Automated electrocardiogram interpretation programs versus cardiologists' triage decision making based on teletransmitted data in patients with suspected acute coronary syndrome

Use of the energy waveform electrocardiogram to detect subclinical left ventricular dysfunction in patients with type 2 diabetes mellitus

BACKGROUND

Recent guidelines propose N-terminal pro-B-type natriuretic peptide (NT-proBNP) for recognition of asymptomatic left ventricular (LV) dysfunction (Stage B Heart Failure, SBHF) in type 2 diabetes mellitus (T2DM). Wavelet Transform based signal-processing transforms electrocardiogram (ECG) waveforms into an energy distribution waveform (ew)ECG, providing frequency and energy features that machine learning can use as additional inputs to improve the identification of SBHF. Accordingly, we sought whether machine learning model based on ewECG features was superior to NT-proBNP, as well as a conventional screening tool-the Atherosclerosis Risk in Communities (ARIC) HF risk score, in SBHF screening among patients with T2DM.

METHODS

Participants in two clinical trials of SBHF (defined as diastolic dysfunction [DD], reduced global longitudinal strain [GLS ≤ 18%] or LV hypertrophy [LVH]) in T2DM underwent 12-lead ECG with additional ewECG feature and echocardiography. Supervised machine learning was adopted to identify the optimal combination of ewECG extracted features for SBHF screening in 178 participants in one trial and tested in 97 participants in the other trial. The accuracy of the ewECG model in SBHF screening was compared with NT-proBNP and ARIC HF.

RESULTS

SBHF was identified in 128 (72%) participants in the training dataset (median 72 years, 41% female) and 64 (66%) in the validation dataset (median 70 years, 43% female). Fifteen ewECG features showed an area under the curve (AUC) of 0.81 (95% CI 0.787-0.794) in identifying SBHF, significantly better than both NT-proBNP (AUC 0.56, 95% CI 0.44-0.68, p < 0.001) and ARIC HF (AUC 0.67, 95%CI 0.56-0.79, p = 0.002). ewECG features were also led to robust models screening for DD (AUC 0.74, 95% CI 0.73-0.74), reduced GLS (AUC 0.76, 95% CI 0.73-0.74) and LVH (AUC 0.90, 95% CI 0.88-0.89).

CONCLUSIONS

Machine learning based modelling using additional ewECG extracted features are superior to NT-proBNP and ARIC HF in SBHF screening among patients with T2DM, providing an alternative HF screening strategy for asymptomatic patients and potentially act as a guidance tool to determine those who required echocardiogram to confirm diagnosis. Trial registration LEAVE-DM, ACTRN 12619001393145 and Vic-ELF, ACTRN 12617000116325.

Compared with physician overread, computer is less accurate but helpful in interpretation of electrocardiography for ST-segment elevation myocardial infarction

INTRODUCTION

Previous studies have demonstrated varying sensitivity and specificity of computer-interpreted electrocardiography (CIE) in identifying ST-segment elevation myocardial infarction (STEMI). This study aims to evaluate the accuracy of contemporary computer software in recognizing electrocardiography (ECG) signs characteristic of STEMI compared to emergency physician overread in clinical practice.

MATERIAL AND METHODS

In this retrospective observational single-center study, we reviewed the records of patients in the emergency department (ED) who underwent ECGs and troponin tests. Both the Philips DXL 16-Lead ECG. Algorithm and on-duty emergency physicians interpreted each standard 12‑lead ECG. The sensitivity and specificity of computer interpretation and physician overread ECGs for the definite diagnosis of STEMI were calculated and compared.

RESULTS

Among the 9340 patients included in the final analysis, 133 were definitively diagnosed with STEMI. When "computer-reported infarct or injury" was used as the indicator, the sensitivity was 87.2% (95% CI 80.3% to 92.4%) and the specificity was 86.2% (95% CI 85.5% to 86.9%). When "physician-overread STEMI" was used as the indicator, the sensitivity was 88.0% (95% CI 81.2% to 93.0%) and the specificity was 99.9% (95% CI 99.8% to 99.9%). The area under the receiver operating characteristic curve for physician-overread STEMI and computer-reported infarct or injury were 0.939 (95% CI 0.907 to 0.972) and 0.867 (95% CI 0.834 to 0.900), respectively.

CONCLUSIONS

This study reveals that while the sensitivity of the computer in recognizing ECG signs of STEMI is similar to that of physicians, physician overread of ECGs is more specific and, therefore, more accurate than CIE.

Management of Acute Coronary Syndromes in Patients in Rural Australia: The MORACS Randomized Clinical Trial

Importance

Treatment of ST-segment elevation myocardial infarction (STEMI) in rural settings involves thrombolysis followed by transfer to a percutaneous coronary intervention-capable hospital. The first step is accurate diagnosis via electrocardiography (ECG), but one-third of all STEMI incidents go unrecognized and hence untreated.

Objective

To reduce missed diagnoses of STEMI.

Design, Setting, and Participants

This cluster randomized clinical trial included 29 hospital emergency departments (EDs) in rural Australia with no emergency medicine specialists, which were randomized to usual care vs automatically triggered diagnostic support from the tertiary referral hospital (management of rural acute coronary syndromes [MORACS] intervention). Patients presenting with symptoms compatible with acute coronary syndromes (ACS) were eligible for inclusion. The study was conducted from December 2018 to April 2020. Data were analyzed in August 2021.

