self-empowerment) the integrated approach in remote patient management solutions performs the best in decreasing HF patients' re-admission rates and overall hospital visits. Given the increased amount of data generated by VHC technologies, artificial intelligence (AI) is being investigated as a tool to aid decision making in the context of primary diagnostics, identifying disease phenotypes, and predicting treatment outcomes. Currently, most AI algorithms are developed using data gathered in clinic and only a few studies deploy AI in the context of VHC. Most successes have been reported in predicting HF outcomes. Since the field of VHC in HF is relatively new and still in flux, this is not a typical systematic review capturing all published studies within this domain. Although the standard methodology for this type of reviews was followed, the nature of this review is qualitative. The main objective was to summarize the most promising results and identify potential research directions.

Instantaneous detection of acute myocardial infarction and ischaemia from a single carotid pressure waveform in rats

Aims

Myocardial infarction (MI) is one of the leading causes of death worldwide. It is well accepted that early diagnosis followed by early reperfusion therapy significantly increases the MI survival. Diagnosis of acute MI is traditionally based on the presence of chest pain and electrocardiogram (ECG) criteria. However, around 50% of the MIs are without chest pain, and ECG is neither completely specific nor definitive. Therefore, there is an unmet need for methods that allow detection of acute MI or ischaemia without using ECG. Our hypothesis is that a hybrid physics-based machine learning (ML) method can detect the occurrence of acute MI or ischaemia from a single carotid pressure waveform.

Methods and results

We used a standard occlusion/reperfusion rat model. Physics-based ML classifiers were developed using intrinsic frequency parameters extracted from carotid pressure waveforms. ML models were trained, validated, and generalized using data from 32 rats. The final ML models were tested on an external stratified blind dataset from additional 13 rats. When tested on blind data, the best ML model showed specificity = 0.92 and sensitivity = 0.92 for detecting acute MI. The best model's specificity and sensitivity for ischaemia detection were 0.85 and 0.92, respectively.

Conclusion

We demonstrated that a hybrid physics-based ML approach can detect the occurrence of acute MI and ischaemia from carotid pressure waveform in rats. Since carotid pressure waveforms can be measured non-invasively, this proof-of-concept pre-clinical study can potentially be expanded in future studies for non-invasive detection of MI or myocardial ischaemia.

Artificial intelligence and heart failure: A state-of-the-art review

Heart failure (HF) is a heterogeneous syndrome affecting more than 60 million individuals globally. Despite recent advancements in understanding of the pathophysiology of HF, many issues remain including residual risk despite therapy, understanding the pathophysiology and phenotypes of patients with HF and preserved ejection fraction, and the challenges related to integrating a large amount of disparate information available for risk stratification and management of these patients. Risk prediction algorithms based on artificial intelligence (AI) may have superior predictive ability compared to traditional methods in certain instances. AI algorithms can play a pivotal role in the evolution of HF care by facilitating clinical decision making to overcome various challenges such as allocation of treatment to patients who are at highest risk or are more likely to benefit from therapies, prediction of adverse outcomes, and early identification of patients with subclinical disease or worsening HF. With the ability to integrate and synthesize large amounts of data with multidimensional interactions, AI algorithms can supply information with which physicians can improve their ability to make timely and better decisions. In this review, we provide an overview of the AI algorithms that have been developed for establishing early diagnosis of HF, phenotyping HF with preserved ejection fraction, and stratifying HF disease severity. This review also discusses the challenges in clinical deployment of AI algorithms in HF, and the potential path forward for developing future novel learning-based algorithms to improve HF care.

Patient profiles in heart failure with reduced ejection fraction: Prevalence, characteristics, treatments and outcomes in a real-world heart failure population

AIMS

The Heart Failure Association of the European Society of Cardiology has recently proposed to optimize guideline-directed medical treatments according to patient's profiles. The aim of this analysis was to investigate prevalence/characteristics/treatments/outcomes for individual profiles.

