Accuracy of Physicians' Electrocardiogram Interpretations: A Systematic Review and Meta-analysis

Artificial neural networks for ECG interpretation in acute coronary syndrome: A scoping review

INTRODUCTION

The electrocardiogram (ECG) is a crucial diagnostic tool in the Emergency Department (ED) for assessing patients with Acute Coronary Syndrome (ACS). Despite its widespread use, the ECG has limitations, including low sensitivity of the STEMI criteria to detect Acute Coronary Occlusion (ACO) and poor inter-rater reliability. Emerging ECG features beyond the traditional STEMI criteria show promise in improving early ACO diagnosis, but complexity hinders widespread adoption. The potential integration of Artificial Neural Networks (ANN) holds promise for enhancing diagnostic accuracy and addressing reliability issues in ECG interpretation for ACO symptoms.

METHODS

Ovid MEDLINE, CINAHL, EMBASE, Cochrane, PubMed and Scopus were searched from inception through to 8th of December 2023. A thorough search of the grey literature and reference lists of relevant articles was also performed to identify additional studies. Articles were included if they reported the use of ANN for ECG interpretation of Acute Coronary Syndrome in the Emergency Department patients.

RESULTS

The search yielded a total of 244 articles. After removing duplicates and excluding non-relevant articles, 14 remained for analysis. There was significant heterogeneity in the types of ANN models used and the outcomes assessed, making direct comparisons challenging. Nevertheless, ANN appeared to demonstrate higher accuracy than physician interpreters for the evaluated outcomes and this proved independent of both specialty and years of experience.

CONCLUSIONS

The interpretation of ECGs in patients with suspected ACS using ANN appears to be accurate and potentially superior when compared to human interpreters and computerised algorithms. This appears consistent across various ANN models and outcome variables. Future investigations should emphasise ANN interpretation of ECGs in patients with ACO, where rapid and accurate diagnosis can significantly benefit patients through timely access to reperfusion therapies.

pECGreview: Assessment of a Novel Tool to Evaluate the Accuracy of Pediatric ECG Interpretation Skills

The skill of interpretation of the electrocardiogram (ECG) remains poor despite existing educational initiatives. We sought to evaluate the validity of using a subjective scoring system to assess the accuracy of ECG interpretations submitted by pediatric cardiology fellows, trainees, and faculty to the Pediatric ECG Review (pECGreview), a web-based ECG interpretation training program. We conducted a retrospective, cross-sectional study of responses submitted to pECGreview. ECG interpretations were assessed independently by four individuals with a range of experience. Accuracy was assessed using a 3-point scale: 100% for generally correct interpretations, 50% for over- or underdiagnosis of minor ECG abnormalities, and 0% for over- or underdiagnosis of major ECG abnormalities. Inter-rater agreement was assessed using expanded Bland-Altman plots, Pearson correlation coefficients, and Intraclass Correlation Coefficients (ICC). 1460 ECG interpretations by 192 participants were analyzed. 107 participants interpreted at least five ECGs. The mean accuracy score was 76.6 ± 13.7%. Participants were correct in 66.1 ± 5.1%, had minor over- or underdiagnosis in 21.5 ± 4.6% and major over- or underdiagnosis in 12.3 ± 3.9% of interpretations. Validation of agreement between evaluators demonstrated limits of agreement of 11.3%. Inter-rater agreement exhibited consistent patterns (all correlations ≥ 0.75). Absolute agreement was 0.74 (95% CI 0.69-0.80), and average measures agreement was 0.92 (95% CI 0.89-0.94). Accuracy score analysis of as few as five ECG interpretations submitted to pECGreview yielded good inter-rater reliability for assessing and ranking ECG interpretation skills in pediatric cardiology fellows in training.

Performance of Manchester Acute Coronary Syndromes decision rules in acute coronary syndrome: a systematic review and meta-analysis

BACKGROUND AND IMPORTANCE

Multiple decision-aiding models are available to help physicians identify acute coronary syndrome (ACS) and accelerate the decision-making process in emergency departments (EDs).

OBJECTIVE

This study evaluates the diagnostic performance of the Manchester Acute Coronary Syndrome (MACS) rule and its derivations, enhancing the evidence for their clinical use.

DESIGN

Systematic review and meta-analysis.

SETTINGS AND PARTICIPANTS

Medline, Embase, Scopus, and Web of Science were searched from inception until October 2023 for studies including adult ED patients with suspected cardiac chest pain and inconclusive findings requiring ACS risk-stratification.

OUTCOME MEASURES AND ANALYSIS

The predictive value of MACS, Troponin-only MACS (T-MACS), or History and Electrocardiogram-only MACS (HE-MACS) decision aids for diagnosing acute myocardial infarction (AMI) and 30-day major adverse cardiac outcomes (MACEs) among patients admitted to ED with chest pain suspected of ACS. Overall sensitivity and specificity were synthesized using the 'Diagma' package in STATA statistical software. Applicability and risk of bias assessment were performed using the QUADAS-2 tool.

MAIN RESULTS

For AMI detection, MACS has a sensitivity of 99% [confidence interval (CI): 97-100], specificity of 19% (CI: 10-32), and AUC of 0.816 (CI: 0.720-0.885). T-MACS shows a sensitivity of 98% (CI: 98-99), specificity of 35% (CI: 29-42), and AUC of 0.859 (CI: 0.824-0.887). HE-MACS exhibits a sensitivity of 99% (CI: 98-100), specificity of 9% (CI: 3-21), and AUC of 0.787 (CI: 0.647-0.882). For MACE detection, MACS demonstrates a sensitivity of 98% (CI: 94-100), specificity of 22% (CI: 10-42), and AUC of 0.804 (CI: 0.659-0.897). T-MACS displays a sensitivity of 96% (CI: 94-98), specificity of 36% (CI: 30-43), and AUC of 0.792 (CI: 0.748-0.830). HE-MACS maintains a sensitivity of 99% (CI: 97-99), specificity of 10% (CI 6-16), and AUC of 0.713 (CI: 0.625-0.787).

CONCLUSION

Of all the MACS models, T-MACS displayed the highest overall accuracy due to its high sensitivity and significantly superior specificity. T-MACS exhibits very good diagnostic performance in predicting both AMI and MACE. This makes it a highly promising tool for managing patients with acute chest pain.

Nurses' competency on electrocardiography interpretation in adult emergency room: Addis Ababa, Ethiopia, 2021. Multicenter cross-sectional study

AIM

This study aimed to assess the proficiency of nurses in interpreting electrocardiogram within the adult emergency units of Addis Ababa, Ethiopia, during the year 2021.

METHODS

This institutional-based descriptive, cross-sectional study involved 175 nurses from five randomly selected hospitals' adult emergency units. Semi-structured, self-administered questionnaires were used for data collection. Data were entered into Epi-Data and analyzed using SPSS version 26. Fisher's exact test identified statistical significance between dependent and independent variables at a p-value < 0.05.

RESULTS

Out of 203 respondents, 175 participated actively, yielding a response rate of 86.2%. Among these nurses, 159 (90.9%) were deemed not competent (scoring < 65%), with a mean score of 6.82 ± 3.65 SD.

PATIENT OR PUBLIC CONTRIBUTION

No patient or public contribution was included in this study.

CONCLUSION

The overall competency level in electrocardiogram interpretation among nurses is significantly poor. This indicates that most nurses in the emergency units are unable to accurately interpret ECG monitoring, potentially leading to the failure to recognize signs of arrhythmias, electrolyte disturbances, and other cardiac abnormalities. Consequently, this may result in inappropriate patient care and increased mortality rates. Education and training were identified as key factors in enhancing their competency.

Virtual Reality Simulation for the Acquisition and Retention of Electrocardiogram Interpretation Skills: A Randomized Controlled Trial Among Undergraduate Medical Students

Introduction The electrocardiogram (ECG) is one of the most important tools in diagnosing cardiac abnormalities, particularly arrhythmias and myocardial infarction. It is one of the certifiable competencies for final-year medical undergraduate students. We determined virtual reality's effectiveness in acquiring and retaining ECG interpretation skills among medical students compared to traditional teaching. Methods One hundred and forty students were randomized into two groups. Seventy-one students (immersion group) were trained using virtual reality simulation to acquire and retain interpretation skills of normal and abnormal ECG. Sixty-nine students (traditional group) were trained in the classroom using chalk and board. The primary outcome of change in acquiring knowledge of the interpretation of ECG was determined by comparing pre and post-test scores. The secondary outcome of retention of knowledge was determined by comparing pre-test and second post-test scores conducted after eight weeks of intervention. The p-value of <0.05 was considered significant. Results Out of 140 students, 50 (35.7%) were males and 90 (64.3%) were female. The mean age of the students was 22.1 (SD 1.1), with 69.3% of them between the ages of 21 and 22 years. Mean pre-test scores for the interpretation of normal ECG among immersion and traditional groups were 9.8 (SD 8.4) and 8.3 (SD 7.5), respectively, and post-test scores for the acquisition of knowledge were 24.3 (SD 5.5) and 24.8 (SD 6.3), respectively. The post-test scores for retention skills were 25.3 (SD 5.6) and 20.7 (SD 6.9) respectively (p<0.001). The mean pre-test scores for the interpretation of abnormal ECG of both groups were 7.0 (SD 6) and 8.3 (SD 6.6), respectively. Mean post-test scores for acquiring knowledge to interpret abnormal ECG were 23.5 (SD 6.2) and 17.7 (SD 9), respectively (p<0.001), and mean post-test scores for retention of interpretation skills of abnormal ECG were 19.2 (SD - 6.9) and 13.3 (SD 10.2) respectively (p=0.001). The pairwise comparison of the immersion group indicates that all the combinations that changed in score from the pre to post-intervention time points, from pre-to-retention time, and from the post-to-retention time were significant (p<0.001). Conclusion Virtual reality teaching had a better impact on acquiring and retaining the skill for interpreting normal and abnormal electrocardiograms.

