Parkinson, the diagnosis with the analysis of the voice to intercept the symptoms before the tremors – time.news

by time news
Of Christine Brown

Lithuanian scientists have developed an algorithm that can recognize early-onset vocal changes. In the future, the technology will also be in an app

Over ten million people worldwide live with Parkinson’s, a slowly but progressively evolving neurodegenerative disease that affects functions such as movement control and balance. There is no cure, but if symptoms are caught early the disease can be controlled. THE early symptoms non-motors can manifesti up to ten years before diagnosis of the disease. By the time characteristic Parkinson’s symptoms such as tremors or stiffness appear, half of the dopamine-producing neurons are already dead. Gianni Pezzolineurologist, president of the Italian Parkinsonian Association and of the Grisons Foundation for Parkinson’s Disease.

Difficulty in speech

One of these symptoms characterized by the
a difficulty pronouncing words
. The voice gradually becomes more weakis often monotonous, with difficulty pronouncing words and sometimes opening the mouth. Typically the patient speaks in a manner less expressive, slower, more fragmented and it is not always easy to realize it with the naked ear. Hoarseness, stuttering, slurred pronunciation of words, and loss of pauses between words become more evident as the disease progresses. The listener often finds himself having to ask to raise his tone because he can’t hear.

The changes in language are gradual and a group of researchers from the Kaunas University of Technology (KTU), Lithuania together with colleagues from the University of Health Sciences have worked precisely to try to identify early symptoms of Parkinson’s disease using speech dataChanges in speech often show up much earlier than impaired motor function, which is why impaired speech could be one of the earliest signs of the disease he says Ritis Maskeliūnas, researcher at the Department of Multimedia Engineering of the KTU. Today, with the advance of technologies it is becoming possible to extract more and more information from the spoken language and the Lithuanian working group used theartificial intelligence to analyze and evaluate speech signals and calculations are performed in seconds, thus facilitating diagnosis. We are not creating an alternative route to the necessary routine examinations – our method designed to facilitate early diagnosis of the disease and to monitor the effectiveness of treatment, says Maskeliūnas.

In the future an app

For now, the algorithm created (the study published in Applied Sciences) has only been tested on patients diagnosed with Parkinson’s. Our system can distinguish people with Parkinson’s from healthy people using a cvocal broad explains Cyprus Pribuhisi, professor of Otolaryngology and one of the authors of the study. In a soundproof booth, a microphone was used to record speech given by people with Parkinson’s and healthy people. An artificial intelligence algorithm has learned to process the signal by evaluating the recordings. The researchers point out that the algorithm does not require particularly powerful hardware and in the future it could also work with an app. Our results have a very high scientific potential, even if there is still a long way to be able to apply the system in daily practice, say the researchers. The next steps will be to expand the patient population to collect as much data as possible and it will also be necessary to verify whether the algorithm works well not only in laboratory environments but also in a doctor’s office or even at the patient’s home.

January 29, 2023 (change January 29, 2023 | 09:09)

You may also like

Leave a Comment