Using Deep-Learning Algorithms to Simultaneously Identify Right and Left Ventricular Dysfunction From the Electrocardiogram

Prediction of adverse cardiovascular events in children using artificial intelligence-based electrocardiogram

BACKGROUND

Convolutional neural networks (CNNs) have emerged as a novel method for evaluating heart failure (HF) in adult electrocardiograms (ECGs). However, such CNNs are not applicable to pediatric HF, where abnormal anatomy of congenital heart defects plays an important role. ECG-based CNNs reflecting neurohormonal activation (NHA) may be a useful marker of pediatric HF. This study aimed to develop and validate an ECG-derived marker of pediatric HF that reflects the risk of future cardiovascular events.

METHODS

Based on 21,378 ECGs from 8324 children, a CNN was trained using B-type natriuretic peptide (BNP) and the occurrence of major adverse cardiovascular events (MACEs). The output of the model, or the electrical heart failure indicator (EHFI), was compared with the BNP regarding its ability to predict MACEs in 813 ECGs from 295 children.

RESULTS

EHFI achieved a better area under the curve than BNP in predicting MACEs within 180 days (0.826 versus 0.691, p = 0.03). On Cox univariable analyses, both EHFI and BNP were significantly associated with MACE (log10 EHFI: hazard ratio [HR] = 16.5, p < 0.005 and log10 BNP: HR = 4.4, p < 0.005). The time-dependent average precisions of EHFI in predicting MACEs were 32.4%-67.9% and 1.6-7.5-fold higher than those of BNP in the early period. Additionally, the MACE rate increased monotonically with EHFI, whereas the rate peaked at approximately 100 pg/mL of BNP and decreased in the higher range.

CONCLUSIONS

ECG-derived CNN is a novel marker of HF with different prognostic potential from BNP. CNN-based ECG analysis may provide a new guide for assessing pediatric HF.

Artificial intelligence for cardiovascular disease risk assessment in personalised framework: a scoping review

Background

The field of precision medicine endeavors to transform the healthcare industry by advancing individualised strategies for diagnosis, treatment modalities, and predictive assessments. This is achieved by utilizing extensive multidimensional biological datasets encompassing diverse components, such as an individual's genetic makeup, functional attributes, and environmental influences. Artificial intelligence (AI) systems, namely machine learning (ML) and deep learning (DL), have exhibited remarkable efficacy in predicting the potential occurrence of specific cancers and cardiovascular diseases (CVD).

Methods

We conducted a comprehensive scoping review guided by the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. Our search strategy involved combining key terms related to CVD and AI using the Boolean operator AND. In August 2023, we conducted an extensive search across reputable scholarly databases including Google Scholar, PubMed, IEEE Xplore, ScienceDirect, Web of Science, and arXiv to gather relevant academic literature on personalised medicine for CVD. Subsequently, in January 2024, we extended our search to include internet search engines such as Google and various CVD websites. These searches were further updated in March 2024. Additionally, we reviewed the reference lists of the final selected research articles to identify any additional relevant literature.

Findings

A total of 2307 records were identified during the process of conducting the study, consisting of 564 entries from external sites like arXiv and 1743 records found through database searching. After 430 duplicate articles were eliminated, 1877 items that remained were screened for relevancy. In this stage, 1241 articles remained for additional review after 158 irrelevant articles and 478 articles with insufficient data were removed. 355 articles were eliminated for being inaccessible, 726 for being written in a language other than English, and 281 for not having undergone peer review. Consequently, 121 studies were deemed suitable for inclusion in the qualitative synthesis. At the intersection of CVD, AI, and precision medicine, we found important scientific findings in our scoping review. Intricate pattern extraction from large, complicated genetic datasets is a skill that AI algorithms excel at, allowing for accurate disease diagnosis and CVD risk prediction. Furthermore, these investigations have uncovered unique genetic biomarkers linked to CVD, providing insight into the workings of the disease and possible treatment avenues. The construction of more precise predictive models and personalised treatment plans based on the genetic profiles of individual patients has been made possible by the revolutionary advancement of CVD risk assessment through the integration of AI and genomics.

Interpretation

The systematic methodology employed ensured the thorough examination of available literature and the inclusion of relevant studies, contributing to the robustness and reliability of the study's findings. Our analysis stresses a crucial point in terms of the adaptability and versatility of AI solutions. AI algorithms designed in non-CVD domains such as in oncology, often include ideas and tactics that might be modified to address cardiovascular problems.

Funding

No funding received.

Deep neural networks detect regional wall motion abnormalities and preclinical cardiovascular disease from 12-lead ECGs

Background

Identifying regional wall motion abnormalities (RWMAs) is critical for diagnosing and risk stratifying patients with cardiovascular disease, particularly ischemic heart disease. We hypothesized that a deep neural network could accurately identify patients with regional wall motion abnormalities from a readily available standard 12-lead electrocardiogram (ECG).

Methods

This observational, retrospective study included patients who were treated at Beth Israel Deaconess Medical Center and had an ECG and echocardiogram performed within 14 days of each other between 2008 and 2019. We trained a convolutional neural network to detect the presence of RWMAs, qualitative global right ventricular (RV) hypokinesis, and varying degrees of left ventricular dysfunction (left ventricular ejection fraction [LVEF] ≤50%, LVEF ≤40%, and LVEF ≤35%) identified by echocardiography, using ECG data alone. Patients were randomly split into development (80%) and test sets (20%). Model performance was assessed using area under the receiver operating characteristic curve (AUC). Cox proportional hazard models adjusted for age and sex were performed to estimate the risk of future acute coronary events.

Results

The development set consisted of 19,837 patients (mean age 66.7±16.4; 46.7% female) and the test set comprised of 4,953 patients (mean age 67.5±15.8 years; 46.5% female). On the test dataset, the model accurately identified the presence of RWMA, RV hypokinesis, LVEF ≤50%, LVEF ≤40%, and LVEF ≤35% with AUCs of 0.87 (95% CI 0.858-0.882), 0.888 (95% CI 0.878-0.899), 0.923 (95% CI 0.914-0.933), 0.93 (95% CI 0.921-0.939), and 0.876 (95% CI 0.858-0.896), respectively. Among patients with normal biventricular function at the time of the index ECG, those classified as having RMWA by the model were 3 times the risk (age- and sex-adjusted hazard ratio, 2.8; 95% CI 1.9-3.9) for future acute coronary events compared to those classified as negative.

Conclusions

We demonstrate that a deep neural network can help identify regional wall motion abnormalities and reduced LV function from a 12-lead ECG and could potentially be used as a screening tool for triaging patients who need either initial or repeat echocardiographic imaging.