[An intelligent model for classifying supraventricular tachycardia mechanisms based on 12-lead wearable electrocardiogram devices]

OBJECTIVE

To develop an intelligent model for differential diagnosis of atrioventricular nodal re-entrant tachycardia (AVNRT) and atrioventricular re-entrant tachycardia (AVRT) using 12-lead wearable electrocardiogram devices.

METHODS

A total of 356 samples of 12-lead supraventricular tachycardia (SVT) electrocardiograms recorded by wearable devices were randomly divided into training and validation sets using 5-fold cross validation to establish the intelligent classification model, and 101 patients with the diagnosis of SVT undergoing electrophysiological studies and radiofrequency ablation from October, 2021 to March, 2023 were selected as the testing set. The changes in electrocardiogram parameters before and during induced tachycardia were compared. Based on multiscale deep neural network, an intelligent diagnosis model for classifying SVT mechanisms was constructed and validated. The 3-lead electrocardiogram signals from Ⅱ, Ⅲ, and Ⅴ1 were extracted to build new classification models, whose diagnostic efficacy was compared with that of the 12-lead model.

RESULTS

Of the 101 patients with SVT in the testing set, 68 were diagnosed with AVNRT and 33 were diagnosed with AVRT by electrophysiological study. The pre-trained model achieved a high area under the precision-recall curve (0.9492) and F1 score (0.8195) for identifying AVNRT in the validation set. The total F1 scores of the lead Ⅱ, Ⅲ, Ⅴ1, 3-lead and 12-lead intelligent diagnostic models in the testing set were 0.5597, 0.6061, 0.3419, 0.6003 and 0.6136, respectively. Compared with the 12-lead classification model, the lead-Ⅲ model had a net reclassification index improvement of -0.029 (P=0.878) and an integrated discrimination index improvement of -0.005 (P=0.965).

CONCLUSION

The intelligent diagnostic model based on multiscale deep neural network using wearable electrocardiogram devices has an acceptable accuracy for classifying SVT mechanisms.

Advancing Fairness in Cardiac Care: Strategies for Mitigating Bias in Artificial Intelligence Models Within Cardiology

In the dynamic field of medical artificial intelligence (AI), cardiology stands out as a key area for its technological advancements and clinical application. In this review we explore the complex issue of data bias, specifically addressing those encountered during the development and implementation of AI tools in cardiology. We dissect the origins and effects of these biases, which challenge their reliability and widespread applicability in health care. Using a case study, we highlight the complexities involved in addressing these biases from a clinical viewpoint. The goal of this review is to equip researchers and clinicians with the practical knowledge needed to identify, understand, and mitigate these biases, advocating for the creation of AI solutions that are not just technologically sound, but also fair and effective for all patients.

Utility of RAND/UCLA appropriateness method in validating multiple-choice questions on ECG

OBJECTIVES

This study aimed to investigate the utility of the RAND/UCLA appropriateness method (RAM) in validating expert consensus-based multiple-choice questions (MCQs) on electrocardiogram (ECG).

METHODS

According to the RAM user's manual, nine panelists comprising various experts who routinely handle ECGs were asked to reach a consensus in three phases: a preparatory phase (round 0), an online test phase (round 1), and a face-to-face expert panel meeting (round 2). In round 0, the objectives and future timeline of the study were elucidated to the nine expert panelists with a summary of relevant literature. In round 1, 100 ECG questions prepared by two skilled cardiologists were answered, and the success rate was calculated by dividing the number of correct answers by 9. Furthermore, the questions were stratified into "Appropriate," "Discussion," or "Inappropriate" according to the median score and interquartile range (IQR) of appropriateness rating by nine panelists. In round 2, the validity of the 100 ECG questions was discussed in an expert panel meeting according to the results of round 1 and finally reassessed as "Appropriate," "Candidate," "Revision," and "Defer."

RESULTS

In round 1 results, the average success rate of the nine experts was 0.89. Using the median score and IQR, 54 questions were classified as " Discussion." In the expert panel meeting in round 2, 23% of the original 100 questions was ultimately deemed inappropriate, although they had been prepared by two skilled cardiologists. Most of the 46 questions categorized as "Appropriate" using the median score and IQR in round 1 were considered "Appropriate" even after round 2 (44/46, 95.7%).

CONCLUSIONS

The use of the median score and IQR allowed for a more objective determination of question validity. The RAM may help select appropriate questions, contributing to the preparation of higher-quality tests.

The Use of Animations Depicting Cardiac Electrical Activity to Improve Confidence in Understanding of Cardiac Pathology and Electrocardiography Traces Among Final-Year Medical Students: Nonrandomized Controlled Trial

Background

Electrocardiography (ECG) interpretation is a fundamental skill for medical students and practicing medical professionals. Recognizing ECG pathologies promptly allows for quick intervention, especially in acute settings where urgent care is needed. However, many medical students find ECG interpretation and understanding of the underlying pathology challenging, with teaching methods varying greatly.

Objective

This study involved the development of novel animations demonstrating the passage of electrical activity for well-described cardiac pathologies and showcased them alongside the corresponding live ECG traces during a web-based tutorial for final-year medical students. We aimed to assess whether the animations improved medical students' confidence in visualizing cardiac electrical activity and ECG interpretation, compared to standard ECG teaching methods.

Methods

Final-year medical students at Imperial College London attended a web-based tutorial demonstrating the 7 animations depicting cardiac electrical activity and the corresponding ECG trace. Another tutorial without the animations was held to act as a control. Students completed a questionnaire assessing their confidence in interpreting ECGs and visualizing cardiovascular electrical transmission before and after the tutorial. Intervention-arm participants were also invited to a web-based focus group to explore their experiences of past ECG teaching and the tutorial, particularly on aspects they found helpful and what could be further improved in the tutorial and animations. Wilcoxon signed-rank tests and Mann-Whitney U tests were used to assess the statistical significance of any changes in confidence. Focus group transcripts were analyzed using inductive thematic analysis.

Results

Overall, 19 students attended the intervention arm, with 15 (79%) completing both the pre- and posttutorial questionnaires and 15 (79%) participating in focus groups, whereas 14 students attended the control arm, with 13 (93%) completing both questionnaires. Median confidence in interpreting ECGs in the intervention arm increased after the tutorial (2, IQR 1.5-3.0 vs 3, IQR 3-4.5; P<.001). Improvement was seen in both confidence in reviewing or diagnosing cardiac rhythms and the visualization of cardiac electrical activity. However, there was no significant difference between the intervention and control arms, for all pathologies (all P>.05). The main themes from the thematic analysis were that ECGs are a complex topic and past ECG teaching has focused on memorizing traces; the visualizations enabled deeper understanding of cardiac pathology; and ECG learning requires repetition, and clinical links remain essential.

Conclusions

This study highlights the value of providing concise explanations of the meaning and pathophysiology behind ECG traces, both visually and verbally. ECG teaching that incorporates relevant pathophysiology, alongside vignettes with discussions regarding investigations and management options, is likely more helpful to students than practices based solely on pattern recognition. Although the animations supported student learning, the key element was the tutor's explanations. These animations may be more helpful as a supplement to teaching, for instance, as open-access videos.

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.

