Left ventricular systolic dysfunction identification using artificial intelligence-augmented electrocardiogram in cardiac intensive care unit patients

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.

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.

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.

Performance of Off-the-Shelf Machine Learning Architectures and Biases in Detection of Low Left Ventricular Ejection Fraction

Artificial intelligence - machine learning (AI-ML) is a computational technique that has been demonstrated to be able to extract meaningful clinical information from diagnostic data that are not available using either human interpretation or more simple analysis methods. Recent developments have shown that AI-ML approaches applied to ECGs can accurately predict different patient characteristics and pathologies not detectable by expert physician readers. There is an extensive body of literature surrounding the use of AI-ML in other fields, which has given rise to an array of predefined open-source AI-ML architectures which can be translated to new problems in an "off-the-shelf" manner. Applying "off-the-shelf" AI-ML architectures to ECG-based datasets opens the door for rapid development and identification of previously unknown disease biomarkers. Despite the excellent opportunity, the ideal open-source AI-ML architecture for ECG related problems is not known. Furthermore, there has been limited investigation on how and when these AI-ML approaches fail and possible bias or disparities associated with particular network architectures. In this study, we aimed to: (1) determine if open-source, "off-the-shelf" AI-ML architectures could be trained to classify low LVEF from ECGs, (2) assess the accuracy of different AI-ML architectures compared to each other, and (3) to identify which, if any, patient characteristics are associated with poor AI-ML performance.

Artificial intelligence-augmented electrocardiography for left ventricular systolic dysfunction in patients undergoing high-sensitivity cardiac troponin T

AIMS

Our goal was to evaluate a previously validated artificial intelligence-augmented electrocardiography (AI-ECG) screening tool for left ventricular systolic dysfunction (LVSD) in patients undergoing high-sensitivity-cardiac troponin T (hs-cTnT).

METHODS AND RESULTS

Retrospective application of AI-ECG for LVSD in emergency department (ED) patients undergoing hs-cTnT. AI-ECG scores (0-1) for probability of LVSD (left ventricular ejection fraction ≤ 35%) were obtained. An AI-ECG score ≥0.256 indicates a positive screen. The primary endpoint was a composite of post-discharge major adverse cardiovascular events (MACEs) at two years follow-up. Among 1977 patients, 248 (13%) had a positive AI-ECG. When compared with patients with a negative AI-ECG, those with a positive AI-ECG had a higher risk for MACE [48 vs. 21%, P < 0.0001, adjusted hazard ratio (HR) 1.39, 95% confidence interval (CI) 1.11-1.75]. This was largely because of a higher rate of deaths (32 vs. 14%, P < 0.0001; adjusted HR 1.26, 95% 0.95-1.66) and heart failure hospitalizations (26 vs. 6.1%, P < 0.001; adjusted HR 1.75, 95% CI 1.25-2.45). Together, hs-cTnT and AI-ECG resulted in the following MACE rates and adjusted HRs: hs-cTnT < 99th percentile and negative AI-ECG: 116/1176 (11%; reference), hs-cTnT < 99th percentile and positive AI-ECG: 28/107 (26%; adjusted HR 1.54, 95% CI 1.01-2.36), hs-cTnT > 99th percentile and negative AI-ECG: 233/553 (42%; adjusted HR 2.12, 95% CI 1.66, 2.70), and hs-cTnT > 99th percentile and positive AI-ECG: 91/141 (65%; adjusted HR 2.83, 95% CI 2.06, 3.87).

CONCLUSION

Among ED patients evaluated with hs-cTnT, a positive AI-ECG for LVSD identifies patients at high risk for MACE. The conjoint use of hs-cTnT and AI-ECG facilitates risk stratification.

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.

Diagnostic AI and Cardiac Diseases

(1) Background: The purpose of this study is to review and highlight recent advances in diagnostic uses of artificial intelligence (AI) for cardiac diseases, in order to emphasize expected benefits to both patients and healthcare specialists; (2) Methods: We focused on four key search terms (Cardiac Disease, diagnosis, artificial intelligence, machine learning) across three different databases (Pubmed, European Heart Journal, Science Direct) between 2017-2022 in order to reach relatively more recent developments in the field. Our review was structured in order to clearly differentiate publications according to the disease they aim to diagnose (coronary artery disease, electrophysiological and structural heart diseases); (3) Results: Each study had different levels of success, where declared sensitivity, specificity, precision, accuracy, area under curve and F1 scores were reported for every article reviewed; (4) Conclusions: the number and quality of AI-assisted cardiac disease diagnosis publications will continue to increase through each year. We believe AI-based diagnosis should only be viewed as an additional tool assisting doctors' own judgement, where the end goal is to provide better quality of healthcare and to make getting medical help more affordable and more accessible, for everyone, everywhere.

