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
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.