Scalar invariant transform based deep learning framework for detecting heart failures using ECG signals

Heart diseases are leading to death across the globe. Exact detection and treatment for heart disease in its early stages could potentially save lives. Electrocardiogram (ECG) is one of the tests that take measures of heartbeat fluctuations. The deviation in the signals from the normal sinus rhythm and different variations can help detect various heart conditions. This paper presents a novel approach to cardiac disease detection using an automated Convolutional Neural Network (CNN) system. Leveraging the Scale-Invariant Feature Transform (SIFT) for unique ECG signal image feature extraction, our model classifies signals into three categories: Arrhythmia (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR). The proposed model has been evaluated using 96 Arrhythmia, 30 CHF, and 36 NSR ECG signals, resulting in a total of 162 images for classification. Our proposed model achieved 99.78% accuracy and an F1 score of 99.78%, which is among one of the highest in the models which were recorded to date with this dataset. Along with the SIFT, we also used HOG and SURF techniques individually and applied the CNN model which achieved 99.45% and 78% accuracy respectively which proved that the SIFT-CNN model is a well-trained and performed model. Notably, our approach introduces significant novelty by combining SIFT with a custom CNN model, enhancing classification accuracy and offering a fresh perspective on cardiac arrhythmia detection. This SIFT-CNN model performed exceptionally well and better than all existing models which are used to classify heart diseases.

Advancing Cardiovascular Risk Assessment with Artificial Intelligence: Opportunities and Implications in North Carolina

Cardiovascular disease mortality is increasing in North Carolina with persistent inequality by race, income, and location. Artificial intelligence (AI) can repurpose the widely available electrocardiogram (ECG) for enhanced assessment of cardiac dysfunction. By identifying accelerated cardiac aging from the ECG, AI offers novel insights into risk assessment and prevention.

Context-independent identification of myocardial ischemia in the prehospital ECG of chest pain patients

Non-traumatic chest pain is a frequent reason for an urgent ambulance visit of a patient by the emergency medical services (EMS). Chest pain (or chest pain-equivalent symptoms) can be innocent, but it can also signal an acute form of severe pathology that may require prompt intervention. One of these pathologies is cardiac ischemia, resulting from a disbalance between blood supply and demand. One cause of a diminished blood supply to the heart is acute coronary syndrome (ACS, i.e., cardiac ischemia caused by a reduced blood supply to myocardial tissue due to plaque instability and thrombus formation in a coronary artery). ACS is dangerous due to the unpredictable process that drives the supply problem and the high chance of fast hemodynamic deterioration (i.e., cardiogenic shock, ventricular fibrillation). This is why an ECG is made at first medical contact in most chest pain patients to include or exclude ischemia as the cause of their complaints. For speedy and adequate triaging and treatment, immediate assessment of this prehospital ECG is necessary, still during the ambulance ride. Human diagnostic efforts supported by automated interpretation algorithms seek to answer questions regarding the urgency level, the decision if and towards which healthcare facility the patient should be transported, and the indicated acute treatment and further diagnostics after arrival in the healthcare facility. In the case of an ACS, a catheter intervention room may be activated during the ambulance ride to facilitate the earliest possible in-hospital treatment. Prehospital ECG assessment and the subsequent triaging decisions are complex because chest pain is not uniquely associated with ACS. The differential diagnosis includes other cardiac, pulmonary, vascular, gastrointestinal, orthopedic, and psychological conditions. Some of these conditions may also involve ECG abnormalities. In practice, only a limited fraction (order of magnitude 10%) of the patients who are urgently transported to the hospital because of chest pain are ACS patients. Given the relatively low prevalence of ACS in this patient mix, the specificity of the diagnostic ECG algorithms should be relatively high to prevent overtreatment and overflow of intervention facilities. On the other hand, only a sufficiently high sensitivity warrants adequate therapy when needed. Here, we review how the prehospital ECG can contribute to identifying the presence of myocardial ischemia in chest pain patients. We discuss the various mechanisms of myocardial ischemia and infarction, the typical patient mix of chest pain patients, the shortcomings of the ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI) ECG criteria to detect a completely occluded culprit artery, the OMI ECG criteria (including the STEMI-equivalent ECG patterns) in detecting completely occluded culprit arteries, and the promise of neural networks in recognizing ECG patterns that represent complete occlusions. We also discuss the relevance of detecting any ACS/ischemia, not necessarily caused by a total occlusion, in the prehospital ECG. In addition, we discuss how serial prehospital ECGs can contribute to ischemia diagnosis. Finally, we discuss the diagnostic contribution of a serial comparison of the prehospital ECG with a previously made nonischemic ECG of the patient.

Automatic triage of twelve-lead electrocardiograms using deep convolutional neural networks: a first implementation study

Aims

Expert knowledge to correctly interpret electrocardiograms (ECGs) is not always readily available. An artificial intelligence (AI)-based triage algorithm (DELTAnet), able to support physicians in ECG prioritization, could help reduce current logistic burden of overreading ECGs and improve time to treatment for acute and life-threatening disorders. However, the effect of clinical implementation of such AI algorithms is rarely investigated.

Methods and results

Adult patients at non-cardiology departments who underwent ECG testing as a part of routine clinical care were included in this prospective cohort study. DELTAnet was used to classify 12-lead ECGs into one of the following triage classes: normal, abnormal not acute, subacute, and acute. Performance was compared with triage classes based on the final clinical diagnosis. Moreover, the associations between predicted classes and clinical outcomes were investigated. A total of 1061 patients and ECGs were included. Performance was good with a mean concordance statistic of 0.96 (95% confidence interval 0.95-0.97) when comparing DELTAnet with the clinical triage classes. Moreover, zero ECGs that required a change in policy or referral to the cardiologist were missed and there was a limited number of cases predicted as acute that did not require follow-up (2.6%).

Conclusion

This study is the first to prospectively investigate the impact of clinical implementation of an ECG-based AI triage algorithm. It shows that DELTAnet is efficacious and safe to be used in clinical practice for triage of 12-lead ECGs in non-cardiology hospital departments.

Validation of an automated artificial intelligence system for 12‑lead ECG interpretation

BACKGROUND

The electrocardiogram (ECG) is one of the most accessible and comprehensive diagnostic tools used to assess cardiac patients at the first point of contact. Despite advances in computerized interpretation of the electrocardiogram (CIE), its accuracy remains inferior to physicians. This study evaluated the diagnostic performance of an artificial intelligence (AI)-powered ECG system and compared its performance to current state-of-the-art CIE.

METHODS

An AI-powered system consisting of 6 deep neural networks (DNN) was trained on standard 12‑lead ECGs to detect 20 essential diagnostic patterns (grouped into 6 categories: rhythm, acute coronary syndrome (ACS), conduction abnormalities, ectopy, chamber enlargement and axis). An independent test set of ECGs with diagnostic consensus of two expert cardiologists was used as a reference standard. AI system performance was compared to current state-of-the-art CIE. The key metrics used to compare performances were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score.

RESULTS

A total of 932,711 standard 12‑lead ECGs from 173,949 patients were used for AI system development. The independent test set pooled 11,932 annotated ECG labels. In all 6 diagnostic categories, the DNNs achieved high F1 scores: Rhythm 0.957, ACS 0.925, Conduction abnormalities 0.893, Ectopy 0.966, Chamber enlargement 0.972, and Axis 0.897. The diagnostic performance of DNNs surpassed state-of-the-art CIE for the 13 out of 20 essential diagnostic patterns and was non-inferior for the remaining individual diagnoses.

CONCLUSIONS

Our results demonstrate the AI-powered ECG model's ability to accurately identify electrocardiographic abnormalities from the 12‑lead ECG, highlighting its potential as a clinical tool for healthcare professionals.

Impact of automatic acquisition of key clinical information on the accuracy of electrocardiogram interpretation: a cross-sectional study

BACKGROUND

The accuracy of electrocardiogram (ECG) interpretation by doctors are affected by the available clinical information. However, having a complete set of clinical details before making a diagnosis is very difficult in the clinical setting especially in the early stages of the admission process. Therefore, we developed an artificial intelligence-assisted ECG diagnostic system (AI-ECG) using natural language processing to provide screened key clinical information during ECG interpretation.

METHODS

Doctors with varying levels of training were asked to make diagnoses from 50 ECGs using a common ECG diagnosis system that does not contain clinical information. After a two-week-blanking period, the same set of ECGs was reinterpreted by the same doctors with AI-ECG containing clinical information. Two cardiologists independently provided diagnostic criteria for 50 ECGs, and discrepancies were resolved by consensus or, if necessary, by a third cardiologist. The accuracy of ECG interpretation was assessed, with each response scored as correct/partially correct = 1 or incorrect = 0.

RESULTS

The mean accuracy of ECG interpretation was 30.2% and 36.2% with the common ECG system and AI-ECG system, respectively. Compared to the unaided ECG system, the accuracy of interpretation was significantly improved with the AI-ECG system (P for paired t-test = 0.002). For senior doctors, no improvement was found in ECG interpretation accuracy, while an AI-ECG system was associated with 27% higher mean scores (24.3 ± 9.4% vs. 30.9 ± 10.6%, P = 0.005) for junior doctors.

CONCLUSION

Intelligently screened key clinical information could improve the accuracy of ECG interpretation by doctors, especially for junior doctors.

Can Orthopaedic Surgeons adequately assess an Electrocardiogram (ECG) trace paper? A cross sectional study

Objectives

The primary objective was to evaluate the ECG trace paper evaluation current knowledge level in a group of Orthopaedic surgeons divided into juniors and seniors according to M.D. degree possession.