METHODS AND RESULTS

Patients with heart failure (HF) with reduced ejection fraction (HFrEF) enrolled in the Swedish Heart Failure Registry (SwedeHF) between 2013 and 2021 were considered. Among 108 profiles generated by combining different strata of renal function (by estimated glomerular filtration rate [eGFR]), systolic blood pressure (sBP), heart rate, atrial fibrillation (AF) status and presence of hyperkalaemia, 93 were identified in our cohort. Event rates for a composite of cardiovascular (CV) mortality or first HF hospitalization were calculated for each profile. The nine most frequent profiles accounting for 70.5% of the population had eGFR 30-60 or ≥60 ml/min/1.73 m2 , sBP 90-140 mmHg and no hyperkalaemia. Heart rate and AF were evenly distributed. The highest risk of CV mortality/first HF hospitalization was observed in those with concomitant eGFR 30-60 ml/min/1.73 m2 and AF. We also identified nine profiles with the highest event rates, representing only 5% of the study population, characterized by no hyperkalaemia, even distribution among the sBP strata, predominance of eGFR <30 ml/min/1.73 m2 and AF. The three profiles with eGFR 30-60 ml/min/1.73 m2 also showed sBP <90 mmHg.

CONCLUSIONS

In a real-world cohort, most patients fit in a few easily identifiable profiles; the nine profiles at highest risk of mortality/morbidity accounted for only 5% of the population. Our data might contribute to identifying profile-tailored approaches to guide drug implementation and follow-up.

Comparing the performance of machine learning and conventional models for predicting atherosclerotic cardiovascular disease in a general Chinese population

BACKGROUND

Accurately predicting the risk of atherosclerotic cardiovascular disease (ASCVD) is crucial for implementing individualized prevention strategies and improving patient outcomes. Our objective is to develop machine learning (ML)-based models for predicting ASCVD risk in a prospective Chinese population and compare their performance with conventional regression models.

METHODS

A hybrid dataset consisting of 551 features was used, including 98 demographic, behavioral, and psychological features, 444 Electrocardiograph (ECG) features, and 9 Echocardiography (Echo) features. Seven machine learning (ML)-based models were trained, validated, and tested after selecting the 30 most informative features. We compared the discrimination, calibration, net benefit, and net reclassification improvement (NRI) of the ML models with those of conventional ASCVD risk calculators, such as the Pooled Cohort Equations (PCE) and Prediction for ASCVD Risk in China (China-PAR).

RESULTS

The study included 9,609 participants (mean age 53.4 ± 10.4 years, 53.7% female), and during a median follow-up of 4.7 years, 431 (4.5%) participants developed ASCVD. In the testing set, the final ML-based ANN model outperformed PCE, China-PAR, recalibrated PCE, and recalibrated China-PAR in predicting ASCVD. This was demonstrated by the model's higher area under the curve (AUC) of 0.800, compared to 0.777, 0.780, 0.779, and 0.779 for the other models, respectively. Additionally, the model had a lower Hosmer-Lemeshow χ2 of 9.1, compared to 37.3, 67.6, 126.6, and 18.6 for the other models. The net benefit at a threshold of 5% was also higher for the ML-based ANN model at 0.017, compared to 0.016, 0.013, 0.017, and 0.016 for the other models, respectively. Furthermore, the NRI was 0.089 for the ML-based ANN model, while it was 0.355, 0.098, and 0.088 for PCE, China-PAR, and recalibrated PCE, respectively.

CONCLUSIONS

Compared to conventional regression ASCVD risk calculators, such as PCE and China-PAR, the ANN prediction model may help optimize identification of individuals at heightened cardiovascular risk by flexibly incorporating a wider range of potential predictors. The findings may help guide clinical decision-making and ultimately contribute to ASCVD prevention and management.

The role of artificial intelligence in hypertensive disorders of pregnancy: towards personalized healthcare

INTRODUCTION

Guidelines advise ongoing follow-up of patients after hypertensive disorders of pregnancy (HDP) to assess cardiovascular risk and manage future patient-specific pregnancy conditions. However, there are limited tools available to monitor patients, with those available tending to be simple risk assessments that lack personalization. A promising approach could be the emerging artificial intelligence (AI)-based techniques, developed from big patient datasets to provide personalized recommendations for preventive advice.

AREAS COVERED

In this narrative review, we discuss the impact of integrating AI and big data analysis for personalized cardiovascular care, focusing on the management of HDP.

EXPERT OPINION

The pathophysiological response of women to pregnancy varies, and deeper insight into each response can be gained through a deeper analysis of the medical history of pregnant women based on clinical records and imaging data. Further research is required to be able to implement AI for clinical cases using multi-modality and multi-organ assessment, and this could expand both knowledge on pregnancy-related disorders and personalized treatment planning.

