Incorporation of Serial 12-Lead Electrocardiogram With Machine Learning to Augment the Out-of-Hospital Diagnosis of Non-ST Elevation Acute Coronary Syndrome

Diagnostic and Prognostic Electrocardiogram-Based Models for Rapid Clinical Applications

Leveraging artificial intelligence (AI) for the analysis of electrocardiograms (ECGs) has the potential to transform diagnosis and estimate the prognosis of not only cardiac but, increasingly, noncardiac conditions. In this review, we summarize clinical studies and AI-enhanced ECG-based clinical applications in the early detection, diagnosis, and estimating prognosis of cardiovascular diseases in the past 5 years (2019-2023). With advancements in deep learning and the rapid increased use of ECG technologies, a large number of clinical studies have been published. However, most of these studies are single-centre, retrospective, proof-of-concept studies that lack external validation. Prospective studies that progress from development toward deployment in clinical settings account for < 15% of the studies. Successful implementations of ECG-based AI applications that have received approval from the Food and Drug Administration have been developed through commercial collaborations, with approximately half of them being for mobile or wearable devices. The field is in its early stages, and overcoming several obstacles is essential, such as prospective validation in multicentre large data sets, addressing technical issues, bias, privacy, data security, model generalizability, and global scalability. This review concludes with a discussion of these challenges and potential solutions. By providing a holistic view of the state of AI in ECG analysis, this review aims to set a foundation for future research directions, emphasizing the need for comprehensive, clinically integrated, and globally deployable AI solutions in cardiovascular disease management.

Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association

A major focus of academia, industry, and global governmental agencies is to develop and apply artificial intelligence and other advanced analytical tools to transform health care delivery. The American Heart Association supports the creation of tools and services that would further the science and practice of precision medicine by enabling more precise approaches to cardiovascular and stroke research, prevention, and care of individuals and populations. Nevertheless, several challenges exist, and few artificial intelligence tools have been shown to improve cardiovascular and stroke care sufficiently to be widely adopted. This scientific statement outlines the current state of the art on the use of artificial intelligence algorithms and data science in the diagnosis, classification, and treatment of cardiovascular disease. It also sets out to advance this mission, focusing on how digital tools and, in particular, artificial intelligence may provide clinical and mechanistic insights, address bias in clinical studies, and facilitate education and implementation science to improve cardiovascular and stroke outcomes. Last, a key objective of this scientific statement is to further the field by identifying best practices, gaps, and challenges for interested stakeholders.

A Novel Algorithm for Improving the Prehospital Diagnostic Accuracy of ST-Segment Elevation Myocardial Infarction

INTRODUCTION

Early detection of ST-segment elevation myocardial infarction (STEMI) on the prehospital electrocardiogram (ECG) improves patient outcomes. Current software algorithms optimize sensitivity but have a high false-positive rate. The authors propose an algorithm to improve the specificity of STEMI diagnosis in the prehospital setting.

METHODS

A dataset of prehospital ECGs with verified outcomes was used to validate an algorithm to identify true and false-positive software interpretations of STEMI. Four criteria implicated in prior research to differentiate STEMI true positives were applied: heart rate <130, QRS <100, verification of ST-segment elevation, and absence of artifact. The test characteristics were calculated and regression analysis was used to examine the association between the number of criteria included and test characteristics.

RESULTS

There were 44,611 cases available. Of these, 1,193 were identified as STEMI by the software interpretation. Applying all four criteria had the highest positive likelihood ratio of 353 (95% CI, 201-595) and specificity of 99.96% (95% CI, 99.93-99.98), but the lowest sensitivity (14%; 95% CI, 11-17) and worst negative likelihood ratio (0.86; 95% CI, 0.84-0.89). There was a strong correlation between increased positive likelihood ratio (r2 = 0.90) and specificity (r2 = 0.85) with increasing number of criteria.

CONCLUSIONS

Prehospital ECGs with a high probability of true STEMI can be accurately identified using these four criteria: heart rate <130, QRS <100, verification of ST-segment elevation, and absence of artifact. Applying these criteria to prehospital ECGs with software interpretations of STEMI could decrease false-positive field activations, while also reducing the need to rely on transmission for physician over-read. This can have significant clinical and quality implications for Emergency Medical Services (EMS) systems.