Energy wavelet signal processed ECG and standard 12 lead ECG: Diagnosis of early diastolic dysfunction

BACKGROUND

Left ventricular (LV) diastolic dysfunction (LVDD) is the result of impaired LV relaxation and identifies those at risk of developing heart failure. Echocardiography has been used as the gold standard to identify early LVDD. The signal processed electrocardiogram (hsECG) has demonstrated effectiveness to detect early LVDD. Whether or not the standard 12‑lead electrocardiogram (ECG) can accurately predict early LVDD is not known.

METHODS

A standard 12‑lead ECG including signal processing (hsECG) was performed in 569 patients. Patients with atrial fibrillation, bundle branch block, pre-excitation, left ventricular hypertrophy or known cardiovascular disease were excluded, leaving 464 examinations for analysis. Early LVDD was diagnosed by established methods using echocardiography. Repolarization abnormalities (T wave discordance) in V1, V6, I and aVL and the hsECG were compared to the echocardiographic findings to establish diagnostic accuracy.

RESULTS

A total of 84 (18.1%) patients were diagnosed with early LVDD. A combination of a borderline or abnormal finding on the hsECG produced the best diagnostic model (sensitivity 84.5%, specificity 47.9%). The best performing ECG lead was V1 with a sensitivity of 38.1% and specificity of 92.1%. Regression analysis demonstrated increasing age and V1 to be predictive of LVDD.

CONCLUSIONS

The hsECG displayed reasonable ability to detect early LVDD. Other than V1, repolarization abnormalities on the standard 12‑lead ECG did not. While lead V1 showed promise in detecting LVDD, whether this or any other simple ECG variable can predict future LVDD would be of further interest.

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.

Myocardial scar and left ventricular ejection fraction classification for electrocardiography image using multi-task deep learning

Myocardial scar (MS) and left ventricular ejection fraction (LVEF) are vital cardiovascular parameters, conventionally determined using cardiac magnetic resonance (CMR). However, given the high cost and limited availability of CMR in resource-constrained settings, electrocardiograms (ECGs) are a cost-effective alternative. We developed computer vision-based multi-task deep learning models to analyze 12-lead ECG 2D images, predicting MS and LVEF < 50%. Our dataset comprises 14,052 ECGs with clinical features, utilizing ground truth labels from CMR. Our top-performing model achieved AUC values of 0.838 (95% CI 0.812-0.862) for MS and 0.939 (95% CI 0.921-0.954) for LVEF < 50% classification, outperforming cardiologists. Moreover, MS predictions in a prevalence-specific test dataset recorded an AUC of 0.812 (95% CI 0.810-0.814). Extracted 1D signals from ECG images yielded inferior performance, compared to the 2D approach. In conclusion, our results demonstrate the potential of computer-based MS and LVEF < 50% classification from ECG scan images in clinical screening offering a cost-effective alternative to CMR.

Preliminary Evidence of the Use of Generative AI in Health Care Clinical Services: Systematic Narrative Review

BACKGROUND

Generative artificial intelligence tools and applications (GenAI) are being increasingly used in health care. Physicians, specialists, and other providers have started primarily using GenAI as an aid or tool to gather knowledge, provide information, train, or generate suggestive dialogue between physicians and patients or between physicians and patients' families or friends. However, unless the use of GenAI is oriented to be helpful in clinical service encounters that can improve the accuracy of diagnosis, treatment, and patient outcomes, the expected potential will not be achieved. As adoption continues, it is essential to validate the effectiveness of the infusion of GenAI as an intelligent technology in service encounters to understand the gap in actual clinical service use of GenAI.

OBJECTIVE

This study synthesizes preliminary evidence on how GenAI assists, guides, and automates clinical service rendering and encounters in health care The review scope was limited to articles published in peer-reviewed medical journals.

METHODS

We screened and selected 0.38% (161/42,459) of articles published between January 1, 2020, and May 31, 2023, identified from PubMed. We followed the protocols outlined in the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to select highly relevant studies with at least 1 element on clinical use, evaluation, and validation to provide evidence of GenAI use in clinical services. The articles were classified based on their relevance to clinical service functions or activities using the descriptive and analytical information presented in the articles.

RESULTS

Of 161 articles, 141 (87.6%) reported using GenAI to assist services through knowledge access, collation, and filtering. GenAI was used for disease detection (19/161, 11.8%), diagnosis (14/161, 8.7%), and screening processes (12/161, 7.5%) in the areas of radiology (17/161, 10.6%), cardiology (12/161, 7.5%), gastrointestinal medicine (4/161, 2.5%), and diabetes (6/161, 3.7%). The literature synthesis in this study suggests that GenAI is mainly used for diagnostic processes, improvement of diagnosis accuracy, and screening and diagnostic purposes using knowledge access. Although this solves the problem of knowledge access and may improve diagnostic accuracy, it is oriented toward higher value creation in health care.

CONCLUSIONS

GenAI informs rather than assisting or automating clinical service functions in health care. There is potential in clinical service, but it has yet to be actualized for GenAI. More clinical service-level evidence that GenAI is used to streamline some functions or provides more automated help than only information retrieval is needed. To transform health care as purported, more studies related to GenAI applications must automate and guide human-performed services and keep up with the optimism that forward-thinking health care organizations will take advantage of GenAI.

Pediatric ECG-Based Deep Learning to Predict Left Ventricular Dysfunction and Remodeling

BACKGROUND

Artificial intelligence-enhanced ECG analysis shows promise to detect ventricular dysfunction and remodeling in adult populations. However, its application to pediatric populations remains underexplored.

METHODS

A convolutional neural network was trained on paired ECG-echocardiograms (≤2 days apart) from patients ≤18 years of age without major congenital heart disease to detect human expert-classified greater than mild left ventricular (LV) dysfunction, hypertrophy, and dilation (individually and as a composite outcome). Model performance was evaluated on single ECG-echocardiogram pairs per patient at Boston Children's Hospital and externally at Mount Sinai Hospital using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC).

