ECG-AI: electrocardiographic artificial intelligence model for prediction of heart failure

Efficacy of the methods of age determination using artificial intelligence in panoramic radiographs - a systematic review

The aim of this systematic review is to analyze the literature to determine whether the methods of artificial intelligence are effective in determining age in panoramic radiographs. Searches without language and year limits were conducted in PubMed/Medline, Embase, Web of Science, and Scopus databases. Hand searches were also performed, and unpublished manuscripts were searched in specialized journals. Thirty-six articles were included in the analysis. Significant differences in terms of root mean square error and mean absolute error were found between manual methods and artificial intelligence techniques, favoring the use of artificial intelligence (p < 0.00001). Few articles compared deep learning methods with machine learning models or manual models. Although there are advantages of machine learning in data processing and deep learning in data collection and analysis, non-comparable data was a limitation of this study. More information is needed on the comparison of these techniques, with particular emphasis on time as a variable.

AI-enabled cardiac chambers volumetry in coronary artery calcium scans (AI-CACTM) predicts heart failure and outperforms NT-proBNP: The multi-ethnic study of Atherosclerosis

INTRODUCTION

Coronary artery calcium (CAC) scans contain useful information beyond the Agatston CAC score that is not currently reported. We recently reported that artificial intelligence (AI)-enabled cardiac chambers volumetry in CAC scans (AI-CAC™) predicted incident atrial fibrillation in the Multi-Ethnic Study of Atherosclerosis (MESA). In this study, we investigated the performance of AI-CAC cardiac chambers for prediction of incident heart failure (HF).

METHODS

We applied AI-CAC to 5750 CAC scans of asymptomatic individuals (52% female, White 40%, Black 26%, Hispanic 22% Chinese 12%) free of known cardiovascular disease at the MESA baseline examination (2000-2002). We used the 15-year outcomes data and compared the time-dependent area under the curve (AUC) of AI-CAC volumetry versus NT-proBNP, Agatston score, and 9 known clinical risk factors (age, gender, diabetes, current smoking, hypertension medication, systolic and diastolic blood pressure, LDL, HDL for predicting incident HF over 15 years.

RESULTS

Over 15 years of follow-up, 256 HF events accrued. The time-dependent AUC [95% CI] at 15 years for predicting HF with AI-CAC all chambers volumetry (0.86 [0.82,0.91]) was significantly higher than NT-proBNP (0.74 [0.69, 0.77]) and Agatston score (0.71 [0.68, 0.78]) (p ​< ​0.0001), and comparable to clinical risk factors (0.85, p ​= ​0.4141). Category-free Net Reclassification Index (NRI) [95% CI] adding AI-CAC LV significantly improved on clinical risk factors (0.32 [0.16,0.41]), NT-proBNP (0.46 [0.33,0.58]), and Agatston score (0.71 [0.57,0.81]) for HF prediction at 15 years (p ​< ​0.0001).

CONCLUSION

AI-CAC volumetry significantly outperformed NT-proBNP and the Agatston CAC score, and significantly improved the AUC and category-free NRI of clinical risk factors for incident HF prediction.

Feasibility of remote monitoring for fatal coronary heart disease using Apple Watch ECGs

Background

Fatal coronary heart disease (FCHD) is often described as sudden cardiac death (affects >4 million people/year), where coronary artery disease is the only identified condition. Electrocardiographic artificial intelligence (ECG-AI) models for FCHD risk prediction using ECG data from wearable devices could enable wider screening/monitoring efforts.

Objectives

To develop a single-lead ECG-based deep learning model for FCHD risk prediction and assess concordance between clinical and Apple Watch ECGs.

Methods

An FCHD single-lead ("lead I" from 12-lead ECGs) ECG-AI model was developed using 167,662 ECGs (50,132 patients) from the University of Tennessee Health Sciences Center. Eighty percent of the data (5-fold cross-validation) was used for training and 20% as a holdout. Cox proportional hazards (CPH) models incorporating ECG-AI predictions with age, sex, and race were also developed. The models were tested on paired clinical single-lead and Apple Watch ECGs from 243 St. Jude Lifetime Cohort Study participants. The correlation and concordance of the predictions were assessed using Pearson correlation (R), Spearman correlation (ρ), and Cohen's kappa.

Results

The ECG-AI and CPH models resulted in AUC = 0.76 and 0.79, respectively, on the 20% holdout and AUC = 0.85 and 0.87 on the Atrium Health Wake Forest Baptist external validation data. There was moderate-strong positive correlation between predictions (R = 0.74, ρ = 0.67, and κ = 0.58) when tested on the 243 paired ECGs. The clinical (lead I) and Apple Watch predictions led to the same low/high-risk FCHD classification for 99% of the participants. CPH prediction correlation resulted in an R = 0.81, ρ = 0.76, and κ = 0.78.

