Early diagnosis of Parkinson’s disease using machine learning algorithms

Parkinson’s disease is caused by the disruption of the brain cells that produce substance to allow brain cells to communicate with each other, called dopamine. The cells that produce dopamine in the brain are responsible for the control, adaptation and fluency of movements. When 60–80%of these cells...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Medical hypotheses Ročník 138; s. 109603
Hlavný autor:	Karapinar Senturk, Zehra
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States Elsevier Ltd 01.05.2020
Predmet:	Algorithms Decision support systems Early Diagnosis Feature selection Humans Machine Learning Medical diagnosis Parkinson Disease - diagnosis Support Vector Machine Support Vector Machines Decision support systems Feature selection Medical diagnosis Support Vector Machines Machine learning
ISSN:	0306-9877, 1532-2777, 1532-2777
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Parkinson’s disease is caused by the disruption of the brain cells that produce substance to allow brain cells to communicate with each other, called dopamine. The cells that produce dopamine in the brain are responsible for the control, adaptation and fluency of movements. When 60–80%of these cells are lost, then enough dopamine is not produced and Parkinson’s motor symptoms appear. It is thought that the disease begins many years before the motor (movement related) symptoms and therefore, researchers are looking for ways to recognize the non-motor symptoms that appear early in the disease as early as possible, thereby halting the progression of the disease. In this paper, machine learning based diagnosis of Parkinson’s disease is presented. The proposed diagnosis method consists of feature selection and classification processes. Feature Importance and Recursive Feature Elimination methods were considered for feature selection task. Classification and Regression Trees, Artificial Neural Networks, and Support Vector Machines were used for the classification of Parkinson's patients in the experiments. Support Vector Machines with Recursive Feature Elimination was shown to perform better than the other methods. 93.84% accuracy was achieved with the least number of voice features for Parkinson’s diagnosis.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0306-9877 1532-2777 1532-2777
DOI:	10.1016/j.mehy.2020.109603