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.

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

STUDY OBJECTIVE: Ischemic electrocardiogram (ECG) changes are subtle and transient in patients with suspected non-ST-segment elevation (NSTE)-acute coronary syndrome. However, the out-of-hospital ECG is not routinely used during subsequent evaluation at the emergency department. Therefore, we sought to compare the diagnostic performance of out-of-hospital and ED ECG and evaluate the incremental gain of artificial intelligence-augmented ECG analysis. METHODS: This prospective observational cohort study recruited patients with out-of-hospital chest pain. We retrieved out-of-hospital-ECG obtained by paramedics in the field and the first ED ECG obtained by nurses during inhospital evaluation. Two independent and blinded reviewers interpreted ECG dyads in mixed order per practice recommendations. Using 179 morphological ECG features, we trained, cross-validated, and tested a random forest classifier to augment non ST-elevation acute coronary syndrome (NSTE-ACS) diagnosis. RESULTS: Our sample included 2,122 patients (age 59 [16]; 53% women; 44% Black, 13.5% confirmed acute coronary syndrome). The rate of diagnostic ST elevation and ST depression were 5.9% and 16.2% on out-of-hospital-ECG and 6.1% and 12.4% on ED ECG, with ∼40% of changes seen on out-of-hospital-ECG persisting and ∼60% resolving. Using expert interpretation of out-of-hospital-ECG alone gave poor baseline performance with area under the receiver operating characteristic (AUC), sensitivity, and negative predictive values of 0.69, 0.50, and 0.92. Using expert interpretation of serial ECG changes enhanced this performance (AUC 0.80, sensitivity 0.61, and specificity 0.93). Interestingly, augmenting the out-of-hospital-ECG alone with artificial intelligence algorithms boosted its performance (AUC 0.83, sensitivity 0.75, and specificity 0.95), yielding a net reclassification improvement of 29.5% against expert ECG interpretation. CONCLUSION: In this study, 60% of diagnostic ST changes resolved prior to hospital arrival, making the ED ECG suboptimal for the inhospital evaluation of NSTE-ACS. Using serial ECG changes or incorporating artificial intelligence-augmented analyses would allow correctly reclassifying one in 4 patients with suspected NSTE-ACS.

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.

Exercise-Related Acute Cardiovascular Events and Potential Deleterious Adaptations Following Long-Term Exercise Training: Placing the Risks Into Perspective-An Update: A Scientific Statement From the American Heart Association.

Epidemiological and biological plausibility studies support a cause-and-effect relationship between increased levels of physical activity or cardiorespiratory fitness and reduced coronary heart disease events. These data, plus the well-documented anti-aging effects of exercise, have likely contributed to the escalating numbers of adults who have embraced the notion that "more exercise is better." As a result, worldwide participation in endurance training, competitive long distance endurance events, and high-intensity interval training has increased markedly since the previous American Heart Association statement on exercise risk. On the other hand, vigorous physical activity, particularly when performed by unfit individuals, can acutely increase the risk of sudden cardiac death and acute myocardial infarction in susceptible people. Recent studies have also shown that large exercise volumes and vigorous intensities are both associated with potential cardiac maladaptations, including accelerated coronary artery calcification, exercise-induced cardiac biomarker release, myocardial fibrosis, and atrial fibrillation. The relationship between these maladaptive responses and physical activity often forms a U- or reverse J-shaped dose-response curve. This scientific statement discusses the cardiovascular and health implications for moderate to vigorous physical activity, as well as high-volume, high-intensity exercise regimens, based on current understanding of the associated risks and benefits. The goal is to provide healthcare professionals with updated information to advise patients on appropriate preparticipation screening and the benefits and risks of physical activity or physical exertion in varied environments and during competitive events.

Overview of featurization techniques used in traditional versus emerging deep learning-based algorithms for automated interpretation of the 12-lead ECG.

