Disagreement in the interpretation of electrocardiographic ST segment elevation: a source of error for emergency physicians?

Artificial neural networks for ECG interpretation in acute coronary syndrome: A scoping review

INTRODUCTION

The electrocardiogram (ECG) is a crucial diagnostic tool in the Emergency Department (ED) for assessing patients with Acute Coronary Syndrome (ACS). Despite its widespread use, the ECG has limitations, including low sensitivity of the STEMI criteria to detect Acute Coronary Occlusion (ACO) and poor inter-rater reliability. Emerging ECG features beyond the traditional STEMI criteria show promise in improving early ACO diagnosis, but complexity hinders widespread adoption. The potential integration of Artificial Neural Networks (ANN) holds promise for enhancing diagnostic accuracy and addressing reliability issues in ECG interpretation for ACO symptoms.

METHODS

Ovid MEDLINE, CINAHL, EMBASE, Cochrane, PubMed and Scopus were searched from inception through to 8th of December 2023. A thorough search of the grey literature and reference lists of relevant articles was also performed to identify additional studies. Articles were included if they reported the use of ANN for ECG interpretation of Acute Coronary Syndrome in the Emergency Department patients.

RESULTS

The search yielded a total of 244 articles. After removing duplicates and excluding non-relevant articles, 14 remained for analysis. There was significant heterogeneity in the types of ANN models used and the outcomes assessed, making direct comparisons challenging. Nevertheless, ANN appeared to demonstrate higher accuracy than physician interpreters for the evaluated outcomes and this proved independent of both specialty and years of experience.

CONCLUSIONS

The interpretation of ECGs in patients with suspected ACS using ANN appears to be accurate and potentially superior when compared to human interpreters and computerised algorithms. This appears consistent across various ANN models and outcome variables. Future investigations should emphasise ANN interpretation of ECGs in patients with ACO, where rapid and accurate diagnosis can significantly benefit patients through timely access to reperfusion therapies.

High-Risk Chief Complaints I: Chest Pain-The Big Three (an Update)

Nontraumatic chest pain is a frequent concern of emergency department patients, with causes that range from benign to immediately life threatening. Identifying those patients who require immediate/urgent intervention remains challenging and is a high-risk area for emergency medicine physicians where incorrect or delayed diagnosis may lead to significant morbidity and mortality. This article focuses on the 3 most prevalent diagnoses associated with adverse outcomes in patients presenting with nontraumatic chest pain, acute coronary syndrome, thoracic aortic dissection, and pulmonary embolism. Important aspects of clinical evaluation, diagnostic testing, treatment, and disposition and other less common causes of lethal chest pain are also discussed.

Diagnostic accuracy of prehospital electrocardiograms interpreted remotely by emergency physicians in myocardial infarction patients

BACKGROUND

Prehospital 12‑lead electrocardiogram (ECG) is the most widely used screening tool for recognition of ST-segment elevation myocardial infarction (STEMI). However, prehospital diagnosis of STEMI based solely on ECGs can be challenging.

OBJECTIVES

To evaluate the ability of emergency department (ED) physicians to accurately interpret prehospital 12‑lead ECGs from a remote location.

METHODS

All suspected prehospital STEMI patients who were transported by EMS and underwent angiography between 2006 and 2014 were included. We reviewed prehospital ECGs and grouped them based on: 1) presence or absence of a culprit artery lesion following angiography; and 2) whether they met the 3rd Universal Definition of Myocardial Infarction. We also described characteristics of ECGs that were misinterpreted by ED physicians.

RESULTS

A total of 625 suspected STEMI cases were reviewed. Following angiography, 94% (590/625) of patients were found having a culprit artery lesion, while 6% (35/625) did not. Among these 35 patients, 24 had ECGs that mimicked STEMI criteria and 9 had non-ischemic signs. Upon ECG reinterpretation, 92% (577/625) had standard STEMI criteria while 8% (48/625) did not. Among these 48 patients, 35 had ischemic signs ECGs and 13 did not. Characteristics of misinterpreted ECGs included pericarditis, early repolarization, STE > 1 mm (1‑lead only), and negative T-wave.

CONCLUSIONS

Remote interpretation of prehospital 12‑lead ECGs by ED physicians was a useful diagnostic tool in this EMS system. Even if the rate of ECG misinterpretation is low, there is still room for ED physicians operating from a remote location to improve their ability to accurately diagnose STEMI patients.

