Can Artificial Intelligence Enhance Syncope Management?: A JACC: Advances Multidisciplinary Collaborative Statement.

Syncope, a form of transient loss of consciousness, remains a complex medical condition for which adverse cardiovascular outcomes, including death, are of major concern but rarely occur. Current risk stratification algorithms have not completely delineated which patients benefit from hospitalization and specific interventions. Patients are often admitted unnecessarily and at high cost. Artificial intelligence (AI) and machine learning may help define the transient loss of consciousness event, diagnose the cause, assess short- and long-term risks, predict recurrence, and determine need for hospitalization and therapeutic intervention; however, several challenges remain, including medicolegal and ethical concerns. This collaborative statement, from a multidisciplinary group of clinicians, investigators, and scientists, focuses on the potential role of AI in syncope management with a goal to inspire creation of AI-derived clinical decision support tools that may improve patient outcomes, streamline diagnostics, and reduce health-care costs.

Impact of Active and Historical Cancers on the Management and Outcomes of Acute Myocardial Infarction Complicating Cardiogenic Shock.

BACKGROUND: There are limited data on the outcomes of acute myocardial infarction-cardiogenic shock (AMI-CS) in patients with concomitant cancer. METHODS: A retrospective cohort of adult AMI-CS admissions was identified from the National Inpatient Sample (2000-2017) and stratified by active cancer, historical cancer, and no cancer. Outcomes of interest included in-hospital mortality, use of coronary angiography, use of percutaneous coronary intervention, do-not-resuscitate status, palliative care use, hospitalization costs, and hospital length of stay. RESULTS: Of the 557,974 AMI-CS admissions during this 18-year period, active and historical cancers were noted in 14,826 (2.6%) and 27,073 (4.8%), respectively. From 2000 to 2017, there was a decline in active cancers (adjusted odds ratio, 0.70 [95% CI, 0.63-0.79]; P < .001) and an increase in historical cancer (adjusted odds ratio, 2.06 [95% CI, 1.89-2.25]; P < .001). Compared with patients with no cancer, patients with active and historical cancer received less-frequent coronary angiography (57%, 67%, and 70%, respectively) and percutaneous coronary intervention (40%, 47%, and 49%%, respectively) and had higher do-not-resuscitate status (13%, 15%, 7%%, respectively) and palliative care use (12%, 10%, 6%%, respectively) (P < .001). Compared with those without cancer, higher in-hospital mortality was found in admissions with active cancer (45.9% vs 37.0%; adjusted odds ratio, 1.29 [95% CI, 1.24-1.34]; P < .001) but not historical cancer (40.1% vs 37.0%; adjusted odds ratio, 1.01 [95% CI, 0.98-1.04]; P = .39). AMI-CS admissions with cancer had a shorter hospitalization duration and lower costs (all P < .001). CONCLUSION: Concomitant cancer was associated with less use of guideline-directed procedures. Active, but not historical, cancer was associated with higher mortality in patients with AMI-CS.

Contemporary procedural trends of Watchman percutaneous left atrial appendage occlusion in the United States.

