| Summary: | 碩士 === 國立中興大學 === 資訊管理學系所 === 105 === Parkinson''s disease is second to Alzheimer disease, one of the slowest degenerative diseases known to affect us. Approximately 6.2 million people globally are battling this disease, and every 147.7 people in 100 thousand Taiwanese will be affected by it. Although people in their middle ages or elderly people are more likely to manifest this disease, it does seem that nowadays even young people can contract it. This is known medically as Early Onset Parkinsonism. It is caused by the deterioration of melanin generated by substantia nigra pars compacta, which in term effected the functions of Basal ganglia, causing the motion of an individual to slow down. In addition, the cognitive ability, such as visual and spacing ability, memory, depression, language ability, of the individual will be largely impeded as well. In the early stages of Parkinson''s disease, individuals may seek professional medical help due to above symptoms but are usually turned away with no diagnosis.
About 70%-90% of Parkinson''s disease owners exhibit one of the common symptoms is language disability and voice abnormality. Their voice is lower. They mumble. Their pronunciation is slow and incoherent. This research uses voice characteristics data, using J48, MLP and KNN algorithm, to construct Parkinson''s disease early detection model. All the three algorithm mentioned above have reached over 90% accuracy in detection and out of the three, KNN’s accuracy has reached as high as 95.4%, demonstrating that it is highly possible to detect Parkinson''s through voice characteristics. This signifies the possibility to apply such data detection method in the medical field. As more and more data is collected and verified, these methods can be used in actual clinical scenarios and help Parkinson''s disease developers to detect it early and start the treatment early.
|
|---|
