Electrocardiogram Interpretation Research Articles

Improved diagnosis of arrhythmogenic right ventricular cardiomyopathy using electrocardiographic deep learning

BackgroundArrhythmogenic right ventricular cardiomyopathy (ARVC) is a rare genetic heart disease associated with life-threatening ventricular arrhythmias. Diagnosis of ARVC is based on the 2010 Task Force Criteria (TFC), application of which often requires clinical expertise at specialized centers. ObjectiveThe purpose of this study was to develop and validate an electrocardiogram (ECG) deep learning (DL) tool for ARVC diagnosis. MethodsECGs of patients referred for ARVC evaluation were used to develop (n = 551 [80.1%]) and test (n = 137 [19.9%]) an ECG-DL model for prediction of TFC-defined ARVC diagnosis. The ARVC ECG-DL model was externally validated in a cohort of patients with pathogenic or likely pathogenic (P/LP) ARVC gene variants identified through the Geisinger MyCode Community Health Initiative (N = 167). ResultsOf 688 patients evaluated at Johns Hopkins Hospital (JHH) (57.3% male, mean age 40.2 years), 329 (47.8%) were diagnosed with ARVC. Although ARVC diagnosis made by referring cardiologist ECG interpretation was unreliable (c-statistic 0.53; confidence interval [CI] 0.52–0.53), ECG-DL discrimination in the hold-out testing cohort was excellent (0.87; 0.86–0.89) and compared favorably to that of ECG interpretation by an ARVC expert (0.85; 0.84–0.86). In the Geisinger cohort, prevalence of ARVC was lower (n = 17 [10.2%]), but ECG-DL–based identification of ARVC phenotype remained reliable (0.80; 0.77–0.83). Discrimination was further increased when ECG-DL predictions were combined with non–ECG-derived TFC in the JHH testing (c-statistic 0.940; 95% CI 0.933–0.948) and Geisinger validation (0.897; 95% CI 0.883–0.912) cohorts. ConclusionECG-DL augments diagnosis of ARVC to the level of an ARVC expert and can differentiate true ARVC diagnosis from phenotype-mimics and at-risk family members/genotype-positive individuals.

A Case of Symptomatic Bradycardia After Valve Replacement.

Editor's note: This is the next installment in a series on electrocardiogram (ECG) interpretation. Nurses in all settings should know the basics, as medications and physiological changes can cause cardiac arrhythmias. Each article will start with a brief case scenario and an ECG strip and then take you step by step through analyzing the heart rhythm.

Racial Disparities in Sports Cardiology

ImportanceRacial disparities in cardiovascular health, including sudden cardiac death (SCD), exist among both the general and athlete populations. Among competitive athletes, disparities in health outcomes potentially influenced by social determinants of health (SDOH) and structural racism remain inadequately understood. This narrative review centers on race in sports cardiology, addressing racial disparities in SCD risk, false-positive cardiac screening rates among athletes, and the prevalence of left ventricular hypertrophy, and encourages a reexamination of race-based practices in sports cardiology, such as the interpretation of screening 12-lead electrocardiogram findings.ObservationsDrawing from an array of sources, including epidemiological data and broader medical literature, this narrative review discusses racial disparities in sports cardiology and calls for a paradigm shift in approach that encompasses 3 key principles: race-conscious awareness, clinical inclusivity, and research-driven refinement of clinical practice. These proposed principles call for a shift away from race-based assumptions towards individualized, health-focused care in sports cardiology. This shift would include fostering awareness of sociopolitical constructs, diversifying the medical team workforce, and conducting diverse, evidence-based research to better understand disparities and address inequities in sports cardiology care.Conclusions and RelevanceIn sports cardiology, inadequate consideration of the impact of structural racism and SDOH on racial disparities in health outcomes among athletes has resulted in potential biases in current normative standards and in the clinical approach to the cardiovascular care of athletes. An evidence-based approach to successfully address disparities requires pivoting from outdated race-based practices to a race-conscious framework to better understand and improve health care outcomes for diverse athletic populations.