Identifying subtypes of heart failure from three electronic health record sources with machine learning: an external, prognostic, and genetic validation study

BACKGROUND

Machine learning has been used to analyse heart failure subtypes, but not across large, distinct, population-based datasets, across the whole spectrum of causes and presentations, or with clinical and non-clinical validation by different machine learning methods. Using our published framework, we aimed to discover heart failure subtypes and validate them upon population representative data.

METHODS

In this external, prognostic, and genetic validation study we analysed individuals aged 30 years or older with incident heart failure from two population-based databases in the UK (Clinical Practice Research Datalink [CPRD] and The Health Improvement Network [THIN]) from 1998 to 2018. Pre-heart failure and post-heart failure factors (n=645) included demographic information, history, examination, blood laboratory values, and medications. We identified subtypes using four unsupervised machine learning methods (K-means, hierarchical, K-Medoids, and mixture model clustering) with 87 of 645 factors in each dataset. We evaluated subtypes for (1) external validity (across datasets); (2) prognostic validity (predictive accuracy for 1-year mortality); and (3) genetic validity (UK Biobank), association with polygenic risk score (PRS) for heart failure-related traits (n=11), and single nucleotide polymorphisms (n=12).

FINDINGS

We included 188 800, 124 262, and 9573 individuals with incident heart failure from CPRD, THIN, and UK Biobank, respectively, between Jan 1, 1998, and Jan 1, 2018. After identifying five clusters, we labelled heart failure subtypes as (1) early onset, (2) late onset, (3) atrial fibrillation related, (4) metabolic, and (5) cardiometabolic. In the external validity analysis, subtypes were similar across datasets (c-statistics: THIN model in CPRD ranged from 0·79 [subtype 3] to 0·94 [subtype 1], and CPRD model in THIN ranged from 0·79 [subtype 1] to 0·92 [subtypes 2 and 5]). In the prognostic validity analysis, 1-year all-cause mortality after heart failure diagnosis (subtype 1 0·20 [95% CI 0·14-0·25], subtype 2 0·46 [0·43-0·49], subtype 3 0·61 [0·57-0·64], subtype 4 0·11 [0·07-0·16], and subtype 5 0·37 [0·32-0·41]) differed across subtypes in CPRD and THIN data, as did risk of non-fatal cardiovascular diseases and all-cause hospitalisation. In the genetic validity analysis the atrial fibrillation-related subtype showed associations with the related PRS. Late onset and cardiometabolic subtypes were the most similar and strongly associated with PRS for hypertension, myocardial infarction, and obesity (p<0·0009). We developed a prototype app for routine clinical use, which could enable evaluation of effectiveness and cost-effectiveness.

INTERPRETATION

Across four methods and three datasets, including genetic data, in the largest study of incident heart failure to date, we identified five machine learning-informed subtypes, which might inform aetiological research, clinical risk prediction, and the design of heart failure trials.

FUNDING

European Union Innovative Medicines Initiative-2.

The impact of heart failure therapy in patients with mildly reduced ejection fraction: a network meta-analysis

BACKGROUND

Recent heart failure (HF) guidelines have re-classified HF patients with left ventricular ejection fraction (LVEF) between 41% and 49% as HF with mildly reduced ejection fraction (HFmrEF). HFmrEF treatment is often considered a grey zone as no randomized controlled trials (RCTs) were conducted exclusively on these patients.

AIMS

A network meta-analysis (NMA) was performed to compare treatment effect of mineralocorticoid receptor antagonists (MRA), angiotensin receptor neprilysin inhibitor (ARNi), angiotensin receptor blockers (ARB), angiotensin-converting-enzyme inhibitors (ACEi), sodium-glucose cotransporter-2 inhibitors (SGLT2i), and beta-blockers (BB) in HFmrEF cardiovascular (CV) outcomes.

