JMIR Publications

ABSTRACT

Background:

A coordinated system of care is essential to provide timely access to treatment for patients who present with a suspected acute stroke. In Northwestern Ontario (NWO), Canada, resources are limited and healthcare providers often must transfer stroke patients to different hospital locations to ensure access to care within recommended timeframes. However, healthcare providers, who are often situated temporarily (locum) in NWO or are providing care remotely, may lack sufficient information about the most appropriate method for providers to access care for a patient with a time-sensitive condition. Suboptimal decision-making may lead to multiple transfers before reaching definitive stroke care, resulting in poor outcomes and additional cost to the healthcare system.

Objective:

Develop an application to assist healthcare providers in determining the best possible transfer options for a patient with an acute stroke based on the circumstances (such as last time the patient was known to be well, patient’s location, treatment options, and imaging availability) using a comprehensive geomapping navigation and estimation system based on machine learning algorithms.

Methods:

Develop an accurate prediction model using machine learning methods and incorporate those into a mobile application.

Results:

The “NWO Navigate Stroke” system was developed. The system provides accurate results and demonstrates that a mobile app has the potential to be a significant tool for healthcare providers navigating stroke care in NWO, potentially impacting patient care and outcomes.

Conclusions:

The system has a data-driven, reliable, and accurate prediction model while considering all variations, and simultaneously, is linked to all required acute stroke management pathways and tools. The system has been fully tested using historical data, and the next step planned to undergo usability testing with end users.