Intervention

Triage of a patient with symptoms compatible with ACS triggered an automated notification to the tertiary hospital coronary care unit. The ECG and point-of-care troponin results were reviewed remotely and a phone call was made to the treating physician in the rural hospital to assist with diagnosis and initiation of treatment.

Main Outcomes and Measures

The proportion of patients with missed STEMI diagnoses.

Results

A total of 6249 patients were included in the study (mean [SD] age, 63.6 [12.2] years; 48% female). Of 7474 ED presentations with suspected ACS, STEMI accounted for 77 (2.0%) in usual care hospitals and 46 (1.3%) in MORACS hospitals. Missed diagnosis of STEMI occurred in 27 of 77 presentations (35%) in usual care hospitals and 0 of 46 (0%) in MORACS hospitals (P < .001). Of eligible patients, 48 of 75 (64%) in the usual care group and 36 of 36 (100%) in the MORACS group received primary reperfusion (P < .001). In the usual care group, 12-month mortality was 10.3% (n = 8) vs 6.5% (n = 3) in the MORACS group (relative risk, 0.64; 95% CI, 0.18-2.23). Patients with missed STEMI diagnoses had a mortality of 25.9% (n = 7) compared with 2.0% (n = 1) for those with accurately diagnosed STEMI (relative risk, 13.2; 95% CI, 1.71-102.00; P = .001). Overall, there were 6 patients who did not have STEMI as a final diagnosis; 5 had takotsubo cardiomyopathy and 1 had pericarditis. There was no difference between groups in the rate of alternative final diagnosis.

Conclusion and Relevance

The findings indicate that MORACS diagnostic support service reduced the proportion of missed STEMI and improved the rates of primary reperfusion therapy. Accurate diagnosis of STEMI was associated with lower mortality.

Trial Registration

anzctr.org.au Identifier: ACTRN12619000533190.

Utility of prehospital electrocardiogram interpretation in ST-segment elevation myocardial infarction utilizing computer interpretation and transmission for interventional cardiologist consultation

Objectives

We examined the appropriateness of prehospital cardiac catheter laboratory activation (CCL‐A) in ST‐segment elevation myocardial infarction (STEMI) utilizing the University of Glasgow algorithm (UGA) and remote interventional cardiologist consultation.

Background

The incremental benefit of prehospital electrocardiogram (PH‐ECG) transmission on the diagnostic accuracy and appropriateness of CCL‐A has been examined in a small number of studies with conflicting results.

Methods

We identified consecutive PH‐ECG transmissions between June 2, 2010 and October 6, 2016. Blinded adjudication of ECGs, appropriateness of CCL‐A, and index diagnoses were performed using the fourth universal definition of MI. The primary outcome was the appropriate CCL‐A rate. Secondary outcomes included rates of false‐positive CCL‐A, inappropriate CCL‐A, and inappropriate CCL nonactivation.

Results

Among 1088 PH‐ECG transmissions, there were 565 (52%) CCL‐As and 523 (48%) CCL nonactivations. The appropriate CCL‐A rate was 97% (550 of 565 CCL‐As), of which 4.9% (n = 27) were false‐positive. The inappropriate CCL‐A rate was 2.7% (15 of 565 CCL‐As) and the inappropriate CCL nonactivation rate was 3.6% (19 of 523 CCL nonactivations). Reasons for appropriate CCL nonactivation (n = 504) included nondiagnostic ST‐segment elevation (n = 128, 25%), bundle branch block (n = 132, 26%), repolarization abnormality (n = 61, 12%), artefact (n = 72, 14%), no ischemic symptoms (n = 32, 6.3%), severe comorbidities (n = 26, 5.2%), transient ST‐segment elevation (n = 20, 4.0%), and others.

Conclusions

PH‐ECG interpretation utilizing UGA with interventional cardiologist consultation accurately identified STEMI with low rates of inappropriate and false‐positive CCL‐As, whereas using UGA alone would have almost doubled CCL‐As. The benefits of cardiologist consultation were identifying “masquerading” STEMI and avoiding unnecessary CCL‐As.

Late Outcomes of Patients With Prehospital ST-Segment Elevation and Appropriate Cardiac Catheterization Laboratory Nonactivation

Background Patients with suspected ST-segment-elevation myocardial infarction (STEMI) and cardiac catheterization laboratory nonactivation (CCL-NA) or cancellation have reportedly similar crude and higher adjusted risks of death compared with those with CCL activation, though reasons for these poor outcomes are not clear. We determined late clinical outcomes among patients with prehospital ECG STEMI criteria who had CCL-NA compared with those who had CCL activation. Methods and Results We identified consecutive prehospital ECG transmissions between June 2, 2010 to October 6, 2016. Diagnoses according to the Fourth Universal Definition of myocardial infarction (MI), particularly rates of myocardial injury, were adjudicated. The primary outcome was all-cause death. Secondary outcomes included cardiovascular death/MI/stroke and noncardiovascular death. To explore competing risks, cause-specific hazard ratios (HRs) were obtained. Among 1033 included ECG transmissions, there were 569 (55%) CCL activations and 464 (45%) CCL-NAs (1.8% were inappropriate CCL-NAs). In the CCL activation group, adjudicated index diagnoses included MI (n=534, 94%, of which 99.6% were STEMI and 0.4% non-STEMI), acute myocardial injury (n=15, 2.6%), and chronic myocardial injury (n=6, 1.1%). In the CCL-NA group, diagnoses included MI (n=173, 37%, of which 61% were non-STEMI and 39% STEMI), chronic myocardial injury (n=107, 23%), and acute myocardial injury (n=47, 10%). At 2 years, the risk of all-cause death was higher in patients who had CCL-NA compared with CCL activation (23% versus 7.9%, adjusted risk ratio, 1.58, 95% CI, 1.24-2.00), primarily because of an excess in noncardiovascular deaths (adjusted HR, 3.56, 95% CI, 2.07-6.13). There was no significant difference in the adjusted risk for cardiovascular death/MI/stroke between the 2 groups (HR, 1.23, 95% CI, 0.87-1.73). Conclusions CCL-NA was not primarily attributable to missed STEMI, but attributable to "masquerading" with high rates of non-STEMI and myocardial injury. These patients had worse late outcomes than patients who had CCL activation, mainly because of higher rates of noncardiovascular deaths.

