IMU-Based Classification of Parkinson's Disease From Gait: A Sensitivity Analysis on Sensor Location and Feature Selection

被引:161
作者
Caramia, Carlotta [1 ]
Torricelli, Diego [2 ]
Schmid, Maurizio [1 ]
Munoz-Gonzalez, Adriana [3 ]
Gonzalez-Vargas, Jose [2 ]
Grandas, Francisco [3 ]
Pons, Jose L. [2 ]
机构
[1] Roma Tre Univ, Dept Engn, I-00154 Rome, Italy
[2] Spanish Natl Res Council, Cajal Inst, Madrid 28006, Spain
[3] Univ Complutense Madrid, Movement Disorders Unit, E-28040 Madrid, Spain
基金
欧盟地平线“2020”;
关键词
Machine learning; wearable sensors; gait analysis; body sensor networks; feature extraction; Parkinson's disease; DIAGNOSIS; PEOPLE; SYSTEM;
D O I
10.1109/JBHI.2018.2865218
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Inertial measurement units (IMUs) have a long-lasting popularity in a variety of industrial applications from navigation systems to guidance and robotics. Their use in clinical practice is now becoming more common, thanks to miniaturization and the ability to integrate on-board computational and decision-support features. IMU-based gait analysis is a paradigm of this evolving process, and in this study its use for the assessment of Parkinson's disease (PD) is comprehensively analyzed. Data coming from 25 individuals with different levels of PD symptoms severity and an equal number of age-matched healthy individuals were included into a set of 6 different machine learning (ML) techniques, processing 18 different configurations of gait parameters taken from 8 IMU sensors. Classification accuracy was calculated for each configuration and ML technique, adding two meta-classifiers based on the results obtained from all individual techniques through majority of voting, with two different weighting schemes. Average classification accuracy ranged between 63% and 80% among classifiers and increased up to 96% for one meta-classifier configuration. Configurations based on a statistical preselection process showed the highest average classification accuracy. When reducing the number of sensors, features based on the joint range of motion were more accurate than those based on spatio-temporal parameters. In particular, best results were obtained with the knee range of motion, calculated with four IMUs, placed bilaterally. The obtained findings provide data-driven evidence on which combination of sensor configurations and classification methods to be used during IMU-based gait analysis to grade the severity level of PD.
引用
收藏
页码:1765 / 1774
页数:10
相关论文
共 43 条
[1]  
Arora Siddharth, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), P3641, DOI 10.1109/ICASSP.2014.6854280
[2]  
Barth J, 2011, IEEE ENG MED BIO, P868, DOI 10.1109/IEMBS.2011.6090226
[3]   IN-FLIGHT ALIGNMENT AND CALIBRATION OF INERTIAL MEASUREMENT UNITS .1. GENERAL FORMULATION [J].
BAZIW, J ;
LEONDES, CT .
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 1972, AES8 (04) :439-&
[4]   Clinical Assessments in Parkinson's Disease: Scales and Monitoring [J].
Bhidayasiri, Roongroj ;
Martinez-Martin, Pablo .
PARKINSON'S DISEASE, 2017, 132 :129-182
[5]  
Chang D., 2014, STANFORD 1231
[6]   A Wearable Inertial Measurement System With Complementary Filter for Gait Analysis of Patients With Stroke or Parkinson's Disease [J].
Chang, Hsing-Cheng ;
Hsu, Yu-Liang ;
Yang, Shih-Chin ;
Lin, Jung-Chin ;
Wu, Zhi-Hao .
IEEE ACCESS, 2016, 4 :8442-8453
[7]   Levodopa Is a Double-Edged Sword for Balance and Gait in People With Parkinson's Disease [J].
Curtze, Carolin ;
Nutt, John G. ;
Carlson-Kuhta, Patricia ;
Mancini, Martina ;
Horak, Fay B. .
MOVEMENT DISORDERS, 2015, 30 (10) :1361-1370
[8]   Metric learning for Parkinsonian identification from IMU gait measurements [J].
Cuzzolin, Fabio ;
Sapienza, Michael ;
Esser, Patrick ;
Saha, Suman ;
Franssen, Miss Marloes ;
Collett, Johnny ;
Dawes, Helen .
GAIT & POSTURE, 2017, 54 :127-132
[9]   Free-living gait characteristics in ageing and Parkinson's disease: impact of environment and ambulatory bout length [J].
Del Din, Silvia ;
Godfrey, Alan ;
Galna, Brook ;
Lord, Sue ;
Rochester, Lynn .
JOURNAL OF NEUROENGINEERING AND REHABILITATION, 2016, 13
[10]   Contribution of a Trunk Accelerometer System to the Characterization of Gait in Patients With Mild-to-Moderate Parkinson's Disease [J].
Demonceau, Marie ;
Donneau, Anne-Francoise ;
Croisier, Jean-Louis ;
Skawiniak, Eva ;
Boutaayamou, Mohamed ;
Maquet, Didier ;
Garraux, Gaetan .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2015, 19 (06) :1803-1808