RESULTS

The training cohort comprised 92 377 ECG-echocardiogram pairs (46 261 patients; median age, 8.2 years). Test groups included internal testing (12 631 patients; median age, 8.8 years; 4.6% composite outcomes), emergency department (2830 patients; median age, 7.7 years; 10.0% composite outcomes), and external validation (5088 patients; median age, 4.3 years; 6.1% composite outcomes) cohorts. Model performance was similar on internal test and emergency department cohorts, with model predictions of LV hypertrophy outperforming the pediatric cardiologist expert benchmark. Adding age and sex to the model added no benefit to model performance. When using quantitative outcome cutoffs, model performance was similar between internal testing (composite outcome: AUROC, 0.88, AUPRC, 0.43; LV dysfunction: AUROC, 0.92, AUPRC, 0.23; LV hypertrophy: AUROC, 0.88, AUPRC, 0.28; LV dilation: AUROC, 0.91, AUPRC, 0.47) and external validation (composite outcome: AUROC, 0.86, AUPRC, 0.39; LV dysfunction: AUROC, 0.94, AUPRC, 0.32; LV hypertrophy: AUROC, 0.84, AUPRC, 0.25; LV dilation: AUROC, 0.87, AUPRC, 0.33), with composite outcome negative predictive values of 99.0% and 99.2%, respectively. Saliency mapping highlighted ECG components that influenced model predictions (precordial QRS complexes for all outcomes; T waves for LV dysfunction). High-risk ECG features include lateral T-wave inversion (LV dysfunction), deep S waves in V1 and V2 and tall R waves in V6 (LV hypertrophy), and tall R waves in V4 through V6 (LV dilation).

CONCLUSIONS

This externally validated algorithm shows promise to inexpensively screen for LV dysfunction and remodeling in children, which may facilitate improved access to care by democratizing the expertise of pediatric cardiologists.

Artificial intelligence-based identification of left ventricular systolic dysfunction from 12-lead electrocardiograms: external validation and advanced application of an existing model

Aims

The diagnostic application of artificial intelligence (AI)-based models to detect cardiovascular diseases from electrocardiograms (ECGs) evolves, and promising results were reported. However, external validation is not available for all published algorithms. The aim of this study was to validate an existing algorithm for the detection of left ventricular systolic dysfunction (LVSD) from 12-lead ECGs.

Methods and results

Patients with digitalized data pairs of 12-lead ECGs and echocardiography (at intervals of ≤7 days) were retrospectively selected from the Heart Center Leipzig ECG and electronic medical records databases. A previously developed AI-based model was applied to ECGs and calculated probabilities for LVSD. The area under the receiver operating characteristic curve (AUROC) was computed overall and in cohorts stratified for baseline and ECG characteristics. Repeated echocardiography studies recorded ≥3 months after index diagnostics were used for follow-up (FU) analysis. At baseline, 42 291 ECG-echocardiography pairs were analysed, and AUROC for LVSD detection was 0.88. Sensitivity and specificity were 82% and 77% for the optimal LVSD probability cut-off based on Youden's J. AUROCs were lower in ECG subgroups with tachycardia, atrial fibrillation, and wide QRS complexes. In patients without LVSD at baseline and available FU, model-generated high probability for LVSD was associated with a four-fold increased risk of developing LVSD during FU.

Conclusion

We provide the external validation of an existing AI-based ECG-analysing model for the detection of LVSD with robust performance metrics. The association of false positive LVSD screenings at baseline with a deterioration of ventricular function during FU deserves a further evaluation in prospective trials.

An Artificial Intelligence Analysis of Electrocardiograms for the Clinical Diagnosis of Cardiovascular Diseases: A Narrative Review

Artificial intelligence (AI) applied to cardiovascular disease (CVD) is enjoying great success in the field of scientific research. Electrocardiograms (ECGs) are the cornerstone form of examination in cardiology and are the most widely used diagnostic tool because they are widely available, inexpensive, and fast. Applications of AI to ECGs, especially deep learning (DL) methods using convolutional neural networks (CNNs), have been developed in many fields of cardiology in recent years. Deep learning methods provide valuable support for rapid ECG interpretation, demonstrating a diagnostic capability overlapping with specialists in the diagnosis of CVD by a classical analysis of macroscopic changes in the ECG trace. Through photoplethysmography, wearable devices can obtain single-derivative ECGs for the recognition of AI-diagnosed arrhythmias. In addition, CNNs have been developed that recognize no macroscopic electrocardiographic changes and can predict, from a 12-lead ECG, atrial fibrillation, even from sinus rhythm; left and right ventricular function; hypertrophic cardiomyopathy; acute coronary syndromes; or aortic stenosis. The fields of application are many, but numerous are the limitations, mainly associated with the reliability of the acquired data, an inability to verify black box processes, and medico-legal and ethical problems. The challenge of modern medicine is to recognize the limitations of AI and overcome them.

Quantitative Prediction of Right Ventricular Size and Function From the ECG

BACKGROUND

Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep learning-enabled ECG analysis for estimation of right ventricular (RV) size or function is unexplored.

METHODS AND RESULTS

We trained a deep learning-ECG model to predict RV dilation (RVEDV >120 mL/m2), RV dysfunction (RVEF ≤40%), and numerical RVEDV and RVEF from a 12-lead ECG paired with reference-standard cardiac magnetic resonance imaging volumetric measurements in UK Biobank (UKBB; n=42 938). We fine-tuned in a multicenter health system (MSHoriginal [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance with area under the receiver operating characteristic curve for categorical and mean absolute error for continuous measures overall and in key subgroups. We assessed the association of RVEF prediction with transplant-free survival with Cox proportional hazards models. The prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.91/0.81/0.92, respectively. MSHoriginal mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m2. The performance of the RVEF model was similar in key subgroups including with and without left ventricular dysfunction. Over a median follow-up of 2.3 years, predicted RVEF was associated with adjusted transplant-free survival (hazard ratio, 1.40 for each 10% decrease; P=0.031).

CONCLUSIONS

Deep learning-ECG analysis can identify significant cardiac magnetic resonance imaging RV dysfunction and dilation with good performance. Predicted RVEF is associated with clinical outcome.

Electrocardiogram Interpretation Using Artificial Intelligence: Diagnosis of Cardiac and Extracardiac Pathologic Conditions. How Far Has Machine Learning Reached?

Artificial intelligence (AI) is already widely used in different fields of medicine, making possible the integration of the paraclinical exams with the clinical findings in patients, for a more accurate and rapid diagnosis and treatment decision. The electrocardiogram remains one of the most important, fastest, cheapest, and noninvasive methods of diagnosis in cardiology, despite the rapid development and progression of the technology. Even if studied a long time ago, it still has a lot of less understood features that, with a better understanding, can give more clues to a correct and prompt diagnosis in a short time. The use of AI in the interpretation of the ECG improved the accuracy and the time to diagnosis in different cardiovascular diseases, and more than this, explaining the decision to make AI diagnosis improved the human understanding of the different features of the ECG that might be considered for a more accurate diagnosis. The purpose of this article is to provide an overview of the most recently published articles about the use of AI in ECG interpretation.