Systematic Review and Meta-Analysis of Diagnostic Accuracy to Identify ST-Segment Elevation Myocardial Infarction on Interpretations of Prehospital Electrocardiograms

Background: The aim of this study was to assess and discuss the diagnostic accuracy of prehospital ECG interpretation through systematic review and meta-analyses.

Methods and Results: Relevant literature published up to July 2020 was identified using PubMed. All human studies of prehospital adult patients suspected of ST-segment elevation myocardial infarction in which prehospital electrocardiogram (ECG) interpretation by paramedics or computers was evaluated and reporting all 4 (true-positive, false-positive, false-negative, and true-negative) values were included. Meta-analyses were conducted separately for the diagnostic accuracy of prehospital ECG interpretation by paramedics (Clinical Question [CQ] 1) and computers (CQ2). After screening, 4 studies for CQ1 and 6 studies for CQ2 were finally included in the meta-analysis. Regarding CQ1, the pooled sensitivity and specificity were 95.5% (95% confidence interval [CI] 82.5–99.0%) and 95.8% (95% CI 82.3–99.1%), respectively. Regarding CQ2, the pooled sensitivity and specificity were 85.4% (95% CI 74.1–92.3%) and 95.4% (95% CI 87.3–98.4%), respectively.

Conclusions: This meta-analysis suggests that the diagnostic accuracy of paramedic prehospital ECG interpretations is favorable, with high pooled sensitivity and specificity, with an acceptable estimated number of false positives and false negatives. Computer-assisted ECG interpretation showed high pooled specificity with an acceptable estimated number of false positives, whereas the pooled sensitivity was relatively low.

Diagnostic Accuracy of the Deep Learning Model for the Detection of ST Elevation Myocardial Infarction on Electrocardiogram

We aimed to measure the diagnostic accuracy of the deep learning model (DLM) for ST-elevation myocardial infarction (STEMI) on a 12-lead electrocardiogram (ECG) according to culprit artery sorts. From January 2017 to December 2019, we recruited patients with STEMI who received more than one stent insertion for culprit artery occlusion. The DLM was trained with STEMI and normal sinus rhythm ECG for external validation. The primary outcome was the diagnostic accuracy of DLM for STEMI according to the three different culprit arteries. The outcomes were measured using the area under the receiver operating characteristic curve (AUROC), sensitivity (SEN), and specificity (SPE) using the Youden index. A total of 60,157 ECGs were obtained. These included 117 STEMI-ECGs and 60,040 normal sinus rhythm ECGs. When using DLM, the AUROC for overall STEMI was 0.998 (0.996–0.999) with SEN 97.4% (95.7–100) and SPE 99.2% (98.1–99.4). There were no significant differences in diagnostic accuracy within the three culprit arteries. The baseline wanders in false positive cases (83.7%, 345/412) significantly interfered with the accurate interpretation of ST elevation on an ECG. DLM showed high diagnostic accuracy for STEMI detection, regardless of the type of culprit artery. The baseline wanders of the ECGs could affect the misinterpretation of DLM.

Prehospital Predictors of Atypical STEMI Symptoms

Introduction: Rapid prehospital identification of patients with ST-elevation myocardial infarction (STEMI) is a critical step to reduce time to treatment. Broad screening with field 12-lead ECGs can lead to a high rate of false positive STEMI activations due to low prevalence. One strategy to reduce false positive STEMI interpretations is to limit acquisition of 12-lead ECGs to patients who have symptoms strongly suggestive of STEMI, but this may delay care in patients who present atypically and lead to disparities in populations with more atypical presentations. We sought to assess patient factors associated with atypical STEMI presentation.Methods: We retrospectively analyzed consecutive adult patients for whom Los Angeles Fire Department paramedics obtained a field 12-lead ECG from July 2011 through June 2012. The regional STEMI receiving center registry was used to identify patients with STEMI. Patients were designated as having typical symptoms if paramedics documented provider impressions of chest pain/discomfort, cardiac arrest, or cardiac symptoms, otherwise they were designated as having atypical symptoms. We utilized logistic regression to determine patient factors (age, sex, race) associated with atypical STEMI presentation.Results: Of the 586 patients who had STEMI, 70% were male, 43% White, 16% Black, 20% Hispanic, 5% Asian and 16% were other or unspecified race. Twenty percent of STEMI patients (n = 117) had atypical symptoms. Women who had STEMI were older than men (74 years [IQR 62-83] vs. 60 years [IQR 53-70], p < 0.001). Univariate predictors of atypical symptoms were older age and female sex (p < 0.0001), while in multivariable analysis older age [odd ratio (OR) 1.05 per year, [95%CI 1.04-1.07, p < 0.0001] and black race (OR vs White 2.18, [95%CI 1.20-3.97], p = 0.011) were associated with atypical presentation.Conclusion: Limiting prehospital acquisition of 12-lead ECGs to patients with typical STEMI symptoms would result in one in five patients with STEMI having delayed recognition, disproportionally impacting patients of older age, women, and Black patients. Age, not sex, may be a better predictor of atypical STEMI presentation.