Influence of different electrode placement patterns on electromagnetic interference generated by Left Ventricular Assist Devices (LVADs) during electrocardiogram performance

Abstract Background Heart failure (HF), with an incidence of approximately 3/1000 person-years, often progresses to advanced stages where symptoms persist despite treatment. In such cases, mechanical circulatory assist devices, particularly left ventricular assist devices (LVADs) in ambulatory patients, enhance survival and quality of life. These LVADs generate electromagnetic interference, resulting in noise artefacts in conventional electrocardiograms (ECGs). The conventional ECG should be configured with a low-pass filter of 150 Hz and a high-pass filter of 0.05 Hz, as recommended by the American Heart Association/American College of Cardiology/Heart Rhythm Society. LVADs, such as the HeartMate 3 (Abbott®), typically operate at a rotational speed of 5000 to 6000 rpm, corresponding to oscillatory frequencies of 83.3 to 100 Hz. Objective To assess the impact of various surface electrode placement strategies and modifications to the low-pass filter on the electromagnetic interference produced by LVADs. Methods We conducted an observational study involving seven patients with HeartMate 3 adjusted to various rotational speeds (refer to Table 1). Three distinct electrode placement schemes (AHA, Mason Likar, and modified Torso) were employed for the frontal plane leads. The horizontal plane leads remained unmodified. Each patient underwent a total of 6 ECGs, corresponding to each of the aforementioned schemes. ECG recordings were performed using a high-pass filter set at 0.05 Hz and a low-pass filter set at 150 Hz. Additionally, a set of ECGs was obtained by modifying the low-pass filter to 40 Hz for further analysis. Results Figure 1 displays ECGs obtained from a male with a HeartMate 3 operating at 4600 rpm or 76.6 Hz. This device employs an algorithm to generate an "artificial pulse" by cyclically accelerating and decelerating the pump speed by 2000 rpm every 2 seconds, resulting in rotational speeds of 2600 rpm and 6600 rpm (43.3 Hz and 110 Hz, respectively). No specific placement scheme demonstrated consistent noise reduction across all cases, likely due to inter-individual variability resulting from factors such as the final position of the LVAD the rpm in each case, and the thoracic impedance of each patient. However, the modification of the low-pass filter to 40 Hz yielded a noteworthy improvement in noise reduction across all cases. In our limited sample, this adjustment did not pose issues for ECG interpretation. Nevertheless, it is essential to acknowledge that excessively low filter settings may not only eliminate noise but also potentially discard clinically relevant high-frequency signals (e.g., pacemaker spikes, large amplitude Rs, QRS notches). Conclusions Individualizing the electrode placement scheme is crucial for minimizing noise generated by LVADs. The adjustment of the low-pass filter to 40 Hz could generally prove beneficial in reducing artifact generation, despite the clinical limitations it may entail.

A Qualitative Analysis of Barriers to Evidence-Based Care in the Prehospital Management of Patients with Suspected Acute Coronary Syndrome