A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System

The emerging field of eXplainable AI (XAI) in the medical domain is considered to be of utmost importance. Meanwhile, incorporating explanations in the medical domain with respect to legal and ethical AI is necessary to understand detailed decisions, results, and current status of the patient's conditions. Successively, we will be presenting a detailed survey for the medical XAI with the model enhancements, evaluation methods, significant overview of case studies with open box architecture, medical open datasets, and future improvements. Potential differences in AI and XAI methods are provided with the recent XAI methods stated as (i) local and global methods for preprocessing, (ii) knowledge base and distillation algorithms, and (iii) interpretable machine learning. XAI characteristics details with future healthcare explainability is included prominently, whereas the pre-requisite provides insights for the brainstorming sessions before beginning a medical XAI project. Practical case study determines the recent XAI progress leading to the advance developments within the medical field. Ultimately, this survey proposes critical ideas surrounding a user-in-the-loop approach, with an emphasis on human-machine collaboration, to better produce explainable solutions. The surrounding details of the XAI feedback system for human rating-based evaluation provides intelligible insights into a constructive method to produce human enforced explanation feedback. For a long time, XAI limitations of the ratings, scores and grading are present. Therefore, a novel XAI recommendation system and XAI scoring system are designed and approached from this work. Additionally, this paper encourages the importance of implementing explainable solutions into the high impact medical field.

Machine Learning Approaches for Phenotyping in Cardiogenic Shock and Critical Illness: Part 2 of 2

Progress in improving cardiogenic shock (CS) outcomes may have been limited by failure to embrace the heterogeneity of pathophysiologic processes driving the underlying syndrome. To better understand the variability inherent to CS populations, recent algorithms for describing underlying CS disease subphenotypes have been described and validated. These strategies hope to identify specific patient subgroups with more favorable responses to standard therapies, as well as those who require novel treatment approaches. This paper is part 2 of a 2-part state-of-the-art review. In this second article, we present machine learning-based statistical approaches to identifying subphenotypes and discuss their strengths and limitations, as well as evidence from other critical illness syndromes and emerging applications in CS. We then discuss how staging and stratification may be considered in CS clinical trials and finally consider future directions for this emerging area of research.

Electrocardiogram-Artificial Intelligence and Immune-Mediated Necrotizing Myopathy: Predicting Left Ventricular Dysfunction and Clinical Outcomes

Objective

To characterize the utility of an existing electrocardiogram (ECG)-artificial intelligence (AI) algorithm of left ventricular dysfunction (LVD) in immune-mediated necrotizing myopathy (IMNM).

Patients and Methods

A retrospective cohort observational study was conducted within our tertiary-care neuromuscular clinic for patients with IMNM meeting European Neuromuscular Centre diagnostic criteria (January 1, 2000, to December 31, 2020). A validated AI algorithm using 12-lead standard ECGs to detect LVD was applied. The output was presented as a percent probability of LVD. Electrocardiograms before and while on immunotherapy were reviewed. The LVD-predicted probability scores were compared with echocardiograms, immunotherapy treatment response, and mortality.

Results

The ECG-AI algorithm had acceptable accuracy in LVD prediction in 74% (68 of 89) of patients with IMNM with available echocardiograms (discrimination threshold, 0.74; 95% CI, 0.6-0.87). This translates into a sensitivity of 80.0% and specificity of 62.8% to detect LVD. Best cutoff probability prediction was 7 times more likely to have LVD (odds ratio, 6.75; 95% CI, 2.11-21.51; P=.001). Early detection occurred in 18% (16 of 89) of patients who initially had normal echocardiograms and were without cardiorespiratory symptoms, of which 6 subsequently advanced to LVD cardiorespiratory failure. The LVD probability scores improved for patients on immunotherapy (median slope, −3.96; R = −0.12; P=.002). Mortality risk was 7 times greater with abnormal LVD probability scores (hazard ratio, 7.33; 95% CI, 1.63-32.88; P=.009).

