Forecasting imminent atrial fibrillation in long-term electrocardiogram recordings

BACKGROUND

Despite the morbidity associated with acute atrial fibrillation (AF), no models currently exist to forecast its imminent onset. We sought to evaluate the ability of deep learning to forecast the imminent onset of AF with sufficient lead time, which has important implications for inpatient care.

METHODS

We utilized the Physiobank Long-Term AF Database, which contains 24-h, labeled ECG recordings from patients with a history of AF. AF episodes were defined as ≥5 min of sustained AF. Three deep learning models incorporating convolutional and transformer layers were created for forecasting, with two models focusing on the predictive nature of sinus rhythm segments and AF epochs separately preceding an AF episode, and one model utilizing all preceding waveform as input. Cross-validated performance was evaluated using area under time-dependent receiver operating characteristic curves (AUC(t)) at 7.5-, 15-, 30-, and 60-min lead times, precision-recall curves, and imminent AF risk trajectories.

RESULTS

There were 367 AF episodes from 84 ECG recordings. All models showed average risk trajectory divergence of those with an AF episode from those without ∼15 min before the episode. Highest AUC was associated with the sinus rhythm model [AUC = 0.74; 7.5-min lead time], though the model using all preceding waveform data had similar performance and higher AUCs at longer lead times.

CONCLUSIONS

In this proof-of-concept study, we demonstrated the potential utility of neural networks to forecast the onset of AF in long-term ECG recordings with a clinically relevant lead time. External validation in larger cohorts is required before deploying these models clinically.

Engaging Multidisciplinary Clinical Users in the Design of an Artificial Intelligence-Powered Graphical User Interface for Intensive Care Unit Instability Decision Support

BACKGROUND

Critical instability forecast and treatment can be optimized by artificial intelligence (AI)-enabled clinical decision support. It is important that the user-facing display of AI output facilitates clinical thinking and workflow for all disciplines involved in bedside care.

OBJECTIVES

Our objective is to engage multidisciplinary users (physicians, nurse practitioners, physician assistants) in the development of a graphical user interface (GUI) to present an AI-derived risk score.

METHODS

Intensive care unit (ICU) clinicians participated in focus groups seeking input on instability risk forecast presented in a prototype GUI. Two stratified rounds (three focus groups [only nurses, only providers, then combined]) were moderated by a focus group methodologist. After round 1, GUI design changes were made and presented in round 2. Focus groups were recorded, transcribed, and deidentified transcripts independently coded by three researchers. Codes were coalesced into emerging themes.

RESULTS

Twenty-three ICU clinicians participated (11 nurses, 12 medical providers [3 mid-level and 9 physicians]). Six themes emerged: (1) analytics transparency, (2) graphical interpretability, (3) impact on practice, (4) value of trend synthesis of dynamic patient data, (5) decisional weight (weighing AI output during decision-making), and (6) display location (usability, concerns for patient/family GUI view). Nurses emphasized having GUI objective information to support communication and optimal GUI location. While providers emphasized need for recommendation interpretability and concern for impairing trainee critical thinking. All disciplines valued synthesized views of vital signs, interventions, and risk trends but were skeptical of placing decisional weight on AI output until proven trustworthy.

CONCLUSION

Gaining input from all clinical users is important to consider when designing AI-derived GUIs. Results highlight that health care intelligent decisional support systems technologies need to be transparent on how they work, easy to read and interpret, cause little disruption to current workflow, as well as decisional support components need to be used as an adjunct to human decision-making.

Integrating multimodal information in machine learning for classifying acute myocardial infarction

OBJECTIVE

Prompt identification and recognization of myocardial ischemia/infarction (MI) is the most important goal in the management of acute coronary syndrome (ACS). The 12-lead electrocardiogram (ECG) is widely used as the initial screening tool for patients with chest pain but its diagnostic accuracy remains limited. There is early evidence that machine learning (ML) algorithms applied to ECG waveforms can improve performance. Most studies are designed to classify MI from healthy controls and thus are limited due to the lack of consideration of ECG abnormalities from other cardiac conditions, leading to false positives. Moreover, clinical information beyond ECG has not yet been well leveraged in existing ML models.