Automated interpretation of the 12-lead ECG has remained an underpinning interest in decades of research that has seen a diversity of computing applications in cardiology. The application of computers in cardiology began in the 1960s with early research focusing on the conversion of analogue ECG signals (voltages) to digital samples. Alongside this, software techniques that automated the extraction of wave measurements and provided basic diagnostic statements, began to emerge. In the years since then there have been many significant milestones which include the widespread commercialisation of 12-lead ECG interpretation software, associated clinical utility and the development of the related regulatory frameworks to promote standardised development. In the past few years, the research community has seen a significant rejuvenation in the development of ECG interpretation programs. This is evident in the research literature where a large number of studies have emerged tackling a variety of automated ECG interpretation problems. This is largely due to two factors. Specifically, the technical advances, both software and hardware, that have facilitated the broad adoption of modern artificial intelligence (AI) techniques, and, the increasing availability of large datasets that support modern AI approaches. In this article we provide a very high-level overview of the operation of and approach to the development of early 12-lead ECG interpretation programs and we contrast this to the approaches that are now seen in emerging AI approaches. Our overview is mainly focused on highlighting differences in how input data are handled prior to generation of the diagnostic statement.

The role of machine learning applications in diagnosing and assessing critical and non-critical CHD: a scoping review.

Machine learning uses historical data to make predictions about new data. It has been frequently applied in healthcare to optimise diagnostic classification through discovery of hidden patterns in data that may not be obvious to clinicians. Congenital Heart Defect (CHD) machine learning research entails one of the most promising clinical applications, in which timely and accurate diagnosis is essential. The objective of this scoping review is to summarise the application and clinical utility of machine learning techniques used in paediatric cardiology research, specifically focusing on approaches aiming to optimise diagnosis and assessment of underlying CHD. Out of 50 full-text articles identified between 2015 and 2021, 40% focused on optimising the diagnosis and assessment of CHD. Deep learning and support vector machine were the most commonly used algorithms, accounting for an overall diagnostic accuracy > 0.80. Clinical applications primarily focused on the classification of auscultatory heart sounds, transthoracic echocardiograms, and cardiac MRIs. The range of these applications and directions of future research are discussed in this scoping review.

Exploring the complex interactions of baseline patient factors to improve nursing triage of acute coronary syndrome.

Emergency department (ED) nurses need to identify patients with potential acute coronary syndrome (ACS) rapidly because treatment delay could impact patient outcomes. Aims of this secondary analysis were to identify key patient factors that could be available at initial ED nurse triage that predict ACS. Consecutive patients with chest pain who called 9-1-1, received a 12-lead electrocardiogram in the prehospital setting, and were transported via emergency medical service were included in the study. A total of 750 patients were recruited. The sample had an average age of 59 years old, was 57% male, and 40% Black. One hundred and fifteen patients were diagnosed with ACS. Older age, non-Caucasian race, and faster respiratory rate were independent predictors of ACS. There was an interaction between heart rate by Type II diabetes receiving insulin in the context of ACS. Type II diabetics requiring insulin for better glycemic control manifested a faster heart rate. By identifying patient factors at ED nurse triage that could be predictive of ACS, accuracy rates of triage may improve, thus impacting patient outcomes.

Comparison of clinical risk scores for triaging high-risk chest pain patients at the emergency department.

BACKGROUND: Many of the clinical risk scores routinely used for chest pain assessment have not been validated in patients at high risk for acute coronary syndrome (ACS). We performed an independent comparison of HEART, TIMI, GRACE, FRISC, and PURSUIT scores for identifying chest pain due to ACS and for predicting 30-day death or re-infarction in patients arriving through Emergency Medical Services (EMS). METHODS AND RESULTS: We enrolled consecutive EMS patients evaluated for chest pain at three emergency departments. A reviewer blinded to outcome data retrospectively reviewed patient charts to compute each risk score. The primary outcome was ACS diagnosed during the primary admission, and the secondary outcome was death or re-infarction within 30-days of initial presentation. Our sample included 750 patients (aged 59 ±â€¯17 years, 42% female), of whom 115 (15.3%) had ACS and 33 (4.4%) had 30-day death or re-infarction. The c-statistics of HEART, TIMI, GRACE, FRISC, and PURSUIT for identifying ACS were 0.87, 0.86, 0.73, 0.84, and 0.79, respectively, and for predicting 30-day death or re-infarction were 0.70, 0.73, 0.72, 0.72, and 0.62, respectively. Sensitivity/negative predictive value of HEART ≥ 4 and TIMI ≥ 3 for ACS detection were 0.94/0.98 and 0.87/0.97, respectively. CONCLUSIONS: In chest pain patients admitted through EMS, HEART and TIMI outperform other scores for identifying chest pain due to ACS. Although both have similar negative predictive value, HEART has better sensitivity and lower rate of false negative results, thus it can be used preferentially over TIMI in the initial triage of this population.

