Algorithm Boosts stroke ‍Triage, Improves Patient Outcomes

‍ ⁢ Updated June 03, 2025

A novel algorithm significantly improves⁢ prehospital stroke ‍triage, leading to better patient outcomes, according to a new study presented at‍ the European‌ Stroke Organization Conference (ESOC)‌ 2025. The computer⁣ modeling study across the U.S. found the algorithm more accurately directs patients to centers equipped for endovascular therapy (EVT).

Dr. Santiago Ortega-Gutierrez, clinical professor at the University of ​Iowa, who led the MAP-STROKE‍ study, said the new Bayesian predictive triage algorithm improves stroke-related neurologic ⁢recovery by speeding up the time ⁤to endovascular therapy, especially for patients with large ⁣vessel occlusion (LVO) strokes. He noted the improvement was most noticeable ⁢in ⁢rural areas.

The algorithm could help approximately 10,000 additional stroke patients⁤ each ‍year achieve ‌good neurological recovery in the U.S., Ortega-Gutierrez estimates.

Stroke is a⁣ leading cause of death in⁢ the U.S., ⁣with LVO strokes accounting for a majority⁤ of stroke-related disabilities. EVT can significantly ⁣improve ‌outcomes, but only about 30% ⁣of the U.S.population lives near a center that offers ⁣it.

The current American Heart Association (AHA) guidelines advise transporting suspected LVO patients to ‍an EVT-capable center within 30 minutes (45 minutes in rural areas). ⁢Otherwise,patients go to the nearest hospital and may require⁢ transfer.

The new‌ algorithm considers factors such as age, gender, blood pressure, stroke severity, medications, and location to estimate stroke type, recommend therapy, and identify the optimal hospital using ‌GPS and web-based mapping.

Researchers simulated over 115 ⁣million​ stroke scenarios,drawing on ⁣data‌ from previous acute stroke studies. The study’s primary endpoint was the percentage of patients achieving a good functional outcome, defined as​ a modified Rankin scale score of 0-2 at 90 days.

The results showed that 58.6% of patients routed using the new algorithm achieved good functional outcomes,⁤ compared to 57.1% under AHA guidelines and 56.5% taken to‌ the nearest hospital.

The algorithm notably benefits patients experiencing an LVO,reducing time to EVT by an ‍average of 90 minutes compared ⁢with guideline-adherent routing and by 136 minutes compared with nearest hospital transport. In‍ rural areas, the time to EVT was reduced by 166 minutes​ compared with guideline-based transport,​ leading to a 7.8% increase in good⁤ neurologic outcomes.

“In the MAP-STROKE study, we showed that a novel Bayesian predictive triage algorithm could improve stroke-related neurologic recovery. These improvements were primarily driven by quicker time to endovascular therapy for patients with large vessel occlusion [LVO] strokes, and ‌the magnitude of improvement ‍was most pronounced in rural areas,” Ortega-Gutierrez said.

However, the ⁢algorithm had a slight negative effect​ on patients without LVO strokes, with a‍ 14-minute delay in reaching the hospital and a 0.12% reduced ‌chance of a good functional outcome.Patients with hemorrhagic stroke⁤ also experienced a 13-minute delay.

“The large ⁢benefit for large vessel occlusion patients vastly outweighs the slight disadvantage to the non–large vessel occlusion ⁤patients. By​ using this algorithm,we believe we will be improving the outcomes of the sickest with minimal repercussions on the less sick,” Ortega-Gutierrez said.

jesse Dawson, professor of stroke medicine at Queen Elizabeth University Hospital, emphasized the importance of the findings, while Guillaume​ Turc, professor ​of neurology at ⁢Université de Paris, called the trial innovative but ​cautioned that the findings rely on certain assumptions and need confirmation.

What’s next

The researchers are planning a real-world clinical⁤ trial to confirm these computer modeling results and‌ further refine the​ stroke triage process.