Conclusion

Risk of FCHD can be predicted from single-lead ECGs obtained from wearable devices and are statistically concordant with lead I of a 12-lead ECG.

Scalable Risk Stratification for Heart Failure Using Artificial Intelligence applied to 12-lead Electrocardiographic Images: A Multinational Study

Background

Current risk stratification strategies for heart failure (HF) risk require either specific blood-based biomarkers or comprehensive clinical evaluation. In this study, we evaluated the use of artificial intelligence (AI) applied to images of electrocardiograms (ECGs) to predict HF risk.

Methods

Across multinational longitudinal cohorts in the integrated Yale New Haven Health System (YNHHS) and in population-based UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), we identified individuals without HF at baseline. Incident HF was defined based on the first occurrence of an HF hospitalization. We evaluated an AI-ECG model that defines the cross-sectional probability of left ventricular dysfunction from a single image of a 12-lead ECG and its association with incident HF. We accounted for the competing risk of death using the Fine-Gray subdistribution model and evaluated the discrimination using Harrel's c-statistic. The pooled cohort equations to prevent HF (PCP-HF) were used as a comparator for estimating incident HF risk.

Results

Among 231,285 individuals at YNHHS, 4472 had a primary HF hospitalization over 4.5 years (IQR 2.5-6.6) of follow-up. In UKB and ELSA-Brasil, among 42,741 and 13,454 people, 46 and 31 developed HF over a follow-up of 3.1 (2.1-4.5) and 4.2 (3.7-4.5) years, respectively. A positive AI-ECG screen portended a 4-fold higher risk of incident HF among YNHHS patients (age-, sex-adjusted HR [aHR] 3.88 [95% CI, 3.63-4.14]). In UKB and ELSA-Brasil, a positive-screen ECG portended 13- and 24-fold higher hazard of incident HF, respectively (aHR: UKBB, 12.85 [6.87-24.02]; ELSA-Brasil, 23.50 [11.09-49.81]). The association was consistent after accounting for comorbidities and the competing risk of death. Higher model output probabilities were progressively associated with a higher risk for HF. The model's discrimination for incident HF was 0.718 in YNHHS, 0.769 in UKB, and 0.810 in ELSA-Brasil. Across cohorts, incorporating model probability with PCP-HF yielded a significant improvement in discrimination over PCP-HF alone.

Conclusions

An AI model applied to images of 12-lead ECGs can identify those at elevated risk of HF across multinational cohorts. As a digital biomarker of HF risk that requires just an ECG image, this AI-ECG approach can enable scalable and efficient screening for HF risk.

Development and validation of an electrocardiographic artificial intelligence model for detection of peripartum cardiomyopathy

BACKGROUND

This study used electrocardiogram data in conjunction with artificial intelligence methods as a noninvasive tool for detecting peripartum cardiomyopathy.

OBJECTIVE

This study aimed to assess the efficacy of an artificial intelligence-based heart failure detection model for peripartum cardiomyopathy detection.

STUDY DESIGN

We first built a deep-learning model for heart failure detection using retrospective data at the University of Tennessee Health Science Center. Cases were adult and nonpregnant female patients with a heart failure diagnosis; controls were adult nonpregnant female patients without heart failure. The model was then tested on an independent cohort of pregnant women at the University of Tennessee Health Science Center with or without peripartum cardiomyopathy. We also tested the model in an external cohort of pregnant women at Atrium Health Wake Forest Baptist. Key outcomes were assessed using the area under the receiver operating characteristic curve. We also repeated our analysis using only lead I electrocardiogram as an input to assess the feasibility of remote monitoring via wearables that can capture single-lead electrocardiogram data.