Cardiac disease prediction using AI algorithms with SelectKBest

Atherosclerotic cardiovascular disease (ASCVD), which includes coronary heart disease (CHD) and ischemic stroke, is the leading cause of mortality globally. According to the European Society of Cardiology (ESC), 26 million people worldwide have heart disease, with 3.6 million diagnosed each year. Early detection of heart disease will aid in lowering the mortality rate. The lack of diversity in training data and the difficulty in comprehending the findings of complicated AI models are the key issues in current research for heart disease prediction using artificial intelligence. To overcome this, in this paper, cardiac disease prediction using AI algorithms with SelectKBest has been proposed. Features are standardized, balanced, and selected using the StandardScaler, SMOTE, and SelectKBest techniques. Machine learning models such as support vector machine (SVM), K-nearest neighbor(KNN), decision tree (DT), logistic regression (LR), adaptive boosting (AB), naive Bayes (NB), random forest (RF), and extra tree (ET) and deep learning models such as vanilla long short-term memory (LSTM), bidirectional long short-term memory (LSTM), stacked long short-term memory (LSTM), and deep neural network (DNN) are assessed using Alizadeh Sani, combined (Cleveland, Hungarian, Switzerland, Long Beach VA, and Stalog), and Pakistan heart failure datasets. As a result of the evaluation, the proposed deep neural network (DNN) with SelectKBest predicted heart disease in a promising way. The prediction rate of unweighted accuracy of 99% on Alizadeh Sani, 98% on combined, and 97% on Pakistan are gained in tenfold cross-validation experiments. The suggested approach can be utilized to diagnose heart disease in its early stages.

Implications of the Use of Artificial Intelligence Predictive Models in Health Care Settings : A Simulation Study

BACKGROUND

Substantial effort has been directed toward demonstrating uses of predictive models in health care. However, implementation of these models into clinical practice may influence patient outcomes, which in turn are captured in electronic health record data. As a result, deployed models may affect the predictive ability of current and future models.

OBJECTIVE

To estimate changes in predictive model performance with use through 3 common scenarios: model retraining, sequentially implementing 1 model after another, and intervening in response to a model when 2 are simultaneously implemented.

DESIGN

Simulation of model implementation and use in critical care settings at various levels of intervention effectiveness and clinician adherence. Models were either trained or retrained after simulated implementation.

SETTING

Admissions to the intensive care unit (ICU) at Mount Sinai Health System (New York, New York) and Beth Israel Deaconess Medical Center (Boston, Massachusetts).

PATIENTS

130 000 critical care admissions across both health systems.

INTERVENTION

Across 3 scenarios, interventions were simulated at varying levels of clinician adherence and effectiveness.

MEASUREMENTS

Statistical measures of performance, including threshold-independent (area under the curve) and threshold-dependent measures.

RESULTS

At fixed 90% sensitivity, in scenario 1 a mortality prediction model lost 9% to 39% specificity after retraining once and in scenario 2 a mortality prediction model lost 8% to 15% specificity when created after the implementation of an acute kidney injury (AKI) prediction model; in scenario 3, models for AKI and mortality prediction implemented simultaneously, each led to reduced effective accuracy of the other by 1% to 28%.

LIMITATIONS

In real-world practice, the effectiveness of and adherence to model-based recommendations are rarely known in advance. Only binary classifiers for tabular ICU admissions data were simulated.

CONCLUSION

In simulated ICU settings, a universally effective model-updating approach for maintaining model performance does not seem to exist. Model use may have to be recorded to maintain viability of predictive modeling.

PRIMARY FUNDING SOURCE

National Center for Advancing Translational Sciences.

Deep Learning on Electrocardiograms for Prediction of In-hospital Intradialytic Hypotension in Patients with ESKD

Intradialytic hypotension is common in patients who are on hemodialysis. We applied deep learning techniques to ECGs to predict patients at risk of IDH. The performance of the model was good with an AUC of 0.763 and AUPRC of 0.35.

Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images

BACKGROUND

Left ventricular (LV) systolic dysfunction is associated with a >8-fold increased risk of heart failure and a 2-fold risk of premature death. The use of ECG signals in screening for LV systolic dysfunction is limited by their availability to clinicians. We developed a novel deep learning-based approach that can use ECG images for the screening of LV systolic dysfunction.

METHODS

Using 12-lead ECGs plotted in multiple different formats, and corresponding echocardiographic data recorded within 15 days from the Yale New Haven Hospital between 2015 and 2021, we developed a convolutional neural network algorithm to detect an LV ejection fraction <40%. The model was validated within clinical settings at Yale New Haven Hospital and externally on ECG images from Cedars Sinai Medical Center in Los Angeles, CA; Lake Regional Hospital in Osage Beach, MO; Memorial Hermann Southeast Hospital in Houston, TX; and Methodist Cardiology Clinic of San Antonio, TX. In addition, it was validated in the prospective Brazilian Longitudinal Study of Adult Health. Gradient-weighted class activation mapping was used to localize class-discriminating signals on ECG images.

RESULTS

Overall, 385 601 ECGs with paired echocardiograms were used for model development. The model demonstrated high discrimination across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROCs], 0.91; area under precision-recall curve [AUPRC], 0.55); and external sets of ECG images from Cedars Sinai (AUROC, 0.90 and AUPRC, 0.53), outpatient Yale New Haven Hospital clinics (AUROC, 0.94 and AUPRC, 0.77), Lake Regional Hospital (AUROC, 0.90 and AUPRC, 0.88), Memorial Hermann Southeast Hospital (AUROC, 0.91 and AUPRC 0.88), Methodist Cardiology Clinic (AUROC, 0.90 and AUPRC, 0.74), and Brazilian Longitudinal Study of Adult Health cohort (AUROC, 0.95 and AUPRC, 0.45). An ECG suggestive of LV systolic dysfunction portended >27-fold higher odds of LV systolic dysfunction on transthoracic echocardiogram (odds ratio, 27.5 [95% CI, 22.3-33.9] in the held-out set). Class-discriminative patterns localized to the anterior and anteroseptal leads (V2 and V3), corresponding to the left ventricle regardless of the ECG layout. A positive ECG screen in individuals with an LV ejection fraction ≥40% at the time of initial assessment was associated with a 3.9-fold increased risk of developing incident LV systolic dysfunction in the future (hazard ratio, 3.9 [95% CI, 3.3-4.7]; median follow-up, 3.2 years).

CONCLUSIONS

We developed and externally validated a deep learning model that identifies LV systolic dysfunction from ECG images. This approach represents an automated and accessible screening strategy for LV systolic dysfunction, particularly in low-resource settings.

Heart failure diagnosis in the general community - Who, how and when? A clinical consensus statement of the Heart Failure Association (HFA) of the European Society of Cardiology (ESC)

A significant proportion of patients experience delays in the diagnosis of heart failure due to the non-specific signs and symptoms of the syndrome. Diagnostic tools such as measurement of natriuretic peptide concentrations are fundamentally important when screening for heart failure, yet are frequently under-utilized. This clinical consensus statement provides a diagnostic framework for general practitioners and non-cardiology community-based physicians to recognize, investigate and risk-stratify patients presenting in the community with possible heart failure.

