Machine Learning Based Method for Huntington's Disease Gait Pattern Recognition

被引：5

作者：

Huang, Xiuyu ^{[1
]}

Khushi, Matloob ^{[1
]}

Latt, Mark ^{[2
]}

Loy, Clement ^{[3
]}

Poon, Simon K. ^{[1
]}

机构：

[1] Univ Sydney, Camperdown, NSW 2006, Australia

[2] Royal Prince Alfred Hosp, Camperdown, NSW 2050, Australia

[3] Westmead Hosp, Sydney, NSW 2145, Australia

来源：

NEURAL INFORMATION PROCESSING (ICONIP 2019), PT IV | 2019年 / 1142卷

关键词：

Huntington's disease; Machine learning; Nested LOOCV; CLASSIFICATION; DISORDERS; DYNAMICS;

D O I：

10.1007/978-3-030-36808-1_66

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Huntington's disease (HD) is an inherited neurodegenerative disorder causing problems with mobility, cognition and mood. Gait abnormality is a potential diagnostic sign as it can occur even in the early stages of HD. We developed a machine learning method for detecting HD with gait dynamics as the model features. Concretely, standard deviation (SD) and interquartile range (IQR) were calculated for 6 gait time series sequences as 12 candidate features. An exhaustive feature and hyperparameter selector was then applied to optimize the features and hyperparameter subsets for 5 different machine learning models. Classification outcomes were determined by nested leave-one-out cross-validation (nested LOOCV) method. Support Vector Machines (SVM) achieved the highest accuracy (97.14%) without overfitting bias assumptions. Our result showed that the machine learning based method with gait dynamics features can be a complementary tool for HD diagnosis.

引用

页码：607 / 614

页数：8

共 21 条

[1]

[Anonymous], 1990, The Analysis of Linear Partial Differential Operators. I. Distribution Theory and Fourier Analysis, DOI DOI 10.1007/978-3-642-61497-2

[2] Complexity analysis of stride interval time series by threshold dependent symbolic entropy [J].