ChatGPT can significantly speed up and improve accuracy in ICD-10 coding of PET/CT exam reports.
Key Details
- 1Study at Charité University Hospital assessed ChatGPT for ICD-10 coding of 100 fictitious PET/CT reports.
- 2ChatGPT-assisted coding reduced median coding time to 8 seconds vs. 135 seconds for manual coding.
- 3ChatGPT outperformed manual coding in accuracy, especially at fourth/fifth ICD-10 code characters (6 errors vs. 17, p = 0.035).
- 4Centers performing 30 PET/CT scans daily could save at least one clinician hour per day using ChatGPT.
- 5The method may be applicable to other modalities like CT or MRI per the researchers.
- 6Awarded RSNA Trainee Research Prize in Resident category.
Why It Matters
Automated coding support with AI like ChatGPT can lower clerical workload, reduce burnout risk, and enhance both productivity and accuracy for radiology professionals. Scalable solutions may improve efficiency across diverse imaging departments.
Source
AuntMinnie
Related News
•AuntMinnie
AI Enhancement Dramatically Improves Quality of Suboptimal Chest CTs
AI-powered image enhancement significantly boosts the diagnostic quality of suboptimal chest CT and CTPA studies.
•AuntMinnie
AI Enables Safe 75% Gadolinium Reduction in Breast MRI Without Losing Sensitivity
AI-enhanced breast MRI with a 75% reduced gadolinium dose maintained diagnostic sensitivity comparable to full-dose protocols.
•Cardiovascular Business
Deep Learning AI Model Detects Coronary Microvascular Dysfunction Via ECG
A new AI algorithm rapidly detects coronary microvascular dysfunction using ECGs, with validation incorporating PET imaging.