Machine Learning to Assess for Acute Myocardial Infarction Within 30 Minutes.

Variations in high-sensitivity cardiac troponin I by age and sex along with various sampling times can make the evaluation for acute myocardial infarction (AMI) challenging. Machine learning integrates these variables to allow a more accurate evaluation for possible AMI. The goal was to test the diagnostic and prognostic utility of a machine learning algorithm in the evaluation of possible AMI. We applied a machine learning algorithm (myocardial-ischemic-injury-index [MI3]) that incorporates age, sex, and high-sensitivity cardiac troponin I levels at time 0 and 30 minutes in 529 patients evaluated for possible AMI in a single urban emergency department. MI3 generates an index value from 0 to 100 reflecting the likelihood of AMI. Patients were followed at 30-45 days for major adverse cardiac events (MACEs). There were 42 (7.9%) patients that had an AMI. Patients were divided into 3 groups by the MI3 score: low-risk (≤ 3.13), intermediate-risk (> 3.13-51.0), and high-risk (> 51.0). The sensitivity for AMI was 100% with a MI3 value ≤ 3.13 and 353 (67%) ruled-out for AMI at 30 minutes. At 30-45 days, there were 2 (0.6%) MACEs (2 noncardiac deaths) in the low-risk group, in the intermediate-risk group 4 (3.0%) MACEs (3 AMIs, 1 cardiac death), and in the high-risk group 4 (9.1%) MACEs (4 AMIs, 2 cardiac deaths). The MI3 algorithm had 100% sensitivity for AMI at 30 minutes and identified a low-risk cohort who may be considered for early discharge.

The utility of risk scores when evaluating for acute myocardial infarction using high-sensitivity cardiac troponin I.

Risk scores including the Thrombolysis in Myocardial Infarction (TIMI) score; History, Electrocardiogram, Age, Risk Factors, and Troponin (HEART) score; and Simplified Emergency Department Assessment of Chest Pain Score (sEDACS) have been used to evaluate patients with symptoms suggestive of acute myocardial infarct (AMI). This study assessed prognostic utility of cardiac risk stratification scores when augmented with a high-sensitivity cardiac troponin-I assay (hs-cTnI). METHODS: This study enrolled 2,505 suspected AMI patients at 29 hospitals in the United States from April 2015 to April 2016. Blood samples were tested for hs-cTnI on the Atellica IM TnIH Assay (Siemens Healthineers). Patients were considered low risk for death/AMI with a TIMI score = 0, HEART ≤3, sEDACS ≤15, and hs-cTnI <45 ng/L (99th percentile) at time 0 and 2-3 hours. RESULTS: There were 2,336 patients included after exclusions for ST-segment elevation myocardial infarction or incomplete data. At 30 days, 283 patients (12.1%) had been diagnosed with AMI, and there were 24 (1.0%) deaths and 213 (9.1%) revascularizations. Of 298 patients with death or AMI, 258 (86.6%) had elevated hs-cTnI. The HEART score and sEDACS identified 34.5% and 36.6% of patients as low risk, respectively. This was significantly more than the 12.1% identified by the TIMI score (P < .01). CONCLUSIONS: The TIMI, HEART, and sEDACS scores all identify low-risk patients when combined with hs-cTnI measurements. The HEART score and sEDACS identified more low-risk patients compared to the TIMI score. These patients could be considered for discharge from the emergency department without further testing.

Chest Pain Evaluation in the Emergency Department: Risk Scores and High-Sensitivity Cardiac Troponin.

PURPOSE OF REVIEW: As many as 10 million patients present annually to the emergency department in the USA with symptoms concerning for acute myocardial infarction. The use of risk scores for patients with chest pain or equivalent without ST-segment elevation on the electrocardiogram. The adaptation in the USA of high sensitivity troponin assays requires rethinking of how to best optimize troponin testing within a risk score. RECENT FINDINGS: Patients are risk stratified using a combination of validated risk scores, biomarkers, and both noninvasive and invasive testing. The advent of high-sensitivity troponins has served to augment existing risk scores in the identification of low-risk patients for early discharge, as well as led to the introduction of new rapid rule-out protocols by which acute myocardial infarction can be excluded by biomarker evaluation more quickly. The emergence of machine learning algorithms may further enhance provider's ability to quickly diagnose or exclude myocardial infarction in the emergency department. The addition of high sensitive troponin assays to established emergency department risk scores is providing new opportunities to improve the timeliness and accuracy of the evaluation of patients presenting with a possible myocardial infarction. Utilizing the time between troponin measures as a variable combined with clinical risk factors with new algorithms may further serve to improve diagnostic accuracy.

Prognostic Utility of the HEART Score in the Observation Unit.