APPROACH

The present study considered downstream clinical implementation scenarios in the initial model design by dichotomizing study recordings from a public large-scale ECG dataset into a MI class and a non-MI class with the inclusion of MI-confounding conditions. Two experiments were conducted to systematically investigate the impact of two important factors entrained in the modeling process, including the duration of ECG, and the value of multimodal information for model training. A novel multimodal deep learning architecture was proposed to learn joint features from both ECG and patient demographics.

MAIN RESULTS

The multimodal model achieved better performance than the ECG-only model, with a mean area under the receiver operating characteristic curve (AUROC) of 92.1% and a mean accuracy of 87.4%, which is on par with existing studies despite the increased task difficulty due to the new class definition. By investigation of model explainability, it revealed the contribution of patient information in model performance and clinical concordance of the model's attention with existing clinical insights.

SIGNIFICANCE

The findings in this study help guide the development of ML solutions for prompt MI detection and move the models one step closer to real-world clinical applications.

An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients

BACKGROUND

False ventricular tachycardia (VT) alarms are common during in-hospital electrocardiographic (ECG) monitoring. Prior research shows that the majority of false VT can be attributed to algorithm deficiencies.

PURPOSE

The purpose of this study was: (1) to describe the creation of a VT database annotated by ECG experts and (2) to determine true vs. false VT using a new VT algorithm created by our group.

METHODS

The VT algorithm was processed in 5320 consecutive ICU patients with 572,574 h of ECG and physiologic monitoring. A search algorithm identified potential VT, defined as: heart rate >100 beats/min, QRSs > 120 ms, and change in QRS morphology in >6 consecutive beats compared to the preceding native rhythm. Seven ECG channels, SpO₂ , and arterial blood pressure waveforms were processed and loaded into a web-based annotation software program. Five PhD-prepared nurse scientists performed the annotations.

RESULTS

Of the 5320 ICU patients, 858 (16.13%) had 22,325 VTs. After three levels of iterative annotations, a total of 11,970 (53.62%) were adjudicated as true, 6485 (29.05%) as false, and 3870 (17.33%) were unresolved. The unresolved VTs were concentrated in 17 patients (1.98%). Of the 3870 unresolved VTs, 85.7% (n = 3281) were confounded by ventricular paced rhythm, 10.8% (n = 414) by underlying BBB, and 3.5% (n = 133) had a combination of both.

CONCLUSIONS

The database described here represents the single largest human-annotated database to date. The database includes consecutive ICU patients, with true, false, and challenging VTs (unresolved) and could serve as a gold standard database to develop and test new VT algorithms.

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.

Emerging ECG methods for acute coronary syndrome detection: Recommendations & future opportunities

Despite being the mainstay for the initial noninvasive assessment of patients with symptomatic coronary artery disease, the 12‑lead ECG remains a suboptimal diagnostic tool for myocardial ischemia detection with only acceptable sensitivity and specificity scores. Although myocardial ischemia affects the configuration of the QRS complex and the STT waveform, current guidelines primarily focus on ST segment amplitude, which constitutes a missed opportunity and may explain the suboptimal diagnostic performance of the ECG. This possible opportunity and the low cost and ease of use of the ECG provide compelling motivation to enhance the diagnostic accuracy of the ECG to ischemia detection. This paper describes numerous computational ECG methods and approaches that have been shown to dramatically increase ECG sensitivity to ischemia detection. Briefly, these emerging approaches can be conceptually grouped into one of the following four approaches: (1) leveraging novel ECG waveform features and signatures indicative of ischemic injury other than the classical ST-T amplitude measures; (2) applying body surface potentials mapping (BSPM)-based approaches to enhance the spatial coverage of the surface ECG to detecting ischemia; (3) developing an inverse ECG solution to reconstruct anatomical models of activation and recovery pathways to detect and localize injury currents; and (4) exploring artificial intelligence (AI)-based techniques to harvest ECG waveform signatures of ischemia. We present recent advances, shortcomings, and future opportunities for each of these emerging ECG methods. Future research should focus on the prospective clinical testing of these approaches to establish clinical utility and to expedite potential translation into clinical practice.

Engaging clinicians early during the development of a graphical user display of an intelligent alerting system at the bedside

BACKGROUND

Artificial Intelligence (AI) is increasingly used to support bedside clinical decisions, but information must be presented in usable ways within workflow. Graphical User Interfaces (GUI) are front-facing presentations for communicating AI outputs, but clinicians are not routinely invited to participate in their design, hindering AI solution potential.