Methods

A cross sectional study through self-administered questionnaires at a university hospital Orthopaedic and Trauma Surgery Department. The questionnaire included five sections: 1-Basic participants' characteristics, 2-Participants' perception of their ECG evaluation current knowledge level, 3-The main body of the questionnaire was an ECG quiz (seven); the participant was asked to determine if it was normal and the possible diagnosis, 4-Participants' desired ECG evaluation knowledge level, and 5-Willingness to attend ECG evaluation workshops.

Results

Of the 121 actively working individuals in the department, 96 (97.3 %) finished the questionnaire, and 85 (77.3 %) were valid for final evaluation. The participants' mean age was 30.4 ± 6.92 years, 76.5 % juniors and 23.5 % seniors. 83.5 % of the participants perceived their current ECG evaluation knowledge as none or limited. For participants' ability to evaluate an ECG, higher scores were achieved when determining if the ECG was normal or abnormal, with a mean score percentage of 79.32 % ± 23.27. However, the scores were lower when trying to reach the diagnosis, with a mean score percentage of 43.02 % ± 27.48. There was a significant negative correlation between the participant's age and answering the normality question correctly (r = -0.277, p = 0.01); and a significant positive correlation between answering the diagnosis question correctly and the desired level of knowledge and the intention to attend a workshop about ECG evaluation, r = 0.355 (p = 0.001), and r = 0.223 (p = 0.04), respectively. Only 56.5 % of the participants desired to get more knowledge, and 81.2 % were interested in attending ECG evaluation workshops.

Conclusion

Orthopaedic surgeons showed sufficient knowledge when determining the normality of ECG trace papers; however, they could not reach the proper diagnosis, and Junior surgeons performed slightly better than their senior peers. Most surgeons are willing to attend ECG evaluation and interpretation workshops to improve their knowledge level.

An Open-Source Graphical User Interface-Embedded Automated Electrocardiogram Quality Assessment: A Balanced Class Representation Approach

The rise in cardiovascular diseases necessitates accurate electrocardiogram (ECG) diagnostics, making high-quality ECG recordings essential. Our CNN-LSTM model, embedded in an open-access GUI and trained on balanced datasets collected in clinical settings, excels in automating ECG quality assessment. When tested across three datasets featuring varying ratios of acceptable to unacceptable ECG signals, it achieved an F1 score ranging from 95.87% to 98.40%. Training the model on real noise sources significantly enhances its applicability in real-life scenarios, compared to simulations. Integrated into a user-friendly toolbox, the model offers practical utility in clinical environments. Furthermore, our study underscores the importance of balanced class representation during training and testing phases. We observed a notable F1 score change from 98.09% to 95.87% when the class ratio shifted from 85:15 to 50:50 in the same testing dataset with equal representation. This finding is crucial for future ECG quality assessment research, highlighting the impact of class distribution on the reliability of model training outcomes.

The HEARTS ECG workshop: a novel approach to resident and student ECG education

OBJECTIVES

ECG interpretation is a life-saving skill in emergency medicine (EM), and a core competency in undergraduate medical curricula; however, confidence for residents/students is low. We developed a novel educational intervention-the HEARTS ECG workshop-that provides a systematic approach to ECG interpretation, teaches EM residents through the process of teaching medical students and highlights emergency management.

METHODS

We used the Kern Approach to Curriculum Development. A review of ECG education literature and a targeted needs assessment of local students/residents led to goals and objectives including systematic ECG interpretation with clinical relevance. ECGs were selected based on a national consensus of EM program directors and categorized into 5 common emergency presentations. The educational strategy included content based on HEARTS approach (Heart rate/rhythm, Electrical conduction, Axis, R-wave progression, Tall/small voltages, and ST/T changes), and methods including flipped classroom and near-peer teaching. Evaluation and feedback were based on the Kirkpatrick program evaluation. The workshop was piloted with 6 junior EM residents and 58 medical students, and repeated with nine residents and 68 students from four medical schools.

RESULTS

Residents and students agreed or strongly agreed that the workshop improved their perceived ability (100% and 95%, respectively) and confidence (77% and 88%, respectively) in interpreting ECGs. Reports of ECG interpretation causing anxiety declined from pre-workshop (61% and 83% respectively) to post-workshop (38% and 37% respectively). Residents reported behavior change: 3 months after the workshop, 92.3% reported ongoing use of the HEARTS approach clinically and through teaching medical students on shifts. Reported workshop strengths included the pre-workshop material, the clinical application, facilitator-to-learner ratio, interactivity, the ease of remembering and applying the HEARTS mnemonic, and the iterative application of the approach. Suggested changes included longitudinal sessions with graded difficulty, and allocating more time for introductory material for ease of understanding.

CONCLUSION

The HEARTS ECG workshop is an innovative pedagogical method that can be adapted for all levels of training. Future directions include integration in undergraduate medical and EM residency curricula, and workshops for physicians to update ECG interpretation skills.

Electrocardiographic interpretation by emergency medical services professionals in Saudi Arabia: A cross sectional study

BACKGROUND

Management of acute myocardial infarction (AMI) and cardiac arrhythmias in prehospital settings is largely determined by providers of emergency medical services (EMS) who can proficiently interpret the electrocardiography (ECG). The aim of this study was to assess the ECG competency of EMS providers in Saudi Arabia.

METHODS

Between Aug and Sep 2022, we invited all EMS providers working for the Saudi Red Crescent Authority in Makkah, Riyadh, and Sharqiyah regions to complete a cross-sectional survey. The survey was used to assess the ability of EMS providers to interpret 12 ECG strips. Characteristics and ECG competency were summarized using descriptive statistics. Differences in ECG competency across paramedics with lower and higher qualifications were assessed.

RESULTS

During the study period, 231 participants completed the survey, and all were included. The overall mean age was 33.4, and most participants were male (94.8%). Nearly half of the participants were paramedics with an associate degree and 46.4% were paramedics with higher degrees. The average rate of correct answers to the 12 ECG strips was 43.3% (95% CI: 35.4%, 51.3%). Atrial flutter, ventricular fibrillation, atrial fibrillation, 3rd degree heart block, and ventricular tachycardia were identified by 52.8%, 60.2%, 42.0%, 40.7%, and 49.4% of the participants, respectively. The strip with an AMI was identified by 41.1%, while a pathological Q wave and ventricular extrasystole were identified by 19.1% and 24.7%, respectively. Paramedics with higher qualifications were as 28.0%-61.0% more likely to correctly interpret the 12 ECG strips compared to those with an associate degree (p-value across all variables was ≤ 0.001).

CONCLUSION

While the majority of participants in our region were unable to correctly answer the 12 ECG questionnaire, paramedics with higher qualifications were. Our study indicates that there is a need for evidenced-based ECG curricula targeting different levels of EMS professionals.

Learn ECG Through a New Class of Graphics

Electrocardiography (ECG) is widely used in clinical diagnosis, but it is complicated to learn. We designed a new kind of graphic for learning ECG. Herein, we described the construction method of such graphics and some characteristics of graphics. At last, we discussed its potential value.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40670-023-01855-3.

Machine learning for the diagnosis of acute coronary syndrome using a 12-lead ECG: a systematic review

OBJECTIVES

Prompt diagnosis of acute coronary syndrome (ACS) using a 12-lead electrocardiogram (ECG) is a critical task for emergency physicians. While computerized algorithms for ECG interpretation are limited in their accuracy, machine learning (ML) models have shown promise in several areas of clinical medicine. We performed a systematic review to compare the performance of ML-based ECG analysis to clinician or non-ML computerized ECG interpretation in the diagnosis of ACS for emergency department (ED) or prehospital patients.

METHODS

We searched Medline, Embase, Cochrane Central, and CINAHL databases from inception to May 18, 2022. We included studies that compared ML algorithms to either clinicians or non-ML based software in their ability to diagnose ACS using only a 12-lead ECG, in adult patients experiencing chest pain or symptoms concerning for ACS in the ED or prehospital setting. We used QUADAS-2 for risk of bias assessment. Prospero registration CRD42021264765.

RESULTS

Our search yielded 1062 abstracts. 10 studies met inclusion criteria. Five model types were tested, including neural networks, random forest, and gradient boosting. In five studies with complete performance data, ML models were more sensitive but less specific (sensitivity range 0.59-0.98, specificity range 0.44-0.95) than clinicians (sensitivity range 0.22-0.93, specificity range 0.63-0.98) in diagnosing ACS. In four studies that reported it, ML models had better discrimination (area under ROC curve range 0.79-0.98) than clinicians (area under ROC curve 0.67-0.78). Heterogeneity in both methodology and reporting methods precluded a meta-analysis. Several studies had high risk of bias due to patient selection, lack of external validation, and unreliable reference standards for ACS diagnosis.

