The application of convolutional neural networks in the diagnosis of Parkinson's disease on the basis of handwriting samples

被引：0

作者：

Bialek, Kamila ^{[1
]}

Jakubowski, Jacek ^{[1
]}

Potulska-Chromik, Anna ^{[2
]}

Nojszewska, Monika ^{[2
]}

Kostera-Pruszczyk, Anna ^{[2
]}

机构：

[1] Mil Univ Technol, Dept Elect, Warsaw, Poland

[2] Med Univ Warsaw, Dept Neurol, Ul Banacha 1A, PL-02097 Warsaw, Poland

来源：

PRZEGLAD ELEKTROTECHNICZNY | 2024年 / 100卷 / 04期

关键词：

convolutional neural networks; neural networks; Parkinson's disease; diagnostics; handwriting; SIZE;

D O I：

10.15199/48.2024.04.53

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The article presents an attempt to use a convolutional neural network to recognize Parkinson's disease on the basis of handwriting images recorded using a graphics tablet. Based on studies with participation of healthy subjects and patients with Parkinson's disease, the overall accuracy of 85.4% of the sick -healthy binary classification was achieved.

引用

页码：261 / 264

页数：4

共 25 条

[1]

[Anonymous], 1995, HDB BRAIN THEORY NEU

[2] Accuracy of subjective and objective handwriting assessment for differentiating Parkinson's disease from tremulous subjects without evidence of dopaminergic deficits (SWEDDs): an FP-CIT-validated study [J].