PURPOSE

To inform early user-engaged design of a GUI prototype aimed at predicting future Cardiorespiratory Insufficiency (CRI) by exploring clinician methods for identifying at-risk patients, previous experience with implementing new technologies into clinical workflow, and user perspectives on GUI screen changes.

METHODS

We conducted a qualitative focus group study to elicit iterative design feedback from clinical end-users on an early GUI prototype display. Five online focus group sessions were held, each moderated by an expert focus group methodologist. Iterative design changes were made sequentially, and the updated GUI display was presented to the next group of participants.

RESULTS

23 clinicians were recruited (14 nurses, 4 nurse practitioners, 5 physicians; median participant age ∼35 years; 60% female; median clinical experience 8 years). Five themes emerged from thematic content analysis: trend evolution, context (risk evolution relative to vital signs and interventions), evaluation/interpretation/explanation (sub theme: continuity of evaluation), clinician intuition, and clinical operations. Based on these themes, GUI display changes were made. For example, color and scale adjustments, integration of clinical information, and threshold personalization.

CONCLUSIONS

Early user-engaged design was useful in adjusting GUI presentation of AI output. Next steps involve clinical testing and further design modification of the AI output to optimally facilitate clinician surveillance and decisions. Clinicians should be involved early and often in clinical decision support design to optimize efficacy of AI tools.

Improving Corrected QT Interval Monitoring in Critical Care Units: A Single Center Report

BACKGROUND

Corrected QT (QTc) interval prolongation is a type of ventricular tachyarrhythmia. Recommendations for QTc interval monitoring for critical care nurses are limited and variable.

LOCAL PROBLEM

The intensive care unit at the study institution had no policies for QTc interval monitoring. A quality improvement initiative for identifying and monitoring at-risk patients was begun.

METHODS

A QTc interval monitoring protocol was developed according to current recommendations for electrocardiogram monitoring and input from experts. Nursing staff received education on the QTc monitoring protocol. Numbers of patients with indications for monitoring were collected for 60 days before and 60 days after implementation. The rate of protocol adherence was collected for 60 days after implementation. Aknowledge assessment was administered to nurses at baseline, immediately after education, and 4 months after education.

RESULTS

Before protocol implementation, 537 patients had indications for monitoring. No QTc intervals were documented by nurses. After protocol implementation, 544 patients had indications for monitoring. Protocol adherence was higher during day shifts than during night shifts (45.3% and 38.4%, respectively). Of 170 documented QTc prolongation events, 26 (15%) were reported to physicians. Nurses' knowledge significantly improved after education and was retained 4 months after education (correct responses to assessment questions: 59% at baseline, 96% immediately after education, and 86% at 4 months after education).

CONCLUSIONS

This QTc interval monitoring protocol improved nurses' ability to identify and monitor patients with increased risk of QTc interval prolongation. Adherence was less than desired, suggesting that further protocol revisions are required.

Your neighborhood matters: A machine-learning approach to the geospatial and social determinants of health in 9-1-1 activated chest pain

Healthcare disparities in the initial management of patients with acute coronary syndrome (ACS) exist. Yet, the complexity of interactions between demographic, social, economic, and geospatial determinants of health hinders incorporating such predictors in existing risk stratification models. We sought to explore a machine-learning-based approach to study the complex interactions between the geospatial and social determinants of health to explain disparities in ACS likelihood in an urban community. This study identified consecutive patients transported by Pittsburgh emergency medical service for a chief complaint of chest pain or ACS-equivalent symptoms. We extracted demographics, clinical data, and location coordinates from electronic health records. Median income was based on US census data by zip code. A random forest (RF) classifier and a regularized logistic regression model were used to identify the most important predictors of ACS likelihood. Our final sample included 2400 patients (age 59 ± 17 years, 47% Females, 41% Blacks, 15.8% adjudicated ACS). In our RF model (area under the receiver operating characteristic curve of 0.71 ± 0.03) age, prior revascularization, income, distance from hospital, and residential neighborhood were the most important predictors of ACS likelihood. In regularized regression (akaike information criterion = 1843, bayesian information criterion = 1912, χ²  = 193, df = 10, p < 0.001), residential neighborhood remained a significant and independent predictor of ACS likelihood. Findings from our study suggest that residential neighborhood constitutes an upstream factor to explain the observed healthcare disparity in ACS risk prediction, independent from known demographic, social, and economic determinants of health, which can inform future work on ACS prevention, in-hospital care, and patient discharge.

