A new tool diagnoses strokes in minutes by analyzing a patient’s speech and facial movements. The iPhone-based app, created by researchers at Houston Methodist Hospital and Penn State, has shown to be as accurate in its diagnosis as an emergency room physician, yet much faster, which is very important to aid in stroke recovery.

“There are millions of neurons dying every minute during a stroke,” said John Volpi, MD, a vascular neurologist and co-director of the Eddy Scurlock Stroke Center at Houston Methodist Hospital. “In severe strokes it is obvious to our providers from the moment the patient enters the emergency department, but studies suggest that in the majority of strokes, which have mild to moderate symptoms, that a diagnosis can be delayed by hours and by then a patient may not be eligible for the best possible treatments.”

Researchers at Houston Methodist and Penn State developed a machine learning model to aid and accelerate the diagnostic process by physicians in a clinical setting. The new model achieved 79 percent accuracy — comparable to diagnostics by emergency room doctors using tests such as CT scans, which can take hours to perform and interpret. The model, however, could achieve this accuracy in as little as four minutes.

Find more information on the tool in a Penn State news release, in coverage on Fox Business News, Interesting Engineering, Science Daily in Upnewsinfo, Futurity.org, Medical Dialogues, Health Europa, dotmed HealthCareBusiness, Fierce Electronics and mHealth Intelligence.

Find details of the research in a paper presented at the 23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), “Toward Rapid Stroke Diagnosis with Multimodal Deep Learning.”