Abstract 17152: Artificial Intelligence ECG for the Detection of Cardiac Injury as Confirmed by High Sensitivity Cardiac Troponin T-Concentrations

Background: High-sensitivity cardiac troponin (hs-cTn) assays quantify cTn in patients at very low concentrations. Myocyte injury due to ischemia or other pathologies cause blood levels to increase, which is prognostic. A noninvasive, rapid, broadly available, home-based test to detect hs-cTn increases would facilitate risk-stratification. Since myocyte injury is associated with ECG changes, we hypothesized an artificial intelligence ECG (AI-ECG) could non-invasively predict current or impending hs-cTnT elevations. Objective: To develop an AI-ECG convolutional neural network (CNN) to detect an abnormal hs-cTnT (5 th Gen cTnT, Roche Diagnostics) concentration using a 12-lead ECG, and a single lead ECG (lead I), which would enable smartphone, home-based detection. Methods: We developed single lead and 12-lead ECG CNNs to detect a) hs-cTnT concentrations that were at or above the 6ng/L limit that can be reported b) above the 99 th percentile upper limits of >15ng/L for men and >10ng/L for women. All ECGs were recorded within one hour of the hs-cTnT measurements. We used 73,012 ECG and hs-cTnT pairs from 47,542 unique patients to train the network, 9031 ECGs from 5,811 patients for internal validation to optimize hyperparameters, and 18,276 ECG and hs-cTnT pairs from 11,904 different patients as a holdout test set to determine the area under the receiver-operator curve (AUC). Results: The mean age was 63.9±17.5 years, and 30,348 of the 59,446 patients (51%) were male. Of the 91,288 hs-cTnT pairs 73,271 (80.2%) were above 6ng/L and 50,799 (55.6%) are above the 99 th percentile. In the test set, the AUC for the detection of a hs-cTnT level higher than 6ng/L was 0.88 using the 12 lead ECG and 0.834 with the single lead. For the detection of hs-cTnT level above of 99 th percentile, the 12 lead ECG AUC was 0.853 and the single lead was 0.806. Conclusion: The AI-ECG permits detection of levels of hs-cTnT consistent with myocardial injury. This may allow a home-based, non-invasive test that would be massively scalable and could further enhance rapid-risk stratification and patient triage with potentially significant cost reductions and enable novel triage strategies at sites without hs-cTn assays.

Pathological features of COVID-19-associated myocardial injury: a multicentre cardiovascular pathology study

Aims Coronavirus disease 2019 (COVID-19) due to severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has been associated with cardiovascular features of myocardial involvement including elevated serum troponin levels and acute heart failure with reduced ejection fraction. The cardiac pathological changes in these patients with COVID-19 have yet to be well described. Methods and results In an international multicentre study, cardiac tissue from the autopsies of 21 consecutive COVID-19 patients was assessed by cardiovascular pathologists. The presence of myocarditis, as defined by the presence of multiple foci of inflammation with associated myocyte injury, was determined, and the inflammatory cell composition analysed by immunohistochemistry. Other forms of acute myocyte injury and inflammation were also described, as well as coronary artery, endocardium, and pericardium involvement. Lymphocytic myocarditis was present in 3 (14%) of the cases. In two of these cases, the T lymphocytes were CD4 predominant and in one case the T lymphocytes were CD8 predominant. Increased interstitial macrophage infiltration was present in 18 (86%) of the cases. A mild pericarditis was present in four cases. Acute myocyte injury in the right ventricle, most probably due to strain/overload, was present in four cases. There was a non-significant trend toward higher serum troponin levels in the patients with myocarditis compared with those without myocarditis. Disrupted coronary artery plaques, coronary artery aneurysms, and large pulmonary emboli were not identified. Conclusions In SARS-CoV-2 there are increased interstitial macrophages in a majority of the cases and multifocal lymphocytic myocarditis in a small fraction of the cases. Other forms of myocardial injury are also present in these patients. The macrophage infiltration may reflect underlying diseases rather than COVID-19.

Abstract 265: Systemic Inflammation and Cardiac Macrophage Infiltration Accompany Stretch-induced Myocardial Injury in Swine Subjected to Transient Pressure Overload

Objective: Transient pressure overload (TPO) elicits stretch-induced myocyte injury in the absence of ischemia or infarction, but the extent to which this is associated with inflammation is unclear. The present study was designed to assess immune activation after TPO in swine and compare the inflammatory cytokine profile to that observed after myocardial infarction (MI). Methods: Swine received a brief infusion of phenylephrine (18 mg/hr iv; 30-60 min) to induce TPO and were studied for 1 hr (n=5), 3 hr (n=6), or 24 hr (n=6) before analysis of myocardial macrophage gene expression (CD68) via qPCR. Serial blood sampling was performed to assess neutrophil and monocyte counts as well as circulating cardiac troponin I (cTnI), IL-6, TNF-α, and CRP. Cytokine levels were compared to those from a separate group (n=5) subjected to a 60 min LAD occlusion to produce MI. Results: TPO increased circulating cTnI (from 20±5 ng/L to 340±58 ng/L at 3 hr and 1520±616 ng/L at 24 hr; p<0.01) without evidence of infarction. Compared with controls (n=6), swine subjected to TPO exhibited increased CD68 gene expression at 1, 3, and 24 hr ( A ). This was accompanied by a rise in peripheral blood neutrophils and monocytes ( B ) as well as an elevation in circulating IL-6, TNF-α, and CRP that was comparable to that observed after MI ( C ). Conclusion: Myocyte injury following TPO elicits mobilization of neutrophils and monocytes and a rise in circulating inflammatory cytokines comparable to that observed after MI. This is accompanied by an increase in cardiac macrophages and may be an important mechanism by which repetitive episodes of TPO lead to interstitial fibrosis and diastolic dysfunction without anatomic hypertrophy.