Performance and limitations of automated ECG interpretation statements in patients with suspected acute coronary syndrome

BACKGROUND

The 12‑lead ECG plays an important role in triaging patients with symptomatic coronary artery disease, making automated ECG interpretation statements of "Acute MI" or "Acute Ischemia" crucial, especially during prehospital transport when access to physician interpretation of the ECG is limited. However, it remains unknown how automated interpretation statements correspond to adjudicated clinical outcomes during hospitalization. We sought to evaluate the diagnostic performance of prehospital automated interpretation statements to four well-defined clinical outcomes of interest: confirmed ST- segment elevation myocardial infarction (STEMI); presence of actionable coronary culprit lesions, myocardial necrosis, or any acute coronary syndrome (ACS).

METHODS

An observational cohort study that enrolled consecutive patients with non-traumatic chest pain transported via ambulance. Prehospital ECGs were obtained with the Philips MRX monitor from the medical command center and re-processed using manufacturer-specific diagnostic algorithms to denote the likelihood of >>>Acute MI<<< or >>>Acute Ischemia<<<. Two independent reviewers retrospectively adjudicated the study outcomes and disagreements were resolved by a third reviewer.

RESULTS

Our study included 2400 patients (age 59 ± 16, 47% females, 41% Black), with 190 (8%) patients with documented automated diagnostic statements of acute MI or acute ischemia. The sensitivity/specificity of the automated algorithm for detecting confirmed STEMI (n = 143, 6%); presence of actionable coronary culprit lesions (n = 258, 11%), myocardial necrosis (n = 291, 12%), or any ACS (n = 378, 16%) were 62.9%/95.6%; 37.2%/95.6%; 38.5%/96.4%; and 30.7%/96.3%, respectively.

CONCLUSION

Although being very specific, automated interpretation statements of acute MI/acute ischemia on prehospital ECGs are not satisfactorily sensitive to exclude symptomatic coronary disease. Patients without these automated interpretation statements should be considered further for significant underlying coronary disease based on the clinical context.

TRIAL REGISTRATION

ClinicalTrials.gov # NCT04237688.

Novel ECG features and machine learning to optimize culprit lesion detection in patients with suspected acute coronary syndrome

BACKGROUND

Novel temporal-spatial features of the 12‑lead ECG can conceptually optimize culprit lesions' detection beyond that of classical ST amplitude measurements. We sought to develop a data-driven approach for ECG feature selection to build a clinically relevant algorithm for real-time detection of culprit lesion.

METHODS

This was a prospective observational cohort study of chest pain patients transported by emergency medical services to three tertiary care hospitals in the US. We obtained raw 10-s, 12‑lead ECGs (500 s/s, HeartStart MRx, Philips Healthcare) during prehospital transport and followed patients 30 days after the encounter to adjudicate clinical outcomes. A total of 557 global and lead-specific features of P-QRS-T waveform were harvested from the representative average beats. We used Recursive Feature Elimination and LASSO to identify 35/557, 29/557, and 51/557 most recurrent and important features for LAD, LCX, and RCA culprits, respectively. Using the union of these features, we built a random forest classifier with 10-fold cross-validation to predict the presence or absence of culprit lesions. We compared this model to the performance of a rule-based commercial proprietary software (Philips DXL ECG Algorithm).

RESULTS

Our sample included 2400 patients (age 59 ± 16, 47% female, 41% Black, 10.7% culprit lesions). The area under the ROC curves of our random forest classifier was 0.85 ± 0.03 with sensitivity, specificity, and negative predictive value of 71.1%, 84.7%, and 96.1%. This outperformed the accuracy of the automated interpretation software of 37.2%, 95.6%, and 92.7%, respectively, and corresponded to a net reclassification improvement index of 23.6%. Metrics of ST80; Tpeak-Tend; spatial angle between QRS and T vectors; PCA ratio of STT waveform; T axis; and QRS waveform characteristics played a significant role in this incremental gain in performance.

CONCLUSIONS

Novel computational features of the 12‑lead ECG can be used to build clinically relevant machine learning-based classifiers to detect culprit lesions, which has important clinical implications.