Machine Learning of ECG Waveforms to Improve Selection for Testing for Asymptomatic Left Ventricular Dysfunction Prompt

OBJECTIVES

To identify whether machine learning from processing of continuous wave transforms (CWTs) to provide an "energy waveform" electrocardiogram (ewECG) could be integrated with echocardiographic assessment of subclinical systolic and diastolic left ventricular dysfunction (LVD).

BACKGROUND

Asymptomatic LVD has management implications, but routine echocardiography is not undertaken in subjects at risk of heart failure. Signal processing of the surface ECG with the use of CWT can identify abnormal myocardial relaxation.

METHODS

EwECG and echocardiography were undertaken in 398 participants at risk of heart failure (HF). Reduced global longitudinal strain (GLS ≤16%)), diastolic abnormalities (E/e' >15, left atrial enlargement with E/e' >10 or impaired relaxation) or LV hypertrophy defined LVD. EwECG feature selection and supervised machine-learning by random forest (RF) classifier was undertaken with 643 CWT-derived features and the Atherosclerosis Risk in Communities (ARIC) heart failure risk score.

RESULTS

The ARIC score and 18 CWT features were selected to build a RF predictive model for LVD in a training dataset (n = 287; 60% female, median age 71 [interquartile range: 68 to 74] years). Model performance was tested in an independent group (n = 111; 49% female, median age 61 years [59 to 66 years]), demonstrating 85% sensitivity and 72% specificity (area under the receiver-operating characteristic curve [AUC]: 0.83; 95% confidence interval [CI]: 0.74 to 0.92). With ARIC score removed, sensitivity was 88% and specificity, 70% (AUC: 0.78; 95% CI: 0.70 to 0.86). RF models for reduced GLS and diastolic abnormalities including similar features had sensitivities that were unsuitable for screening. Conventional candidates for LVD screening (ARIC score, N-terminal pro-B-type natriuretic peptide, and standard automated ECG analysis) had inferior discriminative ability. Integration of ewECG in screening of people at risk of HF would reduce need for echocardiography by 45% while missing 12% of LVD cases.

CONCLUSIONS

Machine learning applied to ewECG is a sensitive screening test for LVD, and its integration into screening of patients at risk for HF would reduce the number of echocardiograms by almost one-half.

Systematic Review of Clinical Decision Support Systems for Prehospital Acute Coronary Syndrome Identification

OBJECTIVES

Timely prehospital diagnosis and treatment of acute coronary syndrome (ACS) are required to achieve optimal outcomes. Clinical decision support systems (CDSS) are platforms designed to integrate multiple data and can aid with management decisions in the prehospital environment. The review aim was to describe the accuracy of CDSS and individual components in the prehospital ACS management.

METHODS

This systematic review examined the current literature regarding the accuracy of CDSS for ACS in the prehospital setting, the influence of computer-aided decision-making and of 4 components: electrocardiogram, biomarkers, patient history, and examination findings. The impact of these components on sensitivity, specificity, and positive and negative predictive values was assessed.

RESULTS

A total of 11,439 articles were identified from a search of databases, of which 199 were screened against the eligibility criteria. Eight studies were found to meet the eligibility and quality criteria. There was marked heterogeneity between studies which precluded formal meta-analysis. However, individual components analysis found that patient history led to significant improvement in the sensitivity and negative predictive values. CDSS which incorporated all 4 components tended to show higher sensitivities and negative predictive values. CDSS incorporating computer-aided electrocardiogram diagnosis showed higher specificities and positive predictive values.

CONCLUSIONS

Although heterogeneity precluded meta-analysis, this review emphasizes the potential of ACS CDSS in prehospital environments that incorporate patient history in addition to integration of multiple components. The higher sensitivity of certain components, along with higher specificity of computer-aided decision-making, highlights the opportunity for developing an integrated algorithm with computer-aided decision support.

Performance of seven ECG interpretation programs in identifying arrhythmia and acute cardiovascular syndrome

BACKGROUND

No direct comparison of current electrocardiogram (ECG) interpretation programs exists.

OBJECTIVE

Assess the accuracy of ECG interpretation programs in detecting abnormal rhythms and flagging for priority review records with alterations secondary to acute coronary syndrome (ACS).

METHODS

More than 2,000 digital ECGs from hospitals and databases in Europe, USA, and Australia, were obtained from consecutive adult and pediatric patients and converted to 10 s analog samples that were replayed on seven electrocardiographs and classified by the manufacturers' interpretation programs. We assessed ability to distinguish sinus rhythm from non-sinus rhythm, identify atrial fibrillation/flutter and other abnormal rhythms, and accuracy in flagging results for priority review. If all seven programs' interpretation statements did not agree, cases were reviewed by experienced cardiologists.

RESULTS

All programs could distinguish well between sinus and non-sinus rhythms and could identify atrial fibrillation/flutter or other abnormal rhythms. However, false-positive rates varied from 2.1% to 5.5% for non-sinus rhythm, from 0.7% to 4.4% for atrial fibrillation/flutter, and from 1.5% to 3.0% for other abnormal rhythms. False-negative rates varied from 12.0% to 7.5%, 9.9% to 2.7%, and 55.9% to 30.5%, respectively. Flagging of ACS varied by a factor of 2.5 between programs. Physicians flagged more ECGs for prompt review, but also showed variance of around a factor of 2. False-negative values differed between programs by a factor of 2 but was high for all (>50%). Agreement between programs and majority reviewer decisions was 46-62%.

