South KoreaHealthcare and life sciences2026 – ongoingAsan Medical Center
AI speech recognition for radiology reports
Asan Medical Center reported about 3 minutes saved per radiology report with speech AI
Problem
Turning radiologists' spoken findings into written reports created transcription work. Report volumes also placed demands on staff outside normal working hours.
Approach
Asan Medical Center used AI speech recognition to convert dictated radiology findings into text. The hospital compared working time before and after implementation. Its AI Innovation Support Office, established in February 2026, managed AI registration and evaluation after deployment.
Results
Takeaway
New staff benefited more than experienced staff. The hospital's evaluation identified hardware and staff training as important areas for improvement.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- Production and qualityInternal work and knowledge management
- Innovation type
- Process innovation
- AI technology
- Conversational and voice AI
- Adoption
- Vendor solution
- Evidence
- Company's own claim
Sources
Source summaries
Hospital AI Innovation Support Office head Dong-Hyun Yang described the hospital's deployed systems and evaluation practices. He reported about 3 minutes saved per radiology report and almost no night or weekend work for transcription staff despite increased report volumes.
Full details are in the original sources.