In Search of an Optimal Subset of ECG Features to Augment the Diagnosis of Acute Coronary Syndrome at the Emergency Department

Background Classical ST-T waveform changes on standard 12-lead ECG have limited sensitivity in detecting acute coronary syndrome (ACS) in the emergency department. Numerous novel ECG features have been previously proposed to augment clinicians' decision during patient evaluation, yet their clinical utility remains unclear. Methods and Results This was an observational study of consecutive patients evaluated for suspected ACS (Cohort 1 n=745, age 59±17, 42% female, 15% ACS; Cohort 2 n=499, age 59±16, 49% female, 18% ACS). Out of 554 temporal-spatial ECG waveform features, we used domain knowledge to select a subset of 65 physiology-driven features that are mechanistically linked to myocardial ischemia and compared their performance to a subset of 229 data-driven features selected by multiple machine learning algorithms. We then used random forest to select a final subset of 73 most important ECG features that had both data- and physiology-driven basis to ACS prediction and compared their performance to clinical experts. On testing set, a regularized logistic regression classifier based on the 73 hybrid features yielded a stable model that outperformed clinical experts in predicting ACS, with 10% to 29% of cases reclassified correctly. Metrics of nondipolar electrical dispersion (ie, circumferential ischemia), ventricular activation time (ie, transmural conduction delays), QRS and T axes and angles (ie, global remodeling), and principal component analysis ratio of ECG waveforms (ie, regional heterogeneity) played an important role in the improved reclassification performance. Conclusions We identified a subset of novel ECG features predictive of ACS with a fully interpretable model highly adaptable to clinical decision support applications. Registration URL: https://www.clinicaltrials.gov; Unique Identifier: NCT04237688.

Association between history of cancer and major adverse cardiovascular events in patients with chest pain presenting to the emergency department: a secondary analysis of a prospective cohort study

OBJECTIVES

Cancer survivorship status among patients evaluated for chest pain at the emergency department (ED) warrants high degree of suspicion. However, it remains unclear whether cancer survivorship is associated with different risk of major adverse cardiac events (MACE) compared to those with no history of cancer. Furthermore, while HEART score is widely used in ED evaluation, it is unclear whether it can adequately triage chest pain events in cancer survivors. We sought to compare the rate of MACE in patients with a recent history of cancer in remission evaluated for acute chest pain at the ED to those with no history of cancer, and compare the performance of a common chest pain risk stratification score (HEART) between the two groups.

METHODS

We performed a secondary analysis of a prospective observational cohort study of chest pain patients presenting to the EDs of three tertiary care hospitals in the USA. Cancer survivorship status, HEART scores, and the presence of MACE within 30 days of admission were retrospectively adjudicated from the charts. We defined patients with recent history of cancer in remission as those with a past history of cancer of less than 10 years, and currently cured or in remission.

RESULTS

The sample included 750 patients (age: 59 ± 17; 42% females, 40% Black), while 69 patients (9.1%) had recent history of cancer in remission. A cancer in remission status was associated with a higher comorbidity burden, older age, and female sex. There was no difference in risk of MACE between those with a cancer in remission and their counterparts in both univariate [17.4 vs. 19.5%, odds ratio (OR) = 0.87 (95% confidence interval (CI), 0.45-1.66], P = 0.67] and multivariable analysis adjusting for demographics and comorbidities [OR = 0.62 (95% CI, 0.31-1.25), P = 0.18]. Patients with cancer in remission had higher HEART score (4.6 ± 1.8 vs. 3.9 ± 2.0, P = 0.006), and a higher proportion triaged as intermediate risk [68 vs. 56%, OR = 1.67 (95% CI, 1.00-2.84), P = 0.05]; however, no difference in the performance of HEART score existed between the groups (area under the curve = 0.86 vs. 0.84, P = 0.76).

CONCLUSIONS

There was no difference in rate of MACE between those with recent history of cancer in remission compared to their counterparts. A higher proportion of patients with cancer in remission was triaged as intermediate risk by the HEART score, but we found no difference in the performance of the HEART score between the groups.

A Novel Non-Invasive Assessment of Cardiac Hemodynamics in Patients With Heart Failure and Atrial Fibrillation

Background

Heart failure (HF) and atrial fibrillation (AF) often coexist. The hemodynamic alterations induced by AF in patients with HF are well studied; however we lack reliable and non-invasive means to study these hemodynamic alterations in ambulatory patients. We sought to evaluate the clinical utility of impedance cardiography (ICG) as a novel and non-invasive tool to evaluate cardiac hemodynamics in ambulatory patients with HF and AF.

