Radiology has listed its top cited articles for 2023, the first four of which all addressed the topic of ChatGPT.
In a commentary published on December 12, Radiology Editor-in-Chief Linda Moy, MD, highlighted the top article, which reported that ChatGPT shows promise for the following:
- Simplifying preauthorization workflow
- Summarizing electronic health records
- Improving the interpretability of computer-aided diagnosis systems
- Drafting matter for advocacy projects targeting political, economic, and social decisions
ChatGPT also has the potential to generate fake scientific works and be misused for image fabrication, Moy noted.
The second- and third-most cited articles explored the tool's use in medical writing, while the fourth tasked GPT-4 for post hoc transformation of free-text radiology reports into structured reporting as it related to a multilingual feasibility study.
This year marked the 100th anniversary of Radiology in publication.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
