Daily Cardiology Research Analysis

IMPORTANCE: Echocardiography is a cornerstone of cardiovascular care, but relies on expert interpretation and manual reporting from a series of videos. An artificial intelligence (AI) system, PanEcho, has been proposed to automate echocardiogram interpretation with multitask deep learning. OBJECTIVE: To develop and evaluate the accuracy of an AI system on a comprehensive set of 39 labels and measurements on transthoracic echocardiography (TTE). DESIGN, SETTING, AND PARTICIPANTS: This study represents the development and retrospective, multisite validation of an AI system. PanEcho was developed using TTE studies conducted at Yale New Haven Health System (YNHHS) hospitals and clinics from January 2016 to June 2022 during routine care. The model was internally validated in a temporally distinct YNHHS cohort from July to December 2022, externally validated across 4 diverse external cohorts, and publicly released. MAIN OUTCOMES AND MEASURES: The primary outcome was the area under the receiver operating characteristic curve (AUC) for diagnostic classification tasks and mean absolute error for parameter estimation tasks, comparing AI predictions with the assessment of the interpreting cardiologist. RESULTS: This study included 1.2 million echocardiographic videos from 32 265 TTE studies of 24 405 patients across YNHHS hospitals and clinics. The AI system performed 18 diagnostic classification tasks with a median (IQR) AUC of 0.91 (0.88-0.93) and estimated 21 echocardiographic parameters with a median (IQR) normalized mean absolute error of 0.13 (0.10-0.18) in internal validation. For instance, the model accurately estimated left ventricular ejection fraction (mean absolute error: 4.2% internal; 4.5% external) and detected moderate or worse left ventricular systolic dysfunction (AUC: 0.98 internal; 0.99 external), right ventricular systolic dysfunction (AUC: 0.93 internal; 0.94 external), and severe aortic stenosis (AUC: 0.98 internal; 1.00 external). The AI system maintained excellent performance in limited imaging protocols, performing 15 diagnosis tasks with a median (IQR) AUC of 0.91 (0.87-0.94) in an abbreviated TTE cohort and 14 tasks with a median (IQR) AUC of 0.85 (0.77-0.87) on real-world point-of-care ultrasonography acquisitions from YNHHS emergency departments. CONCLUSIONS AND RELEVANCE: In this study, an AI system that automatically interprets echocardiograms maintained high accuracy across geography and time from complete and limited studies. This AI system may be used as an adjunct reader in echocardiography laboratories or AI-enabled screening tool in point-of-care settings following prospective evaluation in the respective clinical workflows.

BACKGROUND: Low-dose combinations (LDCs) of 3 or 4 blood pressure (BP)-lowering drugs as a single pill show promise for initial treatment of hypertension. OBJECTIVES: The purpose of this study was to assess the efficacy and safety of single pill LDC therapies compared to placebo, monotherapy, or usual care. METHODS: A systematic search for randomized trials comparing LDC consisting of 3 or 4 BP-lowering drugs all at ≤0.5 standard dose, compared to placebo, monotherapy, or usual care. Mean BP reductions, proportions achieving BP <140/90 mm Hg, and risk of adverse events were summarized using random effects meta-analyses. RESULTS: Twelve trials (N = 2,581) were included which contributed to 12 comparisons of LDCs vs placebo, 6 for LDCs vs monotherapy, and 4 for LDCs vs usual care. LDC reduced BP by 14/6 mm Hg vs placebo at 4 to 12 weeks, with larger systolic BP reductions at higher pretreatment systolic BP. Compared to monotherapy, LDC reduced BP by 7/6 mm Hg and increased the proportion achieving BP <140/90 mm Hg at first follow-up (67% vs 46%). Compared to usual care, LDC-based care was superior for BP reduction (7/4 mm Hg) and BP control (80% vs 65%) over an average 29 weeks; and results were similar whether patients were initially untreated or on monotherapy. LDC was not associated with significant increase in withdrawals due to adverse events compared to placebo (3% vs 2%), monotherapy (1% vs 0%), or usual care (3% vs 4%). CONCLUSIONS: Single pill LDCs are effective and safe as an initial treatment option for hypertension. The degree of BP reduction depends strongly on pretreatment BP level.

BACKGROUND: Transcatheter aortic valve replacement (TAVR) is increasingly used in patients with aortic stenosis; however, the optimal postoperative anticoagulation therapy for patients with atrial fibrillation (AF) remains controversial. We aimed to investigate the association between anticoagulant therapy selection and outcomes in patients with AF after TAVR. METHODS: We retrospectively analyzed patients with AF who underwent TAVR. Patients were divided into 2 groups according to the anticoagulant therapy administered 3 months after the index TAVR (direct oral anticoagulant [DOAC] and vitamin K antagonist [VKA] groups). The primary end points were thromboembolic and major bleeding events after a landmark period of 3 months. We analyzed the association between oral anticoagulants and outcomes using propensity score matching. RESULTS: Among 47 883 patients who underwent TAVR between April 2014 and March 2021, 10 041 had a history of AF and anticoagulant therapy. Of these, 8191 patients were prescribed a DOAC, while 1850 received a VKA. Before matching, the thromboembolic event rate was 2.2 per 100 person-years in the DOAC group and 3.6 per 100 person-years in the VKA group, whereas the bleeding event rates were 7.1 and 10.0 per 100 person-years, respectively. After matching, VKA was associated with higher risks of thromboembolic events (hazard ratio [HR], 1.46 [95% CI, 1.12-1.91]; CONCLUSIONS: DOAC use in patients with AF who undergo TAVR may be preferable to VKA use in a real-world clinical setting.