RESULTS

The University of Tennessee Health Science Center heart failure cohort comprised 346,339 electrocardiograms from 142,601 patients. In this cohort, 60% of participants were Black and 37% were White, with an average age (standard deviation) of 53 (19) years. The heart failure detection model achieved an area under the curve of 0.92 on the holdout set. We then tested the ability of the heart failure model to detect peripartum cardiomyopathy in an independent University of Tennessee Health Science Center cohort of pregnant women and an external Atrium Health Wake Forest Baptist cohort of pregnant women. The independent University of Tennessee Health Science Center cohort included 158 electrocardiograms from 115 patients; our deep-learning model achieved an area under the curve of 0.83 (0.77-0.89) for this data set. The external Atrium Health Wake Forest Baptist cohort involved 80 electrocardiograms from 43 patients; our deep-learning model achieved an area under the curve of 0.94 (0.91-0.98) for this data set. For identifying peripartum cardiomyopathy diagnosed ≥10 days after delivery, the model achieved an area under the curve of 0.88 (0.81-0.94) for the University of Tennessee Health Science Center cohort and of 0.96 (0.93-0.99) for the Atrium Health Wake Forest Baptist cohort. When we repeated our analysis by building a heart failure detection model using only lead-I electrocardiograms, we obtained similarly high detection accuracies, with areas under the curve of 0.73 and 0.93 for the University of Tennessee Health Science Center and Atrium Health Wake Forest Baptist cohorts, respectively.

CONCLUSION

Artificial intelligence can accurately detect peripartum cardiomyopathy from electrocardiograms alone. A simple electrocardiographic artificial intelligence-based peripartum screening could result in a timelier diagnosis. Given that results with 1-lead electrocardiogram data were similar to those obtained using all 12 leads, future studies will focus on remote screening for peripartum cardiomyopathy using smartwatches that can capture single-lead electrocardiogram data.

Multirole of the internet of medical things (IoMT) in biomedical systems for managing smart healthcare systems: An overview of current and future innovative trends

Internet of Medical Things (IoMT) is an emerging subset of Internet of Things (IoT), often called as IoT in healthcare, refers to medical devices and applications with internet connectivity, is exponentially gaining researchers' attention due to its wide-ranging applicability in biomedical systems for Smart Healthcare systems. IoMT facilitates remote health biomedical system and plays a crucial role within the healthcare industry to enhance precision, reliability, consistency and productivity of electronic devices used for various healthcare purposes. It comprises a conceptualized architecture for providing information retrieval strategies to extract the data from patient records using sensors for biomedical analysis and diagnostics against manifold diseases to provide cost-effective medical solutions, quick hospital treatments, and personalized healthcare. This article provides a comprehensive overview of IoMT with special emphasis on its current and future trends used in biomedical systems, such as deep learning, machine learning, blockchains, artificial intelligence, radio frequency identification, and industry 5.0.

AI-based preeclampsia detection and prediction with electrocardiogram data

Introduction

More than 76,000 women die yearly from preeclampsia and hypertensive disorders of pregnancy. Early diagnosis and management of preeclampsia can improve outcomes for both mother and baby. In this study, we developed artificial intelligence models to detect and predict preeclampsia from electrocardiograms (ECGs) in point-of-care settings.

Methods

Ten-second 12-lead ECG data was obtained from two large health care settings: University of Tennessee Health Science Center (UTHSC) and Atrium Health Wake Forest Baptist (AHWFB). UTHSC data was split into 80% training and 20% holdout data. The model used a modified ResNet convolutional neural network, taking one-dimensional raw ECG signals comprising 12 channels as an input, to predict risk of preeclampsia. Sub-analyses were performed to assess the predictive accuracy for preeclampsia prediction within 30, 60, or 90 days before diagnosis.

Results

The UTHSC cohort included 904 ECGs from 759 females (78.8% African American) with a mean ± sd age of 27.3 ± 5.0 years. The AHWFB cohort included 817 ECGs from 141 females (45.4 African American) with a mean ± sd age of 27.4 ± 5.9 years. The cross-validated ECG-AI model yielded an AUC (95% CI) of 0.85 (0.77-0.93) on UTHSC holdout data, and an AUC (95% CI) of 0.81 (0.77-0.84) on AHWFB data. The sub-analysis of different time windows before preeclampsia prediction resulted in AUCs (95% CI) of 0.92 (0.84-1.00), 0.89 (0.81-0.98) and 0.90 (0.81-0.98) when tested on ECGs 30 days, 60 days and 90 days, respectively, before diagnosis. When assessed on early onset preeclampsia (preeclampsia diagnosed at <34 weeks of pregnancy), the model's AUC (95% CI) was 0.98 (0.89-1.00).

Discussion

We conclude that preeclampsia can be identified with high accuracy via application of AI models to ECG data.