Agreement between cardiologists and fellows in interpretation of ischemic electrocardiographic changes in acute myocardial infarction

BACKGROUND

Time from symptom onset may not be the best indicator for choosing reperfusion therapy for patients presenting with acute ST-elevation myocardial infarction (STEMI); consequently ECG-based methods have been developed.

METHODS

This study evaluated the inter-observer agreement between experienced cardiologists and junior doctors in identifying the ECG findings of the pre-infarction syndrome (PIS) and evolving myocardial infarction (EMI). The ECGs of 353 STEMI patients were independently analyzed by two cardiologists, one fellow in cardiology, one fellow in internal medicine and a medical student. The last two were given a half-hour introduction of the PIS/EMI-algorithm.

RESULTS

The inter-observer reliability between all the investigators was found to be good according to kappa statistics (κ 0.632-0.790) for the whole study population. When divided into different subgroups, the inter-observer agreements were from good to very good between the cardiologists and the fellow in cardiology (κ 0.652 -0.813) and from moderate to good (κ 0.464-0.784) between the fellow in internal medicine, medical student and the others.

CONCLUSIONS

The PIS and EMI ECG patterns are reliably identified by experienced cardiologists and can be easily adopted by junior doctors.

A comparative assessment of adverse event classification in the out-of-hospital setting

OBJECTIVES

We sought to test reliability of two approaches to classify adverse events (AEs) associated with helicopter EMS (HEMS) transport.

METHODS

The first approach for AE classification involved flight nurses and paramedics (RN/Medics) and mid-career emergency physicians (MC-EMPs) independently reviewing 50 randomly selected HEMS medical records. The second approach involved RN/Medics and MC-EMPs meeting as a group to openly discuss 20 additional medical records and reach consensus-based AE decision. We compared all AE decisions to a reference criterion based on the decision of three senior emergency physicians (Sr-EMPs). We designed a study to detect an improvement in agreement (reliability) from fair (kappa = 0.2) to moderate (kappa = 0.5). We calculated sensitivity, specificity, percent agreement, and positive and negative predictive values (PPV/NPV).

RESULTS

For the independent reviews, the Sr-EMP group identified 26 AEs while individual clinician reviewers identified between 19 and 50 AEs. Agreement on the presence/absence of an AE between Sr-EMPs and three MC-EMPs ranged from κ = 0.20 to κ = 0.25. Agreement between Sr-EMPs and three RN/Medics ranged from κ = 0.11 to κ = 0.19. For the consensus/open-discussion approach, the Sr-EMPs identified 13 AEs, the MC-EMP group identified 18 AEs, and RN/medic group identified 36 AEs. Agreement between Sr-EMPs and MC-EMP group was (κ = 0.30 95%CI -0.12, 0.72), whereas agreement between Sr-EMPs and RN/medic group was (κ = 0.40 95%CI 0.01, 0.79). Agreement between all three groups was fair (κ = 0.33, 95%CI 0.06, 0.66). Percent agreement (58-68%) and NPV (63-76%) was moderately dissimilar between clinicians, while sensitivity (25-80%), specificity (43-97%), and PPV (48-83%) varied.

CONCLUSIONS

We identified a higher level of agreement/reliability in AE decisions utilizing a consensus-based approach for review rather than independent reviews.

Emergency physician estimates of the probability of acute coronary syndrome in a cohort of patients enrolled in a study of coronary computed tomographic angiography

INTRODUCTION

Little information exists regarding how accurately emergency physicians (EPs) predict the probability of acute coronary syndrome (ACS). Our objective was to determine if EPs can accurately predict ACS in a prospectively identified cohort of emergency department (ED) patients who met enrolment criteria for a study of coronary computed tomographic angiography (CCTA) and were admitted for a "rule out ACS" protocol.

METHODS

A prospective observational pilot study in an academic medical centre was carried out. EPs caring for patients with chest pain provided whole-number estimates of the probability of ACS after clinical review. This substudy was part of the now published Rule Out Myocardial Infarction/Ischemia Using Computer Assisted Tomography (ROMICAT) study, a study of CCTA and admission of patients for a rule out ACS protocol after a nondiagnostic evaluation. Predictions were grouped into probability groups based on the validated Goldman criteria. ACS was determined by an adjudication committee using American Heart Association/American College of Cardiology/European Society of Cardiology guidelines.

RESULTS

A total of 334 predictions were obtained for a study population with a mean age of 54 (SD 12) years, 63% of whom were male. There were 35 ACS events. EPs predicted ACS better than by chance, and increasingly higher estimates were associated with a higher incidence of ACS (p = 0.0004). The percentage of patients with ACS was 0%, 6%, 7%, and 17%, respectively, for very low, low, intermediate, and high probability groups. EPs' estimates had a sensitivity of 63% using a > 20% probability of ACS to define a positive test. Lowering this threshold to > 7% to define a test as positive increased the sensitivity of physician estimates to 89% but lowered specificity from 65% to 24%.

