International Journal of Computer Applications (0975 – 8887) Volume 184 – No.1, March 2022 13 Diagnosis of Parkinson Disease using Handwriting Analysis Nihar Ranjan, PhD Professor Department of Information Technology RSCOE Divya Umesh Kumar Student Department of Information Technology RSCOE Vaishnavi Dongare Student Department of Information Technology RSCOE Kiran Chavan Student Department of Information Technology RSCOE Yuvraj Kuwar Student Department of Information Technology RSCOE ABSTRACT Parkinson is a neurodegenerative disease that affects your ability to control movement. Parkinson's disease starts slowly and worsens over time. The cured for Parkinson‟s disease is still unknown; medications might significantly improve your symptoms. Researchers suggest that early diagnosis of Parkinson can help improve the quality of the patient‟s life. In this survey, handwriting or drawings is considered as an aspect for detecting Parkinson disease using machine learning algorithm such as Random Forest Classifier and for detailed analysis of the drawings we use, Histogram of Oriented Gradients (HOG). We take drawings drawn by Parkinson patients as well as healthy people as input for detecting the Parkinson disease General Terms Handwriting or drawings, Histogram of Oriented Gradients(HOG), Random Forest Classifier. Keywords Parkinson Disease(PD), Handwriting Analysis. 1. INTRODUCTION Parkinson is a central nervous system disorder that affects movement, often including tremors. It leads to destruction of nerve cells which produces dopamine that helps to control the muscles and their movement. Parkinson's often starts with a tremor in one hand. This disease includes some other symptoms such as slow movement, stiffness and loss of balance. It has been observed that, out of every 1,000 people in the world around 1 or 2 that is one percent of the population which is above 60 years old, suffer from PD .In this disease, older age can be considered as a risk factor . Therefore, development of a feasible and reliable diagnostic method for PD detection is necessary which would help in early diagnosis of the disease and help to improve the quality of the patient‟s life [1].The effects of the diseases starts gradually but worsen over time Following are the 5 stages for Parkinson‟s disease: Stage 1 is the mildest form of Parkinson‟s. At this stage the symptoms are mild so they don‟t interfere in daily lifestyle. So there might be chances of missing that symptom. But the changes in your posture, walk, or facial expressions it may noticed by your family and friends. As compared to stage 1, Stage 2 is a moderate form of Parkinson‟s, and the symptoms are much more noticeable than those experienced in stage 1. The symptoms like Stiffness, tremors, and trembling are more noticeable, and changes in facial expressions can occur. The middle stage is 3rd stage in Parkinson‟s, and it marks a major turning point in the progression of the disease. There are many symptoms which are similar to stage 1. However, you would experience loss of balance and decreased reflexes. The overall rate of movements decreases. Because of that reason falls become more common in stage 3.Independence separates people with stage 3 Parkinson‟s from those with stage 4. In stage 4, it‟s impossible to stand without assistance. But, the patient may require a walker or other type of assistance. The most advanced stage of Parkinson‟s disease is stage 5. Advanced stiffness in the legs causes difficulty in standing or walking. Handwriting can be considered as an aspect in the assessment of Parkinson disease. Handwriting consist of cognitive planning, coordination, and execution abilities. To diagnose the disease and its severity handwriting problems can be considered as a prominent aspect, so changes in writing can be considered a prominent biomarker [2].Handwriting is an very complex task. Writing a sentence requires the energetic transaction of the lower arm, wrist, and finger muscle. Currently, the detection is based on the assessment of several aspects such as facial expression difficulties, walking and speaking by Parkinson‟s patient. In this paper we have considered handwriting or drawing as an aspect for detecting the Parkinson disease as it is cost friendly and less time consuming [3]. 2. IDENTIFY, RESEARCH AND COLLECT IDEA In this section, the existing works that relate to the proposed work are presented. This [2] paper is divided into different phases for detection of Parkinson disease. Initial phase is data acquisition which deals with devices as well as handwriting tasks [12]. An electronic pen which considers different features like position, pressure over the writing surface, azimuth and altitude. Also the dataset includes words with repetitive letters which help to better address the motor skills.