CONCLUSIONS

ML models have overall higher discrimination and sensitivity but lower specificity than clinicians and non-ML software in ECG interpretation for the diagnosis of ACS. ML-based ECG interpretation could potentially serve a role as a "safety net", alerting emergency care providers to a missed acute MI when it has not been diagnosed. More rigorous primary research is needed to definitively demonstrate the ability of ML to outperform clinicians at ECG interpretation.

Assessment of real-time electrocardiogram effects on interpretation quality by emergency physicians

BACKGROUND

Electrocardiogram (ECG) is one of the most commonly performed examinations in emergency medicine. The literature suggests that one-third of ECG interpretations contain errors and can lead to clinical adverse outcomes. The purpose of this study was to assess the quality of real-time ECG interpretation by senior emergency physicians compared to cardiologists and an ECG expert.

METHODS

This was a prospective study in two university emergency departments and one emergency medical service. All ECGs were performed and interpreted over five weeks by a senior emergency physician (EP) and then by a cardiologist using the same questionnaire. In case of mismatch between EP and the cardiologist our expert had the final word. The ratio of agreement between both interpretations and the kappa (k) coefficient characterizing the identification of major abnormalities defined the reading ability of the emergency physicians.

RESULTS

A total of 905 ECGs were analyzed, of which 705 (78%) resulted in a similar interpretation between emergency physicians and cardiologists/expert. However, the interpretations of emergency physicians and cardiologists for the identification of major abnormalities coincided in only 66% (k: 0.59 (95% confidence interval (CI): 0.54-0.65); P-value = 1.64e-92). ECGs were correctly classified by emergency physicians according to their emergency level in 82% of cases (k: 0.73 (95% CI: 0.70-0.77); P-value ≈ 0). Emergency physicians correctly recognized normal ECGs (sensitivity = 0.91).

CONCLUSION

Our study suggested gaps in the identification of major abnormalities among emergency physicians. The initial and ongoing training of emergency physicians in ECG reading deserves to be improved.

Self-Attention LSTM-FCN model for arrhythmia classification and uncertainty assessment

This paper presents ArrhyMon, a self-attention-based LSTM-FCN model for arrhythmia classification from ECG signal inputs. ArrhyMon targets to detect and classify six different types of arrhythmia apart from normal ECG patterns. To the best of our knowledge, ArrhyMon is the first end-to-end classification model that successfully targets the classification of six detailed arrhythmia types and compared to previous work does not require additional preprocessing and/or feature extraction operations separate from the classification model. ArrhyMon's deep learning model is designed to capture and exploit both global and local features embedded in ECG sequences by integrating fully convolutional network (FCN) layers and a self-attention-based long and short-term memory (LSTM) architecture. Moreover, to enhance its practicality, ArrhyMon incorporates a deep ensemble-based uncertainty model that generates a confidence-level measure for each classification result. We evaluate ArrhyMon's effectiveness using three publicly available arrhythmia datasets (i.e., MIT-BIH, Physionet Cardiology Challenge 2017 and 2020/2021) to show that ArrhyMon achieves state-of-the-art classification performance (average accuracy 99.63%), and that confidence measures show close correlation with subjective diagnosis made from practitioners.

Data Analysis of Physician Competence Research Trend: Social Network Analysis and Topic Modeling Approach

BACKGROUND

Studies on competency in medical education often explore the acquisition, performance, and evaluation of particular skills, knowledge, or behaviors that constitute physician competency. As physician competency reflects social demands according to changes in the medical environment, analyzing the research trends of physician competency by period is necessary to derive major research topics for future studies. Therefore, a more macroscopic method is required to analyze the core competencies of physicians in this era.

OBJECTIVE

This study aimed to analyze research trends related to physicians' competency in reflecting social needs according to changes in the medical environment.

METHODS

We used topic modeling to identify potential research topics by analyzing data from studies related to physician competency published between 2011 and 2020. We preprocessed 1354 articles and extracted 272 keywords.

RESULTS

The terms that appeared most frequently in the research related to physician competency since 2010 were knowledge, hospital, family, job, guidelines, management, and communication. The terms that appeared in most studies were education, model, knowledge, and hospital. Topic modeling revealed that the main topics about physician competency included Evidence-based clinical practice, Community-based healthcare, Patient care, Career and self-management, Continuous professional development, and Communication and cooperation. We divided the studies into 4 periods (2011-2013, 2014-2016, 2017-2019, and 2020-2021) and performed a linear regression analysis. The results showed a change in topics by period. The hot topics that have shown increased interest among scholars over time include Community-based healthcare, Career and self-management, and Continuous professional development.

CONCLUSIONS

On the basis of the analysis of research trends, it is predicted that physician professionalism and community-based medicine will continue to be studied in future studies on physician competency.

Machine learning for ECG diagnosis and risk stratification of occlusion myocardial infarction

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting electrocardiogram (ECG) are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but, currently, there are no accurate tools to identify them during initial triage. Here we report, to our knowledge, the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI. Using 7,313 consecutive patients from multiple clinical sites, we derived and externally validated an intelligent model that outperformed practicing clinicians and other widely used commercial interpretation systems, substantially boosting both precision and sensitivity. Our derived OMI risk score provided enhanced rule-in and rule-out accuracy relevant to routine care, and, when combined with the clinical judgment of trained emergency personnel, it helped correctly reclassify one in three patients with chest pain. ECG features driving our models were validated by clinical experts, providing plausible mechanistic links to myocardial injury.

Protocol for development of an assessment tool for competency of ECG interpretation: expert consensus by the RAND/UCLA appropriateness method and cross-sectional testing using multidimensional item response theory

INTRODUCTION

Although the ECG is an important diagnostic tool in medical practice, the competency of ECG interpretation is considered to be poor. Diagnostic inaccuracy involving the misinterpretation of ECG can lead to inappropriate medical judgements and cause negative clinical outcomes, unnecessary medical testing and even fatalities. Despite the importance of assessing ECG interpretation skills, there is currently no established universal, standardised assessment tool for ECG interpretation. The current study seeks to (1) develop a set of items (ECG questions) for estimating competency of ECG interpretation by medical personnel by consensus among expert panels following a process based on the RAND/UCLA Appropriateness Method (RAM) and (2) analyse item parameters and multidimensional latent factors of the test set to develop an assessment tool.

METHODS AND ANALYSIS

This study will be conducted in two steps: (1) selection of question items for ECG interpretation assessment by expert panels via a consensus process following RAM and (2) cross-sectional, web-based testing using a set of ECG questions. A multidisciplinary panel of experts will evaluate the answers and appropriateness and select 50 questions as the next step. Based on data collected from a predicted sample size of 438 test participants recruited from physicians, nurses, medical and nursing students, and other healthcare professionals, we plan to statistically analyse item parameters and participant performance using multidimensional item response theory. Additionally, we will attempt to detect possible latent factors in the competency of ECG interpretation. A test set of question items for ECG interpretation will be proposed on the basis of the extracted parameters.

ETHICS AND DISSEMINATION

The protocol of this study was approved by the Institutional Review Board of Ehime University Graduate School of Medicine (IRB number: 2209008). We will obtain informed consent from all participants. The findings will be submitted for publication in peer-reviewed journals.

Comparing the effectiveness of asynchronous e-modules and didactic lectures to teach electrocardiogram interpretation to first year US medical students

BACKGROUND

Medical students are expected to be competent in interpreting electrocardiograms (ECGs) by the time they graduate, but many are unable to master this skill. Studies suggest that e-modules are an effective way to teach ECG interpretation, however they are typically evaluated for use during clinical clerkships. We sought to determine if an e-module could replace a didactic lecture to teach ECG interpretation during a preclinical cardiology course.

METHODS

We developed an asynchronous, interactive e-module that consisted of narrated videos, pop-up questions and quizzes with feedback. Participants were first year medical students who were either taught ECG interpretation during a 2-hour didactic lecture (control group) or were given unlimited access to the e-module (e-module group). First-year internal medicine residents (PGY1 group) were included to benchmark where ECG interpretation skills should be at graduation. At three time-points (pre-course, post-course, and 1-year follow-up), participants were evaluated for ECG knowledge and confidence. A mixed-ANOVA was used to compare groups over time. Students were also asked to describe what additional resources they used to learn ECG interpretation throughout the study.

RESULTS

Data was available for 73 (54%) students in the control group, 112 (81%) in the e-module group and 47 (71%) in the PGY1 group. Pre-course scores did not differ between the control and e-module groups (39% vs. 38%, respectively). However, the e-module group performed significantly better than the control group on the post-course test (78% vs. 66%). In a subsample with 1-year follow-up data, the e-module group's performance decreased, and the control group remained the same. The PGY1 groups' knowledge scores were stable over time. Confidence in both medical student groups increased by the end of the course, however only pre-course knowledge and confidence were significantly correlated. Most students relied on textbooks and course materials for learning ECG, however online resources were also utilized.