Artificial intelligence-enhanced electrocardiography for accurate diagnosis and management of cardiovascular diseases

Electrocardiography (ECG), improved by artificial intelligence (AI), has become a potential technique for the precise diagnosis and treatment of cardiovascular disorders. The conventional ECG is a frequently used, inexpensive, and easily accessible test that offers important information about the physiological and anatomical state of the heart. However, the ECG can be interpreted differently by humans depending on the interpreter's level of training and experience, which could make diagnosis more difficult. Using AI, especially deep learning convolutional neural networks (CNNs), to look at single, continuous, and intermittent ECG leads that has led to fully automated AI models that can interpret the ECG like a human, possibly more accurately and consistently. These AI algorithms are effective non-invasive biomarkers for cardiovascular illnesses because they can identify subtle patterns and signals in the ECG that may not be readily apparent to human interpreters. The use of AI in ECG analysis has several benefits, including the quick and precise detection of problems like arrhythmias, silent cardiac illnesses, and left ventricular failure. It has the potential to help doctors with interpretation, diagnosis, risk assessment, and illness management. Aside from that, AI-enhanced ECGs have been demonstrated to boost the identification of heart failure and other cardiovascular disorders, particularly in emergency department settings, allowing for quicker and more precise treatment options. The use of AI in cardiology, however, has several limitations and obstacles, despite its potential. The effective implementation of AI-powered ECG analysis is limited by issues such as systematic bias. Biases based on age, gender, and race result from unbalanced datasets. A model's performance is impacted when diverse demographics are inadequately represented. Potentially disregarded age-related ECG variations may result from skewed age data in training sets. ECG patterns are affected by physiological differences between the sexes; a dataset that is inclined toward one sex may compromise the accuracy of the others. Genetic variations influence ECG readings, so racial diversity in datasets is significant. Furthermore, issues such as inadequate generalization, regulatory barriers, and interpretability concerns contribute to deployment difficulties. The lack of robustness in models when applied to disparate populations frequently hinders their practical applicability. The exhaustive validation required by regulatory requirements causes a delay in deployment. Difficult models that are not interpretable erode the confidence of clinicians. Diverse dataset curation, bias mitigation strategies, continuous validation across populations, and collaborative efforts for regulatory approval are essential for the successful deployment of AI ECG in clinical settings and must be undertaken to address these issues. To guarantee a safe and successful deployment in clinical practice, the use of AI in cardiology must be done with a thorough understanding of the algorithms and their limits. In summary, AI-enhanced electrocardiography has enormous potential to improve the management of cardiovascular illness by delivering precise and timely diagnostic insights, aiding clinicians, and enhancing patient outcomes. Further study and development are required to fully realize AI's promise for improving cardiology practices and patient care as technology continues to advance.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

[Precision medicine enhances personalized medicine in cardiology]

Personalized medicine and precision medicine, frequently used synonymously, shall be clearly differentiated. Accordingly, personalization in cardiac medicine is based on the clinical presentation of a patient, as well as his/her cardiovascular risk factors and comorbidities, electrocardiography, imaging, and biomarkers for myocardial load and ischemia. Personalization is based on large clinical trials with detailed subgroup analyses and is practiced on the basis of guidelines. Further in depth personalization is achieved by precision medicine, which is based on innovative imaging for myocardial structure, coronary morphology, and electrophysiology. From the clinical perspective, genome analyses are relevant for comparatively rare monogenetic cardiovascular diseases. While these as well as transcriptome and metabolome analyses play a significant role in cardiovascular research with great translation potential, they have not yet been broadly introduced in the diagnosis, prevention, and treatment of complex cardiovascular diseases. Furthermore, digital technologies have considerable potential in cardiovascular precision medicine. On the one hand, this is based on the frequency of the diseases with the availability of Big Data and, on the other hand, on the availability of bio-signals and sensors of those signals in cardiovascular diseases.

Prioritizing the primary prevention of heart failure: Measuring, modifying and monitoring risk

With the rising incidence of heart failure (HF) and increasing burden of morbidity, mortality, and healthcare expenditures, primary prevention of HF targeting individuals in at-risk HF (Stage A) and pre-HF (Stage B) Stages has become increasingly important with the goal to decrease progression to symptomatic (Stage C) HF. Identification of risk based on traditional risk factors (e.g., cardiovascular health which can be assessed with the American Heart Association's Life's Essential 8 framework), adverse social determinants of health, inherited risk of cardiomyopathies, and identification of risk-enhancing factors, such as patients with viral disease, exposure to cardiotoxic chemotherapy, and history of adverse pregnancy outcomes should be the first step in evaluation for HF risk. Next, use of guideline-endorsed risk prediction tools such as Pooled Cohort Equations to Prevent Heart Failure provide quantification of absolute risk of HF based in traditional risk factors. Risk reduction through counseling on traditional risk factors is a core focus of implementation of prevention and may include the use of novel therapeutics that target specific pathways to reduce risk of HF, such as mineralocorticoid receptor agonists (e.g., fineronone), angiotensin-receptor/neprolysin inhibitors, and sodium glucose co-transporter-2 inhibitors. These interventions may be limited in at-risk populations who experience adverse social determinants and/or individuals who reside in rural areas. Thus, strategies like telemedicine may improve access to preventive care. Gaps in the current knowledge base for risk-based prevention of HF are highlighted to outline future research that may target approaches for risk assessment and risk-based prevention with the use of artificial intelligence, genomics-enhanced strategies, and pragmatic trials to develop a guideline-directed medical therapy approach to reduce risk among individuals with Stage A and Stage B HF.

