Natalia Trayanova and Eric Topol on the risk of sudden cardiac death & ICD benefit using AI
Access the PDF of their essay here or view directly in The Lancet.
Access the PDF of their essay here or view directly in The Lancet.
We have received a lot of publicity following Dr. Dan Popescu’s publication in Nature Cardiovascular Research. The cover of the journal’s April issue was designed by Dr. Kimberly Popescu (Dan’s wife!), featuring a schematic of a neural network embedded in Read more…
A new artificial intelligence-based approach can predict if and when a patient could die of cardiac arrest. The technology, built on raw images of patient’s diseased hearts and patient backgrounds, significantly improves on doctor’s predictions and stands to revolutionize clinical Read more…
A team led by Johns Hopkins engineers has found that modeling the heart in 3D using combined imaging techniques can help predict heart rhythm abnormalities, called arrhythmias, in patients with a genetic heart disease. This approach could one day help Read more…
Johns Hopkins method outperforms previous approaches for assessing risk in cardiac sarcoidosis. https://releases.jhu.edu/2021/07/28/new-tool-predicts-sudden-death-in-inflammatory-heart-disease/
New algorithm could warn doctors in advance of cardiac arrest or blood clots in hospitalized COVID-19 patients.
Eric recently competed in and won the Young Investigator Award Competition at the 2020 Asia-Pacific Heart Rhythm Society Virtual Congress!
Hugh Calkins (Johns Hopkins Medical Institutions, Baltimore, USA) told delegates attending the AF Symposium 2020 (23–25 January, Washington, DC, USA) that cryoablation with the Arctic Front catheter (Medtronic) was a safe and effective approach for managing persistent atrial fibrillation (AF). He added that the procedure also improves quality of life and reduces symptoms.
Biomedical engineer recognized for her work developing 3D virtual heart models for patients with irregular heartbeats.
In proof-of-concept study of 10 patients with atrial fibrillation, personalized models accurately predict where surgeons should destroy diseased heart tissue.