Researchers from Lithuania are using new technology to monitor changes in speech, which could be one of the early signs of Parkinson’s disease.
Rytis Maskeliūnas from Kaunas University of Technology (KTU) collaborated with researchers from the Lithuanian University of Health Sciences (LSMU) in detecting early signs of Parkinson’s disease using voice data.
Over ten million people worldwide live with Parkinson’s disease. There is currently no cure for the disease, but if symptoms are identified early, the disease can be controlled. It is common for a patient’s speech to change as the disease progresses.
Parkinson’s disease can cause physical health issues
Parkinson’s disease often leads to a loss of motor function, which can cause hand tremors, muscle stiffness, and balance problems. According to the researchers, the function of the vocal cords, diaphragm, and lungs is likely to deteriorate alongside motor activity.
“Changes in speech often occur even earlier than motor function disorders, which is why the altered speech might be the first sign of the disease,” said Maskeliūnas.
According to Professor Virgilijus Ulozas, of the Department of Ear, Nose, and Throat at the LSMU Faculty of Medicine, patients with early signs of Parkinson’s disease might speak more quietly. Their voice may also become monotonous, less expressive, slower, and more fragmented. These changes can be so minor that they cannot be noticed by the human ear. As Parkinson’s progresses hoarseness, stuttering, slurred pronunciation of words, and loss of pauses between words become more apparent. The joint team of researchers considered these symptoms as they developed a system to detect the disease earlier.
“We are not creating a substitute for a routine examination of the patient. Our method is designed to facilitate early diagnosis of the disease and to track the effectiveness of treatment,” said Maskeliūnas.
The link between Parkinson’s disease and speech abnormalities has been known and researched since the 1960s. Advances in technology have made it possible to extract more information through speech analysis.
Using AI to detect the early signs of Parkinson’s disease
The researchers used artificial intelligence (AI) to analyse patients’ speech signals. Using this method, the researchers were able to make diagnoses in seconds, rather than hours. The researchers also tailored their diagnostic methods to the Lithuanian language, expanding the AI language database.
“So far, our approach is able to distinguish Parkinson’s from healthy people using a speech sample. This algorithm is also more accurate than previously proposed,” Kipras Pribuišis, lecturer at the Department of Ear, Nose, and Throat at the LSMU Faculty of Medicine, emphasising that the study was only carried out on patients who had already been diagnosed with Parkinson’s disease.
The researchers used a microphone to record the speech of healthy patients and Parkinson’s patients in a soundproof booth. The AI algorithm learned to perform signal processing by evaluating these recordings. The researchers have pointed out that the algorithm does not require powerful hardware and could potentially be used via a mobile app in the future.
“Our results, which have already been published, have a very high scientific potential. Sure, there is still a long and challenging way to go before it can be applied in everyday clinical practice,” said Maskeliūnas.
Next, the researchers will increase the number of patients to gather more data and determine whether the proposed algorithm is superior to existing Parkinson’s diagnostics. In addition, the researchers will also need to test the algorithm in non-laboratory settings, such as a doctor’s office or patients’ homes.