METHODS AND RESULTS

RCTs sub-analyses evaluating the efficacy of pharmacological treatment in HFmrEF patients were searched. Hazard ratios (HRs) and their variance were extracted from each RCT for (i) composite of CV death or HF hospitalizations, (ii) CV death, and (iii) HF hospitalizations. A random-effects NMA was performed to compare and assess the treatment efficiency. Six RCTs with subgroup analysis according to participants' ejection fraction, a patient-level pooled meta-analysis of two RCTs, and an individual patient-level analysis of eleven BB RCTs were included, totalling 7966 patients. To our primary endpoint, SGLT2i vs. placebo was the only comparison with significant results, with a 19% risk reduction in the composite of CV death or HF hospitalizations [HR 0.81, 95% confidence interval (CI) 0.67-0.98]. In HF hospitalizations, the impact of the pharmacological therapies was more notorious, and ARNi reduced in 40% the risk of HF hospitalizations (HR 0.60, 95% CI 0.39-0.92), SGLT2i in 26% (HR 0.74, 95% CI 0.59-0.93) and renin-angiotensin system inhibition (RASi) with ARB and ACEi in 28% (HR 0.72, 95% CI 0.53-0.98). Although BBs were globally less beneficial, they were the only class that supported a reduced risk of CV death (HR vs. placebo: 0.48, 95% CI 0.24-0.95). We did not observe a statistically significant difference in any comparison between active treatments. There was a sound reduction with ARNi on the primary endpoint (HR vs. BB: 0.81, 95% CI 0.47-1.41; HR vs. MRA 0.94, 95% CI 0.53-1.66) and on HF hospitalizations (HR vs. RASi 0.83, 95% CI 0.62-1.11; HR vs. SGLT2i 0.80, 95% CI 0.50-1.30).

CONCLUSIONS

In addition to SGLT2i, pharmacological treatment recommended for HF with reduced LVEF, namely, ARNi, MRA, and BB, can also be effective in HFmrEF. This NMA did not show significant superiority over any pharmacological class.

Longitudinal machine learning model for predicting systolic blood pressure in patients with heart failure

Objective

Systolic blood pressure (SBP) strongly indicates the prognosis of heart failure (HF) patients, as it is closely linked to the risk of death and readmission. Hence, maintaining control over blood pressure is a vital factor in the management of these patients. In order to determine significant variables associated with changes in SBP over time and assess the effectiveness of classical and machine learning models in predicting SBP, this study aimed to conduct a comparative analysis between the two.

Methods

This retrospective cohort study involved the analysis of data from 483 patients with HF who were admitted to Farshchian Heart Center located in Hamadan in the west of Iran, and hospitalized at least two times between October 2015 and July 2019. To predict SBP, we utilized a linear mixed-effects model (LMM) and mixed-effects least-square support vector regression (MLS-SVR). The effectiveness of both models was evaluated based on the mean absolute error and root mean squared error.

Results

The LMM analysis revealed that changes in SBP over time were significantly associated with sex, body mass index (BMI), sodium, time, and history of hypertension (P-value < 0.05). Furthermore, according to the MLS-SVR analysis, the four most important variables in predicting SBP were identified as history of hypertension, sodium, BMI, and triglyceride. In both the training and testing datasets, MLS-SVR outperformed LMM in terms of performance.

Conclusions

Based on our results, it appears that MLS-SVR has the potential to serve as a viable alternative to classical longitudinal models for predicting SBP in patients with HF.

Overcoming cohort heterogeneity for the prediction of subclinical cardiovascular disease risk

Cardiovascular disease remains a leading cause of mortality with an estimated half a billion people affected in 2019. However, detecting signals between specific pathophysiology and coronary plaque phenotypes using complex multi-omic discovery datasets remains challenging due to the diversity of individuals and their risk factors. Given the complex cohort heterogeneity present in those with coronary artery disease (CAD), we illustrate several different methods, both knowledge-guided and data-driven approaches, for identifying subcohorts of individuals with subclinical CAD and distinct metabolomic signatures. We then demonstrate that utilizing these subcohorts can improve the prediction of subclinical CAD and can facilitate the discovery of novel biomarkers of subclinical disease. Analyses acknowledging cohort heterogeneity through identifying and utilizing these subcohorts may be able to advance our understanding of CVD and provide more effective preventative treatments to reduce the burden of this disease in individuals and in society as a whole.

Identifying distinct clinical clusters in heart failure with mildly reduced ejection fraction

INTRODUCTION

Heart failure (HF) is a heterogeneous syndrome, and the specific sub-category HF with mildly reduced ejection fraction (EF) range (HFmrEF; 41-49% EF) is only recently recognized as a distinct entity. Cluster analysis can characterize heterogeneous patient populations and could serve as a stratification tool in clinical trials and for prognostication. The aim of this study was to identify clusters in HFmrEF and compare cluster prognosis.

