Researchers showed AI can detect tuberculosis from mobile photos of analog chest x-rays in low-resource settings.
Key Details
- 1Study used 498 photographed chest x-ray films from Ethiopia and Guinea-Bissau for TB diagnosis comparison.
- 2AI tool (qXR, Qure.ai) identified 81 TB cases vs. 50 and 99 by two radiologists.
- 3AI achieved sensitivity of 76.5% and specificity of 85.9% (AUC 0.84) compared with lab-confirmed cases.
- 4AI performance was comparable to experienced radiologists in detecting TB.
- 5Study highlights mobile-based AI screening in areas with limited digital imaging resources.
- 6Moderate inter-reader agreement (kappa = 0.45–0.56) between radiologists and AI.
Why It Matters
This work suggests mobile phone-based AI can bridge diagnostic gaps in TB screening where digital radiology resources are lacking, expanding access to timely diagnosis and care. If validated, this approach could help advance global health initiatives against tuberculosis, particularly in low-income countries.
Source
AuntMinnie
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•Cardiovascular Business
Radiology Maintains Lead in FDA-Cleared AI Algorithms, Cardiology Follows
Radiology remains the top specialty for FDA-cleared AI, with cardiology as a strong second, particularly in cardiovascular imaging.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.