Objectives Prehospital electrocardiogram (ECG) and administration of aspirin are evidence-based strategies for patients with acute coronary syndrome (ACS). However, emergency medical services (EMS) compliance in patients with suspected ACS varies widely. We sought to understand the barriers to prehospital ECG acquisition and aspirin administration for patients with suspected ACS. Methods In this qualitative study, we interviewed EMS clinicians at three geographically diverse United States (U.S.)-based EMS agencies. We interviewed practicing clinicians and quality and operations leaders at these agencies. Based on the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) framework, interviews were recorded, transcribed, and analyzed using a grounded qualitative approach with open coding. The Systems Engineering Initiative for Patient Safety (SEIPS) framework and a constant comparison technique were used to identify and refine themes. Results Twenty-five paramedics and 20 additional agency personnel participated. Median age was 41 (IQR: 34–51) years and 13 (29%) were female. Themes were organized using SEIPS and longitudinally through four phases of an EMS call. During the pre-arrival phase, staffing challenges, training quality, and dispatch may anchor EMS clinicians on a diagnosis. During the diagnosis and treatment phase, safety and communication barriers may take priority over care delivery. Additionally, EMS clinicians must allocate assets (e.g. whether to send an advanced life support unit) and financial resources; veteran EMS clinicians identified their experience whereas newer clinicians cited their recent education when making these decisions. Also, diagnostic uncertainty due to increasing patient complexity and atypical presentations contributed to diagnostic errors. During the response and transport phase, the scope of practice limits the use and interpretation of the ECG, with clinicians reporting that liberal use of ECG led to more rapid decision-making. Finally, in the after phase, personnel reported the “psychologically taxing” nature of the job contributing to biases, bad habits, and burnout. Performance feedback was desired for personal development, though currently perceived as infrequent and punitive. Conclusions Multiple, interrelated themes underscored the complexities of delivering evidence-based care to prehospital patients with ACS. Education in ECG interpretation, resource allocation, bias, and enhancing feedback may serve as strategies to address the identified barriers.

Integrating mixed reality preparation into acute coronary syndrome simulation for nursing students: a single-group pretest-posttest study

BackgroundTimely and effective intervention within the ‘golden hour’—the critical first 90 min after the symptom onset—is crucial for initiating life-saving treatment and reducing mortality in acute coronary syndrome (ACS). This highlights the need for nursing students to be proficient in ACS care, emphasizing the importance of preparatory training. This study enhanced traditional simulation methods by integrating a mixed reality (MR) preparation step, offering a more immersive learning experience. We aimed to evaluate the effectiveness of integrating MR preparation into ACS simulation education, focusing on enhancements in knowledge, self-confidence in learning, and self-efficacy in learning. Additionally, we examined performance, practice immersion, and satisfaction to comprehensively evaluate the MR application.MethodsOne-group pretest-posttest design was implemented in a convenience sample of thirty-nine senior nursing students from a university in South Korea in August 2022. We developed a simulation program integrating MR preparation into ACS simulation (IMRP-ACSS), which was validated through expert review for content validity. The students participated in the simulation program over six hours across two days, including a 40-minute individual session of MR-based simulation preparation using head-mounted displays (the HoloLens 2). Individual changes in knowledge, self-confidence in learning, and self-efficacy in learning evaluated by the survey were analyzed using paired t-tests. Additionally, group performance assessed using the checklist was analyzed. Immersion and satisfaction were measured with a tool and a 10-point Likert scale, respectively.ResultsIndividually, participants demonstrated significantly increased knowledge (t = 11.87, p < .001), self-confidence in learning (t = 7.17, p < .001), and self-efficacy in learning (t = 4.70, p < .001) post-education. Group performance yielded a mean score of 56.43/70 ± 7.45. Groups scored higher in electrocardiogram interpretation, patient safety, and heparin administration. Participants reported a practice immersion level of 37.82/50 ± 9.13 and expressed satisfaction with the program, achieving an average score of 8.85/10 ± 1.35.ConclusionIntegrating MR preparation into ACS simulation enhanced nursing students’ knowledge, self-confidence in learning, and self-efficacy in ACS care, providing a replicable and immersive learning experience. This method is an effective addition to nursing education, preparing students through comprehensive, technology-enhanced training.

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.

Investigating the Effect of Online Gamification on Electrocardiogram Interpretation and Self-Directed Learning in Nursing Students.