METHODS AND RESULTS

Latent class analysis to cluster HFmrEF patients based on their characteristics was performed in the Swedish HF registry (n = 7316). Identified clusters were validated in a Dutch cross-sectional HF registry-based dataset CHECK-HF (n = 1536). In Sweden, mortality and hospitalisation across the clusters were compared using a Cox proportional hazard model, with a Fine-Gray sub-distribution for competing risks and adjustment for age and sex. Six clusters were discovered with the following prevalence and hazard ratio with 95% confidence intervals (HR [95%CI]) vs. cluster 1: 1) low-comorbidity (17%, reference), 2) ischaemic-male (13%, HR 0.9 [95% CI 0.7-1.1]), 3) atrial fibrillation (20%, HR 1.5 [95% CI 1.2-1.9]), 4) device/wide QRS (9%, HR 2.7 [95% CI 2.2-3.4]), 5) metabolic (19%, HR 3.1 [95% CI 2.5-3.7]) and 6) cardio-renal phenotype (22%, HR 2.8 [95% CI 2.2-3.6]). The cluster model was robust between both datasets.

CONCLUSION

We found robust clusters with potential clinical meaning and differences in mortality and hospitalisation. Our clustering model could be valuable as a clinical differentiation support and prognostic tool in clinical trial design.

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.

Clinical application of artificial intelligence algorithm for prediction of one-year mortality in heart failure patients

Risk prediction for heart failure (HF) using machine learning methods (MLM) has not yet been established at practical application levels in clinical settings. This study aimed to create a new risk prediction model for HF with a minimum number of predictor variables using MLM. We used two datasets of hospitalized HF patients: retrospective data for creating the model and prospectively registered data for model validation. Critical clinical events (CCEs) were defined as death or LV assist device implantation within 1 year from the discharge date. We randomly divided the retrospective data into training and testing datasets and created a risk prediction model based on the training dataset (MLM-risk model). The prediction model was validated using both the testing dataset and the prospectively registered data. Finally, we compared predictive power with published conventional risk models. In the patients with HF (n = 987), CCEs occurred in 142 patients. In the testing dataset, the substantial predictive power of the MLM-risk model was obtained (AUC = 0.87). We generated the model using 15 variables. Our MLM-risk model showed superior predictive power in the prospective study compared to conventional risk models such as the Seattle Heart Failure Model (c-statistics: 0.86 vs. 0.68, p < 0.05). Notably, the model with an input variable number (n = 5) has comparable predictive power for CCE with the model (variable number = 15). This study developed and validated a model with minimized variables to predict mortality more accurately in patients with HF, using a MLM, than the existing risk scores.

Phenotyping of Elderly Patients With Heart Failure Focused on Noncardiac Conditions: A Latent Class Analysis From a Multicenter Registry of Patients Hospitalized With Heart Failure

Background The burden of noncardiovascular conditions is becoming increasingly prevalent in patients with heart failure (HF). We aimed to identify novel phenogroups incorporating noncardiovascular conditions to facilitate understanding and risk stratification in elderly patients with HF. Methods and Results Data from a total of 1881 (61.2%) patients aged ≥65 years were extracted from a prospective multicenter registry of patients hospitalized for acute HF (N=3072). We constructed subgroups of patients with HF with preserved ejection fraction (HFpEF; N=826, 43.9%) and those with non-HFpEF (N=1055, 56.1%). Latent class analysis was performed in each subgroup using 17 variables focused on noncardiovascular conditions (including comorbidities, Clinical Frailty Scale, and Geriatric Nutritional Risk Index). The latent class analysis revealed 3 distinct clinical phenogroups in both HFpEF and non-HFpEF subgroups: (1) robust physical and nutritional status (Group 1: HFpEF, 41.2%; non-HFpEF, 46.0%); (2) multimorbid patients with renal impairment (Group 2: HFpEF, 40.8%; non-HFpEF, 41.9%); and (3) malnourished patients (Group 3: HFpEF, 18.0%; non-HFpEF, 12.1%). After multivariable adjustment, compared with Group 1, patients in Groups 2 and 3 had a higher risk for all-cause death over the 1-year postdischarge period (hazard ratio [HR], 2.79 [95% CI, 1.64-4.81] and HR, 2.73 [95% CI, 1.39-5.35] in HFpEF; HR, 1.96 [95% CI, 1.22-3.14] and HR, 2.97 [95% CI, 1.64-5.38] in non-HFpEF; respectively). Conclusions In elderly patients with HF, the phenomapping focused on incorporating noncardiovascular conditions identified 3 phenogroups, each representing distinct clinical outcomes, and the discrimination pattern was similar for both patients with HFpEF and non-HFpEF. This classification provides novel risk stratification and may aid in clinical decision making.