The evaluation of individuals with possible acute myocardial infarction (AMI) is time consuming and costly. Risk stratification early during an acute care encounter presents an opportunity for increased delivery of high-value care. We sought to evaluate if the HEART score could be used in the triage of low-risk versus high-risk patients directly home without cardiac testing. Retrospective review of 838 patients placed in an observation unit for evaluation of AMI was done at a single-center, tertiary care teaching hospital. Primary outcome was major adverse cardiac event-death, AMI, or revascularization-at 30 days from the index encounter. Participants' average age was 60.1 years, 40% were male, and 67% were African American. Complete data were available for all 838 patients, including 30-day follow-up at study completion. The primary endpoint was met in 14 patients (1.7%), all of whom were in the high-risk group, with HEART score ≥4. Of the low-risk patients, 8 (2.8%) had a positive functional study, 5 underwent subsequent coronary angiography, with none (0%) found to have obstructive coronary disease. In conclusion, our results suggest that patients with a HEART score ≤3 being evaluated for chest pain are at extremely low risk for major adverse cardiac events and may be safely discharged without provocative testing. Positive cardiac testing in this population is more likely to represent a false-positive finding, resulting in unnecessary testing. These findings should be prospectively validated.

Targeted Metabolomic Profiling of Plasma and Survival in Heart Failure Patients.

OBJECTIVES: This study sought to derive and validate plasma metabolite associations with survival in heart failure (HF) patients. BACKGROUND: Profiling of plasma metabolites to predict the course of HF appears promising, but validation and incremental value of these profiles are less established. METHODS: Patients (n = 1,032) who met Framingham HF criteria with a history of reduced ejection fraction were randomly divided into derivation and validation cohorts (n = 516 each). Amino acids, organic acids, and acylcarnitines were quantified using mass spectrometry in fasting plasma samples. We derived a prognostic metabolite profile (PMP) in the derivation cohort using Lasso-penalized Cox regression. Validity was assessed by 10-fold cross validation in the derivation cohort and by standard testing in the validation cohort. The PMP was analyzed as both a continuous variable (PMPscore) and dichotomized at the median (PMPcat), in univariate and multivariate models adjusted for clinical risk score and N-terminal pro-B-type natriuretic peptide. RESULTS: Overall, 48% of patients were African American, 35% were women, and the average age was 69 years. After a median follow-up of 34 months, there were 256 deaths (127 and 129 in derivation and validation cohorts, respectively). Optimized modeling defined the 13 metabolite PMPs, which was cross validated as both the PMPscore (hazard ratio [HR]: 3.27; p < 2 × 10-16) and PMPcat (HR: 3.04; p = 2.93 × 10-8). The validation cohort showed similar results (PMPscore HR: 3.9; p < 2 × 10-16 and PMPcat HR: 3.99; p = 3.47 × 10-9). In adjusted models, PMP remained associated with mortality in the cross-validated derivation cohort (PMPscore HR: 1.63; p = 0.0029; PMPcat HR: 1.47; p = 0.081) and the validation cohort (PMPscore HR: 1.54; p = 0.037; PMPcat HR: 1.69; p = 0.043). CONCLUSIONS: Plasma metabolite profiles varied across HF subgroups and were associated with survival incremental to conventional predictors. Additional investigation is warranted to define mechanisms and clinical applications.

Reversing factor Xa inhibitors - clinical utility of andexanet alfa.

Approximately half of patients started on an oral anticoagulant in the USA now receive one of the newer direct oral anticoagulants (DOACs). Although there is an approved reversal agent for the direct thrombin inhibitor dabigatran, a specific reversal agent for the anti-factor Xa (FXa) DOACs has yet to be licensed. Unlike the strategy to reverse the only oral direct thrombin inhibitor with idarucizumab, which is a humanized monoclonal antibody fragment, a different approach is necessary to design a single agent that can reverse multiple anti-FXa medications. Andexanet alfa is a FXa decoy designed to reverse all anticoagulants that act through this part of the coagulation cascade including anti-FXa DOACs, such as apixaban, edoxaban and rivaroxaban, and indirect FXa inhibitors such as low-molecular-weight heparins. This narrative reviews the development of andexanet alfa and explores its basic science, pharmacokinetics/pharmacodynamics, animal models, and human studies.

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.

Stable-isotope probing and metagenomics reveal predation by protozoa drives E. coli removal in slow sand filters.

Stable-isotope probing and metagenomics were applied to study samples taken from laboratory-scale slow sand filters 0.5, 1, 2, 3 and 4 h after challenging with (13)C-labelled Escherichia coli to determine the mechanisms and organisms responsible for coliform removal. Before spiking, the filters had been continuously operated for 7 weeks using water from the River Kelvin, Glasgow as their influent source. Direct counts and quantitative PCR assays revealed a clear predator-prey response between protozoa and E. coli. The importance of top-down trophic-interactions was confirmed by metagenomic analysis, identifying several protozoan and viral species connected to E. coli attrition, with protozoan grazing responsible for the majority of the removal. In addition to top-down mechanisms, indirect mechanisms, such as algal reactive oxygen species-induced lysis, and mutualistic interactions between algae and fungi, were also associated with coliform removal. The findings significantly further our understanding of the processes and trophic interactions underpinning E. coli removal. This study provides an example for similar studies, and the opportunity to better understand, manage and enhance E. coli removal by allowing the creation of more complex trophic interaction models.