Huntley, Geoffrey D.

Background: Diagnosis of heart failure with preserved ejection fraction (HFpEF) is challenging due to non-diagnostic imaging outputs and discordant clinical features. Using only a single videoclip from a standard transthoracic echocardiogram (TTE), we developed an artificial intelligence (AI) model to differentiate patients with HFpEF from those without HFpEF. In a separate test population, we assessed the model’s ability to predict cardiac mortality. Methods: A 3-dimensional convolutional neural network was developed and trained on apical 4-chamber videoclips to classify patients with HFpEF (cases) versus without HFpEF (controls). Overall and cardiac mortality were obtained from the National Death Index. Results: The model was independently tested in 646 cases and 638 controls from 8 centers in 4 states. Sensitivity (87.8%; 84.5-90.9%) and specificity (81.9%; 78.2-85.6%) were high and sustained in various subgroups, including increased left atrial volume index, average E/e’ ≥15, and pulmonary artery systolic pressure >35 mm Hg. During follow-up (median [IQR] 3.4 [1.7-6.5] years), 540 patients died. There were 135 cardiac deaths attributable to heart failure (47%), coronary artery disease (41%), valve disease (4%), arrhythmia (4%), and others (5%). Compared to a negative output, all-cause mortality was higher in patients with a positive (HR 2.9 [2.4-3.5]) or uncertain output (HR 1.8 [1.2-2.5]), and cardiac mortality (Figure) was also higher in patients with a positive (HR 7.7 [4.5-13.3]) or uncertain output (HR 3.4 [1.4-8.1]). Cardiac mortality differences according to AI model prediction remained after age adjustment (positive: HR 5.9 [3.3-10.4], p<0.001; uncertain: HR 2.8 [1.2-6.8], p=0.02). Conclusion: A novel AI model to detect HFpEF based on a single routinely acquired TTE videoclip also identifies those at increased risk of cardiac mortality.

Background: The bicuspid aortic valve (BAV) exhibits abnormal geometry and transvalvular flow and is susceptible to calcification with subsequent cardioembolic stroke from calcific embolic material. However, the description of embolic ischemic strokes in patients with BAV is limited to case reports. Methods: Consecutive patients from 1975-2015 with BAV (n=5401) at our institution were retrospectively identified. Patients with ischemic stroke before aortic valve replacement (AVR) were analyzed, and the stroke was characterized. Patients were grouped according to stroke etiology: calcific embolism from a BAV (BAV stroke); large artery atherosclerotic or lacunar stroke (LA stroke); and non-BAV, non-large artery embolic stroke (nLA stroke). Results: There were 83/5401 (1.5%) patients with ischemic stroke. Mean age was 54 ± 12 years and 28% were female. Stroke etiology was BAV stroke in 26/83 (31%), LA stroke in 23/83 (28%), nLA stroke in 30/83 (36%), and other in 4/83 (5%). Stroke was embolic in 72/83 (87%), as shown in Figure 1. CHA 2 DS 2 -VASc score was not different in patients with BAV stroke (1.4 ± 1.2) versus nLA stroke (1.8 ± 1.2, p=0.188) but was higher in LA stroke (2.3 ± 1.2, p=0.005 vs. BAV stroke). Recurrent stroke occurred in 41% overall (50% BAV stroke vs. 30% LA stroke vs. 47% nLA stroke, both p=NS vs. BAV stroke). BAV stroke was more commonly located in the retinal circulation (39% BAV stroke vs. 13% LA stroke [p=0.044] vs. 0% nLA stroke [p=0.002]). Patients with BAV and LA stroke were more likely to have moderate-to-severe aortic stenosis and undergo AVR sooner after stroke compared to patients with nLA stroke. Conclusions: Stroke is an important complication in patients with BAV. The most common type of stroke in BAV is embolic. Greater than one-third of embolic stroke resulted from embolism from a calcific aortic valve. Patients with BAV stroke commonly have a history of recurrent cerebral ischemic events, severe valvular disease, and proceed to AVR soon after stroke.

Background Description of cerebral and retinal infarction in patients with bicuspid aortic valve (BAV) is limited to case reports. We aimed to characterize cerebral and retinal infarction and examine outcomes in patients with BAV. Methods and Results Consecutive patients from 1975 to 2015 with BAV (n=5401) were retrospectively identified from the institutional database; those with confirmed cerebral or retinal infarction were analyzed. Infarction occurring after aortic valve replacement was not included. Patients were grouped according to infarction pathogenesis: embolism from a degenerative calcific BAV (BAVi); non‐BAV, large artery atherosclerotic or lacunar infarction (LAi); and non‐BAV, non‐large artery embolic infarction (nLAi). There were 83/5401 (1.5%) patients, mean age 54±12 years and 28% female, with confirmed cerebral or retinal infarction (LAi 23/83 [28%]; nLAi 30/83 [36%]; BAVi 26/83 [31%]; other 4/83 [5%]). Infarction was embolic in 72/83 (87%), and 35/72 (49%) were cardioembolic. CHA 2 DS 2 ‐VASc score was 1.4±1.2 in BAVi ( P =0.188 versus nLAi) and 2.3±1.2 in LAi ( P =0.005). Recurrent infarction occurred in 41% overall (50% BAVi, P =0.164 and 0.803 versus LAi and nLAi). BAVi was more commonly retinal (39% BAVi versus 13% LAi, P =0.044 versus 0% nLAi, P =0.002). Patients with BAVi and LAi were more likely to have moderate‐to‐severe aortic stenosis and undergo aortic valve replacement compared with patients with nLAi. Conclusions Cardioembolism, often from degenerative calcification of the aortic valve, is a predominant cause of cerebral and retinal infarction in patients with BAV and is frequently recurrent. Cerebral and retinal infarction should be regarded as a complication of BAV.