The diagnosis of Parkinson’s disease has shaken the lives of many. More than 10 million people live with him around the world. There is no cure, but if symptoms are noticed early, the disease can be controlled. As Parkinson’s disease progresses, speech symptoms change along with other symptoms.
Lithuanian researcher from Kaunas University of Technology (KTU), Rytis Maskeliūnas, together with colleagues from Lithuanian University of Health Sciences (LSMU), attempted to identify early symptoms of Parkinson’s disease using audio data.
Parkinson’s disease is usually associated with loss of motor function – hand tremors, muscle stiffness, or balance problems. According to Masklinas, a researcher in KTU’s Department of Multimedia Engineering, as motor activity decreases, so does the function of the vocal cords, diaphragm and lungs: “Changes in speech often occur even before motor function disorders, which is why speech may be the first sign of the disease “.
Expanding the AI language database
According to Professor Virgilios Olozas, in the Department of Ear, Nose and Throat at LSMU Medical School, patients with early stage Parkinson’s disease may speak in a quieter manner, which can also be monotonous, less expressive, slower, more fragmented, and very difficult to notice. by ear. As the disease progresses, hoarseness, stuttering, slurring of words, and loss of pauses between words can become more pronounced.
With these symptoms in mind, a joint team of Lithuanian researchers has developed a system for early detection of the disease.
“We are not creating a substitute for routine examination of the patient – our method is designed to facilitate early diagnosis of the disease and track the effectiveness of treatment,” says researcher at KTU, Maskeliūnas.
According to him, the link between Parkinson’s disease and speech abnormalities is not new in the world of digital signal analysis – it has been known and researched since the 1960s. However, as technology has advanced, it has become possible to extract more information from speech.
In their study, the researchers used artificial intelligence (AI) to analyze and evaluate speech signals, with calculations and diagnoses performed in seconds rather than hours. This study is also unique – the results are tailored to the characteristics of the Lithuanian language, in this way the AI language database is expanded.
The algorithm will become a mobile app in the future
Speaking about the progress of the study, Kipras Pribuišis, Lecturer in the Department of Ear, Nose and Throat at LSMU Medical School, emphasized that it was only performed on patients already diagnosed with Parkinson’s disease: “So far, our approach is able to distinguish between Parkinson’s disease and healthy people.” using a speech sample. This algorithm is also more accurate than what was previously proposed.”
In a soundproofed room, a microphone was used to record the speech of healthy patients and Parkinson’s patients, and an artificial intelligence algorithm “learned” to perform signal processing by evaluating these recordings. The researchers highlight that the algorithm does not require powerful hardware and could be ported to a mobile app in the future.
“Our results, which have already been published, have a very high scientific potential. Certainly, there is still a long and difficult way to go before it can be applied in everyday clinical practice,” says Maskelinas.
According to the researcher, the next steps include increasing the number of patients to collect more data and to determine whether the proposed algorithm is better than the alternative methods used in the early diagnosis of Parkinson’s disease. In addition, it will be necessary to check whether the algorithm works well not only in laboratory-like environments but also in a doctor’s office or in a patient’s home.