App distinguishes real from fake tremors in alcohol withdrawal patients

Date: Aug-29-2014 Alcohol withdrawal syndrome is a potentially life-threatening situation that can be easily treated with a class of sedatives called benzodiazepine drugs. However, such drugs are often abused and can be dangerous when mixed with alcohol and opiates, making doctors reluctant to prescribe them. Now, researchers from the University of Toronto in Canada have created a phone app that can predict whether a patient's alcohol tremors are authentic or fake.

"We have just begun to scratch the surface of what is possible by applying signal processing and machine learning to body connected sensors," says Prof. Parham Aarabi of the team's new tremor-detecting phone app.

Though tremors in the hands and arms are the most common signs of alcohol withdrawal, judging the severity of such tremors is tricky and requires quite a bit of medical expertise.

Because chronic alcohol abusers often claim to be in withdrawal in order to receive benzodiazepines, it is important for clinicians to accurately determine whether the patient is in withdrawal or faking it.

Health care workers have had no means of objectively determining whether a patient is genuinely in withdrawal, so Narges Norouzi and Profs. Bjug Borgundvaag and Parham Aarabi worked to develop the first app to provide guidance on tremor strength.

The researchers, who are from Toronto's Schwartz/Reisman Emergency Medicine Institute at Mount Sinai Hospital, St. Michael's Hospital and Women's College Hospital, say their app shows promise in making consistent predictions about whether a tremor is real or not.

Norouzi and her team will present their work today at the International Conference of the IEEE Engineering in Medicine and Biology Society in Chicago, IL.

"The exciting thing about our app is that the implications are global," says Prof. Borgundvaag. "Alcohol-related illness is commonly encountered not only in the emergency room, but also elsewhere in the hospital, and this gives clinicians a much easier way to assess patients using real data."

'There's so much work to do in this field'

The team tested their app on 49 patients who presented to the emergency room with tremors and on 12 nurses who attempted to mimic tremors. They say that three quarters of patients with authentic tremors had an average peak frequency higher than seven cycles per second.

And only 17% of the nurses who tried to fake a tremor were able to produce one with an average peak frequency that was above seven cycles per second, which suggests this could be the threshold for determining real tremors from fake ones.

Using data from an iPod's built-in accelerometer, the app measures tremor frequency for 20 seconds in both hands.

Clinicians filmed patients' hand tremors while using the app in the emergency room and later showed the footage to doctors. The video below shows the app in action along with a description for its use:

Though the app was able to assess tremor strength with accuracy similar to that of junior physicians, Norouzi says more senior doctors were better able to judge the symptoms. She plans to continue to sharpen the app and compare its performance with subjective assessments of doctors.

"There's so much work to do in this field," she says. "There is other work out there on Parkinson's tremors, but much less on tremors from alcohol withdrawal."

Prof. Aarabi says:

"We have just begun to scratch the surface of what is possible by applying signal processing and machine learning to body connected sensors. As sensors improve and algorithms become smarter, there's a good chance that we may be able to solve more medical problems and make medical diagnosis more efficient."

Prof. Borgundvaag adds that their app could help withdrawal management staff - who do not usually have clinical training - assess which patients should go to the emergency department for further treatment.

"We think our app has great potential to improve treatment for these patients overall," he says.

Written by Marie Ellis

View all articles written by Marie, or follow her on:

Courtesy: Medical News Today Note: Any medical information available in this news section is not intended as a substitute for informed medical advice and you should not take any action before consulting with a health care professional.