CONCLUSIONS

Automatic interpretations of rhythms and ACS differ between programs. Healthcare institutions should not rely on ECG software "critical result" flags alone to decide the ACS workflow.

Pre-hospital detection of acute ischemic stroke secondary to emergent large vessel occlusion: lessons learned from electrocardiogram and acute myocardial infarction

Currently, there is no device capable of detecting acute ischemic stroke (AIS) secondary to emergent large vessel occlusion (ELVO) in the pre-hospital setting. The inability to reliably identify patients that would benefit from primary treatment with endovascular thrombectomy remains an important limitation to optimizing emergency medical services (EMS) triage models and time-to-treatment. Several clinical grading scales that rely solely on clinical examination have been proposed and have demonstrated only moderate predictive ability for ELVO. Consequently, a technology capable of detecting ELVO in the pre-hospital setting would be of great benefit. An analogous scenario existed decades ago, in which pre-hospital detection of acute myocardial infarction (AMI) was unreliable until the emergence of the 12-lead ECG and its adoption by EMS providers. This review details the implementation of pre-hospital ECG (PHECG) for the detection of AMI and explores how early experience with PHECG may be applied to ELVO detection devices, once they become available.

ANMCO/AIIC/SIT Consensus Information Document: definition, precision, and suitability of electrocardiographic signals of electrocardiographs, ergometry, Holter electrocardiogram, telemetry, and bedside monitoring systems

The electrocardiogram (ECG) signal can be derived from different sources. These include systems for surface ECG, Holter monitoring, ergometric stress tests, and telemetry systems and bedside monitoring of vital parameters, which are useful for rhythm and ST-segment analysis and ECG screening of electrical sudden cardiac death predictors. A precise ECG diagnosis is based upon correct recording, elaboration, and presentation of the signal. Several sources of artefacts and potential external causes may influence the quality of the original ECG waveforms. Other factors that may affect the quality of the information presented depend upon the technical solutions employed to improve the signal. The choice of the instrumentations and solutions used to offer a high-quality ECG signal are, therefore, of paramount importance. Some requirements are reported in detail in scientific statements and recommendations. The aim of this consensus document is to give scientific reference for the choice of systems able to offer high quality ECG signal acquisition, processing, and presentation suitable for clinical use.

Safety of Computer Interpretation of Normal Triage Electrocardiograms

OBJECTIVES

Frequent interruptions within the emergency department may lead to errors that negatively impact patient care. The immediate review of electrocardiograms (ECGs) obtained from triage patients is one source of interruption. Limiting triage ECGs requiring immediate attending review to those interpreted by the computer as abnormal may be one way to reduce interruption. We hypothesize that triage ECGs interpreted by the computer as "normal ECG" are unlikely to have clinical significance that would affect triage care.

METHODS

All triage ECGs performed at the University of North Carolina were collected between November 14, 2014, and March 3, 2015, according to a standard nursing triage protocol using GE machines running Marquette 12SL software. Triage ECGs with a computer interpretation of "normal ECG" were compared to an attending cardiologist's final interpretation. Triage ECGs for which the cardiologist's interpretation differed from the computer interpretation of normal ECG were presented to two emergency physicians (EPs) blinded to the goals of the study. The physicians were asked to evaluate the ECG for clinical significance. Clinical significance was defined as any change from normal that would alter triage care. Triage ECGs were considered true negatives if either the cardiologist agreed with the normal computer interpretation or if both EPs agreed that the ECG did not show clinical significance.

RESULTS

A total of 855 triage ECGs were collected over 16 weeks. A total of 222 (26%) were interpreted by the computer as normal. The negative predictive value for a triage ECGs interpreted by the computer as "normal" was calculated to be 99% (95% confidence interval = 97% to 99%). Of the ECGs with a computer interpretation of normal ECG, 13 had an interpretation by an attending cardiologist other than normal. Two attending EPs reviewed these triage ECGs. One of the 13 ECGs was found to have clinical significance that would alter triage care by one of the EPs. The stated triage intervention was "bed immediately."

CONCLUSIONS

Our data suggest that triage ECGs identified by the computer as normal are unlikely to have clinical significance that would change triage care. Eliminating physician review of triage ECGs with a computer interpretation of normal may be a safe way to improve patient care by decreasing physician interruptions.

Prehospital diagnosis of patients with acute myocardial infarction

Primary percutaneous intervention (PPCI) is the preferred treatment in patients with ST elevation myocardial infarction (STEMI) if this can be performed in a timely manner. The

The Comparison of Physician to Computer Interpreted Electrocardiograms on ST-elevation Myocardial Infarction Door-to-balloon Times

OBJECTIVE

The purpose of the project was to study the impact that immediate physician electrocardiogram (ECG) interpretation would have on door-to-balloon times in ST-elevation myocardial infarction (STEMI) as compared with computer-interpreted ECGs.

METHODS

This was a retrospective cohort study of 340 consecutive patients from September 2003 to December 2009 with STEMI who underwent emergent cardiac catheterization and percutaneous coronary intervention. Patients were stratified into 2 groups based on the computer-interpreted ECG interpretation: those with acute myocardial infarction identified by the computer interpretation and those not identified as acute myocardial infarction. Patients (n = 173) from September 2003 to June 2006 had their initial ECG reviewed by the triage nurse, while patients from July 2006 to December 2009 (n = 167) had their ECG reviewed by the emergency department physician within 10 minutes. Times for catheterization laboratory activation and percutaneous coronary intervention were recorded in all patients.

