Avoiding Misdiagnosis of Parkinson’s Disease With the Use of Wearable Sensors and Artificial Intelligence
| Autor: | Ekaterina Kovalenko, Aleksandr Talitckii, Anna Anikina, Dmitry V. Dylov, Maksim Semenov, Olga Zimniakova, Aleksei Shcherbak, Andrey Somov, Ekaterina Bril |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Parkinson's disease
business.industry 010401 analytical chemistry Feature extraction Wearable computer Disease medicine.disease 01 natural sciences 0104 chemical sciences Extrapyramidal disorder Motor system medicine Artificial intelligence Electrical and Electronic Engineering F1 score business Instrumentation Wearable technology |
| Zdroj: | IEEE Sensors Journal. 21:3738-3747 |
| ISSN: | 2379-9153 1530-437X |
| DOI: | 10.1109/jsen.2020.3027564 |
| Popis: | Parkinson’s Disease (PD) is a neurodegenerative disease associated with the extrapyramidal motor system disorder currently being the second most common neurodegenerative disorder. The first clinical symptoms can manifest themselves long before the retirement age and inevitably lead to reducing the possibility of continuing work. However, PD is sometimes misdiagnosed. In this article, we discuss the typical misdiagnosed cases and propose a second opinion system based on wearable sensors and artificial intelligence. For this reason, we designed a number of common tasks and recorded the movement data using wearable sensors worn by individuals with PD and other extrapyramidal disorders. PD patients are differentiated against other patients with similar diseases and not against healthy subjects. This allows one to measure the true specificity of wearable technologies with regard to detecting PD. Data analysis and classification of the types of tremor using machine learning methods (feature extraction, dimensionality reduction, classification) helps significantly improve the accuracy of PD diagnosis. Our results show that, when considering bradykinesia and tremor together, the accuracy of distinguishing PD from similar diseases increases (f1 score 0.88). This closed-loop configuration makes it possible to tune exercises to maximize the diagnostic value of the entire routine. We report approbation on 56 patients. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|