CONCLUSIONS

An asynchronous, interactive e-module was more effective than a didactic lecture for teaching ECG interpretation, however continued practice is needed regardless of how students learn to interpret ECGs. Various ECG resources are available to students to support their self-regulated learning.

Surfing the clinical trials of ECG teaching to medical students: A systematic review

Interpreting an electrocardiogram (ECG) is crucial for every physician. The physician's competency in ECG interpretation needs to be improved at any stage of medical education. The aim of the present study was to review the currently published clinical trials of ECG teaching to medical students and provide suggestions for future works. On May 1, 2022, PubMed, Scopus, Web of Science, Google Scholar, and ERIC were searched to retrieve relevant articles on clinical trials of ECG teaching to medical students. The quality of the included studies was assessed utilizing the Buckley et al. criteria. The screening, data extraction, and quality appraisal processes were duplicated independently. In case of disagreements, consultation with a third author was put forth. In total, 861 citations were found in the databases. After screening abstracts and full texts, 23 studies were deemed eligible. The majority of the studies were of good quality. Peer teaching (7 studies), self-directed learning (6 studies), web-based learning (10 studies), and various assessment modalities (3 studies) comprised the key themes of the studies. Various methods of ECG teaching were encountered in the reviewed studies. Future studies in ECG training should focus on novel and creative teaching methods, the extent to which self-directed learning can be effective, the utility of peer teaching, and the implications of computer-assisted ECG interpretation (e.g., artificial intelligence) for medical students. Long-term knowledge retention assessment studies based on different approaches integrated with clinical outcomes could be beneficial in determining the most efficient modalities.

ECG Classification Using an Optimal Temporal Convolutional Network for Remote Health Monitoring

Increased life expectancy in most countries is a result of continuous improvements at all levels, starting from medicine and public health services, environmental and personal hygiene to the use of the most advanced technologies by healthcare providers. Despite these significant improvements, especially at the technological level in the last few decades, the overall access to healthcare services and medical facilities worldwide is not equally distributed. Indeed, the end beneficiary of these most advanced healthcare services and technologies on a daily basis are mostly residents of big cities, whereas the residents of rural areas, even in developed countries, have major difficulties accessing even basic medical services. This may lead to huge deficiencies in timely medical advice and assistance and may even cause death in some cases. Remote healthcare is considered a serious candidate for facilitating access to health services for all; thus, by using the most advanced technologies, providing at the same time high quality diagnosis and ease of implementation and use. ECG analysis and related cardiac diagnosis techniques are the basic healthcare methods providing rapid insights in potential health issues through simple visualization and interpretation by clinicians or by automatic detection of potential cardiac anomalies. In this paper, we propose a novel machine learning (ML) architecture for the ECG classification regarding five heart diseases based on temporal convolution networks (TCN). The proposed design, which implements a dilated causal one-dimensional convolution on the input heartbeat signals, seems to be outperforming all existing ML methods with an accuracy of 96.12% and an F1 score of 84.13%, using a reduced number of parameters (10.2 K). Such results make the proposed TCN architecture a good candidate for low power consumption hardware platforms, and thus its potential use in low cost embedded devices for remote health monitoring.

Machine Learning for the ECG Diagnosis and Risk Stratification of Occlusion Myocardial Infarction at First Medical Contact

Patients with occlusion myocardial infarction (OMI) and no ST-elevation on presenting ECG are increasing in numbers. These patients have a poor prognosis and would benefit from immediate reperfusion therapy, but we currently have no accurate tools to identify them during initial triage. Herein, we report the first observational cohort study to develop machine learning models for the ECG diagnosis of OMI. Using 7,313 consecutive patients from multiple clinical sites, we derived and externally validated an intelligent model that outperformed practicing clinicians and other widely used commercial interpretation systems, significantly boosting both precision and sensitivity. Our derived OMI risk score provided superior rule-in and rule-out accuracy compared to routine care, and when combined with the clinical judgment of trained emergency personnel, this score helped correctly reclassify one in three patients with chest pain. ECG features driving our models were validated by clinical experts, providing plausible mechanistic links to myocardial injury.

Personalized LSTM Models for ECG Lead Transformations Led to Fewer Diagnostic Errors Than Generalized Models: Deriving 12-Lead ECG from Lead II, V2, and V6

BACKGROUND AND OBJECTIVE

The prevalence of chronic cardiovascular diseases (CVDs) has risen globally, nearly doubling from 1990 to 2019. ECG is a simple, non-invasive measurement that can help identify CVDs at an early and treatable stage. A multi-lead ECG, up to 15 leads in a wearable form factor, is desirable. We seek to derive multiple ECG leads from a select subset of leads so that the number of electrodes can be reduced in line with a patient-friendly wearable device. We further compare personalized derivations to generalized derivations.

METHODS

Long-Short Term Memory (LSTM) networks using Lead II, V2, and V6 as input are trained to obtain generalized models using Bayesian Optimization for hyperparameter tuning for all patients and personalized models for each patient by applying transfer learning to the generalized models. We compare quantitatively using error metrics Root Mean Square Error (RMSE), R², and Pearson correlation (ρ). We compare qualitatively by matching ECG interpretations of board-certified cardiologists.

RESULTS

ECG interpretations from personalized models, when corrected for an intra-observer variance, were identical to the original ECGs, whereas generalized models led to errors. Mean performance values for generalized and personalized models were (RMSE-74.31 µV, R²-72.05, ρ-0.88) and (RMSE-26.27 µV, R²-96.38, ρ-0.98), respectively.

CONCLUSIONS

Diagnostic accuracy based on derived ECG is the most critical validation of ECG derivation methods. Personalized transformation should be sought to derive ECGs. Performing a personalized calibration step to wearable ECG systems and LSTM networks could yield ambulatory 15-lead ECGs with accuracy comparable to clinical ECGs.

EKG Acquisition Curriculum for Pediatric Trainees

OBJECTIVES

Pediatric residency trainees interface with electrocardiograms (EKG) as part of routine clinical care. Depending on workflow and availability of support staff, trainees may be required to obtain EKGs on patients, though training on this skill varies. Our intervention seeks to train incoming pediatric residents on obtaining EKGs from pediatric patients and identifying common problems that may result in acquisition of low-fidelity EKGs.

METHODS

A team of physicians, EKG technicians, and simulation educators designed a 30-min didactic and experiential learning opportunity for incoming pediatric trainees held prior to their start of clinical responsibilities. During the session, trainees were introduced to the basics of EKG acquisition and common quality issues that arise. Afterwards, they practiced placing EKG leads on a mannequin and a live model. A pre- and post-session survey was utilized to assess the session's utility and participant's learning.

RESULTS

The intervention was perceived as a valuable experience by participants over the course of 2 years. We found increased participant comfort with performing and troubleshooting EKGs (P<.001). There was a 33% improvement in quality assessment of EKG rhythm strips after the session (P<.001).

CONCLUSION

Given the importance of EKGs to the care of pediatric patients, it is essential that pediatricians receive adequate training in acquiring and assessing EKG quality. This intervention was deemed to be highly useful with a demonstrated improvement in EKG troubleshooting skills among first year pediatric residents. This session improves learner comfort with essential clinical responsibilities and identification of low-quality EKGs that often warrant repeat testing.

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.

Assessment of the competence in electrocardiographic interpretation among Arabic resident doctors at the emergency medicine and internal medicine departments: A multi-center online cross-sectional study

Background

This study aims to assess the electrocardiographic interpretation abilities of resident doctors at internal medicine and emergency medicine departments in eight Arabic countries.

Methods

An online cross-sectional study was conducted between October 7, 2022 and October 21, 2022 in eight Arabic countries. The questionnaire consisted of two main sections: the first section included sociodemographic information, while the second section contained 12 clinical case questions of the most severe cardiac abnormalities with their electrocardiography (ECG) recordings.

Results

Out of 2,509 responses, 630 were eligible for the data analysis. More than half of the participants were males (52.4%). Internal medicine residents were (n = 530, 84.1%), whereas emergency medicine residents were (n = 100, 15.9%). Almost participants were in their first or second years of residency (79.8%). Only 36.2% of the inquired resident doctors had attended an ECG course. Most participants, 85.6%, recognized the ECG wave order correctly, and 50.5% of the participants scored above 7.5/10 on the ECG interpretation scale. The proportions of participants who were properly diagnosed with atrial fibrillation, third-degree heart block, and atrial tachycardia were 71.1, 76.7, and 56.6%, respectively. No statistically significant difference was defined between the internal and emergency medicine residents regarding their knowledge of ECG interpretation (p value = 0.42). However, there was a significant correlation between ECG interpretation and medical residency year (p value < 0.001); the fourth-year resident doctors had the highest scores (mean = 9.24, SD = 1.6). As well, participants in the third and second years of postgraduate medical residency have a probability of adequate knowledge of ECG interpretation more than participants in the first year of residency (OR = 2.1, p value = 0.001) and (OR = 1.88, p value = 0.002), respectively.