Artificial intelligence in cardiovascular diseases: diagnostic and therapeutic perspectives

Artificial intelligence (AI), the technique of extracting information from complex database using sophisticated computer algorithms, has incorporated itself in medical field. AI techniques have shown the potential to accelerate the progression of diagnosis and treatment of cardiovascular diseases (CVDs), including heart failure, atrial fibrillation, valvular heart disease, hypertrophic cardiomyopathy, congenital heart disease and so on. In clinical scenario, AI have been proved to apply well in CVD diagnosis, enhance effectiveness of auxiliary tools, disease stratification and typing, and outcome prediction. Deeply developed to capture subtle connections from massive amounts of healthcare data, recent AI algorithms are expected to handle even more complex tasks than traditional methods. The aim of this review is to introduce current applications of AI in CVDs, which may allow clinicians who have limited expertise of computer science to better understand the frontier of the subject and put AI algorithms into clinical practice.

The use of artificial intelligence for delivery of essential health services across WHO regions: a scoping review

Background

Artificial intelligence (AI) is a broad outlet of computer science aimed at constructing machines capable of simulating and performing tasks usually done by human beings. The aim of this scoping review is to map existing evidence on the use of AI in the delivery of medical care.

Methods

We searched PubMed and Scopus in March 2022, screened identified records for eligibility, assessed full texts of potentially eligible publications, and extracted data from included studies in duplicate, resolving differences through discussion, arbitration, and consensus. We then conducted a narrative synthesis of extracted data.

Results

Several AI methods have been used to detect, diagnose, classify, manage, treat, and monitor the prognosis of various health issues. These AI models have been used in various health conditions, including communicable diseases, non-communicable diseases, and mental health.

Conclusions

Presently available evidence shows that AI models, predominantly deep learning, and machine learning, can significantly advance medical care delivery regarding the detection, diagnosis, management, and monitoring the prognosis of different illnesses.

Successes and challenges of artificial intelligence in cardiology

In the past decades there has been a substantial evolution in data management and data processing techniques. New data architectures made analysis of big data feasible, healthcare is orienting towards personalized medicine with digital health initiatives, and artificial intelligence (AI) is becoming of increasing importance. Despite being a trendy research topic, only very few applications reach the stage where they are implemented in clinical practice. This review provides an overview of current methodologies and identifies clinical and organizational challenges for AI in healthcare.

Electrocardiogram to Determine Mitral and Aortic Valve Opening and Closure

PURPOSE

Knowledge of the timing of cardiac valve opening and closing is important in cardiac physiology. The relationship between valve motion and electrocardiogram (ECG) is often assumed, however is not clearly defined. Here we investigate the accuracy of cardiac valve timing estimated using only the ECG, compared to Doppler echocardiography (DE) flow imaging as the gold standard.

METHODS

DE was obtained in 37 patients with simultaneous ECG recording. ECG was digitally processed and identifiable features (QRS, T, P waves) were examined as potential reference points to determine opening and closure of aortic and mitral valves, as compared to DE outflow and inflow measurement. Timing offset of the cardiac valves opening and closure between ECG features and DE was measured from derivation set (n = 19). The obtained mean offset in combination with the ECG features model was then evaluated on a validation set (n = 18). Using the same approach, additional measurement was also done for the right sided valves.

RESULTS

From the derivation set, we found a fixed offset of 22 ± 9 ms, 2 ± 13 ms, 90 ± 26 ms, and - 2 ± - 27 ms when comparing S to aortic valve opening, Tend to aortic valve closure, Tend to mitral valve opening, and R to mitral valve closure respectively. Application of this model to the validation set showed good estimation of aortic and mitral valve opening and closure timing value, with low model absolute error (median of the mean absolute error of the four events = 19 ms compared to the gold standard DE measurement). For the right-sided (tricuspid and pulmonic) valves in our patient set, there was considerably higher median of the mean absolute error of 42 ms for the model.

CONCLUSION

ECG features can be used to estimate aortic and mitral valve timings with good accuracy as compared to DE, allowing useful hemodynamic information to be derived from this easily available test.

Quantitative prediction of right ventricular and size and function from the electrocardiogram

Background

Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep-learning enabled 12-lead electrocardiogram analysis (DL-ECG) for estimation of RV size or function is unexplored.

Methods

We trained a DL-ECG model to predict RV dilation (RVEDV>120 mL/m2), RV dysfunction (RVEF≤40%), and numerical RVEDV/RVEF from 12-lead ECG paired with reference-standard cardiac MRI (cMRI) volumetric measurements in UK biobank (UKBB; n=42,938). We fine-tuned in a multi-center health system (MSHoriginal; n=3,019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance using area under the receiver operating curve (AUROC) for categorical and mean absolute error (MAE) for continuous measures overall and in key subgroups. We assessed association of RVEF prediction with transplant-free survival with Cox proportional hazards models.

Results

Prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model AUROC for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. Prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model AUROC for UKBB/MSHoriginal/MSHvalidation cohorts 0.91/0.81/0.92, respectively. MSHoriginal MAE was RVEF=7.8% and RVEDV=17.6 ml/m2. Performance was similar in key subgroups including with and without left ventricular dysfunction. Over median follow-up of 2.3 years, predicted RVEF was independently associated with composite outcome (HR 1.37 for each 10% decrease, p=0.046).

Conclusions

DL-ECG analysis can accurately identify significant RV dysfunction and dilation both overall and in key subgroups. Predicted RVEF is independently associated with clinical outcome.

Deep Learning for Echocardiography: Introduction for Clinicians and Future Vision: State-of-the-Art Review

Exponential growth in data storage and computational power is rapidly narrowing the gap between translating findings from advanced clinical informatics into cardiovascular clinical practice. Specifically, cardiovascular imaging has the distinct advantage in providing a great quantity of data for potentially rich insights, but nuanced interpretation requires a high-level skillset that few individuals possess. A subset of machine learning, deep learning (DL), is a modality that has shown promise, particularly in the areas of image recognition, computer vision, and video classification. Due to a low signal-to-noise ratio, echocardiographic data tend to be challenging to classify; however, utilization of robust DL architectures may help clinicians and researchers automate conventional human tasks and catalyze the extraction of clinically useful data from the petabytes of collected imaging data. The promise is extending far and beyond towards a contactless echocardiographic exam-a dream that is much needed in this time of uncertainty and social distancing brought on by a stunning pandemic culture. In the current review, we discuss state-of-the-art DL techniques and architectures that can be used for image and video classification, and future directions in echocardiographic research in the current era.

