Title: Video analytics-based multi-symptoms system for determining progression of Parkinson disease

Authors: Jignesh Sisodia; Dhananjay Kalbande

Addresses: Sardar Patel Institute of Technology, Mumbai, India ' Sardar Patel Institute of Technology, Mumbai, India

Abstract: Parkinson disease is the second most common neurodegenerative disease, and its symptoms tend to increase progressively and affect numerous parts of the body. Parkinson disease patients suffer from symptoms such as rigidity in the body, Bradykinesia, tremors in hands, facial tremor, and freezing of gait. Traditionally assessment of Parkinson disease is based on clinician observation on the severity of symptoms of patients during the visit. Symptoms of Parkinson are highly episodic and cannot be completely observed at the doctor's clinic. With the effect of COVID-19, physical visit of the elderly population to the clinic is considered unsafe. Video-based assessment at the patients home led to the solution of avoiding the patient to be exposed to the outside world. We propose a non-invasive video analytics-based assessment of progression of Parkinson disease based on finger tapping and tremor using UPDRS scale. We also propose a video-based technique utilising deep learning and convolutional neural networks which analyse the gait characteristics of patients to identify Parkinson. We intend to distinguish a healthy subject and progression of disease at different stages. These techniques can assist clinical experts for examination of patients to identify the progression of the disease.

Keywords: Parkinson disease; video analytics; deep learning; convolutional neural network; CNN.

DOI: 10.1504/IJBET.2024.137347

International Journal of Biomedical Engineering and Technology, 2024 Vol.44 No.3, pp.288 - 302

Received: 24 Sep 2022
Accepted: 18 Mar 2023
Published online: 13 Mar 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article