Decision support for the initial triage of patients with acute coronary syndromes

Mechanocardiography in the Detection of Acute ST Elevation Myocardial Infarction: The MECHANO-STEMI Study

Novel means to minimize treatment delays in patients with ST elevation myocardial infarction (STEMI) are needed. Using an accelerometer and gyroscope on the chest yield mechanocardiographic (MCG) data. We investigated whether STEMI causes changes in MCG signals which could help to detect STEMI. The study group consisted of 41 STEMI patients and 49 control patients referred for elective coronary angiography and having normal left ventricular function and no valvular heart disease or arrhythmia. MCG signals were recorded on the upper sternum in supine position upon arrival to the catheterization laboratory. In this study, we used a dedicated wearable sensor equipped with 3-axis accelerometer, 3-axis gyroscope and 1-lead ECG in order to facilitate the detection of STEMI in a clinically meaningful way. A supervised machine learning approach was used. Stability of beat morphology, signal strength, maximum amplitude and its timing were calculated in six axes from each window with varying band-pass filters in 2-90 Hz range. In total, 613 features were investigated. Using logistic regression classifier and leave-one-person-out cross validation we obtained a sensitivity of 73.9%, specificity of 85.7% and AUC of 0.857 (SD = 0.005) using 150 best features. As a result, mechanical signals recorded on the upper chest wall with the accelerometers and gyroscopes differ significantly between STEMI patients and stable patients with normal left ventricular function. Future research will show whether MCG can be used for the early screening of STEMI.

Artificial intelligence in emergency medicine: A scoping review

INTRODUCTION

Despite the growing investment in and adoption of artificial intelligence (AI) in medicine, the applications of AI in an emergency setting remain unclear. This scoping review seeks to identify available literature regarding the applications of AI in emergency medicine.

METHODS

The scoping review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for scoping reviews using Medline-OVID, EMBASE, CINAHL, and IEEE, with a double screening and extraction process. The search included articles published until February 28, 2020. Articles were excluded if they did not self-classify as studying an AI intervention, were not relevant to the emergency department (ED), or did not report outcomes or evaluation.

RESULTS

Of the 1483 original database citations, 395 were eligible for full-text evaluation. Of these articles, a total of 150 were included in the scoping review. The majority of included studies were retrospective in nature (n = 124, 82.7%), with only 3 (2.0%) prospective controlled trials. We found 37 (24.7%) interventions aimed at improving diagnosis within the ED. Among the 150 studies, 19 (12.7%) focused on diagnostic imaging within the ED. A total of 16 (10.7%) studies were conducted in the out-of-hospital environment (eg, emergency medical services, paramedics) with the remainder occurring either in the ED or the trauma bay. Of the 24 (16%) studies that had human comparators, there were 12 (8%) studies in which AI interventions outperformed clinicians in at least 1 measured outcome.

CONCLUSION

AI-related research is rapidly increasing in emergency medicine. There are several promising AI interventions that can improve emergency care, particularly for acute radiographic imaging and prediction-based diagnoses. Higher quality evidence is needed to further assess both short- and long-term clinical outcomes.

Diagnostic Errors and the Bedside Clinical Examination

Diagnostic errors are common in clinical practice and lead to adverse patient outcomes. Systematic reviews have shown that inadequate history taking and physical examination lead to a plurality, if not a majority, of diagnostic errors. Recent advances in cognitive science have also shown that unconscious biases likely contribute to many diagnostic errors. Research into diagnostic error has been hampered by methodologic inconsistency and a paucity of studies in real-world clinical settings. The best evidence indicates that educational interventions to reduce diagnostic error should give physicians feedback about clinical outcomes and enhance their ability to recognize signs and symptoms of specific diseases at the bedside.

[Intelligent systems tools in the diagnosis of acute coronary syndromes: A systemic review]

BACKGROUND

Acute myocardial infarction is the leading cause of non-communicable deaths worldwide. Its diagnosis is a highly complex task, for which modelling through automated methods has been attempted. A systematic review of the literature was performed on diagnostic tests that applied intelligent systems tools in the diagnosis of acute coronary syndromes.

METHODS

A systematic review of the literature is presented using Medline, Embase, Scopus, IEEE/IET Electronic Library, ISI Web of Science, Latindex and LILACS databases for articles that include the diagnostic evaluation of acute coronary syndromes using intelligent systems. The review process was conducted independently by 2 reviewers, and discrepancies were resolved through the participation of a third person. The operational characteristics of the studied tools were extracted.

RESULTS

A total of 35 references met the inclusion criteria. In 22 (62.8%) cases, neural networks were used. In five studies, the performances of several intelligent systems tools were compared. Thirteen studies sought to perform diagnoses of all acute coronary syndromes, and in 22, only infarctions were studied. In 21 cases, clinical and electrocardiographic aspects were used as input data, and in 10, only electrocardiographic data were used. Most intelligent systems use the clinical context as a reference standard. High rates of diagnostic accuracy were found with better performance using neural networks and support vector machines, compared with statistical tools of pattern recognition and decision trees.

