Evaluating the Quality and Understandability of Radiology Report Summaries Generated by ChatGPT: Survey Study
ChatGPT-generated summaries could significantly improve perceived comprehension and satisfaction while accurately reflecting most key information from original radiology reports. Instances of minor omissions and under-/overemphasis were noted in some summaries, underscoring the need for ongoing validation and oversight. Overall, these artificial intelligence-generated, patient-centric summaries hold promise for enhancing patient-centered communication in radiology.
Authors
- Jody Tanabe (ORCID: https://orcid.org/0000-0002-7110-8444)
- David Zander (ORCID: https://orcid.org/0000-0002-0808-307X)
- Abraham Sunshine
- Chen‐Tan Lin (ORCID: https://orcid.org/0000-0002-8678-7945)
- Andrew L. Callen (ORCID: https://orcid.org/0000-0003-2315-7767)
- Justin M. Honce (ORCID: https://orcid.org/0000-0003-3799-2624)
- S. Petrucci (ORCID: https://orcid.org/0000-0002-4977-6833)
- Grace H Honce
Institutions
- Coker College (US)
- University of Colorado Anschutz Medical Campus (US)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2025-06-27
- DOI
- https://doi.org/10.2196/76097
- Citations
- 5
- Primary Topic
- Radiology practices and education
- Type
- article
- Field-Weighted Citation Impact
- 6.80