Large Language Model–Enabled Editing of Patient Audio Interviews From “This Is My Story” Conversations: Comparative Study
An AI-based editing pipeline can generate TIMS audio summaries with comparable content and audio quality to novice human editors with one hour of training. AI significantly reduces editing time and removes the need for manual training; with further validation, it could offer a solution to scale TIMS to a large range of health care settings.
Authors
- Jonathan Wang (ORCID: https://orcid.org/0000-0003-2839-0699)
- Sampath Rapuri (ORCID: https://orcid.org/0000-0002-4747-5623)
- Eduardo Reyes
- Elizabeth Tracey (ORCID: https://orcid.org/0000-0001-8134-5016)
- Jason Wilson (ORCID: https://orcid.org/0000-0003-2111-2821)
- Catalina Gómez (ORCID: https://orcid.org/0000-0003-1536-3421)
- Christopher Perry
- Bikram Bains
- Edgar Robitaille (ORCID: https://orcid.org/0009-0005-9741-1598)
- Arnav Khera
Institutions
- Johns Hopkins University (US)
- Johns Hopkins Medicine (US)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-11-04
- DOI
- https://doi.org/10.2196/80205
- Primary Topic
- Radiology practices and education
- Type
- article
- Field-Weighted Citation Impact
- 0.00