The role of heart rate variability, heart rate turbulence, and deceleration capacity in predicting cause-specific mortality in chronic heart failure.

BACKGROUND: The volume of regional denervated myocardium (D-M) on positron emission tomography has been recently suggested as a strong independent predictor of cause-specific mortality from sudden cardiac arrest (SCA) in chronic heart failure. We sought to evaluate whether ECG indices of global autonomic function predict risk of SCA to a similar degree as regional D-M. METHODS: Subjects enrolled in the Prediction of Arrhythmic Events using Positron Emission Tomography (PAREPET) study were included in this study. Patients completed a 24-hour Holter ECG at enrollment and were followed up at 3-month intervals. SCA events were adjudicated by two board-certified cardiologists. Other cardiovascular death events were classified as nonsudden cardiac death (NSCD). Eight measures of heart rate variability were analyzed: SDNN, RMSSD, low-frequency (LF) and high-frequency (HF) power, heart rate turbulence onset and slope, and acceleration and deceleration capacity. We used competing risk regression to delineate cause-specific mortality from SCA versus NSCD. RESULTS: Our sample included 127 patients (age 67 ±â€¯12, 92% male). After a median follow-up of 4.1 years, there were 22 (17%) adjudicated SCA and 18 (14%) adjudicated NSCD events. In multivariate Cox-regression, LF power was the only HRV parameter to predict time-to-SCA. However, in competing risk analysis, reduced LF power was preferentially associated with NSCD rather than SCA (HR = 0.92 [0.85-0.98], p = 0.019). CONCLUSION: Depressed LF power might indicate impaired vagal reflex, which suggests that increasing vagal tone in these patients would have a protective effect against NSCD beyond that achieved by the mere slowing of heart rate using ß-blockers.

Diurnal, weekly and seasonal variations of chest pain in patients transported by emergency medical services.

OBJECTIVES: Chest pain is among the leading causes for emergency medical services (EMS) activation. Acute myocardial infarction (MI) is not only one of the most critical aetiologies of chest pain, but also one of few conditions encountered by EMS that has been shown to follow a circadian pattern. Understanding the diurnal relationship between the inflow of chest pain patients and the likelihood of acute MI may inform prehospital and emergency department (ED) healthcare providers regarding the prediction, and hence prevention, of dire outcomes. METHODS: This was a secondary analysis of previously collected data from an observational prospective study that enrolled consecutive chest pain patients transported by a large metropolitan EMS system in the USA. We used the time of EMS call to determine the time-of-day of the indexed encounter. Two independent reviewers examined available medical data to determine our primary outcome, the presence of MI, and our secondary outcomes, infarct size and 30-day major adverse cardiac events (MACE). We estimated infarct size using peak troponin level. RESULTS: We enrolled 2065 patients (age 56±17, 53% males, 7.5% with MI). Chest pain encounters increased from 9:00 AM to 2:00 PM, with a peak at 1:00 PM and a nadir at 6:00 AM. Acute MI had a bimodal distribution with two peaks: 10 AM in ST-elevation MI, and 10 PM in non-ST-elevation MI. ST-elevation MI with afternoon onset was an independent predictor of infarct size. Acute MI with winter and early spring presentation was an independent predictor of 30-day MACE. CONCLUSIONS: EMS-attended chest pain calls follow a diurnal pattern, with the most vulnerable patients encountered during afternoons and winter/spring seasons. These data can inform prehospital and ED healthcare providers regarding the time of presentation where patients are more likely to have an underlying MI and subsequently worse outcomes.

Evaluation of beat-to-beat ventricular repolarization lability from standard 12-lead ECG during acute myocardial ischemia.