CONCLUSION

Our data suggest that for a selected ED cohort meeting eligibility criteria for a study of CCTA, EPs predict ACS better than by chance, with an increasing proportion of patients proving to have ACS with increasing probability estimates. Lowering the estimate threshold does not result in an overall sensitivity level that is sufficient to send patients home from the ED and is associated with a poor specificity.

Normal coronary angiography and primary percutaneous coronary intervention for ST elevation myocardial infarction: a literature review and audit findings

It is becoming increasingly common to offer primary percutaneous coronary intervention as first line treatment for ST elevation myocardial infarction (STEMI). In a subset of patients presenting with suspected STEMI, coronary arteries appear normal at coronary angiography. In this article, the current literature of this group of patients is reviewed. The incidence of 'normal' angiography, the clinical and electrocardiographic features of this group of patients and the alternative diagnoses for presentation are discussed. This article reviews the factors leading to such presentation, the clinical characteristics of such patients and the implications, clinical and economic.

High-risk chief complaints I: chest pain--the big three

Chest pain is one of the most frequently seen chief complaints in patients presenting to emergency departments, and is considered to be a "high-risk" chief complaint. The differential diagnosis for chest pain is broad, and potential causes range from the benign to the immediately life-threatening. Although many (if not most) emergency department patients with chest pain do not have an immediately life-threatening condition, correct diagnoses can be difficult to make, incorrect diagnoses may lead to catastrophic therapies, and failure to make a timely diagnosis may contribute to significant morbidity and mortality. Several atraumatic "high-risk" causes of chest pain are discussed in this article, including myocardial infarction and ischemia, thoracic aortic dissection, and pulmonary embolism. Also included are brief discussions of tension pneumothorax, esophageal perforation, and cardiac tamponade.

Alarming ST-segment elevation in a young male with left anterior descending coronary artery myocardial bridging

Chest pain continues to be one of the leading emergency department presentations. Acute coronary syndrome is the most dreaded chest pain scenario, as "time is myocardium" in this situation. Numerous benign and less life-threatening diseases like early repolarization, acute pericarditis, and vasospastic angina can present with a similar clinical picture. ST-segment elevation on an electrocardiogram can occur in all these situations and in many others, creating diagnostic dilemma. A young male with chest pain and concurrent ST-segment elevation was reported. He was ultimately discovered to have myocardial bridging of a coronary arterial segment.

The Impact of Emergency Physician–Initiated Primary Percutaneous Coronary Intervention on Mean Door-to-Balloon Time in Patients With ST-Segment-Elevation Myocardial Infarction

STUDY OBJECTIVE

We seek to evaluate how accurately the emergency physician initiates percutaneous coronary intervention for patients presenting to the emergency department (ED) with ST-segment-elevation myocardial infarction (STEMI) and the impact of emergency physician-initiated percutaneous coronary intervention on mean door-to-balloon time.

METHODS

We conducted a before-and-after cohort study of consecutive STEMI patients presenting to a 608-bed tertiary care hospital during a 32-month period. During the first 19 months, percutaneous coronary intervention was available only by consultation with an on-call interventionist. In the subsequent 13 months, percutaneous coronary intervention was initiated by the emergency physician independent of cardiology consultation. All patients presenting during the study period with an appropriate clinical history and characteristic ECG findings of STEMI were eligible. Patients with greater than 12 hours of symptoms, contraindications to percutaneous coronary intervention, a valid do-not-resuscitate order, who died before percutaneous coronary intervention was attempted, who initially refused, or whose door-to-balloon time was greater than 6 hours were excluded. The accuracy of emergency physician identification of STEMI was confirmed by an independent cardiologist. All hospital medical records with a discharge diagnosis of acute myocardial infarction (International Classification of Diseases, Ninth Revision code 410.xx) were reviewed to confirm that no STEMI patients went unidentified. A t test was used to compare mean door-to-balloon time in each cohort.

RESULTS

A total of 172 patients were enrolled in this investigation, 95 STEMI patients in the initial 19-month period and 77 patients in the subsequent 13 months, when percutaneous coronary intervention was initiated solely at the discretion of the emergency physician. Percutaneous coronary intervention was inappropriately initiated by the emergency physician only once, and no ED patients with STEMI were overlooked, resulting in 100% sensitivity (95% confidence interval [CI] 97.3% to 100%) and 99.6% specificity (95% CI 97.7% to 99.9%). Mean door-to-balloon time in the emergency physician-initiated percutaneous coronary intervention cohort improved by 40 minutes (95% CI 26 to 54 minutes) from 131 to 91 minutes.