Predicting Stroke and Mortality in Mitral Regurgitation: A Machine Learning Approach

We hypothesized that an interpretable gradient boosting machine (GBM) model considering comorbidities, P-wave and echocardiographic measurements, can better predict mortality and cerebrovascular events in mitral regurgitation (MR). Patients from a tertiary center were analyzed. The GBM model was used as an interpretable statistical approach to identify the leading indicators of high-risk patients with either outcome of CVAs and all-cause mortality. A total of 706 patients were included. GBM analysis showed that age, systolic blood pressure, diastolic blood pressure, plasma albumin levels, mean P-wave duration (PWD), MR regurgitant volume, left ventricular ejection fraction (LVEF), left atrial dimension at end-systole (LADs), velocity-time integral (VTI) and effective regurgitant orifice were significant predictors of TIA/stroke. Age, sodium, urea and albumin levels, platelet count, mean PWD, LVEF, LADs, left ventricular dimension at end systole (LVDs) and VTI were significant predictors of all-cause mortality. The GBM demonstrates the best predictive performance in terms of precision, sensitivity c-statistic and F1-score compared to logistic regression, decision tree, random forest, support vector machine, and artificial neural networks. Gradient boosting model incorporating clinical data from different investigative modalities significantly improves risk prediction performance and identify key indicators for outcome prediction in MR.

Predicting Physiological Response in Heart Failure Management: A Graph Representation Learning Approach using Electronic Health Records

Heart failure management is challenging due to the complex and heterogenous nature of its pathophysiology which makes the conventional treatments based on the "one size fits all" ideology not suitable. Coupling the longitudinal medical data with novel deep learning and network-based analytics will enable identifying the distinct patient phenotypic characteristics to help individualize the treatment regimen through the accurate prediction of the physiological response. In this study, we develop a graph representation learning framework that integrates the heterogeneous clinical events in the electronic health records (EHR) as graph format data, in which the patient-specific patterns and features are naturally infused for personalized predictions of lab test response. The framework includes a novel Graph Transformer Network that is equipped with a self-attention mechanism to model the underlying spatial interdependencies among the clinical events characterizing the cardiac physiological interactions in the heart failure treatment and a graph neural network (GNN) layer to incorporate the explicit temporality of each clinical event, that would help summarize the therapeutic effects induced on the physiological variables, and subsequently on the patient's health status as the heart failure condition progresses over time. We introduce a global attention mask that is computed based on event co-occurrences and is aggregated across all patient records to enhance the guidance of neighbor selection in graph representation learning. We test the feasibility of our model through detailed quantitative and qualitative evaluations on observational EHR data.

Early Prediction in Classification of Cardiovascular Diseases with Machine Learning, Neuro-Fuzzy and Statistical Methods

Timely and accurate detection of cardiovascular diseases (CVDs) is critically important to minimize the risk of a myocardial infarction. Relations between factors of CVDs are complex, ill-defined and nonlinear, justifying the use of artificial intelligence tools. These tools aid in predicting and classifying CVDs. In this article, we propose a methodology using machine learning (ML) approaches to predict, classify and improve the diagnostic accuracy of CVDs, including support vector regression (SVR), multivariate adaptive regression splines, the M5Tree model and neural networks for the training process. Moreover, adaptive neuro-fuzzy and statistical approaches, nearest neighbor/naive Bayes classifiers and adaptive neuro-fuzzy inference system (ANFIS) are used to predict seventeen CVD risk factors. Mixed-data transformation and classification methods are employed for categorical and continuous variables predicting CVD risk. We compare our hybrid models and existing ML techniques on a CVD real dataset collected from a hospital. A sensitivity analysis is performed to determine the influence and exhibit the essential variables with regard to CVDs, such as the patient's age, cholesterol level and glucose level. Our results report that the proposed methodology outperformed well known statistical and ML approaches, showing their versatility and utility in CVD classification. Our investigation indicates that the prediction accuracy of ANFIS for the training process is 96.56%, followed by SVR with 91.95% prediction accuracy. Our study includes a comprehensive comparison of results obtained for the mentioned methods.

