Dear Healthcare Informatics Insider,
Anyone who uses a speech recognition dictation system knows how easy it is to overlook an error made by a speech engine when proofreading a document, especially if the error is a single-word omission. However, the implications can be profound if the document being prepared is a radiology report of a diagnostic exam.
When radiologists at Cork University Hospital and their oncologist colleagues began to realize some of the reports of cancer patients' images contained errors that could affect patient management, they investigated. At RSNA 2012, Dr. Maria Twomey reported what she and her colleagues discovered and the changes they made.
Another concern anyone involved with healthcare informatics should be aware of is the level of security protecting a RIS, PACS, modalities, and archives. Read what happened to an Australian clinic.
The ability of healthcare IT to span continents has made virtual meetings to discuss radiotherapy treatment plans a reality. Chartrounds is a free-of-charge virtual meeting service in which radiation oncologists from anywhere in the world can present challenging cases to expert specialist consultants for advice and to discuss with other vetted participants. Find out how your colleagues can benefit from participating.
Also, don't overlook two new white papers published by the Integrating the Healthcare Enterprise (IHE) Radiology Technical Committee.
Finally, if you have information to share that will be of interest to the Healthcare Informatics Digital Community, please do contact me.
![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.auntminnieeurope.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)
