AI-derived myosteatosis measurements from CAC CT scans predict future COPD, outperforming emphysema-based biomarkers.
Key Details
- 1Study used baseline CAC CTs from 5,535 participants in the Multi-Ethnic Study of Atherosclerosis with 20-year follow-up.
- 2AI quantified myosteatosis (low thoracic muscle attenuation) and emphysema-like biomarkers from the same scans.
- 3Participants with myosteatosis (lowest quartile) had a 2.74-fold increased risk for COPD after adjusting for covariates.
- 47.1% of the cohort developed COPD over 20 years; myosteatosis better predicted COPD than emphysema (adjusted HR 2.74 vs 1.5).
- 5Predictive value was independent of traditional risk factors such as age, sex, BMI, smoking, and others.
Why It Matters
This research shows opportunistic use of routinely acquired CAC CT scans to derive prognostic information for future chronic diseases, broadening the impact of imaging AI. Early identification of COPD risk in asymptomatic or low-risk populations could enable interventions before clinical disease develops.
Source
AuntMinnie
Related News
•HealthExec
Survey Reveals Hurdles and Hopes for GenAI Adoption in U.S. Healthcare
A new survey finds high confidence in generative AI's potential among U.S. nurses but a lack of preparedness and governance impedes its impact.
•Radiology Business
Organizational Barriers Impact Adoption of Radiology AI Support Tools
New research highlights that integrating radiology decision support tools faces significant organizational and cultural challenges.
•Radiology Business
AI Automates CPT Coding for Interventional Radiology Procedures
Large language models like XLNet show promise in automating CPT code assignment for interventional radiology procedures.