Artificial intelligence (AI) firm Viz.ai and management services organization TeleSpecialists are highlighting data presented February 8 at the International Stroke Conference (ISC) showing reduced patient arrival times from the use of Viz.ai's software.
The data come from the Validation of AI to Limit Delays in Acute Stroke Treatment and Endovascular Therapy (VALIDATE) study. It showed that hospital use of Viz.ai's coordination platform was linked to a 39.5-minute reduction in patient arrival to time of first contact with the neurointerventionalist for need of potential emergency endovascular treatment, according to the companies.
The study analyzed data extracted from acute stroke consultations seen by emergency department neurologists from TeleSpecialists. This included departments from 166 facilities in 17 states. The study also looked at a total of 14,116 patients from two groups: those seen in hospitals using AI (n = 8,557) and those seen in hospitals not using AI (n = 5,559).
The study found that the median door-to-neurointerventionalist-notification time for AI was 50 minutes compared with the median time for non-AI at 89.5 minutes (p < 0.001). It also found statistically significant improvement in time to large clot recognition and contact with the neurointerventional team at Viz-enabled centers (p < 0.01). This was regardless of whether the center did or did not have thrombectomy capabilities, Viz.ai said.
![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)