Cardiac surgery risk prediction using ensemble machine learning to incorporate legacy risk scores: A benchmarking study

Objective

The introduction of new clinical risk scores (e.g. European System for Cardiac Operative Risk Evaluation (EuroSCORE) II) superseding original scores (e.g. EuroSCORE I) with different variable sets typically result in disparate datasets due to high levels of missingness for new score variables prior to time of adoption. Little is known about the use of ensemble learning to incorporate disparate data from legacy scores. We tested the hypothesised that Homogenenous and Heterogeneous Machine Learning (ML) ensembles will have better performance than ensembles of Dynamic Model Averaging (DMA) for combining knowledge from EuroSCORE I legacy data with EuroSCORE II data to predict cardiac surgery risk.

Methods

Using the National Adult Cardiac Surgery Audit dataset, we trained 12 different base learner models, based on two different variable sets from either EuroSCORE I (LogES) or EuroScore II (ES II), partitioned by the time of score adoption (1996-2016 or 2012-2016) and evaluated on holdout set (2017-2019). These base learner models were ensembled using nine different combinations of six ML algorithms to produce homogeneous or heterogeneous ensembles. Performance was assessed using a consensus metric.

Results

Xgboost homogenous ensemble (HE) was the highest performing model (clinical effectiveness metric (CEM) 0.725) with area under the curve (AUC) (0.8327; 95% confidence interval (CI) 0.8323-0.8329) followed by Random Forest HE (CEM 0.723; AUC 0.8325; 95%CI 0.8320-0.8326). Across different heterogenous ensembles, significantly better performance was obtained by combining siloed datasets across time (CEM 0.720) than building ensembles of either 1996-2011 (t-test adjusted, p = 1.67×10-6) or 2012-2019 (t-test adjusted, p = 1.35×10-193) datasets alone.

Conclusions

Both homogenous and heterogenous ML ensembles performed significantly better than DMA ensemble of Bayesian Update models. Time-dependent ensemble combination of variables, having differing qualities according to time of score adoption, enabled previously siloed data to be combined, leading to increased power, clinical interpretability of variables and usage of data.

Clustering analysis of geriatric and acute characteristics in a cohort of very old patients on admission to ICU

PURPOSE

The biological and functional heterogeneity in very old patients constitutes a major challenge to prognostication and patient management in intensive care units (ICUs). In addition to the characteristics of acute diseases, geriatric conditions such as frailty, multimorbidity, cognitive impairment and functional disabilities were shown to influence outcome in that population. The goal of this study was to identify new and robust phenotypes based on the combination of these features to facilitate early outcome prediction.

METHODS

Patients aged 80 years old or older with and without limitations of life-sustaining treatment and with complete data were recruited from the VIP2 study for phenotyping and from the COVIP study for external validation. The sequential organ failure assessment (SOFA) score and its sub-scores taken on admission to ICU as well as demographic and geriatric patient characteristics were subjected to clustering analysis. Phenotypes were identified after repeated bootstrapping and clustering runs.

RESULTS

In patients from the VIP2 study without limitations of life-sustaining treatment (n = 1977), ICU mortality was 12% and 30-day mortality 19%. Seven phenotypes with distinct profiles of acute and geriatric characteristics were identified in that cohort. Phenotype-specific mortality within 30 days ranged from 3 to 57%. Among the patients assigned to a phenotype with pronounced geriatric features and high SOFA scores, 50% died in ICU and 57% within 30 days. Mortality differences between phenotypes were confirmed in the COVIP study cohort (n = 280).

CONCLUSIONS

Phenotyping of very old patients on admission to ICU revealed new phenotypes with different mortality and potential need for anticipatory intervention.

Leveraging Machine Learning Techniques to Forecast Chronic Total Occlusion before Coronary Angiography

BACKGROUND

Chronic total occlusion (CTO) remains the most challenging procedure in coronary artery disease (CAD) for interventional cardiology. Although some clinical risk factors for CAD have been identified, there is no personalized prognosis test available to confidently identify patients at high or low risk for CTO CAD. This investigation aimed to use a machine learning algorithm for clinical features from clinical routine to develop a precision medicine tool to predict CTO before CAG.

METHODS

Data from 1473 CAD patients were obtained, including 1105 in the training cohort and 368 in the testing cohort. The baseline clinical characteristics were collected. Univariate and multivariate logistic regression analyses were conducted to identify independent risk factors that impact the diagnosis of CTO. A CTO predicting model was established and validated based on the independent predictors using a machine learning algorithm. The area under the curve (AUC) was used to evaluate the model.