Methods

This was a single-center observational study. A convenient sample of ambulatory patients with chronic HF underwent non-invasive electrocardiogram (ECG) and hemodynamic monitoring using BioZ Dx impedance cardiographer. Hemodynamics were automatically computed and ECG data were interpreted by an independent reviewer.

Results

A total of 32 patients (62 ± 14 years of age; 66% male; ejection fraction 33±13%) were enrolled. There were no baseline demographic or clinical differences between those with AF (28%) and those without AF (72%). However, patients with AF exhibited lower stroke volume (60 ± 7 vs. 89 ± 29, P = 0.008), left ventricular work (33 ± 9 vs. 45 ± 13, P = 0.016), cardiac contractility (30 ± 8 vs. 40 ± 13, P = 0.037), and arterial elasticity (13 ± 5 vs. 21 ± 5, P = 0.012), as well as higher cardiac afterload (203 ± 57 vs. 151 ± 49, P = 0.015).

Conclusions

Using non-invasive ICG, we have shown that it is feasible to characterize hemodynamics in ambulatory HF patients. We show that AF compromises left ventricular function in patients with HF and is associated with excess afterload and reduced arterial elasticity.

The prognostic value of HEART score in patients with cocaine associated chest pain: An age-and-sex matched cohort study

INTRODUCTION

HEART score is widely used to stratify patients with chest pain in the emergency department but has never been validated for cocaine-associated chest pain (CACP). We sought to evaluate the performance of HEART score in risk stratifying patients with CACP compared to an age- and sex-matched cohort with non-CACP.

METHODS

The parent study was an observational cohort study that enrolled consecutive patients with chest pain. We identified patients with CACP and age/sex matched them to patients with non-CACP in 1:2 fashion. HEART score was calculated retrospectively from charts. The primary outcome was major adverse cardiac events (MACE) within 30 days of indexed encounter.

RESULTS

We included 156 patients with CACP and 312 age-and sex-matched patients with non-CACP (n = 468, mean age 51 ± 9, 22% females). There was no difference in rate of MACE between the groups (17.9% vs. 15.7%, p = 0.54). Compared to the non-CACP group, the HEART score had lower classification performance in those with CACP (AUC = 0.68 [0.56-0.80] vs. 0.84 [0.78-0.90], p = 0.022). In CACP group, Troponin score had the highest discriminatory value (AUC = 0.72 [0.60-0.85]) and Risk factors score had the lowest (AUC = 0.47 [0.34-0.59]). In patients deemed low-risk by the HEART score, those with CACP were more likely to experience MACE (14% vs. 4%, OR = 3.7 [1.3-10.7], p = 0.016).

CONCLUSION

In patients with CACP, HEART score performs poorly in stratifying risk and is not recommended as a rule out tool to identify those at low risk of MACE.

Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram

Prompt identification of acute coronary syndrome is a challenge in clinical practice. The 12-lead electrocardiogram (ECG) is readily available during initial patient evaluation, but current rule-based interpretation approaches lack sufficient accuracy. Here we report machine learning-based methods for the prediction of underlying acute myocardial ischemia in patients with chest pain. Using 554 temporal-spatial features of the 12-lead ECG, we train and test multiple classifiers on two independent prospective patient cohorts (n = 1244). While maintaining higher negative predictive value, our final fusion model achieves 52% gain in sensitivity compared to commercial interpretation software and 37% gain in sensitivity compared to experienced clinicians. Such an ultra-early, ECG-based clinical decision support tool, when combined with the judgment of trained emergency personnel, would help to improve clinical outcomes and reduce unnecessary costs in patients with chest pain.

Identifying the most important ECG predictors of reduced ejection fraction in patients with suspected acute coronary syndrome

BACKGROUND

Non-invasive screening tools of cardiac function can play a significant role in the initial triage of patients with suspected acute coronary syndrome. Numerous ECG features have been previously linked with cardiac contractility in the general population. We sought to identify ECG features that are most predictive for real-time screening of reduced left ventricular ejection fraction (LVEF) in the acute care setting.

