Parkinson's Disease Detection by Machine Learning

Parkinson's disease is a special type of neurological condition which is quite common and has an impact on people's lives all over the world. For the condition to be successfully treated and managed, early detection, attention and diagnosis are very essential. Recent research has demonstrated that early signs of Parkinson's disease might include changes in speech, such as those in speaking rate and voice quality. In this study, this paper suggests a brand-new method for identifying this Parkinson's disease using speech alterations. In this paper, we introduce a machine-learning model that can analyze speech samples and reliably identify Parkinson's illness. Our methods are based on the examination of several speech characteristics, including pitch, jitter, and shimmer, which are well-known to be impacted by the illness. Our results show that our method performs well when applied to a dataset of speech samples from people with and without this disease.