Intelligent Pen for diagnosing early stage symptoms of Parkinson’s disease

Abstract

In this report, we propose a pen device capable of detecting specific features from dynamic handwriting tests for aiding on automatic Parkinson’s disease identification. The method used in this work uses machine learning to compare the raw signals from different sensors in the device coupled to a pen and extract relevant information such as tremors and hand acceleration to diagnose the patient clinically. Additionally, the datasets composed of raw signals from healthy and Parkinson’s disease patients acquired here are made available to further contribute to research related to this topic. This work compiled six new datasets from six different tasks over 40 different patients. Each one was composed of multiple signals from the intelligent pen sensors, hoping to aid future researchers in Parkinson’s disease diagnoses. The HandPD Dataset was used to learn valuable and essential information about the limitations of the mentioned device. Such limitations, i.e., the sensor’s disposition, were responsible for ‘noisy’ data and higher deviation in specific tasks than others. Yet, even with data quality lower than expected, the overall results still surpassed the anticipated. This information proved the device viability and effectiveness in aiding the classification of healthy and parkinsonian groups using an affordable and handier solution than others offered in the market, mainly for faraway places and undeveloped towns. This being the main objective of our work. The low-cost electronics and easier setup for acquiring and assessing the data also contribute to the goals mentioned above.

Shisheer S Kaushik

Quantum Technology enthusiast