Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206690,
        author = {ATUL KUMAR SINGH and Sayali Bhosale},
        title = {Evaluating the Impact of Generative AI Summarization on Radiology Report: Turnaround Time and Clinician Comprehension Report},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {2467-2471},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206690},
        abstract = {Background: Rising demand for diagnostic imaging far exceeds the rate of new radiologist recruitment, creating serious professional disutility. Radiologists are overburdened with report writing, which involves sifting through massive amounts of narrative data, delaying evidence-based clinical decision-making by other physicians. 
Objective: This paper aims to establish how much large language models (LLMs) generated, impression sections reduce overall report Turnaround time (TAT) and facilitate downstream clinical comprehension with particular emphasis on minimizing error free clinical interfaces.
Methods: Two-step mixed methods: (1) retrospective AI-based simulation using LLM fine-tuned on radiology reports to estimate efficiency gains in impression-section generation; (2) Prospective randomized vignette trial among referring physicians to assess changes in text-comprehension scores and cognitive workload using standardized information extraction tasks and modified NASA Task Load Index (TLI).
Results: Preliminary analysis suggests that TAT can be reduced by 15-25%. Text comprehension gains were realized via shorter clinician decision time while maintaining near-zero omissions/hallucinations through mandatory human-in-the-loop verification of AI-generated impressions.
Conclusion: LLM-assisted report summarization can substantially reduce administrative burden on radiologists while hastening clinical decision support for other physicians so long as there is a built-in mechanism for physician-level text verification.},
        keywords = {},
        month = {July},
        }