Knowing and interpreting the Electrocardiogram correctly and taking care based on it is one of the most important ways to save the patient's life. Therefore, this study aimed to investigate the effect of online gamification on the ability to interpret Electrocardiograms and Self-Directed Learning in nursing students. The present study was carried out quasi-experimentally on 44 nursing students (22 participants for each group) in the fifth semester in Ilam city in 2023 using a convenience sampling method by four permutations balanced block randomization to control and intervention groups. During four sessions in four weeks, the participants in the intervention group received Electrocardiogram interpretation as training on the Storyline platform and playing games in the Socrative software. The control group received the same content in the form of education from the same lecturer. ECG Interpretation Learning Test, Self-Directed Learning, Mini-Mental Status Examination, and demographic questionnaires were filled out before the intervention (pre-test). Then, Electrocardiogram Interpretation Learning Test and Self-Directed Learning questionnaires were completed two weeks after the end of the intervention (post-test), and the data were analyzed in the standard error of 0.05 using Shapiro-Wilk, independent t-test, paired t-test, chi-square, and multiple linear regression tests in SPSS V.16. The mean and standard deviation of the participants' age was 21.35 ± 1.02, and 59% of the samples were male. Before the intervention, no significant difference was observed between the two groups, but after the intervention, the mean and standard deviation of the ECG interpretation scores in the intervention group increased significantly (14.1±2.94) compared to the control group (8.8±1.36) (P=0.007). Also, Self-Directed Learning in the intervention group (168±10.42) compared to the control group (125±4.3) showed a statistically significant difference (P=0.003). Using online gamification as a new educational method in nursing students improves the ability to interpret Electrocardiograms and Self-Directed Learning. It is suggested that this method should be used to teach lessons that are more useful and important at the hospital.

Reliability of single-lead electrocardiogram interpretation to detect atrial fibrillation: insights from the SAFER feasibility study.

Single-lead electrocardiograms (ECGs) can be recorded using widely available devices such as smartwatches and handheld ECG recorders. Such devices have been approved for atrial fibrillation (AF) detection. However, little evidence exists on the reliability of single-lead ECG interpretation. We aimed to assess the level of agreement on detection of AF by independent cardiologists interpreting single-lead ECGs and to identify factors influencing agreement. In a population-based AF screening study, adults aged ≥65 years old recorded four single-lead ECGs per day for 1-4 weeks using a handheld ECG recorder. Electrocardiograms showing signs of possible AF were identified by a nurse, aided by an automated algorithm. These were reviewed by two independent cardiologists who assigned participant- and ECG-level diagnoses. Inter-rater reliability of AF diagnosis was calculated using linear weighted Cohen's kappa (κw). Out of 2141 participants and 162 515 ECGs, only 1843 ECGs from 185 participants were reviewed by both cardiologists. Agreement was moderate: κw = 0.48 (95% confidence interval, 0.37-0.58) at participant level and κw = 0.58 (0.53-0.62) at ECG level. At participant level, agreement was associated with the number of adequate-quality ECGs recorded, with higher agreement in participants who recorded at least 67 adequate-quality ECGs. At ECG level, agreement was associated with ECG quality and whether ECGs exhibited algorithm-identified possible AF. Inter-rater reliability of AF diagnosis from single-lead ECGs was found to be moderate in older adults. Strategies to improve reliability might include participant and cardiologist training and designing AF detection programmes to obtain sufficient ECGs for reliable diagnoses.

Multimodal ChatGPT-4V for Electrocardiogram Interpretation: Promise and Limitations.

This study evaluated the capabilities of the newly released ChatGPT-4V, a large language model with visual recognition abilities, in interpreting electrocardiogram waveforms and answering related multiple-choice questions for assisting with cardiovascular care.

Intelligent deep model based on convolutional neural network's and multi-layer perceptron to classify cardiac abnormality in diabetic patients.

