Rewrite this content
Worldwide over ten million people suffer from Parkinson’s disease. It is a neurodegenerative pathology, with a slow but progressive evolution, which mainly involves some functions such as the control of movements and balance. Given that it belongs to a group of diseases classified as “movement disorders”, it tends to be identified by the most significant symptoms linked precisely to the progressive loss of motor functions and by disorders such as hand tremorsmuscle stiffness and balance problems. Yet a study just published on Applied Sciences explains now that among the very first signs of the onset could be language changes.
The survey, signed by the Kaunas University of Technology, actually stems from previous studies on other motor function disorders which had discovered how an altered linguistic property often occurred before further symptoms appeared, those most characterizing the various pathologies. There is no cure for Parkinson’s but of course diagnosing it in time can help contain neurological problems through various therapies. The causes, however, are not entirely clear. Although experts converge in indicating both genetic reasons and those linked to toxic factors of exposure, for example for certain uses.
The interesting aspect of the study is that it exploited systems of artificial intelligence to analyze the language patterns of people, obviously Lithuanian-speaking volunteers. Specifically, participants entered a soundproof booth where a microphone recorded the speech of people with and without Parkinson’s. The algorithm has heard the speech and has somehow “learned” to perform speech processing. As a result, people with early-stage Parkinson’s disease tend to talk more slowly and monotonously, more fragmented. The change can be subtle at first and difficult to detect with the human ear, which requires the help of artificial intelligence. As the disease progresses, the patient’s language becomes more compromised with more evident stuttering, confused pronunciation of words and loss of pauses between them.
The research group of the University of Kaunas has developed a system to detect changes in advance, although optimism has to wait: according to experts it is too early to replace routine diagnostic tests with their system, at least on a large scale. “We are not creating a replacement for a routine examination of the patient: our method is designed to facilitate early diagnosis of the disease and to monitor the effectiveness of the treatment,” explains Rytis Maskeliūnas, researcher at Kaunas University of Technology. The algorithm does not require particular calculation skills and could soon be integrated into an application available to specialists.
The next step the study authors are taking is clearly to broaden the scale of the investigation, involving more and more patients in their experiments. With more data, the algorithm will continue to learn different patterns of human speech ea detect the signs of Parkinson’s even earlier. Another consideration they are evaluating is precisely whether the algorithm would work in real time in a doctor’s office or at a patient’s home instead of in a laboratory.
More stories from Vanity Fair that may interest you
Parkinson’s disease: those early signs not to be underestimated
Don’t call me disease: Parkinson’s told in photos
Write an article about The symptom that may be an early sign of Parkinson’s disease