Search

Artificial intelligence (AI) promises to revolutionize many fields, but its clinical implementation in cardiovascular imaging is still rare despite increasing research. We sought to facilitate discussion across several fields and across the lifecycle of research, development, validation, and implementation to identify challenges and opportunities to further translation of AI in cardiovascular imaging. Furthermore, it seemed apparent that a multidisciplinary effort across institutions would be essential to overcome these challenges. This paper summarizes the proceedings of the National Heart, Lung, and Blood Institute-led workshop, creating consensus around needs and opportunities for institutions at several levels to support and advance research in this field and support future translation.

BackgroundThe levels of circulating troponin are principally required in addition to electrocardiograms for the effective diagnosis of acute coronary syndrome. Current standard-of-care troponin assays provide a snapshot or momentary view of the levels due to the requirement of a blood draw. This modality further restricts the number of measurements given the clinical context of the patient. In this communication, we present the development and early validation of non-invasive transdermal monitoring of cardiac troponin-I to detect its elevated state.MethodsOur device relies on infrared spectroscopic detection of troponin-I through the dermis and is tested in stepwise laboratory, benchtop, and clinical studies. Patients were recruited with suspected acute coronary syndrome.ResultsWe demonstrate a significant correlation (r = 0.7774, P

AimsCoronary artery calcium (CAC) scoring is an established tool for cardiovascular risk stratification. However, the lack of widespread availability and concerns about radiation exposure have limited the universal clinical utilization of CAC. In this study, we sought to explore whether machine learning (ML) approaches can aid cardiovascular risk stratification by predicting guideline recommended CAC score categories from clinical features and surface electrocardiograms.Methods and resultsIn this substudy of a prospective, multicentre trial, a total of 534 subjects referred for CAC scores and electrocardiographic data were split into 80% training and 20% testing sets. Two binary outcome ML logistic regression models were developed for prediction of CAC scores equal to 0 and ≥400. Both CAC = 0 and CAC ≥400 models yielded values for the area under the curve, sensitivity, specificity, and accuracy of 84%, 92%, 70%, and 75%, and 87%, 91%, 75%, and 81%, respectively. We further tested the CAC ≥400 model to risk stratify a cohort of 87 subjects referred for invasive coronary angiography. Using an intermediate or higher pretest probability (≥15%) to predict CAC ≥400, the model predicted the presence of significant coronary artery stenosis (P = 0.025), the need for revascularization (P

BackgroundAlthough early reperfusion is the most desirable intervention after ischemic myocardial insult, it may add to damage through oxidative stress.ObjectivesThis study investigated the cardioprotective effects of a single intravenous dose of heat shock protein-72 (HSP72) coupled to a single-chain variable fragment (Fv) of monoclonal antibody 3E10 (3E10Fv) in a rabbit ischemia-reperfusion model. The Fv facilitates rapid transport of HSP72 into cells, even with intact membranes.MethodsA left coronary artery occlusion (40 min) reperfusion (3 h) model was used in 31 rabbits. Of these, 12 rabbits received the fusion protein (Fv-HSP72) intravenously. The remaining 19 control rabbits received a molar equivalent of 3E10Fv alone (n = 6), HSP72 alone (n = 6), or phosphate-buffered saline (n = 7). Serial echocardiographic examinations were performed to assess left ventricular function before and after reperfusion. Micro-single-photon emission computed tomography imaging of 99mTc-labeled annexin-V was performed with micro-computed tomography scanning to characterize apoptotic damage in vivo, followed by gamma counting of the excised myocardial specimens to quantify cell death. Histopathological characterization of the myocardial tissue and sequential cardiac troponin I measurements were also undertaken.ResultsMyocardial annexin-V uptake was 43% lower in the area at risk (p = 0.0003) in Fv-HSP72-treated rabbits compared with control animals receiving HSP72 or 3E10Fv alone. During reperfusion, troponin I release was 42% lower and the echocardiographic left ventricular ejection fraction 27% higher in the Fv-HSP72-treated group compared with control animals. Histopathological analyses confirmed penetration of 3E10Fv-containing molecules into cardiomyocytes in vivo, and treatment with Fv-HSP72 showed fewer apoptotic nuclei compared with control rabbits.ConclusionsSingle-dose administration of Fv-HSP72 fusion protein at the time of reperfusion reduced myocardial apoptosis by almost one-half and improved left ventricular functional recovery after myocardial ischemia-reperfusion injury in rabbits. It might have potential to serve as an adjunct to early reperfusion in the management of myocardial infarction.

Aims Age-related changes in cardiac structure and function are well recognized and make the clinical determination of abnormal left ventricular (LV) diastolic dysfunction (LVDD) particularly challenging in the elderly. We investigated whether a deep neural network (DeepNN) model of LVDD, previously validated in a younger cohort, can be implemented in an older population to predict incident heart failure (HF). Methods and results A previously developed DeepNN was tested on 5596 older participants (66–90 years; 57% female; 20% Black) from the Atherosclerosis Risk in Communities Study. The association of DeepNN predictions with HF or all-cause death for the American College of Cardiology Foundation/American Heart Association Stage A/B (n = 4054) and Stage C/D (n = 1542) subgroups was assessed. The DeepNN-predicted high-risk compared with the low-risk phenogroup demonstrated an increased incidence of HF and death for both Stage A/B and Stage C/D (log-rank P < 0.0001 for all). In multi-variable analyses, the high-risk phenogroup remained an independent predictor of HF and death in both Stages A/B {adjusted hazard ratio [95% confidence interval (CI)] 6.52 [4.20–10.13] and 2.21 [1.68–2.91], both P < 0.0001} and Stage C/D [6.51 (4.06–10.44) and 1.03 (1.00–1.06), both P < 0.0001], respectively. In addition, DeepNN showed incremental value over the 2016 American Society of Echocardiography/European Association of Cardiovascular Imaging (ASE/EACVI) guidelines [net re-classification index, 0.5 (CI 0.4–0.6), P < 0.001; C -statistic improvement, DeepNN (0.76) vs. ASE/EACVI (0.70), P < 0.001] overall and maintained across stage groups. Conclusion Despite training with a younger cohort, a deep patient-similarity–based learning framework for assessing LVDD provides a robust prediction of all-cause death and incident HF for older patients. [ABSTRACT FROM AUTHOR]