BACKGROUND: Acute myocardial ischemia is a common cause of ventricular arrhythmias, yet recent ECG methods predicting susceptibility to ventricular tachyarrhythmia have not been fully evaluated during spontaneous ischemia. We sought to evaluate the clinical utility of alternans and non-alternans components of repolarization variability from the standard 10-second 12-lead ECG signals to risk stratify patients with acute chest pain. METHODS: We enrolled consecutive, non-traumatic, chest pain patients transported through Emergency Medical Services (EMS) to three tertiary care hospitals with cardiac catheterization lab capabilities in Pittsburgh, PA. ECG signals were manually annotated by an electrophysiologist, then automatically processed using a custom-written software. Both T wave alternans (TWA) and non-alternans repolarization variability (NARV) were calculated using the absolute RMS differences over the repolarization window between odd/even averaged beats and between consecutive averaged pairs, respectively. The primary study outcome was the presence of acute myocardial infarction (AMI) documented by cardiac angiography. RESULTS: After excluding patients with secondary repolarization changes (n=123) and those with excessive noise (n=90), our final sample included 537 patients (age 57±16years, 56% males). Patients with AMI (n=47, 9%) had higher TWA and NARV values (p<0.01). Mean RR correlated with TWA, and noise measures correlated with TWA and NARV, after adjusting for potential confounders. There was a high collinearity between TWA and NARV, and each was separately predictive of AMI after controlling for number of analyzed beats, noise measures, and other clinical variables. CONCLUSIONS: Despite limitations imposed by signal quality, TWA and NARV are higher in patients with AMI, even after correction for potential confounders. The clinical value of TWA and NARV derived from standard ECG using our time-domain RMS method is questionable due to the small number of beats and significant noise.

The prognostic value of discordant T waves in lead aVR: A simple risk marker of sudden cardiac arrest in ischemic cardiomyopathy.

BACKGROUND: Simple and reliable ECG marker(s) for sudden cardiac arrest (SCA) could be very useful in assessing high-risk populations. Since ischemic repolarization abnormalities in the left ventricular (LV) apex are strongly correlated with discordant T waves in lead aVR, we sought to evaluate the clinical and prognostic significance of this feature in ischemic cardiomyopathy. METHODS: The PAREPET trial enrolled patients with ischemic cardiomyopathy eligible for a primary prevention implantable cardiac defibrillator (ICD). Those with persistent pacing or left bundle branch block were excluded. Amplitudes of T/aVR were automatically computed from median ECG beats at enrollment and endpoints were blindly adjudicated. RESULTS: The sample was mainly composed of older men (n=138, age 65±12, 91% male, EF 29±9%). At enrollment, amplitude of T/aVR significantly correlated with EF, indexed LV end-diastolic volume, B-type natriuretic peptide (BNP), regional scar volume, and PET-quantified denervated myocardium. After a median follow up of 4.2years, there were 23 (17%) adjudicated SCA. In multivariate analysis, the presence of discordant T/aVR (>0mm, n=42, 30%) was a significant and independent predictor of SCA (hazard ratio 2.0 [95% CI 1.0-4.9]) and cardiac death (hazard ratio 1.9 [95% CI 1.0-3.7]). CONCLUSIONS: In subjects with ischemic cardiomyopathy, discordant T waves in lead aVR are associated with high-risk clinical parameters including lower ejection fraction, greater ventricular volume, higher BNP, and more denervated myocardium. Furthermore, discordant T/aVR remained an independent predictor of SCA and cardiovascular mortality even after accounting for these prognostic factors.

Rationale, development, and implementation of the Electrocardiographic Methods for the Prehospital Identification of Non-ST Elevation Myocardial Infarction Events (EMPIRE).

BACKGROUND: The serum rise of cardiac troponin remains the gold standard for diagnosing non-ST elevation (NSTE) myocardial infarction (MI) despite its delayed response. Novel methods for real-time detection of NSTEMI would result in more immediate initiation of definitive medical therapy and faster transport to facilities that can provide specialized cardiac care. METHODS: EMPIRE is an ongoing prospective, observational cohort study designed to quantify the magnitude of ischemia-induced repolarization dispersion for the early detection of NSTEMI. In this ongoing study, prehospital ECG data is gathered from patients who call 9-1-1 with a chief complaint of non-traumatic chest pain. This data is then analyzed using the principal component analysis (PCA) technique of 12-lead ECGs to fully characterize the spatial and temporal qualities of STT waveforms. RESULTS: Between May and December of 2013, Pittsburgh EMS obtained and transmitted 351 prehospital ECGs of the 1149 patients with chest pain-related emergency dispatches transported to participating hospitals. After excluding those with poor ECG signal (n=40, 11%) and those with pacing or LBBB (n=50, 14%), there were 261 eligible patients (age 57±16years, 45% female, 45% Black). In this preliminary sample, there were 19 STEMI (7%) and 33 NSTEMI (12%). More than 50% of those with infarction (STEMI or NSTEMI) had initially negative troponin values upon presentation. We present ECG data of such NSTEMI case that was identified correctly using our methods. CONCLUSIONS: Concrete ECG algorithms that can quantify NSTE ischemia and allow differential treatment based on such ECG changes could have an immediate clinical impact on patient outcomes. We describe the rationale, development, design, and potential usefulness of the EMPIRE study. The findings may provide insights that can influence guidelines revisions and improve public health.

