ABSTRACT Parkinson’s disease is a dynamic neurodegenerative disorder influencing over 6 million people worldwide. However there is no recognized test for PD for patients, particularly in the early stages. This results in increased mortality rate. Thus detection system of Parkinson’s disease with easy steps and feasible one to detect parkinson’s disease at the early stage is essential. The proposed system invokes parkinson’s disease detection using voice and spiral drawing dataset. The patients voice dataset is analyzed using RStudio with kmeans clustering and decision tree based machine learning techniques. The patients spiral drawing is analyzed using python. From these drawings principal component analysis (PCA) algorithm for feature extraction from the spiral drawings. From the spiral drawings : X ; Y; Z; Pressure; Grip Angle; Timestamp; Test ID values are been extracted. The extracted values are been matched with the trained database using machine learning technique (Support vector machine) and results are produced. Thus our experimental results will show early detection of disease which facilitates clinical monitoring of elderly people and increase their life span by improving their lifestyle which leads to a peaceful life.