Conclusion

According to our research findings, resident doctors in departments of internal medicine and emergency medicine in Arabic nations have adequate ECG interpretation abilities; nevertheless, additional development is required to avoid misconceptions about critical cardiac conditions.

The ΔWaveECG: The differences to the normal 12‑lead ECG amplitudes

BACKGROUND

The QRS, ST segment, and T-wave waveforms of electrocardiogram are difficult to interpret, especially for non-ECG experts readers, like general practitioners. As the ECG waveforms are influenced by many factors, like body build, age, sex, electrode placement, even for experience ECG readers the waveform is difficult to interpret. In this research we have created a novel method to distinguish normal from abnormal ECG waveforms for an individual ECG based on the ECG amplitude distribution derived from normal standard 12‑lead ECG recordings.

AIM

Creation of a normal ECG amplitude distribution to enable the distinction by non-ECG experts of normal from abnormal waveforms of the standard 12‑lead ECG.

METHODS

The ECGs of healthy normal controls in the PTB-XL database were used to construct a normal amplitude distribution of the 12 lead ECG for males and females. All ECGs were resampled to have the same number of samples to enable the classification of an individual ECG as either normal or abnormal, i.e. within the normal amplitude distribution or outside, the ΔWaveECG.

RESULTS

From the same PTB-XL database six ECG's were selected, normal, left and right bundle branch block, and three with a myocardial infarction. The normal ECG was obviously within the normal distribution, and all other five showed clear abnormal ECG amplitudes outside the normal distribution in any of the ECG segments (QRS, ST segment and remaining STT segment).

CONCLUSION

The ΔWaveECG can distinguish the abnormal from normal ECG waveform segments, making the ECG easier to classify as normal or abnormal. Conduction disorders and ST changes due to ischemia and abnormal T-waves are effortless to detect, also by non-ECG expert readers, thus improving the early detection of cardiac patients.

Interpretable Machine Learning Techniques in ECG-Based Heart Disease Classification: A Systematic Review

Heart disease is one of the leading causes of mortality throughout the world. Among the different heart diagnosis techniques, an electrocardiogram (ECG) is the least expensive non-invasive procedure. However, the following are challenges: the scarcity of medical experts, the complexity of ECG interpretations, the manifestation similarities of heart disease in ECG signals, and heart disease comorbidity. Machine learning algorithms are viable alternatives to the traditional diagnoses of heart disease from ECG signals. However, the black box nature of complex machine learning algorithms and the difficulty in explaining a model's outcomes are obstacles for medical practitioners in having confidence in machine learning models. This observation paves the way for interpretable machine learning (IML) models as diagnostic tools that can build a physician's trust and provide evidence-based diagnoses. Therefore, in this systematic literature review, we studied and analyzed the research landscape in interpretable machine learning techniques by focusing on heart disease diagnosis from an ECG signal. In this regard, the contribution of our work is manifold; first, we present an elaborate discussion on interpretable machine learning techniques. In addition, we identify and characterize ECG signal recording datasets that are readily available for machine learning-based tasks. Furthermore, we identify the progress that has been achieved in ECG signal interpretation using IML techniques. Finally, we discuss the limitations and challenges of IML techniques in interpreting ECG signals.

Development and validation of deep learning ECG-based prediction of myocardial infarction in emergency department patients

Myocardial infarction diagnosis is a common challenge in the emergency department. In managed settings, deep learning-based models and especially convolutional deep models have shown promise in electrocardiogram (ECG) classification, but there is a lack of high-performing models for the diagnosis of myocardial infarction in real-world scenarios. We aimed to train and validate a deep learning model using ECGs to predict myocardial infarction in real-world emergency department patients. We studied emergency department patients in the Stockholm region between 2007 and 2016 that had an ECG obtained because of their presenting complaint. We developed a deep neural network based on convolutional layers similar to a residual network. Inputs to the model were ECG tracing, age, and sex; and outputs were the probabilities of three mutually exclusive classes: non-ST-elevation myocardial infarction (NSTEMI), ST-elevation myocardial infarction (STEMI), and control status, as registered in the SWEDEHEART and other registries. We used an ensemble of five models. Among 492,226 ECGs in 214,250 patients, 5,416 were recorded with an NSTEMI, 1,818 a STEMI, and 485,207 without a myocardial infarction. In a random test set, our model could discriminate STEMIs/NSTEMIs from controls with a C-statistic of 0.991/0.832 and had a Brier score of 0.001/0.008. The model obtained a similar performance in a temporally separated test set of the study sample, and achieved a C-statistic of 0.985 and a Brier score of 0.002 in discriminating STEMIs from controls in an external test set. We developed and validated a deep learning model with excellent performance in discriminating between control, STEMI, and NSTEMI on the presenting ECG of a real-world sample of the important population of all-comers to the emergency department. Hence, deep learning models for ECG decision support could be valuable in the emergency department.

Early detection of myocardial ischemia in 12-lead ECG using deterministic learning and ensemble learning

BACKGROUND AND OBJECTIVE

Early detection of myocardial ischemia is a necessary but difficult problem in cardiovascular diseases. Approaches that exclusively rely on classical ST and T wave changes on the standard 12-lead electrocardiogram (ECG) lack sufficient accuracy in detecting myocardial ischemia. This study aims to construct generalizable models for the detection of myocardial ischemia in patients with subtle ECG waveform changes (namely non-diagnostic ECG) using ensemble learning to integrate ECG dynamic features acquired via deterministic learning.

METHODS

First, cardiodynamicsgram (CDG), a noninvasive spatiotemporal electrocardiographic method, is generated through dynamic modeling of ECG signals using the deterministic learning algorithm. Then, the spectral fitting exponent, Lyapunov exponent, and Lempel-Ziv complexity are extracted from CDG. Subsequently, the bagging-based heterogeneous ensemble algorithm is applied on CDG features to generate diverse base classifiers and aggregate them with weighted voting to obtain an ensemble model for myocardial ischemia detection. Finally, we train and test the proposed heterogeneous ensemble model on a real-world clinical dataset. This dataset consists of 499 non-diagnostic 12-lead ECG records from 499 patients collected from three independent medical centers, including 383 patients with myocardial ischemia and 116 patients without ischemia.

RESULTS

With 10-times 5-fold cross-validation technology, our proposed method achieves an average accuracy of 89.10%, sensitivity of 91.72%, and specificity of 82.69% using the heterogeneous ensemble algorithm on the real-world clinical dataset. On three independent medical centers, our ensemble model also achieves accuracy performance over 82% for patients with non-diagnostic ECG. Furthermore, our ensemble model trained with real-world clinical data yields promising results of 91.11% accuracy, 90.49% sensitivity, and 92.88% specificity on the external test set of the public PTB dataset.

CONCLUSION

The experimental results demonstrate that the proposed model combining ensemble learning and deterministic learning presents excellent diagnostic accuracy and generalization in clinical practice, and could be implemented as a complement to the standard ECG in the clinical diagnosis of myocardial ischemia.

Transfer learning enables prediction of myocardial injury from continuous single-lead electrocardiography

OBJECTIVE

Chest pain is common, and current risk-stratification methods, requiring 12-lead electrocardiograms (ECGs) and serial biomarker assays, are static and restricted to highly resourced settings. Our objective was to predict myocardial injury using continuous single-lead ECG waveforms similar to those obtained from wearable devices and to evaluate the potential of transfer learning from labeled 12-lead ECGs to improve these predictions.

METHODS

We studied 10 874 Emergency Department (ED) patients who received continuous ECG monitoring and troponin testing from 2020 to 2021. We defined myocardial injury as newly elevated troponin in patients with chest pain or shortness of breath. We developed deep learning models of myocardial injury using continuous lead II ECG from bedside monitors as well as conventional 12-lead ECGs from triage. We pretrained single-lead models on a pre-existing corpus of labeled 12-lead ECGs. We compared model predictions to those of ED physicians.

RESULTS

A transfer learning strategy, whereby models for continuous single-lead ECGs were first pretrained on 12-lead ECGs from a separate cohort, predicted myocardial injury as accurately as models using patients' own 12-lead ECGs: area under the receiver operating characteristic curve 0.760 (95% confidence interval [CI], 0.721-0.799) and area under the precision-recall curve 0.321 (95% CI, 0.251-0.397). Models demonstrated a high negative predictive value for myocardial injury among patients with chest pain or shortness of breath, exceeding the predictive performance of ED physicians, while attending to known stigmata of myocardial injury.

CONCLUSIONS

Deep learning models pretrained on labeled 12-lead ECGs can predict myocardial injury from noisy, continuous monitor data early in a patient's presentation. The utility of continuous single-lead ECG in the risk stratification of chest pain has implications for wearable devices and preclinical settings, where external validation of the approach is needed.

