A new AI tool has been developed by University of Colorado Anschutz (CU Anschutz) faculty members that summarizes patient electronic health records (EHRs), facilitating a clearer picture of a patient’s medical needs.
Nikhil Madhuripan, MD, assistant professor of radiology at the CU Anschutz School of Medicine and interim section chief of abdominal imaging, and Aakriti Pandita, MD, assistant professor of medicine, spent two years creating a tool they call AIDA, according to the university.
AIDA is an AI assistant that works with Epic hospital charting software and performs contextual EHR data extraction for radiologists.
Pandita and Madhuripan said that they asked clinicians what they wanted from AI when they first began work on the tool. The overwhelming response was a request for help in summarization, but no such tool existed for radiologists.
An EHR can be a “massive repository of data,” according to Madhuripan and Pandita, and accessing all of the information needed to make diagnostic and care decisions can be a cumbersome process. AIDA was designed to efficiently sort, filter, and summarize important data in the EHR, saving radiologists time and improving the quality of their work, its developers said.
Thus far, 18 radiologists have piloted AIDA; their feedback has been overwhelmingly positive, according to Madhuripan and Pandita, who said they will continue to refine AIDA and its interface.
They added that they hope to widen access to AIDA in the U.S. following a clinical trial. Additionally, AIDA may be adapted for other specialties in the future.
Read more about AIDA here.














![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&fit=crop&h=112&q=70&w=112)