METHODS

We performed a secondary analysis of a prospective, observational cohort study of patients evaluated for suspected acute coronary syndrome. We included consecutive patients in whom an echocardiogram was performed during indexed encounter. We evaluated 554 automated 12-lead ECG features in multivariate linear regression for predicting LVEF. We then used regression trees to identify the most important predictive ECG features.

RESULTS

Our final sample included 297 patients (aged 63 ± 15, 45% females). The mean LVEF was 57% ± 13 (IQR 50%-65%). In multivariate analysis, depolarization dispersion in the horizontal plane; global repolarization dispersion; and abnormal temporal indices in inferolateral leads were all independent predictors of LVEF (R² = 0.452, F = 6.679, p < 0.001). Horizontal QRS axis deviation and prolonged ventricular activation time in left ventricular apex were the most important determinants of reduced LVEF, while global QRS duration was of less importance.

CONCLUSIONS

Poor R wave progression in precordial leads with dominant QS pattern in V3 is the most predictive feature of reduced LVEF in suspected ACS. This feature constitutes a simple visual marker to aid clinicians in identifying those with impaired cardiac function.

Lack of Significant Coronary History and ECG Misinterpretation Are the Strongest Predictors of Undertriage in Prehospital Chest Pain

INTRODUCTION

Appropriate prehospital (PH) triage of patients with chest pain can significantly improve outcomes in acute myocardial infarction (MI). We sought to explore how PH providers triage chest pain as high versus low risk and to evaluate the accuracy and predictors of their triage decision.

METHODS

This was a prospective, observational cohort study that enrolled consecutive patients with chest pain transported by emergency medical services (EMS) to 3 tertiary care hospitals in the US. EMS triage decision (high risk versus low-risk) was defined based on the transmission of PH electrocardiogram (ECG) to a command center for medical consultation with or without catheter laboratory activation. Two independent reviewers examined in-hospital medical records to adjudicate the presence of acute MI and to audit the findings on the presenting ECG.

RESULTS

We enrolled 2,065 patients (aged 56 ± 17, 53% male) of whom 768 (37%) were triaged as high risk. Those triaged as high risk were older, were more likely to be men or have significant cardiac history, and had a higher rate of acute MI events (14.2% versus 3.5%). The sensitivity and specificity for triaging MI events as high risk were 70% and 97%, respectively. A total of 46/155 (30%) MI events were misclassified as low risk. No previous coronary revascularization and ECG misinterpretation were strong independent predictors of such undertriage.

CONCLUSIONS

PH providers have moderate sensitivity in triaging high-risk patients; 1 in 3 MI events are undertriaged. Emergency nurses need to pay special attention to patients with benign past histories during transition of care and should always reinterpret ECGs for subtle ischemic changes.

Nonspecific electrocardiographic abnormalities are associated with increased length of stay and adverse cardiac outcomes in prehospital chest pain

BACKGROUND

Nonspecific ST-T repolarization (NST) abnormalities alter the ST-segment for reasons often unrelated to acute myocardial ischemia, which could contribute to misdiagnosis or inappropriate treatment. We sought to define the prevalence of NST patterns in patients with chest pain and evaluate how such patterns correlate with the eventual etiology of chest pain and course of hospitalization.

METHODS

This was a prospective observational study that included consecutive prehospital chest pain patients from three tertiary care hospitals in the U.S. Two independent reviewers blinded from clinical data audited the prehospital 12-lead ECG for the presence or absence of NST patterns (i.e., right or left bundle branch block, left ventricular hypertrophy with strain pattern, ventricular pacing, ventricular rhythm, or coarse atrial fibrillation). The primary outcome was 30-day major adverse cardiac events (MACE) defined as cardiac arrest, acute heart failure, post-discharge infarction, or all-cause death.

RESULTS

The final sample included 750 patients (age 59 ± 17, 58% males). A total of 40 patients (5.3%) experienced 30-MACE and 131 (17.5%) had NST patterns. The presence of NST patterns was an independent multivariate predictor of 30-day MACE (9.9% vs. 4.4%, OR = 2.2 [95% CI = 1.1-4.5]. Patients with NST patterns had increased median length of stay (1.0 [IQR 0.5-3] vs. 2.0 [IQR 1-4] days, p < 0.05) independent of the etiology of chest pain.

CONCLUSIONS

One in six prehospital ECGs of patients with chest pain has NST patterns. This pattern is associated with increased length of stay and adverse cardiac outcomes, suggesting the need of preventive measures and close follow up in such patients.