The ECG is a crucial tool in the medical field for recording the heartbeat signal over time, aiding in the identification of various cardiac diseases. Commonly, the interpretation of ECGs necessitates specialized knowledge. However, this paper explores the application of machine learning algorithms and deep learning algorithm to autonomously identify cardiac diseases in diabetic patients in the absence of expert intervention. Two models are introduced in this study: The MLP model effectively distinguishes between individuals with heart diseases and those without, achieving a high level of accuracy. Subsequently, the deep CNN model further refines the identification of specific cardiac conditions. The PTB-Diagnostic ECG dataset commonly used in the field of biomedical signal processing and machine learning, particularly for tasks related to electrocardiogram (ECG) analysis. a widely recognized dataset in the field, is employed for training, testing, and validation of both the MLP and CNN models. This dataset comprises a diverse range of ECG recordings, providing a comprehensive representation of cardiac conditions. The proposed models feature two hidden layers with weights and biases in the MLP, and a three-layer CNN, facilitating the mapping of ECG data to different disease classes. The experimental results demonstrate that the MLP and deep CNN based models attain accuracy levels of up to 90.0% and 98.35%, and sensitivity 97.8%, 95.77%, specificity 88.9%, 96.3% F1-Score 93.13%, 95.84% respectively. These outcomes underscore the efficacy of deep learning approaches in automating the diagnosis of cardiac diseases through ECG analysis, showcasing the potential for accurate and efficient healthcare solutions.

Bridging Gaps: A Quality Improvement Project for the Continuing Medical Education on Stick (CMES) Program.

Aimed at bridging the gap in continuing medical education (CME) resource availability in low- and middle-income countries (LMICs), the "Continuing Medical Education on Stick" (CMES) program introduces two technological solutions: a universal serial bus (USB) drive and the CMES-Pi computer facilitating access to monthly updated CME content without data cost. Feedback from users suggests a lack of content on tropical infectious diseases (IDs) and content from a Western perspective, which may be less relevant in LMIC settings. This quality improvement project was intended to identify areas for improvement of the CMES database to better meet the educational needs of users. We compared the CMES content with the American Board of Emergency Medicine (ABEM) Exam content outline to identify gaps. The curriculum map of the CMES library, encompassing content from 2019 to 2024, was reviewed. An anonymous survey was conducted among 47 global users to gather feedback on unmet educational needs and suggestions for content improvements. All healthcare workers who were members of the CMES WhatsApp group were eligible to participate in the survey. The curriculum map included 2,572 items categorized into 23 areas. The comparison with the ABEM outline identified gaps in several clinical areas, including procedures, traumatic disorders, and geriatrics, which were represented -5%, -5%, and -4% in the CMES library compared with the ABEM outline, respectively. Free responses from users highlighted a lack of content on practical skills, such as electrocardiogram (ECG) interpretation and management of tropical diseases. Respondents identified emergency medical services (EMS)/prehospital care (81%), diagnostic imaging (62%), and toxicology/pharmacology (40%) as the most beneficial areas for clinical practice. In response to feedback from users, new content was added to the CMES platform on the management of sickle cell disease and dermatologic conditions in darkly pigmented skin. Furthermore, a targeted podcast series called "ID for Users of the CMES Program (ID4U)" has been launched, focusing on tropical and locally relevant ID, with episodes now being integrated into the CMES platform. The project pinpointed critical gaps in emergency medicine (EM) content pertinent to LMICs and led to targeted enhancements in the CMES library. Ongoing updates will focus on including more prehospital medicine, diagnostic imaging, and toxicology content. Further engagement with users and education on utilizing the CMES platform will be implemented to maximize its educational impact. Future adaptations will consider local relevance over the ABEM curriculum to better serve the diverse needs of global users.

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 (SD1.1), 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(SD8.4) and 8.3(SD7.5), respectively, and post-test scores for the acquisition of knowledge were 24.3(SD5.5) and 24.8(SD6.3), respectively. The post-test scores for retention skills were 25.3(SD5.6) and 20.7 (SD6.9) respectively (p<0.001).The mean pre-test scores for the interpretation of abnormal ECG of both groups were 7.0(SD6) and 8.3 (SD6.6), respectively. Mean post-test scores for acquiring knowledge to interpret abnormal ECG were 23.5(SD6.2) and 17.7 (SD9), respectively(p<0.001), and mean post-test scores for retention of interpretation skillsof abnormal ECG were 19.2 (SD - 6.9) and 13.3 (SD10.2) 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.