Prior electrocardiograms not useful for machine learning predictions of major adverse cardiac events in emergency department chest pain patients

At the emergency department (ED), it is important to quickly and accurately determine which patients are likely to have a major adverse cardiac event (MACE). Machine learning (ML) models can be used to aid physicians in detecting MACE, and improving the performance of such models is an active area of research. In this study, we sought to determine if ML models can be improved by including a prior electrocardiogram (ECG) from each patient. To that end, we trained several models to predict MACE within 30 days, both with and without prior ECGs, using data collected from 19,499 consecutive patients with chest pain, from five EDs in southern Sweden, between the years 2017 and 2018. Our results indicate no improvement in AUC from prior ECGs. This was consistent across models, both with and without additional clinical input variables, for different patient subgroups, and for different subsets of the outcome. While contradicting current best practices for manual ECG analysis, the results are positive in the sense that ML models with fewer inputs are more easily and widely applicable in practice.

Personalized ECG monitoring and adaptive machine learning

This non-technical review introduces key concepts in personalized ECG monitoring (pECG), which aims to optimize the detection of clinical events and their warning signs as well as the selection of alarm thresholds. We review several pECG methods, including anomaly detection and adaptive machine learning (ML), in which learning is performed sequentially as new data are collected. We describe a distributed-network multiscale pECG system to show how the computational load and time associated with adaptive ML could be optimized. In this architecture, the limited analysis of ECG waveforms is performed locally (e.g., on a smart phone) to determine a small number of clinically important ECG elements, and an adaptive ML engine is located on a remote server (Internet cloud) to determine an individual's "fingerprint" basis patterns and to detect anomalies in those patterns.

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.

Post hoc labeling an acute ECG as ischemic or non-ischemic based on clinical data: A necessary challenge

The ECG is crucial in the prehospital (and early inhospital) phase of patients with symptoms suggestive of myocardial ischemia. Therefore, new algorithms for ECG-based myocardial ischemia detection are continuously being researched. Development and validation of these algorithms require a database of acute ECGs (from the prehospital or emergency department setting) including a representative mix of cases (ischemia present) and controls (no ischemia present). Therefore, for every patient in this mix, the "truth" regarding the actual presence or absence of myocardial ischemia during the recording of the acute ECG has to be determined to compare the newly developed algorithm against. This post hoc adjudication process of determining whether an acute (either prehospitally acquired or acquired in the emergency department) ECG was made under ischemic conditions should use all available clinical data (the clinical diagnosis, cardiac imaging data, and laboratory values) of the subsequent patient's admission. Even with all data at hand, post hoc labeling a patient and their acute ECG as a myocardial ischemia case or control cannot be forced into a binary division between definite cases and definite controls. More specifically, to be used for the development of a new algorithm, the patients' ECG has to be scored for the presence or absence of myocardial ischemia at the exact moment of its recording, which renders the classification even more difficult. For instance, even though it may be plausible that myocardial ischemia was present at a given moment during the patient's admission, this is not necessarily proof that the prehospital (or early inhospital) ECG was also made in ischemic conditions: ischemia can be a fluctuating process (as is, e.g., the case in unstable angina pectoris). Therefore, post hoc classification of an acute ECG in terms of the absence or presence of ischemia requires a multipoint scale ranging between definite ischemic to definite non-ischemic, for instance using a 5-point scale (presumed non-ischemic, probably non-ischemic, uncertain, probably ischemic, presumed ischemic). To summarize, the post hoc adjudication process of ECGs of ambulance (and emergency department) patients cannot result in a binary division into definite cases and controls (i.e., patients with or without myocardial ischemia during the recording of the acute ECG), as myocardial ischemia is often dynamic rather than constant. ECGs could be labeled on a multi-point scale, in which the label represents the probability of the actual presence (or absence) of myocardial ischemia at the exact moment of the recording of that ECG. Further development of algorithms for myocardial ischemia detection should consider this concept.

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.

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.