Mortality and Heart Failure Hospitalization Among Young Adults With and Without Cardiogenic Shock After Acute Myocardial Infarction.

OBJECTIVES: To investigate risk factors and outcomes of cardiogenic shock complicating acute myocardial infarction (AMI-CS) in young patients with AMI. BACKGROUND: AMI-CS is associated with high morbidity and mortality rates. Data regarding AMI-CS in younger individuals are limited. METHODS AND RESULTS: Consecutive patients with type 1 AMI aged 18-50 years admitted to 2 large tertiary-care academic centers were included, and they were adjudicated as having cardiogenic shock (CS) by physician review of electronic medical records using the Society for Cardiovascular Angiography and Interventions CS classification system. Outcomes included all-cause mortality (ACM), cardiovascular mortality (CVM) and 1-year hospitalization for heart failure (HHF). In addition to using the full population, matching was also used to define a comparator group in the non-CS cohort. Among 2097 patients (mean age 44 ± 5.1 years, 74% white, 19% female), AMI-CS was present in 148 (7%). Independent risk factors of AMI-CS included ST-segment elevation myocardial infarction, left main disease, out-of-hospital cardiac arrest, female sex, peripheral vascular disease, and diabetes. Over median follow-up of 11.2 years, young patients with AMI-CS had a significantly higher risk of ACM (adjusted HR 2.84, 95% CI 1.68-4.81; P < 0.001), CVM (adjusted HR 4.01, 95% CI 2.17-7.71; P < 0.001), and 1-year HHF (adjusted HR 5.99, 95% CI 2.04-17.61; P = 0.001) compared with matched non-AMI-CS patients. Over the course of the study, there was an increase in the incidence of AMI-CS among young patients with MI as well as rising mortality rates for patients with both AMI-CS and non-AMI-CS. CONCLUSIONS: Of young patients with AMI, 7% developed AMI-CS, which was associated with a significantly elevated risk of mortality and HHF.

Explainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging.

Artificial intelligence may improve accuracy of myocardial perfusion imaging (MPI) but will likely be implemented as an aid to physician interpretation rather than an autonomous tool. Deep learning (DL) has high standalone diagnostic accuracy for obstructive coronary artery disease (CAD), but its influence on physician interpretation is unknown. We assessed whether access to explainable DL predictions improves physician interpretation of MPI. Methods: We selected a representative cohort of patients who underwent MPI with reference invasive coronary angiography. Obstructive CAD, defined as stenosis ≥50% in the left main artery or ≥70% in other coronary segments, was present in half of the patients. We used an explainable DL model (CAD-DL), which was previously developed in a separate population from different sites. Three physicians interpreted studies first with clinical history, stress, and quantitative perfusion, then with all the data plus the DL results. Diagnostic accuracy was assessed using area under the receiver-operating-characteristic curve (AUC). Results: In total, 240 patients with a median age of 65 y (interquartile range 58-73) were included. The diagnostic accuracy of physician interpretation with CAD-DL (AUC 0.779) was significantly higher than that of physician interpretation without CAD-DL (AUC 0.747, P = 0.003) and stress total perfusion deficit (AUC 0.718, P < 0.001). With matched specificity, CAD-DL had higher sensitivity when operating autonomously compared with readers without DL results (P < 0.001), but not compared with readers interpreting with DL results (P = 0.122). All readers had numerically higher accuracy with CAD-DL, with AUC improvement 0.02-0.05, and interpretation with DL resulted in overall net reclassification improvement of 17.2% (95% CI 9.2%-24.4%, P < 0.001). Conclusion: Explainable DL predictions lead to meaningful improvements in physician interpretation; however, the improvement varied across the readers, reflecting the acceptance of this new technology. This technique could be implemented as an aid to physician diagnosis, improving the diagnostic accuracy of MPI.

Transient ischaemic dilation and post-stress wall motion abnormality increase risk in patients with less than moderate ischaemia: analysis of the REFINE SPECT registry.

AIMS: Ischaemia on single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is strongly associated with cardiovascular risk. Transient ischaemic dilation (TID) and post-stress wall motion abnormalities (WMA) are non-perfusion markers of ischaemia with incremental prognostic utility. Using a large, multicentre SPECT MPI registry, we assessed the degree to which these features increased the risk of major adverse cardiovascular events (MACE) in patients with less than moderate ischaemia. METHODS AND RESULTS: Ischaemia was quantified with total perfusion deficit using semiautomated software and classified as: none (<1%), minimal (1 to <5%), mild (5 to <10%), moderate (10 to <15%), and severe (≥15%). Univariable and multivariable Cox proportional hazard analyses were used to assess associations between high-risk imaging features and MACE. We included 16 578 patients, mean age 64.2 and median follow-up 4.7 years. During follow-up, 1842 patients experienced at least one event. Patients with mild ischaemia and TID were more likely to experience MACE compared with patients without TID [adjusted hazard ratio (HR) 1.42, P = 0.023], with outcomes not significantly different from patients with moderate ischaemia without other high-risk features (unadjusted HR 1.15, P = 0.556). There were similar findings in patients with post-stress WMA. However, in multivariable analysis of patients with mild ischaemia, TID (adjusted HR 1.50, P = 0.037), but not WMA, was independently associated with increased MACE. CONCLUSION: In patients with mild ischaemia, TID or post-stress WMA identify groups of patients with outcomes similar to patients with moderate ischaemia. Whether these combinations identify patients who may derive benefit from revascularization deserves further investigation.