Assessment of current pediatric electrocardiogram (ECG) interpretation practices

BackgroundDespite improvements in digital electrocardiograms (ECGs), current standard of care requires physician confirmation. Mismatched expectations between ordering providers and ECG readers, often pediatric cardiologists and electrophysiologists (EPs), are common, especially since there are no standardized practices for pediatric ECG reading. ObjectivesThe aim of this study was to understand current practices in pediatric ECG reading. MethodsAn electronic survey was sent to members of the Pediatric and Congenital Electrophysiology Society (PACES). Participation was optional; results were recorded from 12/19/22–1/9/23. Only complete and non-duplicate entries were included. ResultsA total of 127 responses were received, 93 were analyzed. Most responses were from centers in North America (n = 65, 70 %), including the US (n = 58, 62 %), Canada (n = 6, 6 %), and Mexico (n = 1, 1 %). The remaining were from Europe (n = 18, 19 %), Asia (n = 7, 8 %), Australia (n = 2, 2 %), and South America (n = 1, 1 %). Most (n = 46, 49 %) were from small centers (0–25 ECGs read per day), 27 respondents (29 %) were from medium centers (26–50 ECGs read per day), 20 respondents (22 %) were from large centers (>50 ECGs read per day). The majority (n = 65, 70 %) reported >3 readers/day for inpatient and emergency department ECGs. 49 % (n = 46) of centers read ECGs >2 times/day on weekdays with more variable practice on weekends. For critical/time sensitive findings, most centers (n = 90, 97 %) used verbal communication +/− the EMR. There was consensus (≥50 % agreement) that the following findings are critical/time sensitive: QTc >500 ms, T-wave alternans, narrow complex tachycardia, wide complex tachycardia, pre-excited atrial fibrillation, focal ischemic changes, second degree heart block type II, complete heart block, and pacemaker malfunction. ConclusionReading practices are variable. Critical/time sensitive findings are most often communicated verbally, however, there is no agreed upon standard. There was consensus in critical/time-sensitive findings. Improved understanding of common practices and resource allocation may lead to increased consistency in pediatric ECG reading.

Artificial Intelligence in Sports Medicine: Reshaping Electrocardiogram Analysis for Athlete Safety-A Narrative Review.

Artificial Intelligence (AI) is redefining electrocardiogram (ECG) analysis in pre-participation examination (PPE) of athletes, enhancing the detection and monitoring of cardiovascular health. Cardiovascular concerns, including sudden cardiac death, pose significant risks during sports activities. Traditional ECG, essential yet limited, often fails to distinguish between benign cardiac adaptations and serious conditions. This narrative review investigates the application of machine learning (ML) and deep learning (DL) in ECG interpretation, aiming to improve the detection of arrhythmias, channelopathies, and hypertrophic cardiomyopathies. A literature review over the past decade, sourcing from PubMed and Google Scholar, highlights the growing adoption of AI in sports medicine for its precision and predictive capabilities. AI algorithms excel at identifying complex cardiac patterns, potentially overlooked by traditional methods, and are increasingly integrated into wearable technologies for continuous monitoring. Overall, by offering a comprehensive overview of current innovations and outlining future advancements, this review supports sports medicine professionals in merging traditional screening methods with state-of-the-art AI technologies. This approach aims to enhance diagnostic accuracy and efficiency in athlete care, promoting early detection and more effective monitoring through AI-enhanced ECG analysis within athlete PPEs.

Does ChatGPT-4 succeed in the ECG interpretation: friend or foe to cardiologists?