The Prevalence of Clinical and Electrocardiographic Risk Factors of Cardiovascular Death Among On-duty Professional Firefighters.

BACKGROUND: Firefighters have twice as many cardiovascular deaths as police officers and 4 times as many as emergency medical responders. The etiology for this high rate of mortality remains unknown. The electrocardiogram (ECG) is a widely used tool to screen populations at risk, yet there are no available on-duty, high-resolution ECG recordings from firefighters. OBJECTIVE: We sought to evaluate the prevalence of clinical and ECG risk factors among on-duty professional firefighters during 12-lead ECG holter monitoring and exercise stress testing. METHODS: Firefighters were recruited from Surveying & Assessing Firefighters Fitness & Electrocardiogram (SAFFE) study. This descriptive study recruited firefighters from 7 firehouses across Upstate New York who completed on-duty 24-hour Holter ECG monitoring and a standard exercise stress test. All analyses were completed by a reviewer blinded to all clinical data. RESULTS: A total of 112 firefighters (mean [SD] age, 44 [8] years; mostly white men) completed the study. Although all firefighters were in normal sinus rhythm, more than half of them had at least 1 high-risk ECG risk factor present, including abnormal sympathetic tone (elevated heart rate, 54%), abnormal repolarization (wide QRS-T angle, 25%), myocardial scarring (fragmented QRS, 24%), and myocardial ischemia (ST depression, 24%). Most firefighters tolerated the treadmill exercise stress test well (metabolic equivalent tasks, 11.8 + 2.5]); however, almost one-third had abnormal results of stress tests that required further evaluation to rule out subclinical coronary artery disease. CONCLUSIONS: Among on-duty professional firefighters, high-risk ECG markers of fatal cardiac events and abnormal stress test results that warrant further evaluation are prevalent. Annual physical checkups with routine 12-lead ECG can identify those who might benefit from preventive cardiovascular services.

Novel technical solutions for wireless ECG transmission & analysis in the age of the internet cloud.

Current guidelines recommend early reperfusion therapy for ST-elevation myocardial infarction (STEMI) within 90 min of first medical encounter. Telecardiology entails the use of advanced communication technologies to transmit the prehospital 12-lead electrocardiogram (ECG) to offsite cardiologists for early triage to the cath lab; which has been shown to dramatically reduce door-to-balloon time and total mortality. However, hospitals often find adopting ECG transmission technologies very challenging. The current review identifies seven major technical challenges of prehospital ECG transmission, including: paramedics inconvenience and transport delay; signal noise and interpretation errors; equipment malfunction and transmission failure; reliability of mobile phone networks; lack of compliance with the standards of digital ECG formats; poor integration with electronic medical records; and costly hardware and software pre-requisite installation. Current and potential solutions to address each of these technical challenges are discussed in details and include: automated ECG transmission protocols; annotatable waveform-based ECGs; optimal routing solutions; and the use of cloud computing systems rather than vendor-specific processing stations. Nevertheless, strategies to monitor transmission effectiveness and patient outcomes are essential to sustain initial gains of implementing ECG transmission technologies.

Unsupervised machine learning identifies symptoms of indigestion as a predictor of acute decompensation and adverse cardiac events in patients with heart failure presenting to the emergency department.

