Bag of Samplings for computer-assisted Parkinson's disease diagnosis based on Recurrent Neural Networks

• Published in: Computers in biology and medicine 2019-12, Vol.115, p.103477-103477, Article 103477
• Main Authors: Ribeiro, Luiz C.F., Afonso, Luis C.S., Papa, João P.
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Bag of samplings; Gait; Handwriting; Handwritten dynamics; Identification; Learning algorithms; Life expectancy; Life span; Machine learning; Medical diagnosis; Memory; Movement disorders; Neural networks; Neurodegenerative diseases; Parkinson's disease; Patients; Recurrent Neural Networks; Sensors; Time dependence; Tremor; Tremors
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.103477

Parkinson's Disease (PD) is a clinical syndrome that affects millions of people worldwide. Although considered as a non-lethal disease, PD shortens the life expectancy of the patients. Many studies have been dedicated to evaluating methods for early-stage PD detection, which includes machine learning techniques that employ, in most cases, motor dysfunctions, such as tremor. This work explores the time dependency in tremor signals collected from handwriting exams. To learn such temporal information, we propose a model based on Bidirectional Gated Recurrent Units along with an attention mechanism. We also introduce the concept of “Bag of Samplings” that computes multiple compact representations of the signals. Experimental results have shown the proposed model is a promising technique with results comparable to some state-of-the-art approaches in the literature. •A new approach to diagnose Parkinson's Disease using handwritten analysis.•To introduce the concept of Bag of Samplings in the context of handwritten analysis.•To evaluate Bidirectional Gated Recurrent Units and attention mechanisms for computer-assisted Parkinson's Disease diagnosis.•Proposed approach outperformed previous works.