An AI model achieved high accuracy in identifying esophageal achalasia on chest x-rays, surpassing physician performance.
Key Details
- 1Deep-learning AI model trained using 207 x-rays from 144 achalasia patients and 240 controls.
- 2Validation performed on a separate test set: 17 achalasia and 64 control x-rays.
- 3Model achieved AUC of 0.964, sensitivity 0.941, and specificity 0.891.
- 4Outperformed four physicians on the same test cases.
- 5Achalasia is a rare disorder with diagnosis often delayed by 6.5 years on average.
- 6Noninvasive screening using existing chest x-ray data may enable earlier diagnosis.
Why It Matters
Utilizing routine chest x-rays and AI, clinicians could screen for achalasia in a noninvasive way, potentially reducing diagnostic delays and improving patient outcomes. This highlights AI's growing role in enhancing radiological workflows.
Source
AuntMinnie
Related News
•Radiology Business
AI Automates Head CT Reformatting, Improving Efficiency and Consistency
Researchers at UC Irvine used deep learning to automate head CT reformatting, improving workflow standardization and efficiency.
•Radiology Business
Google's Gemini Outperforms Providers in Communicating IR Procedures
Large language models like Google's Gemini demonstrate higher accuracy and greater empathy than human providers when answering patient questions about interventional radiology.
•AuntMinnie
Comparing False-Positive Findings: AI vs. Radiologists in DBT Screening
AI and radiologists differ in the types and patient characteristics of false-positive findings in digital breast tomosynthesis breast cancer screening.