A research team of neurologists and engineers led by RMIT University in Melbourne recently developed a novel screening test app which could help in the early detection of severe COVID-19 and Parkinson’s diseases with just the use of people’s voice recordings.
Parkinson’s is a degenerative brain condition which is difficult to diagnose because individual symptoms may vary. Some common symptoms include tremor, imbalance, slow movement, and rigidity. Presently, Parkinson’s can be diagnosed through a neurology evaluation which takes about 90 minutes.
Using artificial intelligence, the smartphone app records the user’s voice, and takes 10 seconds to reveal the possibility of having Parkinson’s disease, and if they should be referred to a neurologist.
Professor Dinesh Kumar, lead researcher from RMIT’s School of Engineering, stated that the simple screening test made it ideal for a national screening program.
‘Early detection, diagnosis and treatment could help manage these illnesses, and so making screening faster and more accessible is critical.
This research will allow a non-contact, easy-to-use and low-cost test that can be performed routinely anywhere in the world, where the clinicians can monitor their patients remotely.
It could also promote a community-wide screening program, reaching people who might not otherwise seek treatment until it’s too late,’ said Kumar.
The results of the research are published in IEEE Access, Computers in Biology and Medicine, and IEEE Journal of Translational Engineering in Health and Medicine.
The voices of people who have Parkinson’s disease often change as a result of tremor, slowness (also known as bradykinesia), and rigidity. This assessment can be done by expert clinicians, but it can be challenging because of the natural differences in people’s voices.
Kumar stated that previous attempts to design a computerized voice assessment to detect Parkinson’s diseases were unsuccessful because of the differences in people’s voices.
‘As part of our research, we used voice recordings of people with Parkinson’s and a controlled group of so-called healthy people saying three sounds- A, O and M— which is similar to the Hindu meditation chant,’ said Kumar.
‘These sounds result in a more accurate detection of the disease. Again, due to large differences in people’s voices, pulmonary disease is difficult to recognize in its early stages,’ he said.
‘We have overcome this limitation with the choice of those same three sounds and the AI method of analysis we’ve developed.’
The system is trained to identify the diseases before it performs an analysis of the voice. Next, the software compares the results against existing samples of voices of people that have Parkinson’s disease against those that do not.
Dr. Quoc Cuong Ngo, co-researcher from RMIT’s School of Engineering, stated that the novel technology was faster and more efficient than any other AI-based approach.
‘Our screening test app can measure, with great precision, how the voice of someone with Parkinson’s disease of person at high risk of hospitalization from COVID-19 is different from health people,’ he said.
In the future, the team aims to perform a large observational study to detect the progression of the pulmonary and Parkinson’s diseases.
‘We are also keen to test the efficacy of this technology for other diseases, such as other neurological conditions and sleep disorders,’ said Kumar.
‘We are looking for a commercial partner and clinical partner ahead of a clinical trial planned for next year.’
By Marvellous Iwendi.
Source: News (Medical & Life Sciences)