Deep Learning of Electrocardiograms in Sinus Rhythm From US Veterans to Predict Atrial Fibrillation

Importance

Early detection of atrial fibrillation (AF) may help prevent adverse cardiovascular events such as stroke. Deep learning applied to electrocardiograms (ECGs) has been successfully used for early identification of several cardiovascular diseases.

Objective

To determine whether deep learning models applied to outpatient ECGs in sinus rhythm can predict AF in a large and diverse patient population.

Design, Setting, and Participants

This prognostic study was performed on ECGs acquired from January 1, 1987, to December 31, 2022, at 6 US Veterans Affairs (VA) hospital networks and 1 large non-VA academic medical center. Participants included all outpatients with 12-lead ECGs in sinus rhythm.

Main Outcomes and Measures

A convolutional neural network using 12-lead ECGs from 2 US VA hospital networks was trained to predict the presence of AF within 31 days of sinus rhythm ECGs. The model was tested on ECGs held out from training at the 2 VA networks as well as 4 additional VA networks and 1 large non-VA academic medical center.

Results

A total of 907 858 ECGs from patients across 6 VA sites were included in the analysis. These patients had a mean (SD) age of 62.4 (13.5) years, 6.4% were female, and 93.6% were male, with a mean (SD) CHA2DS2-VASc (congestive heart failure, hypertension, age, diabetes mellitus, prior stroke or transient ischemic attack or thromboembolism, vascular disease, age, sex category) score of 1.9 (1.6). A total of 0.2% were American Indian or Alaska Native, 2.7% were Asian, 10.7% were Black, 4.6% were Latinx, 0.7% were Native Hawaiian or Other Pacific Islander, 62.4% were White, 0.4% were of other race or ethnicity (which is not broken down into subcategories in the VA data set), and 18.4% were of unknown race or ethnicity. At the non-VA academic medical center (72 483 ECGs), the mean (SD) age was 59.5 (15.4) years and 52.5% were female, with a mean (SD) CHA2DS2-VASc score of 1.6 (1.4). A total of 0.1% were American Indian or Alaska Native, 7.9% were Asian, 9.4% were Black, 2.9% were Latinx, 0.03% were Native Hawaiian or Other Pacific Islander, 74.8% were White, 0.1% were of other race or ethnicity, and 4.7% were of unknown race or ethnicity. A deep learning model predicted the presence of AF within 31 days of a sinus rhythm ECG on held-out test ECGs at VA sites with an area under the receiver operating characteristic curve (AUROC) of 0.86 (95% CI, 0.85-0.86), accuracy of 0.78 (95% CI, 0.77-0.78), and F1 score of 0.30 (95% CI, 0.30-0.31). At the non-VA site, AUROC was 0.93 (95% CI, 0.93-0.94); accuracy, 0.87 (95% CI, 0.86-0.88); and F1 score, 0.46 (95% CI, 0.44-0.48). The model was well calibrated, with a Brier score of 0.02 across all sites. Among individuals deemed high risk by deep learning, the number needed to screen to detect a positive case of AF was 2.47 individuals for a testing sensitivity of 25% and 11.48 for 75%. Model performance was similar in patients who were Black, female, or younger than 65 years or who had CHA2DS2-VASc scores of 2 or greater.

Conclusions and Relevance

Deep learning of outpatient sinus rhythm ECGs predicted AF within 31 days in populations with diverse demographics and comorbidities. Similar models could be used in future AF screening efforts to reduce adverse complications associated with this disease.

A generalizable electrocardiogram-based artificial intelligence model for 10-year heart failure risk prediction

Background

Heart failure (HF) is a progressive condition with high global incidence. HF has two main subtypes: HF with preserved ejection fraction (HFpEF) and HF with reduced ejection fraction (HFrEF). There is an inherent need for simple yet effective electrocardiogram (ECG)-based artificial intelligence (AI; ECG-AI) models that can predict HF risk early to allow for risk modification.

