The use of AI can target the job of first-medical responders when it comes to treating patients who have a stroke.
An artificial intelligence tool has been developed that diagnoses strokes over the phone.
The smart device is better than emergency call handlers at identifying one of the world’s biggest killers, Danish scientists say.
Cases often go unrecognized. Early treatment is vital in improving survival rates.
Lead author Dr. Jonathan Wenstrup, of Copenhagen University Hospital, said: “As one of the first points of contact for patients seeking medical assistance, emergency call handlers play a critical role in facilitating early and accurate stroke recognition.
“Many stroke cases can go undetected at this stage, leading to delays in treatment that can have potentially life-threatening consequences for patients.”
An evaluation metric that assessed the predictive skill of the machine learning technique found it was up to 10 percent more accurate than human experts.
The researchers trained it using data from the Danish Stroke Registry and over 7,000 stroke-related calls made to the Copenhagen Emergency Medical Services between 2015 and 2020.
Dr. Wenstrup said: “With the implementation of this new, cost-effective supporting tool, we can enhance stroke identification by call handlers and ensure more patients receive appropriate and timely care, ultimately improving patient outcomes.”
A stroke occurs when blood supply is cut off to the brain. It is the fourth single leading cause of death in the UK, responsible for 38,000 deaths annually.
Incidence is rising because of the obesity crisis. The condition is a major cause of disability across Europe, affecting more than a million adults a year.
As populations continue to grow and age, the number of people living with stroke is projected to increase by 27 percent by 2047.
Despite this, many strokes can be prevented, and if treated early, the likelihood of a positive outcome can be greatly improved.
The main symptoms include sudden numbness or weakness in the face, arm, or leg, especially on one side of the body.
Others are confusion, trouble speaking, or difficulty understanding speech, trouble seeing in one or both eyes, difficulty walking, dizziness, loss of balance and lack of coordination.
Dr. Wenstrup added: “As with any new tool, further research and development are necessary to improve the framework’s accuracy and expand its capabilities.
“In the future, it may be possible to train the framework directly from the call audio, bypassing the transcription step, as well as incorporating non-word audio – such as a slurred voice – into the training data.
“However, given the promising results of this study, it is already clear that technologies like this have the capability to completely transform stroke diagnosis and care.”
He presented it at the European Stroke Organisation Conference in Munich, Germany.
Produced in association with SWNS Talker