The American College of Radiology (ACR)'s Data Science Institute (DSI) has drafted a model application programming interface (API) aimed at making it easier for artificial intelligence (AI) software developers to create algorithms for healthcare applications.
Created in collaboration with industry, organizational, and other partners, the draft model API will assist with standardizing communications to newly created AI models, enabling them to be platform-agnostic, according to the institute.
The ACR DSI said it's seeking public comments on the model API, as well as interest in evaluating a proof-of-concept implementation. The draft API can be found on the ACR DSI's website, and comments will be accepted until August 14.
![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)