Abstract Background/Introduction Artificial intelligence (AI) and large language models (LLMs) are increasingly being tested for medical purposes, especially in clinical settings and one of the most well-known LLMs is OpenAI’s ChatGPT-4. Recent explorations have considered using ChatGPT to answer medical questions, and the new ChatGPT-4 also allows graphical inputs, which could aid medical doctors in interpreting electrocardiograms (ECGs) in everyday practice. AI-powered ECG interpretation has shown promising results, improving the detection of arrhythmias, ST-segment changes, QT prolongation, and other ECG abnormalities. However, whether ChatGPT4’s interpretation of ECGs is comparable to that of experienced cardiologists has yet to be established. Purpose We sought to test whether ChatGPT-4 could analyze and interpret ECGs similarly to experienced cardiologists. Methods We tasked ChatGPT-4 with interpreting, for scientific purposes, 12-lead ECGs, from 150 patients included in our prospective CaRD registry, presenting with various cardiac pathologies, including acute coronary syndrome, arrhythmias (primarily atrial fibrillation), conduction abnormalities, pacemaker rhythms and normal ECGs. Four experienced cardiologists reviewed the ECG interpretations provided by ChatGPT-4. The model provided information on rate, rhythm, axis, P-wave, PR interval, QRS complex, ST segment, T wave, differential diagnoses, most likely diagnosis and further diagnostic step. Results In this observational study, ChatGPT-4 demonstrated low overall accuracy in interpreting ECGs, with only 24% of the most likely diagnosis being correct. ChatGPT-4 performed the best when interpreting normal ECGs with sinus rhythm, achieving 62% accuracy rate, followed by 17%, 10% and 7.3% for ECGs with arrhythmias, acute ischemic changes, and conduction abnormalities or pacing rhythms, respectively. Conclusion ChatGPT-4 exhibited very low accuracy in interpreting different categories of pathology in 12-lead ECG, yielding less than 20% success rate. While the use of AI in medical diagnostics is an appealing concept in theory, the results suggest that, in its current state, ChatGPT-4 would not provide significant aid to experienced cardiologists in clinical settings.

Can prediction of acute myocardial infarction using a deep learning-enabled electrocardiogram be used in real-world practice?

Abstract Background Diagnosing acute myocardial infarction (MI) in the emergency department poses challenges. The utilization of a 12-lead electrocardiogram (ECG) is pivotal for detecting ST-segment elevation myocardial infarction (STEMI), yet enhancing ECG interpretation through a systematic algorithm could significantly improve diagnostic accuracy. Nonetheless, delayed diagnosis or misdiagnosis of STEMI is not uncommon in daily practice. Purpose This study aims to develop a fully convolutional network (FCN) based on ECG data as a diagnostic support tool and to evaluate its effectiveness in STEMI detection. Methods A retrospective cohort study involved 3,298 patients with angiographically confirmed STEMI and 37,393 control ECGs, comprising normal readings, false positives, and ECGs mimicking STEMI. The FCN underwent internal training, external validation, and testing across various data splits (80:10:10, 70:15:15, and 60:20:20). Performance evaluation on validation data included assessing the area under the receiver operating characteristic curve (AUC). Subsequently, the trained model predicted unseen data, and sensitivity, specificity, false positives, and false negatives were calculated to evaluate model performance. Results The FCN exhibited exceptional performance in STEMI detection during both internal training and external validation across different data splits. The receiver operating characteristic curves yielded AUC values of 0.995 (80:10:10), 0.994 (70:15:15), and 0.995 (60:20:20). Consistently high values were observed in precision-recall curves, with AUC values of 0.974 (80:10:10), 0.962 (70:15:15), and 0.973 (60:20:20). When utilizing this FCN model in the clinical setting to reanalyze 20 cases of previously misdiagnosed electrocardiograms, it correctly diagnosed 17 cases. Conclusion Integrating the FCN into clinical practice can notably improve the timely and accurate diagnosis of acute MI, reducing instances of delayed or erroneous STEMI diagnoses and facilitating prompt reperfusion therapy.

Role of Machine Learning and Artificial Intelligence in Arrhythmias and Electrophysiology.