Multi-center retrospective cohort study applying deep learning to electrocardiograms to identify left heart valvular dysfunction

BACKGROUND

Aortic Stenosis and Mitral Regurgitation are common valvular conditions representing a hidden burden of disease within the population. The aim of this study was to develop and validate deep learning-based screening and diagnostic tools that can help guide clinical decision making.

METHODS

In this multi-center retrospective cohort study, we acquired Transthoracic Echocardiogram reports from five Mount Sinai hospitals within New York City representing a demographically diverse cohort of patients. We developed a Natural Language Processing pipeline to extract ground-truth labels about valvular status and paired these to Electrocardiograms (ECGs). We developed and externally validated deep learning models capable of detecting valvular disease, in addition to considering scenarios of clinical deployment.

RESULTS

We use 617,338 ECGs paired to transthoracic echocardiograms from 123,096 patients to develop a deep learning model for detection of Mitral Regurgitation. Area Under Receiver Operating Characteristic curve (AUROC) is 0.88 (95% CI:0.88-0.89) in internal testing, and 0.81 (95% CI:0.80-0.82) in external validation. To develop a model for detection of Aortic Stenosis, we use 617,338 Echo-ECG pairs for 128,628 patients. AUROC is 0.89 (95% CI: 0.88-0.89) in internal testing, going to 0.86 (95% CI: 0.85-0.87) in external validation. The model's performance increases leading up to the time of the diagnostic echo, and it performs well in validation against requirement of Transcatheter Aortic Valve Replacement procedures.

CONCLUSIONS

Deep learning based tools can increase the amount of information extracted from ubiquitous investigations such as the ECG. Such tools are inexpensive, can help in earlier disease detection, and potentially improve prognosis.

Artificial intelligence enabled ECG screening for left ventricular systolic dysfunction: a systematic review

Screening for left ventricular systolic dysfunction (LVSD), defined as reduced left ventricular ejection fraction (LVEF), deserves renewed interest as the medical treatment for the prevention and progression of heart failure improves. We aimed to review the updated literature to outline the potential and caveats of using artificial intelligence-enabled electrocardiography (AIeECG) as an opportunistic screening tool for LVSD.We searched PubMed and Cochrane for variations of the terms "ECG," "Heart Failure," "systolic dysfunction," and "Artificial Intelligence" from January 2010 to April 2022 and selected studies that reported the diagnostic accuracy and confounders of using AIeECG to detect LVSD.Out of 40 articles, we identified 15 relevant studies; eleven retrospective cohorts, three prospective cohorts, and one case series. Although various LVEF thresholds were used, AIeECG detected LVSD with a median AUC of 0.90 (IQR from 0.85 to 0.95), a sensitivity of 83.3% (IQR from 73 to 86.9%) and a specificity of 87% (IQR from 84.5 to 90.9%). AIeECG algorithms succeeded across a wide range of sex, age, and comorbidity and seemed especially useful in non-cardiology settings and when combined with natriuretic peptide testing. Furthermore, a false-positive AIeECG indicated a future development of LVSD. No studies investigated the effect on treatment or patient outcomes.This systematic review corroborates the arrival of a new generic biomarker, AIeECG, to improve the detection of LVSD. AIeECG, in addition to natriuretic peptides and echocardiograms, will improve screening for LVSD, but prospective randomized implementation trials with added therapy are needed to show cost-effectiveness and clinical significance.

Deep Learning Using Electrocardiograms in Patients on Maintenance Dialysis

Cardiovascular morbidity and mortality occur with an extraordinarily high incidence in the hemodialysis-dependent end-stage kidney disease population. There is a clear need to improve identification of those individuals at the highest risk of cardiovascular complications in order to better target them for preventative therapies. Twelve-lead electrocardiograms are ubiquitous and use inexpensive technology that can be administered with minimal inconvenience to patients and at a minimal burden to care providers. The embedded waveforms encode significant information on the cardiovascular structure and function that might be unlocked and used to identify at-risk individuals with the use of artificial intelligence techniques like deep learning. In this review, we discuss the experience with deep learning-based analysis of electrocardiograms to identify cardiovascular abnormalities or risk and the potential to extend this to the setting of dialysis-dependent end-stage kidney disease.

Mortality impact of low CAC density predominantly occurs in early atherosclerosis: explainable ML in the CAC consortium

BACKGROUND

Machine learning (ML) models of risk prediction with coronary artery calcium (CAC) and CAC characteristics exhibit high performance, but are not inherently interpretable.

OBJECTIVES

To determine the direction and magnitude of impact of CAC characteristics on 10-year all-cause mortality (ACM) with explainable ML.

METHODS

We analyzed asymptomatic subjects in the CAC consortium. We trained ML models on 80% and tested on 20% of the data with XGBoost, using clinical characteristics ​+ ​CAC (ML 1) and additional CAC characteristics of CAC density and number of calcified vessels (ML 2). We applied SHAP, an explainable ML tool, to explore the relationship of CAC and CAC characteristics with 10-year all-cause and CV mortality.

RESULTS

2376 deaths occurred among 63,215 patients [68% male, median age 54 (IQR 47-61), CAC 3 (IQR 0-94.3)]. ML2 was similar to ML1 to predict all-cause mortality (Area Under the Curve (AUC) 0.819 vs 0.821, p ​= ​0.23), but superior for CV mortality (0.847 vs 0.845, p ​= ​0.03). Low CAC density increased mortality impact, particularly ≤0.75. Very low CAC density ≤0.75 was present in only 4.3% of the patients with measurable density, and 75% occurred in CAC1-100. The number of diseased vessels did not increase mortality overall when simultaneously accounting for CAC and CAC density.

CONCLUSION

CAC density contributes to mortality risk primarily when it is very low ≤0.75, which is primarily observed in CAC 1-100. CAC and CAC density are more important for mortality prediction than the number of diseased vessels, and improve prediction of CV but not all-cause mortality. Explainable ML techniques are useful to describe granular relationships in otherwise opaque prediction models.

Electrocardiogram-based artificial intelligence for the diagnosis of heart failure: a systematic review and meta-analysis

BACKGROUND

The electrocardiogram (ECG) is an inexpensive and easily accessible investigation for the diagnosis of cardiovascular diseases including heart failure (HF). The application of artificial intelligence (AI) has contributed to clinical practice in terms of aiding diagnosis, prognosis, risk stratification and guiding clinical management. The aim of this study is to systematically review and perform a meta-analysis of published studies on the application of AI for HF detection based on the ECG.

