ABSTRACT
Doppler echocardiography is a widely utilised non-invasive imaging modality for assessing the functionality of heart valves, including the mitral valve. Manual assessments of Doppler traces by clinicians introduce variability, prompting the need for automated solutions. This study introduces an innovative deep learning model for automated detection of peak velocity measurements from mitral inflow Doppler images, independent from Electrocardiogram information. A dataset of Doppler images annotated by multiple expert cardiologists was established, serving as a robust benchmark. The model leverages heatmap regression networks, achieving 96% detection accuracy. The model discrepancy with the expert consensus falls comfortably within the range of inter- and intra-observer variability in measuring Doppler peak velocities. The dataset and models are open-source, fostering further research and clinical application.
Subject(s)
Deep Learning , Blood Flow Velocity , Echocardiography, Doppler/methods , Mitral Valve/diagnostic imaging , Ultrasonography, DopplerSubject(s)
Aneurysm, False/diagnostic imaging , Aorta, Thoracic/diagnostic imaging , Aortic Diseases/diagnostic imaging , Chest Pain/etiology , Contrast Media , Phospholipids , Sulfur Hexafluoride , Thrombosis/diagnostic imaging , Aneurysm, False/complications , Aortic Diseases/complications , Aortitis/diagnosis , Aortography , Biopsy , Contraindications , Diagnosis, Differential , Echocardiography, Doppler, Color , Female , Humans , Lung/diagnostic imaging , Middle Aged , Tomography, X-Ray Computed , Vascular Neoplasms/diagnosisABSTRACT
Using genome-wide association, we identify common variants at 2p12-p13, 6q26, 17q23 and 19q13 associated with serum creatinine, a marker of kidney function (P = 10(-10) to 10(-15)). Of these, rs10206899 (near NAT8, 2p12-p13) and rs4805834 (near SLC7A9, 19q13) were also associated with chronic kidney disease (P = 5.0 x 10(-5) and P = 3.6 x 10(-4), respectively). Our findings provide insight into metabolic, solute and drug-transport pathways underlying susceptibility to chronic kidney disease.
Subject(s)
Kidney Failure, Chronic/genetics , Kidney/physiology , Biological Transport , Creatinine/blood , Cystatin C/metabolism , Europe , Gene Expression Regulation , Genetic Markers/genetics , Genetic Predisposition to Disease , Genetic Variation , Genome-Wide Association Study , Genotype , Glomerular Filtration Rate , Humans , Kidney Failure, Chronic/pathology , Models, GeneticABSTRACT
To identify genetic factors influencing cardiac conduction, we carried out a genome-wide association study of electrocardiographic time intervals in 6,543 Indian Asians. We identified association of a nonsynonymous SNP, rs6795970, in SCN10A (P = 2.8 x 10(-15)) with PR interval, a marker of cardiac atrioventricular conduction. Replication testing among 6,243 Indian Asians and 5,370 Europeans confirmed that rs6795970 (G>A) is associated with prolonged cardiac conduction (longer P-wave duration, PR interval and QRS duration, P = 10(-5) to 10(-20)). SCN10A encodes Na(V)1.8, a sodium channel. We show that SCN10A is expressed in mouse and human heart tissue and that PR interval is shorter in Scn10a(-/-) mice than in wild-type mice. We also find that rs6795970 is associated with a higher risk of heart block (P < 0.05) and a lower risk of ventricular fibrillation (P = 0.01). Our findings provide new insight into the pathogenesis of cardiac conduction, heart block and ventricular fibrillation.