Altered speech may be the first sign of Parkinson’s disease – Zoo House News
The diagnosis of Parkinson’s disease has shattered many lives. More than 10 million people worldwide live with it. There is no cure, but if symptoms are caught early, the disease can be controlled. As Parkinson’s disease progresses, along with other symptoms, language changes.
Lithuanian researcher Rytis Maskeliūnas from Kaunas University of Technology (KTU) together with colleagues from the Lithuanian University of Health Sciences (LSMU) tried to use speech data to identify early symptoms of Parkinson’s disease.
Parkinson’s disease is usually associated with a loss of motor function — hand tremors, muscle stiffness, or problems with balance. According to Maskeliūnas, a researcher at the Chair of Multimedia Technology at KTU, the function of the vocal cords, diaphragm and lungs also decreases with motor activity: “Changes in speech often occur even earlier than motor dysfunction, which is why the altered speech could be the first be signs of the disease.”
Extension of the AI language database
According to Professor Virgilijus Ulozas of the Department of Otorhinolaryngology, LSMU School of Medicine, patients with early Parkinson’s disease may speak more softly, which is also monotonous, less expressive, slower, and more fragmented, and this is with the ear very difficult to perceive. As the disease progresses, hoarseness, stuttering, slurring of words, and loss of pauses between words may become more noticeable.
Taking these symptoms into account, a joint team of Lithuanian researchers have developed a system to detect the disease earlier.
“We are not creating a substitute for a routine examination of the patient – our method is intended to facilitate the early detection of the disease and track the effectiveness of the treatment,” says KTU researcher Maskeliūnas.
According to him, the connection between Parkinson’s disease and speech disorders is not new to the world of digital signal analysis, but has been known and researched since the 1960s. However, as technology advances, it becomes possible to extract more information from speech.
In their study, the researchers used artificial intelligence (AI) to analyze and evaluate speech signals, performing calculations and diagnostics in seconds instead of hours. This study is also unique – the results are tailored to the peculiarities of the Lithuanian language and thus expand the AI language database.
The algorithm will become a mobile app in the future
Commenting on the progress of the study, Kipras Pribuišis, lecturer at the Department of Ear, Nose and Throat Medicine at the Medical Faculty of the LSMU, emphasizes that it was only carried out on patients who had already been diagnosed with Parkinson’s: “So far, our approach in the able to distinguish Parkinson’s from healthy people using a speech sample. This algorithm is also more accurate than previously proposed.”
In a soundproof booth, the speech of healthy people and Parkinson’s patients was recorded with a microphone and an artificial intelligence algorithm “learned” how to process the signal by evaluating these recordings. The researchers emphasize that the algorithm does not require powerful hardware and could be ported to a mobile app in the future.
“Our already published results have a very high scientific potential. It will certainly still be a long and challenging road before it can be used in everyday clinical practice,” says Maskeliūnas.
According to the researcher, the next steps include increasing the number of patients to collect more data and determine whether the proposed algorithm is superior to alternative methods for early detection of Parkinson’s. In addition, it must be checked whether the algorithm works well not only in laboratory-like environments, but also in the doctor’s office or at the patient’s home.