RESULTS

Of the 340 patients with confirmed STEMI, 102 (30%) patients were not identified by computer interpretation. Comparing the prior protocol of computer ECG to physician interpretation, the latter resulted in significant improvements in median catheterization laboratory activation time {19 minutes [interquartile range (IQR): 10-37] vs. 16 minutes [IQR: 8-29]; P < 0.029} and in median door-to-balloon time [113 minutes (IQR: 86-143) vs. 85 minutes (IQR: 62-106); P < 0.001].

CONCLUSION

The computer-interpreted ECG failed to identify a significant number of patients with STEMI. The immediate review of ECGs by an emergency physician led to faster activation of the catheterization laboratory, and door-to-balloon times in patients with STEMI.

Innovations in telemedicine for cardiovascular care

Cardiovascular disease is one of the main fields of application for telemedicine, with benefits in almost all areas in the continuum of cardiovascular disease. The greatest impact has been shown in the early diagnosis of cardiovascular disease, in second consultation, between non-cardiologist and cardiologist and between cardiologists, and in follow-up and secondary prevention of cardiovascular disease. At present, the main area of implementation for telemedicine in cardiovascular disease is represented by pre-hospital triage, with telemedicine electrocardiogram in acute myocardial infarction. Significant results have also been achieved in the second opinion consultation of pediatric subjects with congenital cardiovascular disease, home-monitoring and the management of patients affected by chronic heart failure or with an implanted device. However, there is significant room for further improvement in delivering telemedicine assistance even in 'very-remote' populations, such as detainees, patients in developing countries or in underdeveloped areas of developed countries.

Computerized interpretation of the prehospital electrocardiogram: predictive value for ST segment elevation myocardial infarction and impact on on-scene time

Introduction:

Computerized interpretation of the prehospital electrocardiogram (ECG) is increasingly being used in the basic life support (BLS) ambulance setting to reduce delays to treatment for patients suspected of ST segment elevation myocardial infarction (STEMI).

Objectives:

To estimate 1) predictive values of computerized prehospital 12-lead ECG interpretation for STEMI and 2) additional on-scene time for 12-lead ECG acquisition.

Methods:

Over a 2-year period, 1,247 ECGs acquired by primary care paramedics for suspected STEMI were collected. ECGs were interpreted in real time by the GEMarquette 12SL ECG analysis program. Predictive values were estimated with a bayesian latent class model incorporating the computerized ECG interpretations, consensus ECG interpretations by study cardiologists, and hospital diagnosis. On-scene time was compared for ambulance-transported patients with (n 5 985) and without (n 5 5,056) prehospital ECGs who received prehospital aspirin and/or nitroglycerin.

Results:

The computer's positive and negative predictive values for STEMI were 74.0% (95% credible interval [CrI] 69.6–75.6) and 98.1% (95% CrI 97.8–98.4), respectively. The sensitivity and specificity were 69.2% (95% CrI 59.0–78.5) and 98.9% (95% CrI 98.1–99.4), respectively. Prehospital ECGs were associated with a mean increase in on-scene time of 5.9 minutes (95% confidence interval 5.5–6.3).

Conclusions:

The predictive values of the computerized prehospital ECG interpretation appear to be adequate for diversion programs that direct patients with a positive result to hospitals with angioplasty facilities. The estimated 26.0% chance that a positive interpretation is false is likely too high for activation of a catheterization laboratory from the field. Acquiring prehospital ECGs does not substantially increase on-scene time in the BLS setting.

Telemedicine for cardiovascular disease continuum: A position paper from the Italian Society of Cardiology Working Group on Telecardiology and Informatics

Telemedicine is the provision of health care services, through the use of information and communication technology, in situations where the health care professional and the patient, or 2 health care professionals, are not in the same location. It involves the secure transmission of medical data and information, through text, sound, images, or other forms needed for the prevention, diagnosis, treatment, and follow-up of a patient. First data on implementation of telemedicine for the diagnosis and treatment of acute myocardial infarction date from more than 10 years ago. Telemedicine has a potential broad application to the cardiovascular disease continuum and in many branches of cardiology, at least including heart failure, ischemic heart disease and arrhythmias. Telemedicine might have an important role as part of a strategy for the delivery of effective health care for patients with cardiovascular disease. In this document the Working Group on Telecardiology and Informatics of the Italian Society of Cardiology intends to remark some key-points regarding potential benefit achievable with the implementation of telemedicine support in the continuum of cardiovascular disease.

Diagnostic accuracy of ST-segment elevation myocardial infarction by various healthcare providers

BACKGROUND

This study aimed to compare the accuracy of ECG interpretation for diagnosis of STEMI by different groups of healthcare professionals involved in the STEMI program at our institution.

METHODS

We selected 21 ECGs from patients with typical symptoms of MI that were diagnosed with STEMI, and 10 ECGs of STEMI mimics. STEMI mimic ECGs were repeated in the package with a story of typical and atypical chest pain. ECGs were interpreted to diagnose STEMI and identify need for initiation of the cardiac catheterization lab (CCL). Participants identified confidence in STEMI recognition, and average number of ECGs read per week.