Objective

The main objectives were to validate HF risk prediction models using Multi-Ethnic Study of Atherosclerosis (MESA) data and assess performance on HFpEF and HFrEF classification.

Methods

There were six models in comparision derived using ARIC data. 1) The ECG-AI model predicting HF risk was developed using raw 12-lead ECGs with a convolutional neural network. The clinical models from 2) ARIC (ARIC-HF) and 3) Framingham Heart Study (FHS-HF) used 9 and 8 variables, respectively. 4) Cox proportional hazards (CPH) model developed using the clinical risk factors in ARIC-HF or FHS-HF. 5) CPH model using the outcome of ECG-AI and the clinical risk factors used in CPH model (ECG-AI-Cox) and 6) A Light Gradient Boosting Machine model using 288 ECG Characteristics (ECG-Chars). All the models were validated on MESA. The performances of these models were evaluated using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test.

Results

ECG-AI, ECG-Chars, and ECG-AI-Cox resulted in validation AUCs of 0.77, 0.73, and 0.84, respectively. ARIC-HF and FHS-HF yielded AUCs of 0.76 and 0.74, respectively, and CPH resulted in AUC = 0.78. ECG-AI-Cox outperformed all other models. ECG-AI-Cox provided an AUC of 0.85 for HFrEF and 0.83 for HFpEF.

Conclusion

ECG-AI using ECGs provides better-validated predictions when compared to HF risk calculators, and the ECG feature model and also works well with HFpEF and HFrEF classification.

Clinical Applications, Methodology, and Scientific Reporting of Electrocardiogram Deep-Learning Models: A Systematic Review

BACKGROUND

The electrocardiogram (ECG) is one of the most common diagnostic tools available to assess cardio-vascular health. The advent of advanced computational techniques such as deep learning has dramatically expanded the breadth of clinical problems that can be addressed using ECG data, leading to increasing popularity of ECG deep-learning models aimed at predicting clinical endpoints.

OBJECTIVES

The purpose of this study was to define the current landscape of clinically relevant ECG deep-learning models and examine practices in the scientific reporting of these studies.

METHODS

We performed a systematic review of PubMed and EMBASE databases to identify clinically relevant ECG deep-learning models published through July 1, 2022.

RESULTS

We identified 44 manuscripts including 53 unique, clinically relevant ECG deep-learning models. The rate of publication of ECG deep-learning models is increasing rapidly. The most common clinical applications of ECG deep learning were identification of cardiomyopathy (14/53 [26%]), followed by arrhythmia detection (9/53 [17%]). Methodologic reporting varied; while 33/44 (75%) publications included model architecture diagrams, complete information required to reproduce these models was provided in only 10/44 (23%). Saliency analysis was performed in 20/44 (46%) of publications. Only 18/53 (34%) models were tested within external validation cohorts. Model code or resources allowing for model implementation by external groups were available for only 5/44 (11%) publications.

CONCLUSIONS

While ECG deep-learning models are increasingly clinically relevant, their reporting is highly variable, and few publications provide sufficient detail for methodologic reproduction or model validation by external groups. The field of ECG deep learning would benefit from adherence to a set of standardized scientific reporting guidelines.

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.

Externally validated deep learning model to identify prodromal Parkinson's disease from electrocardiogram

Little is known about electrocardiogram (ECG) markers of Parkinson's disease (PD) during the prodromal stage. The aim of the study was to build a generalizable ECG-based fully automatic artificial intelligence (AI) model to predict PD risk during the prodromal stage, up to 5 years before disease diagnosis. This case-control study included samples from Loyola University Chicago (LUC) and University of Tennessee-Methodist Le Bonheur Healthcare (MLH). Cases and controls were matched according to specific characteristics (date, age, sex and race). Clinical data were available from May, 2014 onward at LUC and from January, 2015 onward at MLH, while the ECG data were available as early as 1990 in both institutes. PD was denoted by at least two primary diagnostic codes (ICD9 332.0; ICD10 G20) at least 30 days apart. PD incidence date was defined as the earliest of first PD diagnostic code or PD-related medication prescription. ECGs obtained at least 6 months before PD incidence date were modeled to predict a subsequent diagnosis of PD within three time windows: 6 months-1 year, 6 months-3 years, and 6 months-5 years. We applied a novel deep neural network using standard 10-s 12-lead ECGs to predict PD risk at the prodromal phase. This model was compared to multiple feature engineering-based models. Subgroup analyses for sex, race and age were also performed. Our primary prediction model was a one-dimensional convolutional neural network (1D-CNN) that was built using 131 cases and 1058 controls from MLH, and externally validated on 29 cases and 165 controls from LUC. The model was trained on 90% of the MLH data, internally validated on the remaining 10% and externally validated on LUC data. The best performing model resulted in an external validation AUC of 0.67 when predicting future PD at any time between 6 months and 5 years after the ECG. Accuracy increased when restricted to ECGs obtained within 6 months to 3 years before PD diagnosis (AUC 0.69) and was highest when predicting future PD within 6 months to 1 year (AUC 0.74). The 1D-CNN model based on raw ECG data outperformed multiple models built using more standard ECG feature engineering approaches. These results demonstrate that a predictive model developed in one cohort using only raw 10-s ECGs can effectively classify individuals with prodromal PD in an independent cohort, particularly closer to disease diagnosis. Standard ECGs may help identify individuals with prodromal PD for cost-effective population-level early detection and inclusion in disease-modifying therapeutic trials.