Conclusion

In IMNM, an AI-ECG algorithm assists detection of LVD, enhancing the decision to advance to echocardiogram testing, while also informing on mortality risk, which is important in the decision of immunotherapy escalation and monitoring.

Deep learning of ECG waveforms for diagnosis of heart failure with a reduced left ventricular ejection fraction

The performance and clinical implications of the deep learning aided algorithm using electrocardiogram of heart failure (HF) with reduced ejection fraction (DeepECG-HFrEF) were evaluated in patients with acute HF. The DeepECG-HFrEF algorithm was trained to identify left ventricular systolic dysfunction (LVSD), defined by an ejection fraction (EF) < 40%. Symptomatic HF patients admitted at Seoul National University Hospital between 2011 and 2014 were included. The performance of DeepECG-HFrEF was determined using the area under the receiver operating characteristic curve (AUC) values. The 5-year mortality according to DeepECG-HFrEF results was analyzed using the Kaplan–Meier method. A total of 690 patients contributing 18,449 ECGs were included with final 1291 ECGs eligible for the study (mean age 67.8 ± 14.4 years; men, 56%). HFrEF (+) identified an EF < 40% and HFrEF (−) identified EF ≥ 40%. The AUC value was 0.844 for identifying HFrEF among patients with acute symptomatic HF. Those classified as HFrEF (+) showed lower survival rates than HFrEF (−) (log-rank p < 0.001). The DeepECG-HFrEF algorithm can discriminate HFrEF in a real-world HF cohort with acceptable performance. HFrEF (+) was associated with higher mortality rates. The DeepECG-HFrEF algorithm may help in identification of LVSD and of patients at risk of worse survival in resource-limited settings.

Mortality Prediction in Cardiac Intensive Care Unit Patients: A Systematic Review of Existing and Artificial Intelligence Augmented Approaches

The medical complexity and high acuity of patients in the cardiac intensive care unit make for a unique patient population with high morbidity and mortality. While there are many tools for predictions of mortality in other settings, there is a lack of robust mortality prediction tools for cardiac intensive care unit patients. The ongoing advances in artificial intelligence and machine learning also pose a potential asset to the advancement of mortality prediction. Artificial intelligence algorithms have been developed for application of electrocardiogram interpretation with promising accuracy and clinical application. Additionally, artificial intelligence algorithms applied to electrocardiogram interpretation have been developed to predict various variables such as structural heart disease, left ventricular systolic dysfunction, and atrial fibrillation. These variables can be used and applied to new mortality prediction models that are dynamic with the changes in the patient's clinical course and may lead to more accurate and reliable mortality prediction. The application of artificial intelligence to mortality prediction will fill the gaps left by current mortality prediction tools.

Artificial Intelligence Application in Graves Disease: Atrial Fibrillation, Heart Failure and Menstrual Changes

OBJECTIVE

To study the utility of artificial intelligence (AI)-enabled electrocardiograms (ECGs) in patients with Graves disease (GD) in identifying patients at high risk of atrial fibrillation (AF) and heart failure with reduced ejection fraction (HFrEF), and to study whether AI-ECG can reflect hormonal changes and the resulting menstrual changes in GD.

PATIENTS AND METHODS

Patients diagnosed with GD between January 1, 2009, and December 31, 2019, were included. We considered AF diagnosed at 30 days or fewer before or any time after GD and de novo HFrEF not explained by ischemia, valve disorder, or other cardiomyopathy at/after GD diagnosis. Electrocardiograms at/after index condition were excluded. A subset analysis included females younger than 45 years of age to study the association between ECG-derived female probability and menstrual changes (shorter, lighter, or newly irregular cycles).

RESULTS

Among 430 patients (mean age, 50±17 years; 337 (78.4%) female), independent risk factors for AF included ECG probability of AF (hazard ratio [HR], 1.5; 95% CI, 1.2 to 1.6 per 10%; P<.001), older age (HR, 1.05; 95% CI, 1.03 to 1.07 per year; P<.001), and overt hyperthyroidism (HR, 3.9; 95% CI, 1.2 to 12.7; P=.03). The C-statistic was 0.85 for the combined model. Among 495 patients (mean age, 52±17 years; 374 (75.6%) female), independent risk factors for HFrEF were ECG probability of low ejection fraction (HR, 1.4; 95% CI, 1.1 to 1.6 per 10%; P=.001) and presence of AF (HR, 8.3; 95% CI, 2.2 to 30.9; P=.002), and a C-statistic of 0.89 for the combined model. Lastly, of 72 females younger than 45 years, 30 had menstrual changes at time of GD and had a significantly lower AI ECG-derived female probability [median 77.3; (IQR 57.9 to 94.4)% vs. median 97.7 (IQR 92.4 to 99.5)%, P<.001].