OBJECTIVE: To determine trends in real-world utilization and in-hospital adverse events from Watchman implantation since its approval by the Food and Drug Administration in 2015. BACKGROUND: The risk of embolic stroke caused by atrial fibrillation is reduced by oral anticoagulants, but not all patients can tolerate long-term anticoagulation. Left atrial appendage occlusion with the Watchman device has emerged as an alternative therapy. METHODS: This was a retrospective cohort study utilizing data from National Inpatient Sample for calendar years 2015-2017. The outcomes assessed in this study were associated complications, in-hospital mortality, and resource utilization trends after Watchman implantation. Trends analysis were performed using analysis of variance. Multivariable adjusted logistic regression analysis was performed to determine predictors of mortality. RESULTS: A total of 17 700 patients underwent Watchman implantation during the study period. There was a significantly increased trend in the number of Watchman procedures performed over the study years (from 1195 in 2015 to 11 165 devices in 2017, p < .01). A significant decline in the rate of complications (from 26.4% in 2015% to 7.9% in 2017, p < .01) and inpatient mortality (from 1.3% in 2015% to 0.1% in 2017, p < .01) were noted. Predictors of in-hospital mortality included a higher CHA2 DS2 -VASc score (odds ratio [OR]: 2.61 per 1-point increase, 95% confidence interval [CI]: 1.91-3.57), chronic blood loss anemia (OR: 3.63, 95% CI: 1.37-9.61) and coagulopathy (OR: 4.90, 95% CI: 2.32-10.35). CONCLUSION: In contemporary United States clinical practice, Watchman utilization has increased significantly since approval in 2015, while complications and in-patient mortality have declined.

Implantable Defibrillator Therapy in Cardiac Arrest Survivors With a Reversible Cause.

BACKGROUND: Current guidelines recommend implantable cardioverter-defibrillator (ICD) therapy in survivors of sudden cardiac arrest (SCA), except in those with completely reversible causes. We sought to examine the impact of ICD therapy on mortality in survivors of SCA associated with reversible causes. METHODS AND RESULTS: We evaluated the records of 1433 patients managed at our institution between 2000 and 2012 who were discharged alive after SCA. A reversible and correctable cause was identified in 792 (55%) patients. Reversible SCA cause was defined as significant electrolyte or metabolic abnormality, evidence of acute myocardial infarction or ischemia, recent initiation of antiarrhythmic drug or illicit drug use, or other reversible circumstances. Of the 792 SCA survivors because of a reversible and correctable cause (age 61±15 years, 40% women), 207 (26%) patients received an ICD after their index SCA. During a mean follow-up of 3.8±3.1 years, 319 (40%) patients died. ICD implantation was highly associated with lower all-cause mortality (P<0.001) even after correcting for unbalanced baseline characteristics (P<0.001). In subgroup analyses, only patients whose SCA was not associated with myocardial infarction extracted benefit from ICD (P<0.001). CONCLUSIONS: In survivors of SCA because of a reversible and correctable cause, ICD therapy is associated with lower all-cause mortality except if the SCA was because of myocardial infarction. These data deserve further investigation in a prospective multicenter randomized controlled trial, as they may have important and immediate clinical implications.

Relationship between left ventricular dyssynchrony and scar burden in the genesis of ventricular tachyarrhythmia.

BACKGROUND: Left ventricular (LV) ejection fraction (EF) has poor predictive value for ventricular tachyarrhythmia (VT). Other parameters such as LV dyssynchrony (LVD), and LV scar burden have also been individually associated with VT, but the interplay of these factors in the genesis of VT has not been explored. This retrospective study sought to evaluate the relationship between LVD and imaging characteristics of the myocardial substrate in predicting VT. METHODS: We identified 183 patients (150 men; mean age: 64 ± 14 years and mean LVEF: 23% ± 7%), who received an implantable cardioverter defibrillator (ICD) for primary prevention and who underwent a gated single-photon emission computed tomography (GSPECT) myocardial perfusion scan prior to ICD implantation. LVD was determined by phase analysis of the GSPECT images. Occurrence of VTs was established through routine ICD interrogations and review of electronic medical records. RESULTS: LVD was present in 136 (74%) patients. VT occurred in 48 (26%) patients. Ninety-eight percent of patient who experienced VT had LVD. Patients without LVD had a significantly better survival free of both sustained and non-sustained VT (HR, 95% CI 4.90, 2.12-11.20; P < 0.0001). The combination of LVD and myocardial scar occupying > 6% of LV myocardium accounted for 83% of all VT events. CONCLUSIONS: LVD assessment by GSPECT is strongly associated with incident VT in patients with low LVEF. The combination of LVD and scar burden predicted the majority of VT events.