Abstract
Purpose To evaluate the current evidence comparing artificial intelligence (AI)-generated radiology reports with radiologist-written reports, emphasizing diagnostic accuracy, clinical reasoning, workflow efficiency, and patient safety.
Method A literature review was performed using peer-reviewed articles identified through The University of Texas MD Anderson Cancer Center Research Medical Library. Studies evaluating AI-generated radiology reports were analyzed using AI-assisted thematic synthesis to identify recurring patterns related to report quality, diagnostic performance, and clinical implementation.
Results The literature consistently identified three overarching themes: (a) AI-generated reports demonstrated improvements in structured reporting and factual consistency but exhibited variable diagnostic accuracy; (b) current AI systems had difficulty recognizing subtle imaging findings, incorporating clinical context, and applying nuanced diagnostic reasoning; and (c) successful implementation depended on maintaining radiologist oversight while integrating AI into existing clinical workflows.
Discussion Although AI-generated reporting has advanced considerably, the evidence indicates that these systems currently function best as decision-support tools rather than independent report generators. Improvements in efficiency and report standardization must be balanced with the need for accurate interpretation, contextual reasoning, and patient safety. Radiologists continue to provide the clinical judgment required to interpret complex findings, resolve ambiguity, and ensure high-quality patient care.
Conclusion AI has the potential to enhance radiology reporting by improving workflow efficiency and supporting report generation. However, continued refinement, rigorous clinical validation, and ongoing radiologist oversight remain essential before AI-generated reports can be relied upon for independent clinical practice.
DOI
https://doi.org/10.52519/00275
Graduation Date
Summer 8-7-2026
Document Type
Poster
Degree Name
Master of Science in Radiologic Science
Program
The School of Health Professions
Faculty Advisor
Kevin R. Clark
Director, Graduate Program
William A. Undie
Dean
Kimberly Hoggatt Krumwiede
Recommended Citation
Webb, L. Comparing AI-Generated and Human-Written Radiology Reports: Evidence from the Literature. [poster]. University of Texas MD Anderson Cancer Center; 2026. https://doi.org/10.52519/00275
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
