Spotlight
Topics
DI Executive
Subscribe
- AI
- Molecular Imaging
- CT
- X-Ray
- Ultrasound
- MRI
- Facility Management
- Mammography
FDA Clears AI-Powered Ultrasound Software for Cardiac Amyloidosis Detection
The AI-enabled EchoGo® Amyloidosis software for echocardiography has reportedly demonstrated an 84.5 percent sensitivity rate for diagnosing cardiac amyloidosis in heart failure patients 65 years of age and older.
The Food and Drug Administration (FDA) has granted 510(k) clearance for the artificial intelligence (AI) software EchoGo® Amyloidosis, which may help bolster early detection of cardiac amyloidosis, a diagnosis that is commonly missed in high-risk patients with heart failure and preserved ejection fraction (HFpEF).
Requiring only a single apical four-chamber echocardiography video clip, the EchoGo Amyloidosis software facilitates improved accuracy in the detection of cardiac amyloidosis, according to Ultromics, the manufacturer of the software.
The newly FDA-cleared EchoGo Amyloidosis AI software has demonstrated 84.5 percent sensitivity for diagnosing cardiac amyloidosis in patients with heart failure that are 65 years of age and older, according to Ultromics, the developer of the software. (Image courtesy of Ultromics.)
Citing research submitted to the FDA, Ultromics noted that EchoGo Amyloidosis has 84.5 percent sensitivity and 89.7 percent specificity in diagnosing cardiac amyloidosis in patients with heart failure that are 65 years of age and older.
The company also pointed out that the AI software’s has demonstrated consistent sensitivity rates across different subtypes of amyloidosis such as AL (primary) amyloidosis (84.4 percent), hereditary transthyretin amyloidosis (TTRv) (86.3 percent), and wild-type transthyretin amyloidosis (85.8 percent).
“Improving the detection of cardiac amyloidosis is vital as early detection provides the greatest therapeutic benefit for patients. Novel AI-based diagnostic tools such as EchoGo® Amyloidosis from Ultromics should help facilitate disease identification, particularly in clinics and hospitals restricted by expertise and resource,” noted Sanjiv J. Shah, M.D., the director of the Heart Failure with Preserved Ejection Fraction (HFpEF) Program and the Center for Deep Phenotyping and Precision Medicine in the Institute for Augmented Intelligence in Medicine at the Northwestern University Feinberg School of Medicine.
Recent Videos
Related Content
New Study Examines Short-Term Consistency of Large Language Models in Radiology
November 22nd 2024Article
While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Podcast
Nina 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.
New Study Examines Agreement Between Radiologists and Referring Clinicians on Follow-Up Imaging
November 18th 2024Article
Agreement on follow-up imaging was 41 percent more likely with recommendations by thoracic radiologists and 36 percent less likely on recommendations for follow-up nuclear imaging, according to new research.
