Objective: We developed an artificial intelligence decision support algorithm (AI-DSA) that uses routine echocardiographic measurements to identify severe aortic stenosis (AS) phenotypes associated with high mortality.
Methods: 631 824 individuals with 1.08 million echocardiograms were randomly spilt into two groups. Data from 442 276 individuals (70%) entered a Mixture Density Network (MDN) model to train an AI-DSA to predict an aortic valve area <1 cm, excluding all left ventricular outflow tract velocity or dimension measurements and then using the remainder of echocardiographic measurement data. The optimal probability threshold for severe AS detection was identified at the f1 score probability of 0.235. An automated feature also ensured detection of guideline-defined severe AS. The AI-DSA's performance was independently evaluated in 184 301 (30%) individuals.
Results: The area under receiver operating characteristic curve for the AI-DSA to detect severe AS was 0.986 (95% CI 0.985 to 0.987) with 4622/88 199 (5.2%) individuals (79.0±11.9 years, 52.4% women) categorised as 'high-probability' severe AS. Of these, 3566 (77.2%) met guideline-defined severe AS. Compared with the AI-derived low-probability AS group (19.2% mortality), the age-adjusted and sex-adjusted OR for actual 5-year mortality was 2.41 (95% CI 2.13 to 2.73) in the high probability AS group (67.9% mortality)-5-year mortality being slightly higher in those with guideline-defined severe AS (69.1% vs 64.4%; age-adjusted and sex-adjusted OR 1.26 (95% CI 1.04 to 1.53), p=0.021).
Conclusions: An AI-DSA can identify the echocardiographic measurement characteristics of AS associated with poor survival (with not all cases guideline defined). Deployment of this tool in routine clinical practice could improve expedited identification of severe AS cases and more timely referral for therapy.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10373677 | PMC |
| http://dx.doi.org/10.1136/openhrt-2023-002265 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Anatomical Predictors of Access-Related Vascular Complications Following Transfemoral Transcatheter Aortic Valve Replacement.
Catheter Cardiovasc Interv
January 2025
Department of Cardiology, Istanbul Mehmet Akif Ersoy Thoracic and Cardiovascular Surgery Training and Research Hospital, Istanbul, Turkey.
Background: Access-related vascular complications (VCs) after percutaneous transfemoral transcatheter aortic valve replacement (TAVR) are associated with poor clinical outcomes and remain a significant challenge despite technological advances. The aim of this study was to identify anatomic predictors of access-related VCs after TAVR on preprocedural contrast-enhanced multidetector computed tomography (MDCT).
Aims: The aim of this study was to identify anatomical predictors of access-related VCs after TAVR on preprocedural contrast-enhanced MDCT.
Mid-trimester resolution of marked dextroposition of the fetal heart preceding regression of extensive left fetal lung lesion consisting of hybrid congenital pulmonary airway malformation (CPAM) and bronchopulmonary sequestration (BPS).
Radiol Case Rep
March 2025
Division of Maternal Fetal Medicine, Department of Obstetrics and Gynecology, State University of New York (SUNY), Downstate Health Sciences University, Brooklyn, NY, USA.
Extensive congenital pulmonary airway malformation (CPAM) of the left fetal lung and associated marked dextroposition of the fetal heart were noted at 21 weeks' gestation. The right fetal lung appeared compressed with the cardiomediastinal shift angle measuring approximately 20 degrees. Potential subsequent right pulmonary hypoplasia was considered.
View Article and Find Full Text PDFNovel approach to treating calcified infrarenal aortic stenosis using intravascular lithotripsy without stenting.
J Vasc Surg Cases Innov Tech
April 2025
Vascular Surgery Unit, S. Chiara Hospital, APSS Trento, Trento, Italy.
This case report presents the use of intravascular lithotripsy (IVL) in a 68-year-old woman with disabling bilateral claudication owing to a heavily calcified subocclusive stenosis of the infrarenal aorta. The patient had a history of tobacco use, dyslipidemia, and chronic obstructive pulmonary disease, with absent femoral pulses and severe arterial calcification. A 12-mm Shockwave L6 lithotripsy catheter was employed to treat the aortic lesion, resulting in a significant decrease in the aortic pressure gradient without the need for stenting.
View Article and Find Full Text PDFTransaxillary endovascular aortic aneurysm repair using a reverse mounted Gore Excluder endograft for a patient with abdominal aortic aneurysm and severe iliofemoral occlusive disease.
J Vasc Surg Cases Innov Tech
April 2025
Division of Vascular and Endovascular Surgery, Department of Surgery, University of Texas Southwestern Medical Center, Dallas, TX.
Adverse iliofemoral anatomy represents a unique challenge for endovascular aortic aneurysm repair (EVAR). This report describes a transaxillary EVAR in a patient with severe iliofemoral occlusive disease and an infrarenal aortic aneurysm. A reversely mounted Gore Excluder graft was advanced and deployed in the infrarenal aorta using the left axillary artery.
View Article and Find Full Text PDFEpicardial fat tissue, a hidden enemy against the early recovery of left ventricular systolic function after transcatheter aortic valve implantation.
Int J Cardiol Heart Vasc
February 2025
Department of Cardiology, Leiden University Medical Center, Leiden, the Netherlands.
Background: Epicardial fat tissue (EFT) is an active organ that can affect cardiac function and structure through endocrine, paracrine, and proinflammatory mechanisms. We hypothesized that greater thickness of EFT may harm the recovery of left ventricular (LV) systolic function in patients with severe aortic stenosis (AS) and reduced LV ejection fraction (EF ≤ 50 %) undergoing transcatheter aortic valve implantation (TAVI).
Methods: A sixty six patients with severe AS and 20 % ≥ LVEF ≤ 50 % who underwent TAVI were included.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!