Machine learning (ML), a subset of artificial intelligence (AI) centered on machines learning from extensive datasets, stands at the forefront of a technological revolution shaping various facets of society. Cardiovascular medicine has emerged as a key domain for ML applications, with considerable efforts to integrate these innovations into routine clinical practice. Within cardiac electrophysiology, ML applications, especially in the automated interpretation of electrocardiograms, have garnered substantial attention in existing literature. However, less recognized are the diverse applications of ML in cardiac electrophysiology and arrhythmias, spanning basic science research on arrhythmia mechanisms, both experimental and computational, as well as contributions to enhanced techniques for mapping cardiac electrical function and translational research related to arrhythmia management. This comprehensive review delves into various ML applications within the scope of this journal, organized into 3 parts. The first section provides a fundamental understanding of general ML principles and methodologies, serving as a foundational resource for readers interested in exploring ML applications in arrhythmia research. The second part offers an in-depth review of studies in arrhythmia and electrophysiology that leverage ML methodologies, showcasing the broad potential of ML approaches. Each subject is thoroughly outlined, accompanied by a review of notable ML research advancements. Finally, the review delves into the primary challenges and future perspectives surrounding ML-driven cardiac electrophysiology and arrhythmias research.

Time to ECG diagnosis delays inter-hospital transfer to revascularization in STEMI patients presenting to a regional emergency department: a five-year audit

BackgroundReducing the door-to-balloon time (D2BT) in ST-elevation myocardial infarction (STEMI) patients maximizes myocardial salvage and mitigates morbidity/mortality.AimsTo assess the D2BT in STEMI patients requiring inter-hospital transfer for revascularization and identify any potential causes of delay.MethodsConsecutive patients presenting to the Connolly Hospital Blanchardstown (CHB) emergency department (ED) who were transferred to the Mater Misericordiae University Hospital in Dublin for primary percutaneous coronary intervention from January 2018 to October 2022 were identified in a regional database and their D2BTs calculated. D2BTs were further sub-categorized into key intervals to identify any potential causes of delay.ResultsA total of 90 patients were included for analysis, with a median D2BT of 117.5 min (interquartile range [IQR]: 99.3–170.8 min) and 52.5% of patients achieving the ≤ 120 min target. Despite being the shortest interval considered, the time from arrival at the CHB ED to diagnostic electrocardiogram (ECG) was a substantial contributor to the overall delay to revascularization given its wide variability (median: 18.0 min; IQR: 9.0–46.8 min), with only 28.8% of patients achieving the ≤ 10 min target.ConclusionsNearly half of the patients studied failed to achieve the overall target D2BT for revascularization. The time from arrival at the CHB ED to diagnostic ECG was identified as a substantial contributor to this failure, with a median time almost twice that of the target and a quarter of all patients spending longer than 46.8 min. These findings highlight a need to improve the implementation of ECG triage and interpretation in the ED.

Place de l’électrocardiogramme dans la visite de non-contre-indication à la pratique sportive de compétition entre 12 et 35 ans : enquête auprès des médecins membres de l'Association Guinéenne des Médecins Sportifs

IntroductionAn electrocardiogram (ECG), combined with a well-conducted clinical examination, is more effective than the clinical examination alone in detecting underlying cardiac pathologies in athletes. The aim of this study was to evaluate the use of ECGs by physicians who are members of the Guinean Association of Sports Physicians, during the non-contraindication visit for competitive sports between the ages of 12 and 35. MethodologyWe conducted a web-survey from July 15 to August 15, 2023. A survey form was created on “Google Docs” and pre-tested. It was then broadcast on all the communication networks used by these doctors. The data were secured using “Google Drive” software. Analyses were performed using SPSS version 20 software. ResultsOf the 51 included, 74.51% said they had received at least one training session on ECG interpretation for athletes. All of them either requested or performed an ECG at least once in a while, as part of the check-up for non-contraindication to competitive sport. The ECG was systematic, according to 72.55% of doctors. Three quarters referred to a sports cardiologist in the event of an abnormal ECG, 66.67% to a cardiology resident and 58.82% to a cardiologist. In the absence of an ECG, the presence of functional signs on exertion, the notion of a family history of cardiovascular disease and the presence of at least two cardiovascular risk factors were the main reasons for seeking an opinion. ConclusionA resting ECG is carried out almost systematically by doctors who are members of the Guinean Association of Sports Doctors, as part of the check-up for non-contraindication to practising sport.