A new study from Oxford University is showing promising results when it comes to judging the effectiveness of new drug treatments for Parkinson’s Disease.
The process includes the use of six sensors placed on the patient that monitor normal daily activity.
The sensors utilize a combination of accelerometers, gyroscopes, and magnetometers to measure the subject’s gait and balance.
These devices are not a cure for Parkinson’s, but a much better evaluator of the progress of the disease and treatments.
Once the data is gathered, scientists utilize Machine Learning algorithms to evaluate the patient data.
Parkinson’s disease is a progressive brain disorder that causes unintended or uncontrollable movements.
It affects the nervous system and the parts of the body controlled by the nerves.
Doctors working on new treatments evaluate their effectiveness through observation which often misses micromovements and small balance issues.
However, the Machine Learning algorithm paired with the sensors is proving much more effective in spotting and categorizing issues.
When applied to undiagnosed older patients, the ML tools and sensors are able to accurately predict patients at risk for Parkinson’s, catching the disease earlier in its progression.
The lead researcher from Oxford, neuroscientist Chrystalina Antoniades, said that the process holds a lot of promise in the diagnosis and treatment of a “plethora of diseases that bring together bioengineering, clinical science, and movement science.”
Wearable tech has made great strides in the last 10 years and a host of solutions have been approved by the FDA to measure everything from blood pressure and breathing rate to skin temp and glucose levels.
The application of machine learning and artificial intelligence on top of the data gathered from these devices promises to be a huge leap forward in medical diagnostics.