Toward a Wearable System for Predicting Freezing of Gait in People Affected by Parkinson's Disease

被引:50
作者
Demrozi, Florenc [1 ]
Bacchin, Ruggero [2 ]
Tamburin, Stefano [2 ]
Cristani, Marco [1 ]
Pravadelli, Graziano [1 ]
机构
[1] Univ Verona, Dept Comp Sci, I-37129 Verona, Italy
[2] Univ Verona, Dept Neurosci Biomed & Movement Sci, I-37134 Verona, Italy
关键词
Feature extraction; Accelerometers; Principal component analysis; Kernel; Classification algorithms; Sensors; Machine learning; Freezing of gait; wearable device; accelerometer; explainable machine learning; classifica-tion; FALLS; RISK;
D O I
10.1109/JBHI.2019.2952618
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Some wearable solutions exploiting on-body acceleration sensors have been proposed to recognize Freezing of Gait (FoG) in people affected by Parkinson Disease (PD). Once a FoG event is detected, these systems generate a sequence of rhythmic stimuli to allow the patient restarting the gait. While these solutions are effective in detecting FoG events, they are unable to predict FoG to prevent its occurrence. This paper fills in the gap by presenting a machine learning-based approach that classifies accelerometer data from PD patients, recognizing a pre-FOG phase to further anticipate FoG occurrence in advance. Gait was monitored by three tri-axial accelerometer sensors worn on the back, hip and ankle. Gait features were then extracted from the accelerometer's raw data through data windowing and non-linear dimensionality reduction. A k-nearest neighbor algorithm (k-NN) was used to classify gait in three classes of events: pre-FoG, no-FoG and FoG. The accuracy of the proposed solution was compared to state-of-the-art approaches. Our study showed that: (i) we achieved performances overcoming the state-of-the-art approaches in terms of FoG detection, (ii) we were able, for the very first time in the literature, to predict FoG by identifying the pre-FoG events with an average sensitivity and specificity of, respectively, 94.1% and 97.1%, and (iii) our algorithm can be executed on resource-constrained devices. Future applications include the implementation on a mobile device, and the administration of rhythmic stimuli by a wearable device to help the patient overcome the FoG.
引用
收藏
页码:2444 / 2451
页数:8
相关论文
共 35 条
[1]   Recurrent Falls in Parkinson's Disease: A Systematic Review [J].
Allen, Natalie E. ;
Schwarzel, Allison K. ;
Canning, Colleen G. .
PARKINSONS DISEASE, 2013, 2013
[2]   Home-Based Risk of Falling Assessment Test Using a Closed-Loop Balance Model [J].
Ayena, Johannes C. ;
Zaibi, Helmi ;
Otis, Martin J. -D. ;
Menelas, Bob-Antoine J. .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2016, 24 (12) :1351-1362
[3]   Wearable Assistant for Parkinson's Disease Patients With the Freezing of Gait Symptom [J].
Baechlin, Marc ;
Plotnik, Meir ;
Roggen, Daniel ;
Maidan, Inbal ;
Hausdorff, Jeffrey M. ;
Giladi, Nir ;
Troester, Gerhard .
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2010, 14 (02) :436-446
[4]   Falls and freezing of gait in Parkinson's disease: A review of two interconnected, episodic phenomena [J].
Bloem, BR ;
Hausdorff, JA ;
Visser, JE ;
Giladi, N .
MOVEMENT DISORDERS, 2004, 19 (08) :871-884
[5]   Deep learning for freezing of gait detection in Parkinson's disease patients in their homes using a waist-worn inertial measurement unit [J].
Camps, Julia ;
Sama, Albert ;
Martin, Mario ;
Rodriguez-Martin, Daniel ;
Perez-Lopez, Carlos ;
Moreno Arostegui, Joan M. ;
Cabestany, Joan ;
Catala, Andreu ;
Alcaine, Sheila ;
Mestre, Berta ;
Prats, Anna ;
Crespo-Maraver, Maria C. ;
Counihan, Timothy J. ;
Browne, Patrick ;
Quinlan, Leo R. ;
Laighin, Gearoid O. ;
Sweeney, Dean ;
Lewy, Hadas ;
Vainstein, Gabriel ;
Costa, Alberto ;
Annicchiarico, Roberta ;
Bayes, Angels ;
Rodriguez-Molinero, Alejandro .
KNOWLEDGE-BASED SYSTEMS, 2018, 139 :119-131
[6]  
Cole BT, 2011, IEEE ENG MED BIO, P5649, DOI 10.1109/IEMBS.2011.6091367
[7]   FPGA-Based Embedded Cyber-Physical Platform to Assess Gait and Postural Stability in Parkinson's Disease [J].
De Venuto, Daniela ;
Annese, Valerio Francesco ;
Mezzina, Giovanni ;
Defazio, Giovanni .
IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY, 2018, 8 (07) :1167-1179
[8]   The use of multiple measurements in taxonomic problems [J].
Fisher, RA .
ANNALS OF EUGENICS, 1936, 7 :179-188
[9]   Freezing of gait: Promising avenues for future treatment [J].
Gilat, Moran ;
Silva de Lima, Ana Ligia ;
Bloem, Bastiaan R. ;
Shine, James M. ;
Nonnekes, Jorik ;
Lewis, Simon J. G. .
PARKINSONISM & RELATED DISORDERS, 2018, 52 :7-16
[10]  
Handojoseno AMA, 2013, IEEE ENG MED BIO, P4263, DOI 10.1109/EMBC.2013.6610487