Automated electrocardiogram signal quality assessment based on Fourier analysis and template matching

We developed and tested a novel template matching approach for signal quality assessment on electrocardiogram (ECG) data. A computational method was developed that uses a sinusoidal approximation to the QRS complex to generate a correlation value at every point of an ECG. The strength of this correlation can be numerically adapted into a 'score' for each segment of an ECG, which can be used to stratify signal quality. The algorithm was tested on lead II ECGs of intensive care unit (ICU) patients admitted to the Mount Sinai Hospital (MSH) from January to July 2020 and on records from the MIT BIH arrhythmia database. The algorithm was found to be 98.9% specific and 99% sensitive on test data from the MSH ICU patients. The routine performs in linear O(n) time and occupies O(1) heap space in runtime. This approach can be used to lower the burden of pre-processing in ECG signal analysis. Given its runtime (O(n)) and memory (O(1)) complexity, there are potential applications for signal quality stratification and arrhythmia detection in wearable devices or smartphones.

Risk prediction of heart failure in patients with ischemic heart disease using network analytics and stacking ensemble learning

BACKGROUND

Heart failure (HF) is a major complication following ischemic heart disease (IHD) and it adversely affects the outcome. Early prediction of HF risk in patients with IHD is beneficial for timely intervention and for reducing disease burden.

METHODS

Two cohorts, cases for patients first diagnosed with IHD and then with HF (N = 11,862) and control IHD patients without HF (N = 25,652), were established from the hospital discharge records in Sichuan, China during 2015-2019. Directed personal disease network (PDN) was constructed for each patient, and then these PDNs were merged to generate the baseline disease network (BDN) for the two cohorts, respectively, which identifies the health trajectories of patients and the complex progression patterns. The differences between the BDNs of the two cohort was represented as disease-specific network (DSN). Three novel network features were exacted from PDN and DSN to represent the similarity of disease patterns and specificity trends from IHD to HF. A stacking-based ensemble model DXLR was proposed to predict HF risk in IHD patients using the novel network features and basic demographic features (i.e., age and sex). The Shapley Addictive exPlanations method was applied to analyze the feature importance of the DXLR model.

RESULTS

Compared with the six traditional machine learning models, our DXLR model exhibited the highest AUC (0.934 ± 0.004), accuracy (0.857 ± 0.007), precision (0.723 ± 0.014), recall (0.892 ± 0.012) and F₁ score (0.798 ± 0.010). The feature importance showed that the novel network features ranked as the top three features, playing a notable role in predicting HF risk of IHD patient. The feature comparison experiment also indicated that our novel network features were superior to those proposed by the state-of-the-art study in improving the performance of the prediction model, with an increase in AUC by 19.9%, in accuracy by 18.7%, in precision by 30.7%, in recall by 37.4%, and in F₁ score by 33.7%.

CONCLUSIONS

Our proposed approach that combines network analytics and ensemble learning effectively predicts HF risk in patients with IHD. This highlights the potential value of network-based machine learning in disease risk prediction field using administrative data.

