Back

Automated Phenotyping of Mitral Stenosis Using Deep Learning

2026-03-04 cardiovascular medicine Title + abstract only
View on medRxiv
Show abstract

Background and AimsAccurate classification of mitral stenosis (MS) remains a significant clinical challenge. This study aimed to develop an artificial intelligence (AI) framework to automatically detect clinically significant MS from echocardiography. MethodsWe developed EchoNet-MS, an open-source end-to-end integrated approach combining video based convolutional neural networks to assess MS severity and differentiate rheumatic etiology from echocardiography and validated its performance across...

Predicted journal destinations

1
Circulation
37 training papers
Top 0.2% 14.7%
2
Scientific Reports
701 training papers
Top 12% 11.9%
3
Journal of the American Heart Association
92 training papers
Top 4% 9.1%
4
European Heart Journal - Digital Health
15 training papers
Top 0.3% 6.5%
5
Frontiers in Cardiovascular Medicine
33 training papers
Top 3% 6.5%
6
npj Digital Medicine
85 training papers
Top 5% 5.1%
7
Circulation: Genomic and Precision Medicine
30 training papers
Top 3% 4.2%
8
PLOS ONE
1737 training papers
Top 86% 3.9%
9
Heart Rhythm
16 training papers
Top 2% 3.9%
10
The American Journal of Cardiology
15 training papers
Top 2% 3.9%
11
Open Heart
18 training papers
Top 3% 3.1%
12
Computers in Biology and Medicine
39 training papers
Top 3% 2.0%
13
Journal of Clinical Medicine
77 training papers
Top 11% 1.6%
14
Nature Communications
483 training papers
Top 42% 1.6%
15
Nature Medicine
88 training papers
Top 7% 1.3%
16
Hypertension
20 training papers
Top 4% 1.3%
17
eLife
262 training papers
Top 34% 1.3%
18
Frontiers in Physiology
18 training papers
Top 1% 1.3%
19
BMJ Open
553 training papers
Top 59% 1.2%
20
Journal of the American Medical Informatics Association
53 training papers
Top 6% 1.2%
21
Atherosclerosis
16 training papers
Top 4% 1.2%
22
EBioMedicine
21 training papers
Top 0.7% 1.0%
23
Frontiers in Neurology
74 training papers
Top 11% 1.0%
24
Nature
58 training papers
Top 7% 1.0%
25
PLOS Digital Health
88 training papers
Top 24% 0.5%