A deep learning model using echocardiography accurately detects cardiac amyloidosis, outperforming traditional methods.
Key Details
- 1AI model trained on echocardiography video clips from 2,612 patients across multiple sites and ethnic groups.
- 2External validation performed on 18 global sites; included 597 amyloidosis cases and 2,122 controls.
- 3Achieved AUROC of 0.93 (after excluding 13% uncertain predictions), sensitivity of 85%, specificity of 93%.
- 4Performance was consistent across amyloidosis subtypes and various subgroups.
- 5The AI model outperformed transthyretin cardiac amyloidosis (TTR-CA) score (AUROC = 0.73) and wall thickness scoring (AUROC = 0.8).
- 6Ultromics employees contributed and funded the study.
Why It Matters
This work demonstrates the robust, generalizable performance of AI to enhance echocardiographic detection of cardiac amyloidosis, surpassing current clinical scoring tools and suggesting real-world impact for earlier and more accurate diagnosis in routine practice.
Source
AuntMinnie
Related News
•AuntMinnie
Radiology Receives Declining Share of Industry Research Funding
Radiologists received only 1.1% of industry-funded research payments in 2024, with a continuing downward trend.
•AuntMinnie
GPT-4o AI Matches Radiologists in Follow-Up Imaging Recommendations
GPT-4o matched the performance of experienced radiologists and surpassed residents in recommending follow-up imaging from routine radiology reports.
•Cardiovascular Business
AI Leverages Head CTs for Automated Heart Risk Assessments
AI models can turn routine head CT scans into automated cardiovascular risk assessments, expanding the utility of radiology studies.