Myeloid-related protein 8/14 and high-sensitivity cardiac troponin I to differentiate type 2 myocardial infarction.

Myocardial infarction (MI) not only defines acute MI with obstructed coronary arteries (T1MI) but also myocardial necrosis caused by myocardial oxygen supply/demand mismatch as type 2 MI (T2MI); only T1MI patients benefit from an early invasive management. Myeloid-related protein(MRP)-8/14 is a biomarker described in various inflammatory diseases and in MI patients. Here we evaluate the potential of MRP-8/14 and high-sensitivity troponin I (hs-cTnI) to differentiate T2MI from T1MI. Patients with final diagnosis NSTEMI (n = 254; 33.1% female) enrolled in a prospective biomarker registry between 08/2011 and 10/2016 were analysed. Median baseline MRP-8/14 levels were higher in T2MI (n = 55; 3.37(1.88-6.48)µg/mL) than in T1MI (n = 199; 2.4 [1.4-3.79]µg/mL) (p = .013) patients, in contrast to hs-cTnI (T2MI:52[11.65-321.4]ng/L vs. T1MI:436.5 [61.25-1973.8]ng/L; p < .001). To detect the strength of this association odds ratios(OR) were calculated with MRP-8/14 yielding 2.13(1.16-3.92; p = .015) to predict T2MI and 0.47(0.26-0.87; p = .015) for T1MI. As expected, hs-cTnI yielded an OR of to predict T2MI 0.34(0.17-0.65; p = .001) and 2.98(1.53-5.81; p = .001) for T1MI. Both markers show comparable and independent results if adjust to hs-cTnI/MRP-8/14, TIMI risk score and CRP. T2MI is associated with higher MRP-8/14 and lower hs-cTnI concentrations than T1MI. Our data suggest that MRP-8/14 as a marker of inflammation might provide usable discriminatory information complementing hs-cTnI in a diagnostic procedure evaluating the type of MI directly upon hospital admission.

Identifying Heart Failure in ECG Data With Artificial Intelligence-A Meta-Analysis.

Introduction: Electrocardiography (ECG) is a quick and easily accessible method for diagnosis and screening of cardiovascular diseases including heart failure (HF). Artificial intelligence (AI) can be used for semi-automated ECG analysis. The aim of this evaluation was to provide an overview of AI use in HF detection from ECG signals and to perform a meta-analysis of available studies. Methods and Results: An independent comprehensive search of the PubMed and Google Scholar database was conducted for articles dealing with the ability of AI to predict HF based on ECG signals. Only original articles published in peer-reviewed journals were considered. A total of five reports including 57,027 patients and 579,134 ECG datasets were identified including two sets of patient-level data and three with ECG-based datasets. The AI-processed ECG data yielded areas under the receiver operator characteristics curves between 0.92 and 0.99 to identify HF with higher values in ECG-based datasets. Applying a random-effects model, an sROC of 0.987 was calculated. Using the contingency tables led to diagnostic odds ratios ranging from 3.44 [95% confidence interval (CI) = 3.12-3.76] to 13.61 (95% CI = 13.14-14.08) also with lower values in patient-level datasets. The meta-analysis diagnostic odds ratio was 7.59 (95% CI = 5.85-9.34). Conclusions: The present meta-analysis confirms the ability of AI to predict HF from standard 12-lead ECG signals underlining the potential of such an approach. The observed overestimation of the diagnostic ability in artificial ECG databases compared to patient-level data stipulate the need for robust prospective studies.