Current and Future Use of Artificial Intelligence in Electrocardiography

Artificial intelligence (AI) is increasingly used in electrocardiography (ECG) to assist in diagnosis, stratification, and management. AI algorithms can help clinicians in the following areas: (1) interpretation and detection of arrhythmias, ST-segment changes, QT prolongation, and other ECG abnormalities; (2) risk prediction integrated with or without clinical variables (to predict arrhythmias, sudden cardiac death, stroke, and other cardiovascular events); (3) monitoring ECG signals from cardiac implantable electronic devices and wearable devices in real time and alerting clinicians or patients when significant changes occur according to timing, duration, and situation; (4) signal processing, improving ECG quality and accuracy by removing noise/artifacts/interference, and extracting features not visible to the human eye (heart rate variability, beat-to-beat intervals, wavelet transforms, sample-level resolution, etc.); (5) therapy guidance, assisting in patient selection, optimizing treatments, improving symptom-to-treatment times, and cost effectiveness (earlier activation of code infarction in patients with ST-segment elevation, predicting the response to antiarrhythmic drugs or cardiac implantable devices therapies, reducing the risk of cardiac toxicity, etc.); (6) facilitating the integration of ECG data with other modalities (imaging, genomics, proteomics, biomarkers, etc.). In the future, AI is expected to play an increasingly important role in ECG diagnosis and management, as more data become available and more sophisticated algorithms are developed.

A fully-automated paper ECG digitisation algorithm using deep learning

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60-70% and the average correlation of 3-by-1 ECGs achieved 80-90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects.

vital_sqi: A Python package for physiological signal quality control

Electrocardiogram (ECG) and photoplethysmogram (PPG) are commonly used to determine the vital signs of heart rate, respiratory rate, and oxygen saturation in patient monitoring. In addition to simple observation of those summarized indexes, waveform signals can be analyzed to provide deeper insights into disease pathophysiology and support clinical decisions. Such data, generated from continuous patient monitoring from both conventional bedside and low-cost wearable monitors, are increasingly accessible. However, the recorded waveforms suffer from considerable noise and artifacts and, hence, are not necessarily used prior to certain quality control (QC) measures, especially by those with limited programming experience. Various signal quality indices (SQIs) have been proposed to indicate signal quality. To facilitate and harmonize a wider usage of SQIs in practice, we present a Python package, named vital_sqi, which provides a unified interface to the state-of-the-art SQIs for ECG and PPG signals. The vital_sqi package provides with seven different peak detectors and access to more than 70 SQIs by using different settings. The vital_sqi package is designed with pipelines and graphical user interfaces to enable users of various programming fluency to use the package. Multiple SQI extraction pipelines can take the PPG and ECG waveforms and generate a bespoke SQI table. As these SQI scores represent the signal features, they can be input in any quality classifier. The package provides functions to build simple rule-based decision systems for signal segment quality classification using user-defined SQI thresholds. An experiment with a carefully annotated PPG dataset suggests thresholds for relevant PPG SQIs.

Korotkoff sounds dynamically reflect changes in cardiac function based on deep learning methods

Korotkoff sounds (K-sounds) have been around for over 100 years and are considered the gold standard for blood pressure (BP) measurement. K-sounds are also unique for the diagnosis and treatment of cardiovascular diseases; however, their efficacy is limited. The incidences of heart failure (HF) are increasing, which necessitate the development of a rapid and convenient pre-hospital screening method. In this review, we propose a deep learning (DL) method and the possibility of using K-methods to predict cardiac function changes for the detection of cardiac dysfunctions.

Artificial Intelligence (AI) and Internet of Medical Things (IoMT) Assisted Biomedical Systems for Intelligent Healthcare

Artificial intelligence (AI) is a modern approach based on computer science that develops programs and algorithms to make devices intelligent and efficient for performing tasks that usually require skilled human intelligence. AI involves various subsets, including machine learning (ML), deep learning (DL), conventional neural networks, fuzzy logic, and speech recognition, with unique capabilities and functionalities that can improve the performances of modern medical sciences. Such intelligent systems simplify human intervention in clinical diagnosis, medical imaging, and decision-making ability. In the same era, the Internet of Medical Things (IoMT) emerges as a next-generation bio-analytical tool that combines network-linked biomedical devices with a software application for advancing human health. In this review, we discuss the importance of AI in improving the capabilities of IoMT and point-of-care (POC) devices used in advanced healthcare sectors such as cardiac measurement, cancer diagnosis, and diabetes management. The role of AI in supporting advanced robotic surgeries developed for advanced biomedical applications is also discussed in this article. The position and importance of AI in improving the functionality, detection accuracy, decision-making ability of IoMT devices, and evaluation of associated risks assessment is discussed carefully and critically in this review. This review also encompasses the technological and engineering challenges and prospects for AI-based cloud-integrated personalized IoMT devices for designing efficient POC biomedical systems suitable for next-generation intelligent healthcare.

Artificial Intelligence in Cardiovascular Medicine: Current Insights and Future Prospects

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

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.