FDA Clears Emerging AI-Enabled Software for Cardiac Ultrasound
Recent research has demonstrated that the AI software HeartFocus enabled novice health-care providers to achieve greater than 85 percent agreement with expert sonographers in assessing echocardiographic parameters.
The Food and Drug Administration (FDA) has granted 510(k) clearance for the AI-powered echocardiography HeartFocus software, which reportedly allows health-care providers with limited echocardiography experience to obtain heart scans.
In addition to offering quality and precision indicators via real-time feedback, the HeartFocus software provides automated recording of top quality clips for 10 ultrasound cardiac reference views, according to DESKi, the manufacturer of the software.
In research presented recently at the American College of Cardiology (ACC) conference, the newly FDA-cleared AI software HeartFocus enabled health-care providers with novice-level echocardiography experience to achieve greater than 85 percent agreement with expert assessment of echocardiographic parameters. (Image courtesy of DESKi.)
In a prospective multicenter trial, presented recently at the American College of Cardiology (ACC) conference, researchers found that health-care providers with limited echocardiography experience who used the HeartFocus software were able to achieve greater than 85 percent agreement with expert sonographers in assessing 12 echocardiographic parameters.
“The clinical trial results and subsequent FDA clearance mark a major step forward in making echocardiography more accessible in the community. Proving that it can successfully guide any healthcare professional to capture high-quality heart scans, HeartFocus will help patients get diagnosed sooner and move more quickly toward the treatment they need,” posited Varinder P. Singh, M.D., the chair of the Department of Cardiology at Lenox Hill Hospital in New York, and senior vice president and executive director of global and international health for Northwell Health.
Could AI-Powered Abbreviated MRI Reinvent Detection for Structural Abnormalities of the Knee?
April 24th 2025Employing deep learning image reconstruction, parallel imaging and multi-slice acceleration in a sub-five-minute 3T knee MRI, researchers noted 100 percent sensitivity and 99 percent specificity for anterior cruciate ligament (ACL) tears.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.
Meta-Analysis Shows Merits of AI with CTA Detection of Coronary Artery Stenosis and Calcified Plaque
April 16th 2025Artificial intelligence demonstrated higher AUC, sensitivity, and specificity than radiologists for detecting coronary artery stenosis > 50 percent on computed tomography angiography (CTA), according to a new 17-study meta-analysis.
