Ambulance Routing for Optimizing Stroke Patient Outcomes

In the absence of a comprehensive stroke policy, stroke patients are typically routed to the nearest hospital, a method that fails to account for the varying capabilities of hospitals to treat strokes of different severities. These patients, when routed to a facility incapable of providing necessary and timely treatment, often experience critical delays in receiving appropriate care. Given the urgent nature of stroke treatment, where a patient loses on average 2 million neurons every minute, such delays can significantly diminish the chances of a favorable patient outcome. This paper introduces an approach that formulates the patient-routing problem as a Markov decision process (MDP). We integrate patient information including location, time from stroke onset, and stroke type (ischemic vs. hemorrhagic) to generate an optimal routing decision to maximize the probability of a positive patient outcome. Our research demonstrates that the implementation of a data-driven, patient-specific stroke policy could significantly improve quality of stroke care, fostering equitable healthcare access and potentially establishing a new standard in emergency stroke response.