Arterial Stiffness Is Associated With QTc Interval Prolongation in Patients With Heart Failure

BACKGROUND

A prolonged corrected QT (QTc) interval is a known risk factor for adverse cardiac events. Understanding the determinants and physiologic correlates of QTc is necessary for selecting proper strategies to reduce the risk of adverse events in high-risk patients. We sought to evaluate the role of arterial stiffness in heart failure as a determinant of QTc prolongation.

METHOD

This was an observational study that recruited ambulatory heart failure patients (New York Heart Association Classes I-II) from an outpatient heart failure clinic. In the supine resting position, consented patients underwent noninvasive 12-lead electrocardiograph (ECG) and hemodynamic monitoring using BioZ Dx impedance cardiography. ECGs were evaluated by a reviewer blinded to clinical data, and QTc interval was automatically computed. Patients with pacing or bundle branch block (BBB) were analyzed separately. Strengths of associations were evaluated using Pearson's r coefficients and multivariate linear regression.

RESULTS

The final sample ( N = 44) was 62 ± 13 years of age and 64% male with ejection fraction of 34% ± 12%. At univariate level, QTc interval moderately ( r > .50) correlated with cardiac output, left cardiac work index, systemic vascular resistance, and total arterial compliance in patients with intrinsically narrow QRS complexes. At the multivariate level, increasing systemic vascular resistance and decreasing total arterial compliance remained independent predictors of widening QTc interval in this group ( R² = .54). No significant correlations were seen in patients with pacing or BBB.

CONCLUSIONS

In the absence of conduction abnormalities, magnitude of arterial stiffness, an indirect measure of endothelial dysfunction, is associated with QTc interval prolongation.

Spatial indices of repolarization correlate with non-ST elevation myocardial ischemia in patients with chest pain

Mild-to-moderate ischemia does not result in ST segment elevation on the electrocardiogram (ECG), but rather non-specific changes in the T wave, which are frequently labeled as non-diagnostic for ischemia. Robust methods to quantify such T wave heterogeneity can have immediate clinical applications. We sought to evaluate the effects of spontaneous ischemia on the evolution of spatial T wave changes, based on the eigenvalues of the spatial correlation matrix of the ECG, in patients undergoing nuclear cardiac imaging for evaluating intermittent chest pain. We computed T wave complexity (TWC), the ratio of the second to the first eigenvalue of repolarization, from 5-min baseline and 5-min peak-stress Holter ECG recordings. Our sample included 30 males and 20 females aged 63 ± 11 years. Compared to baseline, significant changes in TWC were only seen in patients with ischemia (n = 10) during stress testing, but not among others. The absolute changes in TWC were significantly larger in the ischemia group compared to others, with a pattern that seemed to depend on the severity or anatomic distribution of ischemia. Our results demonstrate that ischemia-induced changes in T wave morphology can be meaningfully quantified from the surface 12-lead ECG, suggesting an important opportunity for improving diagnostics in patients with chest pain.

The Selvester QRS Score is more accurate than Q waves and fragmented QRS complexes using the Mason-Likar configuration in estimating infarct volume in patients with ischemic cardiomyopathy

Infarct volume independently predicts cardiovascular events. Fragmented QRS complexes (fQRS) may complement Q waves for identifying infarction; however, their utility in advanced coronary disease is unknown. We tested whether fQRS could improve the electrocardiographic prediction of infarct volume by positron emission tomography in 138 patients with ischemic cardiomyopathy (ejection fraction, 0.27 +/- 0.09). Indices of infarction (pathologic Q waves, fQRS, and Selvester QRS Score) were analyzed by blinded observers. In patients with QRS duration less than 120 milliseconds, number of leads with pathologic Q waves (mean, 1.6 +/- 1.7) correlated weakly with infarct volume (r = 0.30, P < .05). Adding fQRS increased the number of affected leads (3.6 +/- 2.5), but the significant correlation with infarct volume was lost (r = 0.02, P = .10). Selvester Score was the most accurate (mean, 5.9 +/- 4.9 points; r = 0.49; P < .001). Fragmented QRS was not predictive of infarct size in patients with QRS duration of at least 120 milliseconds (r = 0.02, P = .19). Thus, in ischemic cardiomyopathy, consideration of fQRS complexes does not improve Q wave prediction of infarct volume; but Selvester Score was more accurate.