METHODS

We searched Embase, PubMed and Web of Science databases to identify literature using AI for HF detection based on ECG data. The quality of included studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria. Random-effects models were used for calculating the effect estimates and hierarchical receiver operating characteristic curves were plotted. Subgroup analysis was performed. Heterogeneity and the risk of bias were also assessed.

RESULTS

A total of 11 studies including 104,737 subjects were included. The area under the curve for HF diagnosis was 0.986, with a corresponding pooled sensitivity of 0.95 (95% CI: 0.86-0.98), specificity of 0.98 (95% CI: 0.95-0.99) and diagnostic odds ratio of 831.51 (95% CI: 127.85-5407.74). In the patient selection domain of QUADAS-2, eight studies were designated as high risk.

CONCLUSIONS

According to the available evidence, the incorporation of AI can aid the diagnosis of HF. However, there is heterogeneity among machine learning algorithms and improvements are required in terms of quality and study design.

Machine learning derived ECG risk score improves cardiovascular risk assessment in conjunction with coronary artery calcium scoring

Background

Precision estimation of cardiovascular risk remains the cornerstone of atherosclerotic cardiovascular disease (ASCVD) prevention. While coronary artery calcium (CAC) scoring is the best available non-invasive quantitative modality to evaluate risk of ASCVD, it excludes risk related to prior myocardial infarction, cardiomyopathy, and arrhythmia which are implicated in ASCVD. The high-dimensional and inter-correlated nature of ECG data makes it a good candidate for analysis using machine learning techniques and may provide additional prognostic information not captured by CAC. In this study, we aimed to develop a quantitative ECG risk score (eRiS) to predict major adverse cardiovascular events (MACE) alone, or when added to CAC. Further, we aimed to construct and validate a novel nomogram incorporating ECG, CAC and clinical factors for ASCVD.

Methods

We analyzed 5,864 patients with at least 1 cardiovascular risk factor who underwent CAC scoring and a standard ECG as part of the CLARIFY study (ClinicalTrials.gov Identifier: NCT04075162). Events were defined as myocardial infarction, coronary revascularization, stroke or death. A total of 649 ECG features, consisting of measurements such as amplitude and interval measurements from all deflections in the ECG waveform (53 per lead and 13 overall) were automatically extracted using a clinical software (GE Muse™ Cardiology Information System, GE Healthcare). The data was split into 4 training (S_tr) and internal validation (S_v) sets [S_tr (1): S_v (1): 50:50; S_tr (2): S_v (2): 60:40; S_tr (3): S_v (3): 70:30; S_tr (4): S_v (4): 80:20], and the results were compared across all the subsets. We used the ECG features derived from S_tr to develop eRiS. A least absolute shrinkage and selection operator-Cox (LASSO-Cox) regularization model was used for data dimension reduction, feature selection, and eRiS construction. A Cox-proportional hazards model was used to assess the benefit of using an eRiS alone (M_ecg), CAC alone (M_cac) and a combination of eRiS and CAC (M_ecg+cac) for MACE prediction. A nomogram (M_nom) was further constructed by integrating eRiS with CAC and demographics (age and sex). The primary endpoint of the study was the assessment of the performance of M_ecg, M_cac, M_ecg+cac and M_nom in predicting CV disease-free survival in ASCVD.

Findings

Over a median follow-up of 14 months, 494 patients had MACE. The feature selection strategy preserved only about 18% of the features that were consistent across the various strata (S_tr). The M_ecg model, comprising of eRiS alone was found to be significantly associated with MACE and had good discrimination of MACE (C-Index: 0.7, p = <2e-16). eRiS could predict time-to MACE (C-Index: 0.6, p = <2e-16 across all S_v). The M_ecg+cac model was associated with MACE (C-index: 0.71). Model comparison showed that M_ecg+cac was superior to M_ecg (p = 1.8e-10) or M_cac (p < 2.2e-16) alone. The M_nom, comprising of eRiS, CAC, age and sex was associated with MACE (C-index 0.71). eRiS had the most significant contribution, followed by CAC score and other clinical variables. Further, M_nom was able to identify unique patient risk-groups based on eRiS, CAC and clinical variables.

Conclusion

The use of ECG features in conjunction with CAC may allow for improved prognostication and identification of populations at risk. Future directions will involve prospective validation of the risk score and the nomogram across diverse populations with a heterogeneity of treatment effects.

Automated Determination of Left Ventricular Function Using Electrocardiogram Data in Patients on Maintenance Hemodialysis

BACKGROUND AND OBJECTIVES

Left ventricular ejection fraction is disrupted in patients on maintenance hemodialysis and can be estimated using deep learning models on electrocardiograms. Smaller sample sizes within this population may be mitigated using transfer learning.

DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS

We identified patients on hemodialysis with transthoracic echocardiograms within 7 days of electrocardiogram using diagnostic/procedure codes. We developed four models: (1) trained from scratch in patients on hemodialysis, (2) pretrained on a publicly available set of natural images (ImageNet), (3) pretrained on all patients not on hemodialysis, and (4) pretrained on patients not on hemodialysis and fine-tuned on patients on hemodialysis. We assessed the ability of the models to classify left ventricular ejection fraction into clinically relevant categories of ≤40%, 41% to ≤50%, and >50%. We compared performance by area under the receiver operating characteristic curve.

RESULTS

We extracted 705,075 electrocardiogram:echocardiogram pairs for 158,840 patients not on hemodialysis used for development of models 3 and 4 and n=18,626 electrocardiogram:echocardiogram pairs for 2168 patients on hemodialysis for models 1, 2, and 4. The transfer learning model achieved area under the receiver operating characteristic curves of 0.86, 0.63, and 0.83 in predicting left ventricular ejection fraction categories of ≤40% (n=461), 41%-50% (n=398), and >50% (n=1309), respectively. For the same tasks, model 1 achieved area under the receiver operating characteristic curves of 0.74, 0.55, and 0.71, respectively; model 2 achieved area under the receiver operating characteristic curves of 0.71, 0.55, and 0.69, respectively, and model 3 achieved area under the receiver operating characteristic curves of 0.80, 0.51, and 0.77, respectively. We found that predictions of left ventricular ejection fraction by the transfer learning model were associated with mortality in a Cox regression with an adjusted hazard ratio of 1.29 (95% confidence interval, 1.04 to 1.59).

CONCLUSION

A deep learning model can determine left ventricular ejection fraction for patients on hemodialysis following pretraining on electrocardiograms of patients not on hemodialysis. Predictions of low ejection fraction from this model were associated with mortality over a 5-year follow-up period.

PODCAST

This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2022_06_06_CJN16481221.mp3.

