Alcohol withdrawal is no joke. A new app aims to identify whether a person is actually suffering from withdrawal of if he or she is faking symptoms to obtain drugs.
Patients often arrive at the emergency room with tremors and other withdrawal symptoms from quitting alcohol cold turkey. Usually withdrawal is treated with benzodiazepine drugs, which are also used to treat issues such as anxiety.
A tremor is the most common clinical sign of alcohol withdrawal, however many alcoholics will fake a tremor to get benzodiazepines. This could be very dangerous when mixed with other drugs, especially alcohol and opiates.
The problem with tremors is that it can be very difficult for doctors to discern whether a patient's tremor is real or fake and even within groups of doctors with a lot of experience, the estimates vary.
Researchers at the University of Toronto developed an app that measures tremor strength in order to guide doctors in determining whether a patient's tremor is real or fake. Their app was able to discern real versus fake tremors with the skill of a junior physician.
The researchers' studies showed that tremors in patients suffering from genuine alcohol withdrawal had a peak frequency of seven cycles per second. Only 17 percent of the nurses who tried to fake a tremor were able to produce the same frequency.
The app uses the iPod's built in accelerometer to measure the frequency of the tremor. It measures the patient's tremor frequency for 20 seconds on each hand.
"The exciting thing about our app is that the implications are global," said Bjug Borgundvaag, one of the app developers. "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."
He also hopes this app will be able to help staff members who do not have training in discerning the difference between a real tremor and a fake tremor.
So far, the app has been tested on about 80 patients, but more testing and validation of the data is needed.
"We have just begun to scratch the surface of what is possible by applying signal processing and machine learning to body connected sensors," said Parham Aarabi, another one of the app's developers. "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."