RESULTS

The CTO prediction model was developed with the training cohort using the machine learning algorithm. Eight variables were confirmed as 'important': gender (male), neutrophil percentage (NE%), hematocrit (HCT), total cholesterol (TC), high-density lipoprotein cholesterol (HDL), ejection fraction (EF), troponin I (TnI), and N-terminal pro-B-type natriuretic peptide (NT-proBNP). The model achieved good concordance indices of 0.724 and 0.719 in the training and testing cohorts, respectively.

CONCLUSIONS

An easy-to-use tool to predict CTO in patients with CAD was developed and validated. More research with larger cohorts are warranted to improve the prediction model, which can support clinician decisions on the early discerning CTO in CAD patients.

Ensemble Technique Coupled with Deep Transfer Learning Framework for Automatic Detection of Tuberculosis from Chest X-ray Radiographs

Tuberculosis (TB) is an infectious disease affecting humans' lungs and is currently ranked the 13th leading cause of death globally. Due to advancements in technology and the availability of medical datasets, automatic analysis and classification of chest X-rays (CXRs) into TB and non-TB can be a reliable alternative for early TB screening. We propose an automatic TB detection system using advanced deep learning (DL) models. A substantial part of a CXR image is dark, with no relevant information for diagnosis and potentially confusing DL models. In this work, the U-Net model extracts the region of interest from CXRs and the segmented images are fed to the DL models for feature extraction. Eight different convolutional neural networks (CNN) models are employed in our experiments, and their classification performance is compared based on three publicly available CXR datasets. The U-Net model achieves segmentation accuracy of 98.58%, intersection over union (IoU) of 93.10, and a Dice coefficient score of 96.50. Our proposed stacked ensemble algorithm performed better by achieving accuracy, sensitivity, and specificity values of 98.38%, 98.89%, and 98.70%, respectively. Experimental results confirm that segmented lung CXR images with ensemble learning produce a better result than un-segmented lung CXR images.

Machine Learning for the Prevalence and Severity of Coronary Artery Calcification in Nondialysis Chronic Kidney Disease Patients: A Chinese Large Cohort Study

PURPOSE

This study sought to determine whether machine learning (ML) can be used to better identify the risk factors and establish the prediction models for the prevalence and severity of coronary artery calcification (CAC) in nondialysis chronic kidney disease (CKD) patients and compare the performance of distinctive ML models with conventional logistic regression (LR) model.

MATERIALS AND METHODS

In all, 3701 Chinese nondialysis CKD patients undergoing noncontrast cardiac computed tomography (CT) scanning were enrolled from November 2013 to December 2017. CAC score derived from the cardiac CT was calculated with the calcium scoring software and was used to assess and stratify the prevalence and severity of CAC. Four ML models (LR, random forest, support vector machine, and k-nearest neighbor) and the corresponding feature ranks were conducted. The model that incorporated the independent predictors was shown as the receiver-operating characteristic (ROC) curve. Area under the curve (AUC) was used to present the prediction value. ML model performance was compared with the traditional LR model using pairwise comparisons of AUCs.

RESULTS

Of the 3701 patients, 943 (25.5%) patients had CAC. Of the 943 patients with CAC, 764 patients (20.6%) and 179 patients (4.8%) had an Agatston CAC score of 1 to 300 and ≥300, respectively. The primary cohort and the independent validation cohort comprised 2957 patients and 744 patients, respectively. For the prevalence of CAC, the AUCs of ML models were from 0.78 to 0.82 in the training data set and the internal validation cohort. For the severity of CAC, the AUCs of the 4 ML models were from 0.67 to 0.70 in the training data set and from 0.53 to 0.70 in the internal validation cohort. For the prevalence of CAC, the AUC was 0.80 (95% confidence interval [CI]: 0.77-0.83) for ML (LR) versus 0.80 (95% CI: 0.77-0.83) for the traditional LR model ( P =0.2533). For the severity of CAC, the AUC was 0.70 (95% CI: 0.63-0.77) for ML (LR) versus 0.70 (95% CI: 0.63-0.77) for traditional LR model ( P =0.982).

CONCLUSIONS

This study constructed prediction models for the presence and severity of CAC based on Agatston scores derived from noncontrast cardiac CT scanning in nondialysis CKD patients using ML, and showed ML LR had the best performance.