Scholarlink

Background <p>Radiologist burnout affects approximately 40% of US radiologists. Large language models (LLMs) may improve workflow efficiency, but real-world implementation data are limited.</p> Objective <p>To evaluate the impact of an LLM-assisted workflow on radiologist efficiency using the Unified Theory of Acceptance and Use of Technology (UTAUT) framework.</p> Design, setting, and participants <p>HIPAA-compliant, IRB-approved retrospective cohort study of a single fellowship-trained abdominal radiologist exploratory study at Mayo Clinic Arizona. We compared baseline (January–April 2024) and post-implementation (December 2025–February 2026) periods. A custom generative pre-trained transformer was developed using ChatGPT Enterprise Model 5.2 Thinking with disease-specific templates.</p> Main outcome measures <p>Inter-study interval time, used as a proxy for interpretation time, compared using Wilcoxon rank-sum tests with Bonferroni correction (α = 0.01). UTAUT constructs assessed: performance expectancy (efficiency), effort expectancy (training burden), facilitating conditions (infrastructure), and behavioral intention (satisfaction).</p> Results <p>We analyzed 609 studies (495 CT, 114 MRI). LLM assistance significantly reduced inter-study intervals for outpatient CT with contrast (23.0 vs. 13.0&#xa0;min; difference 10&#xa0;min; <i>p</i> = 0.0021) and without contrast (18.5 vs. 7.0&#xa0;min; difference 11.5&#xa0;min; <i>p</i> = 0.0017). No improvement occurred for MRI with contrast (14.0 vs. 16.0&#xa0;min; <i>p</i> = 0.2808) or without contrast (14.0 vs. 7.0&#xa0;min; <i>p</i> = 0.0889). The radiologist reported improved work-life balance for CT but neutral satisfaction for complex MRI templates. Training required 10&#xa0;h over 5 days.</p> Conclusions <p>LLM-assisted workflow reduced inter-study interpretation times for standardized CT studies and no clear efficiency benefit was observed for MRI in this small implementation sample, when interpreted through a UTAUT lens, particularly on performance expectancy and task–technology fit as adoption drivers. Efficiency gains may reduce documentation burden when tools align with task complexity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Large language model–assisted radiology reporting in a single-radiologist implementation: a retrospective cohort study interpreted through a UTAUT lens

  • 期刊论文

  • 发表日期：

    2026年4月20日

查看全文
  • Nelly Tan

摘要

Background

Radiologist burnout affects approximately 40% of US radiologists. Large language models (LLMs) may improve workflow efficiency, but real-world implementation data are limited.

Objective

To evaluate the impact of an LLM-assisted workflow on radiologist efficiency using the Unified Theory of Acceptance and Use of Technology (UTAUT) framework.

Design, setting, and participants

HIPAA-compliant, IRB-approved retrospective cohort study of a single fellowship-trained abdominal radiologist exploratory study at Mayo Clinic Arizona. We compared baseline (January–April 2024) and post-implementation (December 2025–February 2026) periods. A custom generative pre-trained transformer was developed using ChatGPT Enterprise Model 5.2 Thinking with disease-specific templates.

Main outcome measures

Inter-study interval time, used as a proxy for interpretation time, compared using Wilcoxon rank-sum tests with Bonferroni correction (α = 0.01). UTAUT constructs assessed: performance expectancy (efficiency), effort expectancy (training burden), facilitating conditions (infrastructure), and behavioral intention (satisfaction).

Results

We analyzed 609 studies (495 CT, 114 MRI). LLM assistance significantly reduced inter-study intervals for outpatient CT with contrast (23.0 vs. 13.0 min; difference 10 min; p = 0.0021) and without contrast (18.5 vs. 7.0 min; difference 11.5 min; p = 0.0017). No improvement occurred for MRI with contrast (14.0 vs. 16.0 min; p = 0.2808) or without contrast (14.0 vs. 7.0 min; p = 0.0889). The radiologist reported improved work-life balance for CT but neutral satisfaction for complex MRI templates. Training required 10 h over 5 days.

Conclusions

LLM-assisted workflow reduced inter-study interpretation times for standardized CT studies and no clear efficiency benefit was observed for MRI in this small implementation sample, when interpreted through a UTAUT lens, particularly on performance expectancy and task–technology fit as adoption drivers. Efficiency gains may reduce documentation burden when tools align with task complexity.