A new tool created by researchers at Penn State University in the United States could diagnose a stroke based on abnormalities in a patient’s speech ability and facial movements, with the same accuracy of an emergency room doctor, all within minutes from an interaction with a smartphone.

Professor James Wang and his colleagues developed a machine learning model to potentially speed up the diagnostic process for stroke victims.

“When a patient experiences symptoms of a stroke, every minute counts,” Prof. Wang explained.

“But when it comes to diagnosing a stroke, emergency room physicians have limited options: send the patient for often expensive and time-consuming radioactivity-based scans or call a neurologist — a specialist who may not be immediately available — to perform clinical diagnostic tests.

“Currently, physicians have to use their past training and experience to determine at what stage a patient should be sent for a CT scan,” said Prof. Wang.

“We are trying to simulate or emulate this process by using our machine learning approach.”

The team’s approach is the first to analyse the presence of stroke among actual emergency room patients with suspicion of stroke by using computational facial motion analysis and natural language processing to identify abnormalities in a patient’s face or voice, such as a drooping cheek or slurred speech.

To train the computer model, the researchers built a dataset from more than 80 patients experiencing stroke symptoms.

Each patient was asked to perform a speech test to analyse their speech and cognitive communication while being recorded on an Apple iPhone.

The researchers found that its performance achieved 79 per cent accuracy — comparable to clinical diagnostics by emergency room doctors, who use additional tests such as CT scans. 

However, the model could help save valuable time in diagnosing a stroke, with the ability to assess a patient in as little as four minutes.

Will AI modelling eventually be able to diagnose all diseases and conditions? Are you hopeful that AI may eventually provide early warning signals for diseases?