Strom, Jordan B.

Background: Pulmonary hypertension (PH) is a life-threatening disease affecting up to 1% of the global population. Diagnosis can be challenging and is often delayed due to the need for advanced imaging and invasive procedures. The use of artificial intelligence applied to ECGs (ECG-AI) has been shown to detect subtle patterns in voltage-time data and may be a valuable tool for the early detection of PH. Hypothesis and Purpose: To evaluate the performance of a previously trained, ECG-AI algorithm to detect PH (ECG-AI PH) using real-world data (RWD) collected in a multicenter, validation study. A joint primary hypothesis required sensitivity (Sn), specificity (Sp), positive predictive value (PPV), and negative predictive value (NPV) to exceed the null values of 76%, 70%, 10% and 90%. Study Design and Methods: This retrospective validation study was conducted at 5 geographically diverse U.S. health systems. Adult subjects were eligible for inclusion if they had a 12-lead ECG paired with an echocardiogram (Echo) in which tricuspid regurgitation velocity (TRV) was recorded, following presentation with dyspnea. Patients were classified according to echocardiographic criteria as either PH (PH+, TRV >3.4 m/s) or controls (PH-, TRV ≤2.8 m/s) to simulate the real-world use of ECG-AI, where a positive result could lead to a follow-up Echo. The study database was locked before processing the digital ECGs with ECG-AI PH. Performance was also estimated in a subset of subjects that later had a right heart catheterization using mPAP ≥ 20mmHg as the definition of PH. Results: A total of 14281 subjects (53% female, 63% aged 50+ years) met the inclusion criteria, including 3019 PH+ cases and 11262 PH- controls (Figure). Sn and Sp were 84.0% (95% CI: 82.6%, 85.3%) and 71.7% (95% CI: 70.9%, 72.6%), respectively. The positive and negative predictive values were 18.9% (95% CI: 18.4%, 19.4%) and 98.3% (95% CI: 98.1%, 98.4%), respectively, at 7.3% prevalence. Each endpoint met pre-defined performance criteria. In the subset of 1683 subjects with a follow up RHC, performance remained robust (Sn 85% (1155/1358); Sp 46% (151/325)). Conclusion: While ECG-AI PH was first developed as an investigational tool to detect PH, continued development as software as a medical device for clinical use demonstrated that the algorithm retained strong performance to detect PH in diverse, non-overlapping clinical settings and patient populations.

Abstract Background and Aims Accurate differentiation of cardiac amyloidosis (CA) from phenotypic mimics remains challenging using current clinical and echocardiographic techniques. The accuracy of a novel artificial intelligence (AI) screening algorithm for echocardiography-based CA detection was assessed. Methods Utilizing a multisite, multiethnic dataset (n = 2612, 52% CA), a convolutional neural network was trained to differentiate CA from phenotypic controls using transthoracic apical four-chamber video clips. External validation was conducted globally across 18 sites including 597 CA cases and 2122 controls. Classification accuracy was assessed on the entire external validation dataset, and subgroup analyses were performed both on technetium pyrophosphate scintigraphy referrals, and individuals matched for age, sex, and wall thickness. Model accuracy was also compared with the transthyretin CA score and the increased wall thickness score within a subset of older heart failure with preserved ejection fraction patients with increased wall thickness. Results Cardiac amyloidosis patients and controls displayed similar age, sex, race, and comorbidities. After the removal of uncertain AI predictions (13%), model discrimination and classification were excellent for the entire external validation dataset [area under the receiver operating characteristic curve (AUROC) 0.93, sensitivity 85%, specificity 93%], irrespective of CA subtype (sensitivity: light-chain = 84%, wild-type transthyretin = 85%, and hereditary transthyretin = 86%). Performance was maintained in subgroup analysis in patients clinically referred for technetium pyrophosphate scintigraphy imaging (AUROC 0.86, sensitivity 77%, specificity 86%) and matched patients (AUROC 0.92, sensitivity 84%, specificity 91%). The AI model (AUROC 0.93) also outperformed transthyretin CA score (AUROC 0.73) and increased wall thickness (AUROC 0.80) scores. Conclusions This AI screening model—using only an apical four-chamber view—effectively differentiated CA from other causes of increased left ventricular wall thickness.

Background The mortality risk attributable to moderate aortic stenosis (AS) remains incompletely characterized and has historically been underestimated. We aim to evaluate the association between moderate AS and all‐cause death, comparing it with no/mild AS (in a general referral population and in patients with heart failure with reduced ejection fraction). Methods and Results A systematic review and pooled meta‐analysis of Kaplan–Meier‐derived reconstructed time‐to‐event data of studies published by June 2023 was conducted to evaluate survival outcomes among patients with moderate AS in comparison with individuals with no/mild AS. Ten studies were included, encompassing a total of 409 680 patients (11 527 with moderate AS and 398 153 with no/mild AS). In the overall population, the 15‐year overall survival rate was 23.3% (95% CI, 19.1%–28.3%) in patients with moderate AS and 58.9% (95% CI, 58.1%–59.7%) in patients with no/mild aortic stenosis (hazard ratio [HR], 2.55 [95% CI, 2.46–2.64]; P <0.001). In patients with heart failure with reduced ejection fraction, the 10‐year overall survival rate was 15.5% (95% CI, 10.0%–24.0%) in patients with moderate AS and 37.3% (95% CI, 36.2%–38.5%) in patients with no/mild AS (HR, 1.83 [95% CI, 1.69–2.0]; P <0.001). In both populations (overall and heart failure with reduced ejection fraction), these differences correspond to significant lifetime loss associated with moderate AS during follow‐up (4.4 years, P <0.001; and 1.9 years, P <0.001, respectively). A consistent pattern of elevated mortality rate associated with moderate AS in sensitivity analyses of matched studies was observed. Conclusions Moderate AS was associated with higher risk of death and lifetime loss compared with patients with no/mild AS.

Abstract In response to the coronavirus disease 2019 (COVID-19) pandemic, the Cardio-Oncology and Imaging Councils of the American College of Cardiology offers recommendations to clinicians regarding the cardiovascular care of cardio-oncology patients in this expert consensus statement. Cardio-oncology patients—individuals with an active or prior cancer history and with or at risk of cardiovascular disease—are a rapidly growing population who are at increased risk of infection, and experiencing severe and/or lethal complications by COVID-19. Recommendations for optimizing screening and monitoring visits to detect cardiac dysfunction are discussed. In addition, judicious use of multimodality imaging and biomarkers are proposed to identify myocardial, valvular, vascular, and pericardial involvement in cancer patients. The difficulties of diagnosing the etiology of cardiovascular complications in patients with cancer and COVID-19 are outlined, along with weighing the advantages against risks of exposure, with the modification of existing cardiovascular treatments and cardiotoxicity surveillance in patients with cancer during the COVID-19 pandemic.