RESULTS

A total of 64 participants completed the study package. Cardiologists were more likely to provide correct interpretation compared to other groups. False positive diagnoses were more likely made by paramedics when compared to cardiologists (p < 0.01). There was a positive correlation between increased exposure to ECGs and accurate STEMI diagnosis (r = 0.482, p < 0.001). A threshold of ≥ 20 ECGs read per week showed a statistically significant improvement in accuracy (p < 0.001). Self-reported confidence correlated positively with accuracy (r = 0.402, p =< 0.001). Changing the ECG narrative of the STEMI mimic ECGs had a significant effect on interpretation between groups (p = 0.043).

CONCLUSIONS

Our study showed that healthcare profession and number of ECGs reviewed per week are predictive of the accuracy of ECG interpretation of STEMI. Cardiologists are the most accurate diagnosticians, and are the least likely to falsely activate the CCL. Weekly exposure of ≥ 20 ECGs may improve diagnostic accuracy regardless of underlying experience.

Difficult ECGs in STEMI: lessons learned from serial sampling of pre- and in-hospital ECGs

Prehospital interpretation of electrocardiograms (ECGs) is crucial to ensure early diagnosis and optimal treatment of patients with ST elevation myocardial infarction (STEMI). Recognition of ST-segment elevations (STE) by qualified personnel in the prehospital phase has successfully reduced the delay from the first medical contact to reperfusion. A few other ECG patterns without true STE, referred to as "STEMI equivalents", bear the same prognostic significance, reflect imminent or ongoing transmural ischemia, but are less easily identified. Hyperacute T waves, de Winter ST-T complex, Wellens' syndrome, and posterior STEMI, as well as myocardial infarction in the presence of left bundle branch block, paced rhythm or left ventricular hypertrophy, among others are diagnostic challenges. This article reviews some critical examples of ischemic ECG patterns that may be ephemeral, misinterpreted by medical staff or not identified by automated ECG algorithms, and it emphasizes the importance of serial ECG acquisition.

Mobile, cloud, and big data computing: contributions, challenges, and new directions in telecardiology

Many studies have indicated that computing technology can enable off-site cardiologists to read patients’ electrocardiograph (ECG), echocardiography (ECHO), and relevant images via smart phones during pre-hospital, in-hospital, and post-hospital teleconsultation, which not only identifies emergency cases in need of immediate treatment, but also prevents the unnecessary re-hospitalizations. Meanwhile, several studies have combined cloud computing and mobile computing to facilitate better storage, delivery, retrieval, and management of medical files for telecardiology. In the future, the aggregated ECG and images from hospitals worldwide will become big data, which should be used to develop an e-consultation program helping on-site practitioners deliver appropriate treatment. With information technology, real-time tele-consultation and tele-diagnosis of ECG and images can be practiced via an e-platform for clinical, research, and educational purposes. While being devoted to promote the application of information technology onto telecardiology, we need to resolve several issues: (1) data confidentiality in the cloud, (2) data interoperability among hospitals, and (3) network latency and accessibility. If these challenges are overcome, tele-consultation will be ubiquitous, easy to perform, inexpensive, and beneficial. Most importantly, these services will increase global collaboration and advance clinical practice, education, and scientific research in cardiology.

Pros, cons, and organization of prehospital thrombolysis

BACKGROUND

Early initiation of reperfusion therapy in ST-segment elevation myocardial infarction improves outcome. Prehospital thrombolysis (PHT) is 1 strategy to deliver earlier reperfusion.

OBJECTIVE

The goal of this study was to discuss the pros and cons of PHT and to describe the implementation of a program of PHT in the Hunter Region of Australia.

METHODS

Recent literature on PHT was reviewed to present a critical assessment of the evidence to support PHT. Different models of PHT are presented including the experience of the introduction of the Hunter program.

RESULTS

Meta-analyses of clinical trials and registries have shown that PHT significantly decreases the time to thrombolysis, with reduction in the incidence of cardiogenic shock and a trend to a mortality benefit. The STREAM study reinforces current policy, which favors primary percutaneous coronary intervention (PCI) over thrombolysis, providing that PCI can be performed within an appropriate time interval; emphasizes that timely thrombolysis linked to an early invasive strategy provides an equivalent outcome when timely primary PCI is not possible; and supports other published experience that early-rescue PCI can be performed safely after administration of PHT. Although PHT can be implemented by trained paramedics working with on-board physicians, the Hunter Region has successfully used paramedics and ECG telemetry in consultation with hospital-based physicians. When the time to open the artery is ≤90 minutes, primary PCI is preferred. When the time to open the artery is >90 minutes, PHT with immediate transport postthrombolysis to a PCI-capable hospital is feasible and effective.

CONCLUSIONS

PHT delivered by trained paramedics with telemetery backup to assist ECG interpretation is feasible and delivers the prospect of early reperfusion.

Comparison of an automated algorithm to expert physician interpretation of 80-lead body surface mapping in the evaluation of acute myocardial ischemia and infarction in patients presenting to the emergency department with chest pain: results from the Optimal Cardiovascular Diagnostic Evaluation Enabling Faster Treatment of Myocardial Infarction trial

INTRODUCTION/BACKGROUND

Eighty-lead (80 L) body surface map (BSM) technology provides electrocardiogram data for the clinician to interpret. A BSM device also offers an automated interpretation. Little information is available about the performance of automated algorithm interpretation in comparison to human interpretation of the 80 L BSM.

METHODS

Interpretations of BSMs by automated algorithm and a core laboratory of physician readers from The Optimal Cardiovascular Diagnostic Evaluation Enabling Faster Treatment of Myocardial Infarction trial were compared. The κ statistic and its 95% confidence interval for concordance were calculated. The effect of BSM quality on concordance was also analyzed.