CONCLUSION

AI-enabled ECG identifies patients at risk for GD-related AF and HFrEF and was associated with menstrual changes in women with GD.

Artificial intelligence opportunities in cardio-oncology: Overview with spotlight on electrocardiography

Cardiovascular disease is a leading cause of death among cancer survivors, second only to cancer recurrence or development of new tumors. Cardio-oncology has therefore emerged as a relatively new specialty focused on prevention and management of cardiovascular consequences of cancer therapies. Yet challenges remain regarding precision and accuracy with predicting individuals at highest risk for cardiotoxicity. Barriers such as access to care also limit screening and early diagnosis to improve prognosis. Thus, developing innovative approaches for prediction and early detection of cardiovascular illness in this population is critical. In this review, we provide an overview of the present state of machine learning applications in cardio-oncology. We begin by outlining some factors that should be considered while utilizing machine learning algorithms. We then examine research in which machine learning has been applied to improve prediction of cardiac dysfunction in cancer survivors. We also highlight the use of artificial intelligence (AI) in conjunction with electrocardiogram (ECG) to predict cardiac malfunction and also atrial fibrillation (AF), and we discuss the potential role of wearables. Additionally, the article summarizes future prospects and critical takeaways for the application of machine learning in cardio-oncology. This study is the first in a series on artificial intelligence in cardio-oncology, and complements our manuscript on echocardiography and other forms of imaging relevant to cancer survivors cared for in cardiology clinical practice.

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

OBJECTIVES

This study sought to develop DL models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.

BACKGROUND

Rapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECGs) can assist diagnostic workflow. However, DL tools to estimate right- ventricular (RV) function do not exist, whereas those to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.

METHODS

A multicenter study was conducted with data from 5 New York City hospitals: 4 for internal testing and 1 serving as external validation. We created novel DL models to classify left ventricular ejection fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.

RESULTS

We obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used natural language processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients. For LVEF classification in internal testing, area under curve (AUC) at detection of LVEF ≤40%, 40% < LVEF ≤50%, and LVEF >50% was 0.94 (95% CI: 0.94-0.94), 0.82 (95% CI: 0.81-0.83), and 0.89 (95% CI: 0.89-0.89), respectively. For external validation, these results were 0.94 (95% CI: 0.94-0.95), 0.73 (95% CI: 0.72-0.74), and 0.87 (95% CI: 0.87-0.88). For regression, the mean absolute error was 5.84% (95% CI: 5.82%-5.85%) for internal testing and 6.14% (95% CI: 6.13%-6.16%) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (95% CI: 0.84-0.84) in both internal testing and external validation.

CONCLUSIONS

DL on ECG data can be used to create inexpensive screening, diagnostic, and predictive tools for both LV and RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

The application of deep learning in electrocardiogram: Where we came from and where we should go?

Electrocardiogram (ECG) is a commonly-used, non-invasive examination recording cardiac voltage versus time traces over a period. Deep learning technology, a robust artificial intelligence algorithm, can imitate the data processing patterns of the human brain, and it has experienced remarkable success in disease screening, diagnosis, and prediction. Compared with traditional machine learning, deep learning algorithms possess more powerful learning capabilities and can automatically extract features without extensive data pre-processing or hand-crafted feature extraction, which makes it a suitable tool to analyze complex structures of high-dimensional data. With the advances in computing power and digitized data availability, deep learning provides us an opportunity to improve ECG data interpretation with higher efficacy and accuracy and, more importantly, expand the original functions of ECG. The application of deep learning has led us to stand at the edge of ECG innovation and will potentially change the current clinical monitoring and management strategies. In this review, we introduce deep learning technology and summarize its advantages compared with traditional machine learning algorithms. Moreover, we provide an overview on the current application of deep learning in ECGs, with a focus on arrhythmia (especially atrial fibrillation during normal sinus rhythm), cardiac dysfunction, electrolyte imbalance, and sleep apnea. Last but not least, we discuss the current challenges and prospect directions for the following studies.