BACKGROUND: Patients with known heart failure (HF) present to emergency departments (ED) with a plethora of symptoms. Although symptom clusters have been suggested as prognostic features, accurately triaging HF patients is a longstanding challenge. OBJECTIVES: We sought to use machine learning to identify subtle phenotypes of patient symptoms and evaluate their diagnostic and prognostic value among HF patients seeking emergency care. METHODS: This was a secondary analysis of a prospective cohort study of consecutive patients seen in the ED for chest pain or equivalent symptoms. Independent reviewers extracted clinical data from charts, including nine categories of subjective symptoms reported during initial evaluation. The diagnostic outcome was acute HF exacerbation and prognostic outcome was 30-day major adverse cardiac events (MACE). Outcomes were adjudicated by two independent reviewers. K-means clustering was used to derive latent patient symptom clusters, and their associations with outcomes were assessed using multivariate logistic regression. RESULTS: Sample included 438 patients (age 65±14 years; 45% female, 49% Black, 18% HF exacerbation, 32% MACE). K-means clustering identified three presentation phenotypes: patients with dyspnea only (Cluster A, 40%); patients with indigestion, with or without dyspnea (Cluster B, 23%); patients with neither dyspnea nor indigestion (Cluster C, 37%). Compared to Cluster C, indigestion was a significant predictor of acute HF exacerbation (OR=1.8, 95%CI=1.0-3.4) and 30-day MACE (OR=1.8, 95%CI=1.0-3.1), independent of age, sex, race, and other comorbidities. CONCLUSION: Indigestion symptoms in patients with known HF signify excess risk of adverse events, suggesting that these patients should be triaged as high-risk during initial ED evaluation.

Ventricular tachycardia and in-hospital mortality in the intensive care unit.

Background: Continuous electrocardiographic (ECG) monitoring is used to identify ventricular tachycardia (VT), but false alarms occur frequently. Objective: The purpose of this study was to assess the rate of 30-day in-hospital mortality associated with VT alerts generated from bedside ECG monitors to those from a new algorithm among intensive care unit (ICU) patients. Methods: We conducted a retrospective cohort study in consecutive adult ICU patients at an urban academic medical center and compared current bedside monitor VT alerts, VT alerts from a new-unannotated algorithm, and true-annotated VT. We used survival analysis to explore the association between VT alerts and mortality. Results: We included 5679 ICU admissions (mean age 58 ± 17 years; 48% women), 503 (8.9%) experienced 30-day in-hospital mortality. A total of 30.1% had at least 1 current bedside monitor VT alert, 14.3% had a new-unannotated algorithm VT alert, and 11.6% had true-annotated VT. Bedside monitor VT alert was not associated with increased rate of 30-day mortality (adjusted hazard ratio [aHR] 1.06; 95% confidence interval [CI] 0.88-1.27), but there was an association for VT alerts from our new-unannotated algorithm (aHR 1.38; 95% CI 1.12-1.69) and true-annotated VT(aHR 1.39; 95% CI 1.12-1.73). Conclusion: Unannotated and annotated-true VT were associated with increased rate of 30-day in-hospital mortality, whereas current bedside monitor VT was not. Our new algorithm may accurately identify high-risk VT; however, prospective validation is needed.

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.

High-risk electrocardiographic parameters are ubiquitous in patients with ischemic cardiomyopathy.

BACKGROUND: The electrocardiogram (ECG) can be used to predict cardiovascular risk; however, like all risk factors with imperfect specificity, studies in low risk populations have been plagued by poor predictive accuracy. Although predictive accuracy might be improved among cohorts with a higher likelihood of cardiovascular events, this would also affect the prevalence of abnormal parameters and their exclusions. METHOD: To determine the magnitude of these changes in a cohort with ischemic cardiomyopathy we analyzed 15 previously validated high-risk parameters from the resting and ambulatory ECG in subjects enrolled in the Prediction of Arrhythmic Events with Positron Emission Tomography (PAREPET) study (n = 198). RESULTS: Using the published exclusion criteria from the validation studies (i.e., atrial fibrillation, persistent pacing, prolonged QRS), only 4 high-risk ECG parameters (27%) could be evaluated in all subjects and only 42% of subjects could have all 15 ECG parameters assessed. Nevertheless, almost every subject (97%) had at least one abnormal parameter. On average, there were 3.4 ± 1.8 (range, 0-8) high-risk ECG parameters per subject among the 11.7 ± 4.5 (range, 4-15) parameters that could be assessed. CONCLUSIONS: Thus, 34% of all assessable parameters were abnormal. In conclusion, a significant proportion of ECG parameters cannot be assessed in patients with ischemic cardiomyopathy, but high-risk results are ubiquitous. The influence of these issues will be clarified when the results of the PAREPET study are available to actually determine the predictive value of these parameters on cause-specific mortality in a high-risk cohort.