Prior electrocardiograms not useful for machine learning predictions of major adverse cardiac events in emergency department chest pain patients.

At the emergency department (ED), it is important to quickly and accurately determine which patients are likely to have a major adverse cardiac event (MACE). Machine learning (ML) models can be used to aid physicians in detecting MACE, and improving the performance of such models is an active area of research. In this study, we sought to determine if ML models can be improved by including a prior electrocardiogram (ECG) from each patient. To that end, we trained several models to predict MACE within 30 days, both with and without prior ECGs, using data collected from 19,499 consecutive patients with chest pain, from five EDs in southern Sweden, between the years 2017 and 2018. Our results indicate no improvement in AUC from prior ECGs. This was consistent across models, both with and without additional clinical input variables, for different patient subgroups, and for different subsets of the outcome. While contradicting current best practices for manual ECG analysis, the results are positive in the sense that ML models with fewer inputs are more easily and widely applicable in practice.

Machine learning for early prediction of acute myocardial infarction or death in acute chest pain patients using electrocardiogram and blood tests at presentation.

AIMS: In the present study, we aimed to evaluate the performance of machine learning (ML) models for identification of acute myocardial infarction (AMI) or death within 30 days among emergency department (ED) chest pain patients. METHODS AND RESULTS: Using data from 9519 consecutive ED chest pain patients, we created ML models based on logistic regression or artificial neural networks. Model inputs included sex, age, ECG and the first blood tests at patient presentation: High sensitivity TnT (hs-cTnT), glucose, creatinine, and hemoglobin. For a safe rule-out, the models were adapted to achieve a sensitivity > 99% and a negative predictive value (NPV) > 99.5% for 30-day AMI/death. For rule-in, we set the models to achieve a specificity > 90% and a positive predictive value (PPV) of > 70%. The models were also compared with the 0 h arm of the European Society of Cardiology algorithm (ESC 0 h); An initial hs-cTnT < 5 ng/L for rule-out and ≥ 52 ng/L for rule-in. A convolutional neural network was the best model and identified 55% of the patients for rule-out and 5.3% for rule-in, while maintaining the required sensitivity, specificity, NPV and PPV levels. ESC 0 h failed to reach these performance levels. DISCUSSION: An ML model based on age, sex, ECG and blood tests at ED arrival can identify six out of ten chest pain patients for safe early rule-out or rule-in with no need for serial blood tests. Future studies should attempt to improve these ML models further, e.g. by including additional input data.

Comparison of diagnostic accuracy of current left bundle branch block and ventricular pacing ECG criteria for detection of occlusion myocardial infarction.

BACKGROUND: Electrocardiographic detection of patients with occlusion myocardial infarction (OMI) can be difficult in patients with left bundle branch block (LBBB) or ventricular paced rhythm (VPR) and several ECG criteria for the detection of OMI in LBBB/VPR exist. Most recently, the Barcelona criteria, which includes concordant ST deviation and discordant ST deviation in leads with low R/S amplitudes, showed superior diagnostic accuracy but has not been validated externally. We aimed to describe the diagnostic accuracy of four available ECG criteria for OMI detection in patients with LBBB/VPR at the emergency department. METHODS: The unweighted Sgarbossa criteria, the modified Sgarbossa criteria (MSC), the Barcelona criteria and the Selvester criteria were applied to chest pain patients with LBBB or VPR in a prospectively acquired database from five emergency departments. RESULTS: In total, 623 patients were included, among which 441 (71%) had LBBB and 182 (29%) had VPR. Among these, 82 (13%) patients were diagnosed with AMI, and an OMI was identified in 15 (2.4%) cases. Sensitivity/specificity of the original unweighted Sgarbossa criteria were 26.7/86.2%, for MSC 60.0/86.0%, for Barcelona criteria 53.3/82.2%, and for Selvester criteria 46.7/88.3%. In this setting with low prevalence of OMI, positive predictive values were low (Sgarbossa: 4.6%; MSC: 9.4%; Barcelona criteria: 6.9%; Selvester criteria: 9.0%) and negative predictive values were high (all >98.0%). CONCLUSIONS: Our results suggests that ECG criteria alone are insufficient in predicting presence of OMI in an ED setting with low prevalence of OMI, and the search for better rapid diagnostic instruments in this setting should continue.

The skåne emergency medicine (SEM) cohort.

BACKGROUND: In the European Union alone, more than 100 million people present to the emergency department (ED) each year, and this has increased steadily year-on-year by 2-3%. Better patient management decisions have the potential to reduce ED crowding, the number of diagnostic tests, the use of inpatient beds, and healthcare costs. METHODS: We have established the Skåne Emergency Medicine (SEM) cohort for developing clinical decision support systems (CDSS) based on artificial intelligence or machine learning as well as traditional statistical methods. The SEM cohort consists of 325 539 unselected unique patients with 630 275 visits from January 1st, 2017 to December 31st, 2018 at eight EDs in the region Skåne in southern Sweden. Data on sociodemographics, previous diseases and current medication are available for each ED patient visit, as well as their chief complaint, test results, disposition and the outcome in the form of subsequent diagnoses, treatments, healthcare costs and mortality within a follow-up period of at least 30 days, and up to 3 years. DISCUSSION: The SEM cohort provides a platform for CDSS research, and we welcome collaboration. In addition, SEM's large amount of real-world patient data with almost complete short-term follow-up will allow research in epidemiology, patient management, diagnostics, prognostics, ED crowding, resource allocation, and social medicine.

A Dynamic Model of Resource Allocation in Response to the Presence of a Synthetic Construct.

Introducing synthetic constructs into bacteria often carries a burden that leads to reduced fitness and selective pressure for organisms to mutate their constructs and hence to a reduced functional lifetime. Understanding burden requires suitable methods for accurate measurement and quantification. We develop a dynamic growth model from physiologically relevant first-principles that allows parameters relevant to burden to be extracted from standard growth curves. We test several possibilities for the response of a bacterium to a new environment in terms of resource allocation. We find that burden manifests in the time taken to respond to new conditions as well as the rate of growth in exponential phase. Furthermore, we see that the presence of a synthetic construct hastens the reduction of ribosomes when approaching stationary phase, altering memory effects from previous periods of growth.