Artificial Intelligence-Enabled Electrocardiogram Predicted Left Ventricle Diameter as an Independent Risk Factor of Long-Term Cardiovascular Outcome in Patients With Normal Ejection Fraction

Background

Heart failure (HF) is a global disease with increasing prevalence in an aging society. However, the survival rate is poor despite the patient receiving standard treatment. Early identification of patients with a high risk of HF is important but challenging. Left ventricular end-diastolic diameter (LV-D) increase was an independent risk factor of HF and adverse cardiovascular (CV) outcomes. In this study, we aimed to develop an artificial intelligence (AI) enabled electrocardiogram (ECG) system to detect LV-D increase early.

Objective

We developed a deep learning model (DLM) to predict left ventricular end-diastolic and end-systolic diameter (LV-D and LV-S) with internal and external validations and investigated the relationship between ECG-LV-D and echocardiographic LV-D and explored the contributions of ECG-LV-D on future CV outcomes.

Methods

Electrocardiograms and corresponding echocardiography data within 7 days were collected and paired for DLM training with 99,692 ECGs in the development set and 20,197 ECGs in the tuning set. The other 7,551 and 11,644 ECGs were collected from two different hospitals to validate the DLM performance in internal and external validation sets. We analyzed the association and prediction ability of ECG-LVD for CV outcomes, including left ventricular (LV) dysfunction, CV mortality, acute myocardial infarction (AMI), and coronary artery disease (CAD).

Results

The mean absolute errors (MAE) of ECG-LV-D were 5.25/5.29, and the area under the receiver operating characteristic (ROC) curves (AUCs) were 0.8297/0.8072 and 0.9295/0.9148 for the detection of mild (56 ≦ LV-D < 65 mm) and severe (LV-D ≧ 65 mm) LV-D dilation in internal/external validation sets, respectively. Patients with normal ejection fraction (EF) who were identified as high ECHO-LV-D had the higher hazard ratios (HRs) of developing new onset LV dysfunction [HR: 2.34, 95% conference interval (CI): 1.78–3.08], CV mortality (HR 2.30, 95% CI 1.05–5.05), new-onset AMI (HR 2.12, 95% CI 1.36–3.29), and CAD (HR 1.59, 95% CI 1.26–2.00) in the internal validation set. In addition, the ECG-LV-D presents a 1.88-fold risk (95% CI 1.47–2.39) on new-onset LV dysfunction in the external validation set.

Conclusion

The ECG-LV-D not only identifies high-risk patients with normal EF but also serves as an independent risk factor of long-term CV outcomes.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

Artificial Intelligence-Enabled Electrocardiography Predicts Left Ventricular Dysfunction and Future Cardiovascular Outcomes: A Retrospective Analysis

BACKGROUND: The ejection fraction (EF) provides critical information about heart failure (HF) and its management. Electrocardiography (ECG) is a noninvasive screening tool for cardiac electrophysiological activities that has been used to detect patients with low EF based on a deep learning model (DLM) trained via large amounts of data. However, no studies have widely investigated its clinical impacts. OBJECTIVE: This study developed a DLM to estimate EF via ECG (ECG-EF). We further investigated the relationship between ECG-EF and echo-based EF (ECHO-EF) and explored their contributions to future cardiovascular adverse events. METHODS: There were 57,206 ECGs with corresponding echocardiograms used to train our DLM. We compared a series of training strategies and selected the best DLM. The architecture of the DLM was based on ECG12Net, developed previously. Next, 10,762 ECGs were used for validation, and another 20,629 ECGs were employed to conduct the accuracy test. The changes between ECG-EF and ECHO-EF were evaluated. The primary follow-up adverse events included future ECHO-EF changes and major adverse cardiovascular events (MACEs). RESULTS: The sex-/age-matching strategy-trained DLM achieved the best area under the curve (AUC) of 0.9472 with a sensitivity of 86.9% and specificity of 89.6% in the follow-up cohort, with a correlation of 0.603 and a mean absolute error of 7.436. In patients with accurate prediction (initial difference < 10%), the change traces of ECG-EF and ECHO-EF were more consistent (R-square = 0.351) than in all patients (R-square = 0.115). Patients with lower ECG-EF (≤35%) exhibited a greater risk of cardiovascular (CV) complications, delayed ECHO-EF recovery, and earlier ECHO-EF deterioration than patients with normal ECG-EF (>50%). Importantly, ECG-EF demonstrated an independent impact on MACEs and all CV adverse outcomes, with better prediction of CV outcomes than ECHO-EF. CONCLUSIONS: The ECG-EF could be used to initially screen asymptomatic left ventricular dysfunction (LVD) and it could also independently contribute to the predictions of future CV adverse events. Although further large-scale studies are warranted, DLM-based ECG-EF could serve as a promising diagnostic supportive and management-guided tool for CV disease prediction and the care of patients with LVD.

Artificial intelligence-enabled electrocardiogram screens low left ventricular ejection fraction with a degree of confidence

Background

Artificial intelligence-enabled electrocardiogram has become a substitute tool for echocardiography in left ventricular ejection fraction estimation. However, the direct use of artificial intelligence-enabled electrocardiogram may be not trustable due to the uncertainty of the prediction.

Objective

The study aimed to establish an artificial intelligence-enabled electrocardiogram with a degree of confidence to identify left ventricular dysfunction.

Methods

The study collected 76,081 and 11,771 electrocardiograms from an academic medical center and a community hospital to establish and validate the deep learning model, respectively. The proposed deep learning model provided the point estimation of the actual ejection fraction and its standard deviation derived from the maximum probability density function of a normal distribution. The primary analysis focused on the accuracy of identifying patients with left ventricular dysfunction (ejection fraction ≤ 40%). Since the standard deviation was an uncertainty indicator in a normal distribution, we used it as a degree of confidence in the artificial intelligence-enabled electrocardiogram. We further explored the clinical application of estimated standard deviation and followed up on the new-onset left ventricular dysfunction in patients with initially normal ejection fraction.

Results

The area under receiver operating characteristic curves (AUC) of detecting left ventricular dysfunction were 0.9549 and 0.9365 in internal and external validation sets. After excluding the cases with a lower degree of confidence, the artificial intelligence-enabled electrocardiogram performed better in the remaining cases in internal (AUC = 0.9759) and external (AUC = 0.9653) validation sets. For the application of future left ventricular dysfunction risk stratification in patients with initially normal ejection fraction, a 4.57-fold risk of future left ventricular dysfunction when the artificial intelligence-enabled electrocardiogram is positive in the internal validation set. The hazard ratio was increased to 8.67 after excluding the cases with a lower degree of confidence. This trend was also validated in the external validation set.

Conclusion

The deep learning model with a degree of confidence can provide advanced improvements in identifying left ventricular dysfunction and serve as a decision support and management-guided screening tool for prognosis.