CONCLUSION

The emergency physician is able to accurately initiate percutaneous coronary intervention for ED patients presenting with STEMI independent of cardiology consultation. Emergency physician-initiated percutaneous coronary intervention significantly reduces mean door-to-balloon time for these patients.

Interpreting 12-Lead Electrocardiograms for Acute ST-Elevation Myocardial Infarction

In patients with acute myocardial infarction, early reperfusion and sustained patency of the culprit artery are important determinants of survival. The 12-lead electrocardiogram (ECG) is considered the noninvasive gold standard for identification of acute ST-elevation myocardial infarction. Nurses play a critical role in the process of obtaining, interpreting, and communicating ECG findings. This study evaluates nurses' ability to differentiate ischemic from nonischemic ECG patterns, to detect affected ECG leads and location of ischemia, and assesses skill level by hospital unit type. Seventy-five nurses were given a set of 6 patient scenarios, each with a corresponding 12-lead ECG, and asked to identify the presence or absence of ischemia. Fourteen (19%) of the 75 nurses correctly identified the presence or absence of ischemia in all 6 scenarios. Of the 3 ECGs with a myocardial infarction pattern, 59 (79%) of the nurses identified all 3 as ischemic; however, no one was able to determine the correct leads, location, or amplitude of ST-segment elevation. For the 3 nonischemic ECGs, 37 (49%) of the nurses identified a normal ECG as ischemic, 47 (63%) determined that an early repolarization pattern was ischemic, and 34 (45%) indicated that a left bundle branch block pattern was ischemic. These results not only identify educational opportunities but also provide important information for researchers implementing clinical trials evaluating the use of bedside ECG monitoring systems for detection of acute myocardial ischemia.

Electrocardiographic features and prognosis in acute diagonal or marginal branch occlusion

The aim of our study was to analyze electrocadiographic changes in patients with acute myocardial infarction related to the occlusion of diagonal (DG) or marginal (MG) branch. We selected 13 cases with DG and 12 with MG occlusion on angiography and evaluated their electrocardiogram (ECG) patterns on admission obtained in emergency department (ED) of university hospital with catheterization laboratory serving everyday interventional cardiology duty for ACS. Most characteristic ECG changes in acute occlusion of DG observed in 12 patients (92.3%) included ST-segment elevation in leads V(2) and V(3) (mean, 1.2 +/- 0.5 mm; maximum, 1.7 mm) and ST-segment depression in leads II and III (mean, 0.9 +/- 0.4 mm; maximum, 1.5 mm). Most characteristic ECG changes for acute occlusion of MG were ST-segment depression in leads V(5) and V(6) (mean, 0.9 +/- 0.4 mm; maximal, 1 mm) observed in 11 (91.7%) patients, ST-segment depression in lead II (mean, 0.7 +/- 0.2 mm; maximal, 0.8 mm) in 10 (83.3%,) and in leads V(2) and V(3), and aVF in 8 (66.7%) of cases. Risk of complications including cardiogenic shock and death was high in both groups especially during acute phase of myocardial infarction. Prevalence of borderline ECG changes in patients with acute coronary occlusion confirms how important is precise ECG interpretation usually initially done by ED physician.

Digital output volumetric pulmonary artery catheters eliminate interoperator interpretation variability and improve consistency of treatment decisions

BACKGROUND

The pulmonary artery catheter (PAC) has been fraught with controversy over issues of safety and impact on outcomes variables for many years. Multiple attempts to quantify the utility of this diagnostic instrument have failed to resolve the matter. Previous investigations have focused on either quantifying inter-rater variability of waveform output interpretation from PACs or on clinical outcomes when PACs are used in care. We tested the hypothesis that the true link between a diagnostic tool and outcomes is treatment selection, and an instrument that minimizes or eliminates the need for data interpretation would also minimize the variability of treatment selections.

STUDY DESIGN

We performed a prospective, single institutional, single blinded survey study.

RESULTS

The inter-rater variability of waveform interpretation among all raters was notable (p < 0.01); for continuous end diastolic volume index interpretation, there was no notable inter-rater variability (p=1.0). Inter-rater variability of treatment selections based on waveform interpretation was notable for all raters (p < 0.01). Continuous end diastolic volume index data presentation of hemodynamic status did not result in notable inter-rater variability in treatment selections (p=0.10). Treatment choices based on continuous end diastolic volume index among raters with 5 or more years of experience are not different from clinical practice guideline-directed choices (p > 0.05), independent of patient ventilator status.