CONCLUSIONS

Extensive evidence was found that shows that using intelligent systems tools achieves a greater degree of accuracy than some clinical algorithms or scales and, thus, should be considered appropriate tools for supporting diagnostic decisions of acute coronary syndromes.

What decides the suspicion of acute coronary syndrome in acute chest pain patients?

Background

Physicians assessing chest pain patients in the emergency department (ED) base the likelihood of acute coronary syndrome (ACS) mainly on ECG, symptom history and blood markers of myocardial injury. Among these, the ECG has been stated to be the most important diagnostic tool. We aimed to analyze the relative contributions of these three diagnostic modalities to the ED physicians’ evaluation of ACS likelihood in clinical practice.

Methods

1151 consecutive ED chest pain patients were prospectively included. The ED physician’s subjective assessment of the patient’s likelihood of ACS (obvious ACS, strong, vague or no suspicion of ACS), the symptoms and the ECG were recorded on a special form. The ED TnT value was retrieved from the medical records. Frequency tables and logistic regression models were used to evaluate the contributions of the diagnostic tests to the level of ACS suspicion.

Results

Symptoms determined whether the physician had any suspicion of ACS (odds ratio, OR 526 for symptoms typical compared to not suspicious of ACS) since neither ECG nor TnT contributed significantly (ORs not significantly different from 1) to this assessment. ACS was suspected in only one in ten patients with symptoms not suspicious of ACS. Symptoms were also more important (OR 620 for typical symptoms) than ECG (OR 31 for ischemic ECG) and TnT (OR 3.4 for a positive TnT) for the assessment of obvious ACS/strong suspicion versus vague/no suspicion. Of the patients with ST-elevation on ECG, 71% were considered to have an obvious ACS, as opposed to only 6% of those with symptoms typical of ACS and 10% of those with a positive TnT.

Conclusion

The ED physicians used symptoms as the most important assessment tool and applied primarily the symptoms to determine the level of ACS suspicion and to rule out ACS. The ECG was primarily used to rule in ACS. The TnT level played a minor role for the assessment of ACS likelihood. Further studies regarding ACS prediction based on symptoms may help improve decision-making in ED patients with possible ACS.

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.

Identifying QT prolongation from ECG impressions using a general-purpose Natural Language Processor

OBJECTIVE

Typically detected via electrocardiograms (ECGs), QT interval prolongation is a known risk factor for sudden cardiac death. Since medications can promote or exacerbate the condition, detection of QT interval prolongation is important for clinical decision support. We investigated the accuracy of natural language processing (NLP) for identifying QT prolongation from cardiologist-generated, free-text ECG impressions compared to corrected QT (QTc) thresholds reported by ECG machines.

METHODS

After integrating negation detection to a locally developed natural language processor, the KnowledgeMap concept identifier, we evaluated NLP-based detection of QT prolongation compared to the calculated QTc on a set of 44,318 ECGs obtained from hospitalized patients. We also created a string query using regular expressions to identify QT prolongation. We calculated sensitivity and specificity of the methods using manual physician review of the cardiologist-generated reports as the gold standard. To investigate causes of "false positive" calculated QTc, we manually reviewed randomly selected ECGs with a long calculated QTc but no mention of QT prolongation. Separately, we validated the performance of the negation detection algorithm on 5000 manually categorized ECG phrases for any medical concept (not limited to QT prolongation) prior to developing the NLP query for QT prolongation.

RESULTS

The NLP query for QT prolongation correctly identified 2364 of 2373 ECGs with QT prolongation with a sensitivity of 0.996 and a positive predictive value of 1.000. There were no false positives. The regular expression query had a sensitivity of 0.999 and positive predictive value of 0.982. In contrast, the positive predictive value of common QTc thresholds derived from ECG machines was 0.07-0.25 with corresponding sensitivities of 0.994-0.046. The negation detection algorithm had a recall of 0.973 and precision of 0.982 for 10,490 concepts found within ECG impressions.

CONCLUSION

NLP and regular expression queries of cardiologists' ECG interpretations can more effectively identify QT prolongation than the automated QTc intervals reported by ECG machines. Future clinical decision support could employ NLP queries to detect QTc prolongation and other reported ECG abnormalities.

In search of the best method to predict acute coronary syndrome using only the electrocardiogram from the emergency department

INTRODUCTION

The aim of this study was to compare different methods to predict acute coronary syndrome (ACS) using only data from a single electrocardiogram (ECG) in the emergency department (ED).

METHOD

We compared the ACS prediction abilities of classical ECG criteria, human expert ECG interpretation, a logistic regression model and an artificial neural network ensemble (ANN). The ED ECG and discharge diagnoses were retrieved for 861 patient visits to the ED for chest pain. Cross-validation was used to estimate the generalization performance of the logistic regression and the ANN model.