Exploring decision making 'noise' when interpreting the electrocardiogram in the context of cardiac cath lab activation

In this commentary paper, we discuss the use of the electrocardiogram to help clinicians make diagnostic and patient referral decisions in acute care settings. The paper discusses the factors that are likely to contribute to the variability and noise in the clinical decision making process for catheterization lab activation. These factors include the variable competence in reading ECGs, the intra/inter rater reliability, the lack of standard ECG training, the various ECG machine and filter settings, cognitive biases (such as automation bias which is the tendency to agree with the computer-aided diagnosis or AI diagnosis), the order of the information being received, tiredness or decision fatigue as well as ECG artefacts such as the signal noise or lead misplacement. We also discuss potential research questions and tools that could be used to mitigate this 'noise' and improve the quality of ECG based decision making.

EASI™ 12‑lead ECG with a handheld computer refines cardiovascular diagnosis in general practice

BACKGROUND

Electrocardiogram (ECG) is used to a small extent in general medicine, because of general practitioner (GP) apprehension about interpretation and time consumption.

AIM

This study tested the hypothesis that user-friendly EASI ECG improves GP diagnosis of cardiovascular symptoms.

METHOD

Patients over 18 years with recent cardiovascular symptoms or auscultation rhythm abnormalities were included in this prospective, multicentric study (10 practices, 17 GPs). ECG recordings were made with Cardiosecur® (4‑lead ECG connected to a handheld computer for EASI™ processing). Besides clinical data, diagnosis/patient referral were noted before and after ECG and interpretation. GP diagnosis and ECG interpretation were compared with a reference diagnosis made by ECG specialist.

RESULTS

There were 338 patients; 66% had cardiovascular risk factors. ECGs were performed for chest pain (41%), auscultation rhythm abnormalities (33%) or palpitations (19%). Average time to perform ECG was 4.7 ± 2.1 min, with possible home recordings. Compared with standard ECG, improvement provided by Cardiosecur® was scored 9/10 (range 7-10) by GPs. GPs correctly interpreted ECG normality/abnormality in 77% of patients. Diagnosis was correctly changed for 14% of patients thanks to the ECG, and wrongly changed for 2%. One new appropriate final diagnosis was achieved for 9 ECG recordings (p < 0.001). Diagnostic certainty increased 1.9 ± 2.1/10 (p < 0.001). ECG brought about changes in GP decision making: referral or treatment changed for 82 patients (24%) and complementary test for 69 patients (20%).

CONCLUSION

The EASI™ algorithm coupled with a handheld computer facilitates ECG recordings in the primary care setting, providing improved diagnosis.

Analysis of an adaptive lead weighted ResNet for multiclass classification of 12-lead ECGs

Background. Twelve lead ECGs are a core diagnostic tool for cardiovascular diseases. Here, we describe and analyse an ensemble deep neural network architecture to classify 24 cardiac abnormalities from 12 lead ECGs.Method. We proposed a squeeze and excite ResNet to automatically learn deep features from 12-lead ECGs, in order to identify 24 cardiac conditions. The deep features were augmented with age and gender features in the final fully connected layers. Output thresholds for each class were set using a constrained grid search. To determine why the model made incorrect predictions, two expert clinicians independently interpreted a random set of 100 misclassified ECGs concerning left axis deviation.Results. Using the bespoke weighted accuracy metric, we achieved a 5-fold cross-validation score of 0.684, and sensitivity and specificity of 0.758 and 0.969, respectively. We scored 0.520 on the full test data, and ranked 2nd out of 41 in the official challenge rankings. On a random set of misclassified ECGs, agreement between two clinicians and training labels was poor (clinician 1:κ= -0.057, clinician 2:κ= -0.159). In contrast, agreement between the clinicians was very high (κ= 0.92).Discussion. The proposed prediction model performed well on the validation and hidden test data in comparison to models trained on the same data. We also discovered considerable inconsistency in training labels, which is likely to hinder development of more accurate models.

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.

Physician Training for Electrocardiogram Interpretation: A Systematic Review and Meta-Analysis

PURPOSE

Using electrocardiogram (ECG) interpretation as an example of a widely taught diagnostic skill, the authors conducted a systematic review and meta-analysis to demonstrate how research evidence on instruction in diagnosis can be synthesized to facilitate improvement of educational activities (instructional modalities, instructional methods, and interpretation approaches), guide the content and specificity of such activities, and provide direction for research.

METHOD

The authors searched PubMed/MEDLINE, Embase, Cochrane CENTRAL, PsycInfo, CINAHL, ERIC, and Web of Science databases through February 21, 2020, for empirical investigations of ECG interpretation training enrolling medical students, residents, or practicing physicians. They appraised study quality with the Medical Education Research Study Quality Instrument and pooled standardized mean differences (SMDs) using random effects meta-analysis.

RESULTS

Of 1,002 articles identified, 59 were included (enrolling 17,251 participants). Among 10 studies comparing instructional modalities, 8 compared computer-assisted and face-to-face instruction, with pooled SMD 0.23 (95% CI, 0.09, 0.36) indicating a small, statistically significant difference favoring computer-assisted instruction. Among 19 studies comparing instructional methods, 5 evaluated individual versus group training (pooled SMD -0.35 favoring group study [95% CI, -0.06, -0.63]), 4 evaluated peer-led versus faculty-led instruction (pooled SMD 0.38 favoring peer instruction [95% CI, 0.01, 0.74]), and 4 evaluated contrasting ECG features (e.g., QRS width) from 2 or more diagnostic categories versus routine examination of features within a single ECG or diagnosis (pooled SMD 0.23 not significantly favoring contrasting features [95% CI, -0.30, 0.76]). Eight studies compared ECG interpretation approaches, with pooled SMD 0.92 (95% CI, 0.48, 1.37) indicating a large, statistically significant effect favoring more systematic interpretation approaches.

CONCLUSIONS

Some instructional interventions appear to improve learning in ECG interpretation; however, many evidence-based instructional strategies are insufficiently investigated. The findings may have implications for future research and design of training to improve skills in ECG interpretation and other types of visual diagnosis.

Electrocardiogram-based mortality prediction in patients with COVID-19 using machine learning

Background and purpose

The electrocardiogram (ECG) is frequently obtained in the work-up of COVID-19 patients. So far, no study has evaluated whether ECG-based machine learning models have added value to predict in-hospital mortality specifically in COVID-19 patients.

Methods

Using data from the CAPACITY-COVID registry, we studied 882 patients admitted with COVID-19 across seven hospitals in the Netherlands. Raw format 12-lead ECGs recorded within 72 h of admission were studied. With data from five hospitals (n = 634), three models were developed: (a) a logistic regression baseline model using age and sex, (b) a least absolute shrinkage and selection operator (LASSO) model using age, sex and human annotated ECG features, and (c) a pre-trained deep neural network (DNN) using age, sex and the raw ECG waveforms. Data from two hospitals (n = 248) was used for external validation.

Results

Performances for models a, b and c were comparable with an area under the receiver operating curve of 0.73 (95% confidence interval [CI] 0.65–0.79), 0.76 (95% CI 0.68–0.82) and 0.77 (95% CI 0.70–0.83) respectively. Predictors of mortality in the LASSO model were age, low QRS voltage, ST depression, premature atrial complexes, sex, increased ventricular rate, and right bundle branch block.

Conclusion

This study shows that the ECG-based prediction models could be helpful for the initial risk stratification of patients diagnosed with COVID-19, and that several ECG abnormalities are associated with in-hospital all-cause mortality of COVID-19 patients. Moreover, this proof-of-principle study shows that the use of pre-trained DNNs for ECG analysis does not underperform compared with time-consuming manual annotation of ECG features.

Supplementary Information

The online version of this article (10.1007/s12471-022-01670-2) contains supplementary material, which is available to authorized users.

Improving R Peak Detection in ECG Signal Using Dynamic Mode Selected Energy and Adaptive Window Sizing Algorithm with Decision Tree Algorithm

R peak detection is crucial in electrocardiogram (ECG) signal analysis to detect and diagnose cardiovascular diseases (CVDs). Herein, the dynamic mode selected energy (DMSE) and adaptive window sizing (AWS) algorithm are proposed for detecting R peaks with better efficiency. The DMSE algorithm adaptively separates the QRS components and all non-objective components from the ECG signal. Based on local peaks in QRS components, the AWS algorithm adaptively determines the Region of Interest (ROI). The Feature Extraction process computes the statistical properties of energy, frequency, and noise from each ROI. The Sequential Forward Selection (SFS) procedure is used to find the best subsets of features. Based on these characteristics, an ensemble of decision tree algorithms detects the R peaks. Finally, the R peak position on the initial ECG signal is adjusted using the R location correction (RLC) algorithm. The proposed method has an experimental accuracy of 99.94%, a sensitivity of 99.98%, positive predictability of 99.96%, and a detection error rate of 0.06%. Given the high efficiency in detection and fast processing speed, the proposed approach is ideal for intelligent medical and wearable devices in the diagnosis of CVDs.