CONCLUSIONS

Digital output volumetric PACs eliminate inter-rater variability of data interpretation, decrease inter-rater variability of data-driven treatment selections, and improve rater agreement with clinical practice guidelines when compared with traditional waveform output PACs.

Use of ED diagnosis to determine medical necessity of EMS transports

OBJECTIVE

To examine interrater agreement for classifying emergency medical services transports as medically unnecessary using emergency department diagnosis as the sole determining factor.

METHODS

Three emergency physicians and two family medicine physicians classified 913 International Classification of Diseases, Ninth Revision (ICD-9) codes as medically necessary, unnecessary, or uncertain. Overall agreement, interrater agreement, and agreement within 17 major disease categories were measured using kappa statistics in SAS.

RESULTS

Physicians rated between 25% and 65% of diagnoses codes as medically unnecessary. Overall agreement was fair (kappa = 0.31). Agreement within specialties was higher among family medicine-trained physicians than among emergency physicians (kappa = 0.52 and kappa = 0.22, respectively). Agreement across all raters was highest for diseases classified as symptoms, signs, and ill-defined conditions (kappa = 0.40) and lowest for diseases of the blood and blood-forming organs (kappa = -0.17). Agreement was observably better between physicians with more experience.

CONCLUSIONS

Considerable doubts about the utility of emergency department diagnosis as a criterion are raised from study findings. Further development of Neely Conference criteria is needed. Priority should be given to testing and validation of criteria as well as exploration of differences in judgment between specialists representative of the medical director profession.

Implications of the failure to identify high-risk electrocardiogram findings for the quality of care of patients with acute myocardial infarction: results of the Emergency Department Quality in Myocardial Infarction (EDQMI) study

BACKGROUND

The impact of misinterpretation of the ECG in patients with acute myocardial infarction (AMI) in the emergency department (ED) setting is not well known. Our goal was to assess the prevalence of the failure to identify high-risk ECG findings in ED patients with AMI and to determine whether this failure is associated with lower-quality care.

METHODS AND RESULTS

In a retrospective cohort study of consecutive patients presenting to 5 EDs in California and Colorado from July 1, 2000, through June 30, 2002, with confirmed AMI (n=1684), we determined the frequency of the failure by the treating provider to identify significant ST-segment depressions, ST-segment elevations, or T-wave inversions on the presenting ECG. In multivariable models, we assessed the relationship between missed high-risk ECG findings and evidence-based therapy in the ED after adjustment for patient characteristics and site of care. High-risk ECG findings were not documented in 201 patients (12%). The failure to identify high-risk findings was independently associated with a higher odds of not receiving treatment among ideal candidates for aspirin (odds ratio [OR], 2.13; 95% confidence interval [CI], 1.51 to 2.94), beta-blockers (OR, 1.85; 95% CI, 1.14 to 3.03), and reperfusion therapy (OR, 7.69; 95% CI, 3.57 to 16.67). Among patients with missed high-risk ECG findings, in-hospital mortality was 7.9% compared with 4.9% among those without missed findings (P=0.1).

CONCLUSIONS

The failure to identify high-risk ECG findings in patients with AMI results in lower-quality care in the ED. Systematic processes to improve ECG interpretation may have important implications for patient treatment and outcomes.

ECG Patterns Confounding the ECG Diagnosis of Acute Coronary Syndrome: Left Bundle Branch Block, Right Ventricular Paced Rhythms, and Left Ventricular Hypertrophy

The ECG has limitations in the evaluation of the chest-pain patient, including the presence of confounding ECG patterns; the ECG patterns that confound the diagnosis of acute myocardial infarction(AMI) include left bundle branch block (LBBB), ventricular paced rhythms (VPR), and left ventricular hypertrophy (LVH). These patterns produce new ST-segment/T-wave abnormalities, which are the new normal findings in these patients and may lead the clinician astray in two distinct instances: (1) diagnosing ECG change related to acute coronary syndromes (ACS) when the abnormality results solely from the confounding pattern; and (2) not acknowledging the confounding nature of these ECG patterns in the evaluation of potential ACS, thereby placing excessive diagnostic confidence in the ECG. This article highlights the diagnostic dilemma encountered in these confounding ECG patterns; the discussion focuses on the expected ECG abnormalities in these patients and the findings seen in ACS.