RESULTS

The logistic regression model had the overall best performance in predicting ACS with an area under the receiver operating characteristic curve of 0.88. The sensitivities of logistic regression, ANN, expert physicians, and classical ECG criteria were 95%, 95%, 82%, and 75%, respectively, and the specificities were 54%, 44%, 63%, and 69%.

CONCLUSION

Our logistic regression model was the best overall method to predict ACS, followed by our ANN. Decision support models have the potential to improve even experienced ECG readers' ability to predict ACS in the ED.

Automatic covariate selection in logistic models for chest pain diagnosis: a new approach

A newly established method for optimizing logistic models via a minorization-majorization procedure is applied to the problem of diagnosing acute coronary syndromes (ACS). The method provides a principled approach to the selection of covariates which would otherwise require the use of a suboptimal method owing to the size of the covariate set. A strategy for building models is proposed and two models optimized for performance and for simplicity are derived via 10-fold cross-validation. These models confirm that a relatively small set of covariates including clinical and electrocardiographic features can be used successfully in this task. The performance of the models is comparable with previously published models using less principled selection methods. The models prove to be portable when tested on data gathered from three other sites. Whilst diagnostic accuracy and calibration diminishes slightly for these new settings, it remains satisfactory overall. The prospect of building predictive models that are as simple as possible for a required level of performance is valuable if data-driven decision aids are to gain wide acceptance in the clinical situation owing to the need to minimize the time taken to gather and enter data at the bedside.

New methods for improved evaluation of patients with suspected acute coronary syndrome in the emergency department

This paper aims to identify and review new and unproven emergency department (ED) methods for improved evaluation in cases of suspected acute coronary syndrome (ACS). Systematic news coverage through PubMed from 2000 to 2006 identified papers on new methods for ED assessment of patients with suspected ACS. Articles found described decision support models, new ECG methods, new biomarkers and point-of-care testing, cardiac imaging, immediate exercise tests and the chest pain unit concept. None of these new methods is likely to be the perfect solution, and the best strategy today is therefore a combination of modern methods, where the optimal protocol depends on local resources and expertise. With a suitable combination of new methods, it is likely that more patients can be managed as outpatients, that length of stay can be shortened for those admitted, and that some patients with ACS can get earlier treatment.

Best leads in the standard electrocardiogram for the emergency detection of acute coronary syndrome

BACKGROUND AND PURPOSE

The purpose of this study was to determine which leads in the standard 12-lead electrocardiogram (ECG) are the best for detecting acute coronary syndrome (ACS) among chest pain patients in the emergency department.

METHODS

Neural network classifiers were used to determine the predictive capability of individual leads and combinations of leads from 862 ECGs from chest pain patients in the emergency department at Lund University Hospital.

RESULTS

The best individual lead was aVL, with an area under the receiver operating characteristic curve of 75.5%. The best 3-lead combination was III, aVL, and V2, with a receiver operating characteristic area of 82.0%, compared with the 12-lead ECG performance of 80.5%.

CONCLUSIONS

Our results indicate that leads III, aVL, and V2 are sufficient for computerized prediction of ACS. The present results are likely important in situations where the 12-lead ECG is impractical and for the creation of clinical decision support systems for ECG prediction of ACS.

Automated assessment of myocardial SPECT perfusion scintigraphy: a comparison of different approaches of case-based reasoning

OBJECTIVE

This study compared the diagnostic accuracy of different approaches of case-based reasoning (CBR) for the assessment of coronary artery disease (CAD) using thallium-201 myocardial perfusion scintigraphy in comparison with coronary angiography.

METHODS AND MATERIAL

For each scintigraphic image set, regional myocardial tracer uptake was obtained by polar map analysis. CBR algorithms based on a similarity measure were employed to identify similar scintigraphic images within the case library, where each case contained the scintigraphic data together with results of coronary angiography. The angiographic data of retrieved cases were then used to determine whether significant CAD was present in one of the major coronary arteries. Three different approaches of CBR were compared: (1) case retrieval based on a global comparison of polar map data (GLOB), (2) case retrieval based on a territorial comparison of polar map data (TER), and (3) case retrieval based on a comparison of a given case with eight sub-libraries classified according to the involvement of the three major coronary vessels using a group similarity measure (GROUP). Two matching algorithms the best-match approach and an adapted retrieving approach were combined with all three case retrieval methods and their influence on the diagnostic accuracy were investigated.

RESULTS

For overall detection of significant CAD, the best-match approach of both TER and GROUP retrieval methods showed a higher diagnostic accuracy than the GLOB retrieval method (75% and 77% versus 70%, respectively). ROC analysis for the adapted retrieving approach showed a similar diagnostic accuracy for all three methods with an area under the curve of 0.79, 0.8, and 0.8 for GLOB, TER, and GROUP, respectively.

CONCLUSION

The observed improvement in the diagnostic accuracy by the new approaches may lead to further improvements of CBR systems, which have the potential to offer valuable decision support for human readers, especially for less experienced investigators.