RESULTS

3405 maps for 1601 subjects were reviewed by the core laboratory and automated algorithm. There was a combined concordance rate of 87.3% (κ = 0.46; 95% confidence interval, 0.40-0.52). A decrease in signal quality was associated with a decrease in concordance between human and automated algorithm interpretation (κ = 0.52 for good quality vs κ = 0.30 for poor quality).

CONCLUSION

A moderate degree of concordance was noted between physician and automated algorithm interpretation of 80 L BSMs. Signal quality of 80 L electrocardiographic BSM directly affected concordance.

Prehospital diagnosis and triage of ST-elevation myocardial infarction by paramedics without advanced care training

BACKGROUND

Prehospital triage of ST-elevation myocardial infarction (STEMI) for primary percutaneous coronary intervention (PCI) reduces treatment times. Prehospital triage and transport of STEMI patients have traditionally been undertaken in emergency medical service systems with Advanced Care Paramedics (ACPs). However, ACPs are not available in many regions. A pilot study was conducted to determine the feasibility of prehospital STEMI triage in a region with only Primary Care Paramedics.

METHODS

Hemodynamically stable patients with chest pain and suspected STEMI were brought directly to a catheterization laboratory for primary PCI. End points included accuracy of prehospital STEMI identification, complications during transfer, and treatment times.

RESULTS

One hundred thirty-four consecutive patients with suspected STEMI were triaged for primary PCI. Only 1 patient developed complications during transport (rapid atrial flutter) that required ACP skills. One hundred thirty-three patients underwent urgent angiography, and 105 patients underwent PCI. Based on physician interpretation of the prehospital electrocardiogram, there was agreement with triage decision for 121 (90%) of the 134 cases. The final diagnosis based on the angiogram and cardiac markers was true STEMI for 106 patients and false positive for 28 patients. The median first medical contact to balloon time was 91 (81-115) minutes.

CONCLUSIONS

Hemodynamically stable patients with suspected STEMI can be safely and effectively transported directly for primary PCI by paramedics without advanced care training. Prehospital STEMI triage for primary PCI can be extended to regions that have few or no paramedics with advanced care training.

An artificial neural network to safely reduce the number of ambulance ECGs transmitted for physician assessment in a system with prehospital detection of ST elevation myocardial infarction

Background

Pre-hospital electrocardiogram (ECG) transmission to an expert for interpretation and triage reduces time to acute percutaneous coronary intervention (PCI) in patients with ST elevation Myocardial Infarction (STEMI). In order to detect all STEMI patients, the ECG should be transmitted in all cases of suspected acute cardiac ischemia. The aim of this study was to examine the ability of an artificial neural network (ANN) to safely reduce the number of ECGs transmitted by identifying patients without STEMI and patients not needing acute PCI.

Methods

Five hundred and sixty ambulance ECGs transmitted to the coronary care unit (CCU) in routine care were prospectively collected. The ECG interpretation by the ANN was compared with the diagnosis (STEMI or not) and the need for an acute PCI (or not) as determined from the Swedish coronary angiography and angioplasty register. The CCU physician's real time ECG interpretation (STEMI or not) and triage decision (acute PCI or not) were registered for comparison.

Results

The ANN sensitivity, specificity, positive and negative predictive values for STEMI was 95%, 68%, 18% and 99%, respectively, and for a need of acute PCI it was 97%, 68%, 17% and 100%. The area under the ANN's receiver operating characteristics curve for STEMI detection was 0.93 (95% CI 0.89-0.96) and for predicting the need of acute PCI 0.94 (95% CI 0.90-0.97). If ECGs where the ANN did not identify a STEMI or a need of acute PCI were theoretically to be withheld from transmission, the number of ECGs sent to the CCU could have been reduced by 64% without missing any case with STEMI or a need of immediate PCI.

Conclusions

Our ANN had an excellent ability to predict STEMI and the need of acute PCI in ambulance ECGs, and has a potential to safely reduce the number of ECG transmitted to the CCU by almost two thirds.

Differentiating ST-elevation myocardial infarction from nonischemic ST-elevation in patients with chest pain

Current guidelines state that patients with compatible symptoms and ST-segment elevation (STE) in ≥2 contiguous electrocardiographic leads should undergo immediate reperfusion therapy. Aggressive attempts at decreasing door-to-balloon times have led to more frequent activation of primary percutaneous coronary intervention (pPCI) protocols. However, it remains crucial to correctly differentiate STE myocardial infarction (STEMI) from nonischemic STE (NISTE). We assessed the ability of experienced interventional cardiologists in determining whether STE represents acute STEMI or NISTE. Seven readers studied electrocardiograms of consecutive patients showing STE. Patients with left bundle branch block or ventricular rhythms were excluded. Readers decided if, based on electrocardiographic results, they would have activated the pPCI protocol. If NISTE was chosen, readers selected from 12 possible explanations as to why STE was present. Of 84 patients, 40 (48%) had adjudicated STEMI. The percentage for which readers recommended pPCI varied (33% to 75%). Readers' sensitivity and specificity ranged from 55% to 83% (average 71%) and 32% to 86% (average 63%), respectively. Positive and negative predictive values ranged from 52% to 79% (average 66%) and 67% to 79% (average 71%), respectively. Broad inconsistencies existed among readers as to the chosen reasons for NISTE classification. In conclusion, we found wide variations in experienced interventional cardiologists in differentiating STEMI with a need for pPCI from NISTE.