Real-time detection of freezing of gait in Parkinson's disease using multi-head convolutional neural networks and a single inertial sensor

被引:18
|
作者
Borzi, Luigi [1 ]
Sigcha, Luis [2 ,3 ]
Rodriguez-Martin, Daniel [4 ,5 ]
Olmo, Gabriella [1 ]
机构
[1] Politecn Torino, Dept Control & Comp Engn, Corso Duca Abruzzi 24, I-10129 Turin, Italy
[2] Univ Politecn Madrid, Instrumentat & Appl Acoust Res Grp I2A2, Ctra Valencia,Km 7, Madrid 28031, Spain
[3] Univ Minho, Sch Engn, ALGORITMI Res Ctr, P-4800058 Guimaraes, Portugal
[4] Sense4Care SL, Barcelona 08940, Spain
[5] Univ Politecn Cataluna, Tech Res Ctr Dependency Care & Autonomous Living, Vilanova I La Geltru 08800, Spain
关键词
Parkinson?s disease; Freezing of gait; Activities of daily living; Wearable sensors; Accelerometer; Convolutional neural network; Deep learning; FEATURES; PEOPLE; WORN;
D O I
10.1016/j.artmed.2022.102459
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Background: Freezing of gait (FOG) is one of the most disabling symptoms of Parkinson's disease (PD), contributing to poor quality of life and increased risk of falls. Wearable sensors represent a valuable means for detecting FOG in the home environment. Moreover, real-time feedback has proven to help reduce the duration of FOG episodes. This work proposes a robust real-time FOG detection algorithm, which is easy to implement in stand-alone devices working in non-supervised conditions.Method: Data from three different data sets were used in this study, with two employed as independent test sets. Acceleration recordings from 118 PD patients and 21 healthy elderly subjects were collected while they performed simulated daily living activities. A single inertial sensor was attached to the waist of each subject. More than 17 h of valid data and a total number of 1110 FOG episodes were analyzed in this study. The implemented algorithm consisted of a multi-head convolutional neural network, which exploited different spatial resolutions in the analysis of inertial data. The architecture and the model parameters were designed to provide optimal performance while reducing computational complexity and testing time.Results: The developed algorithm demonstrated good to excellent classification performance, with more than 50% (30%) of FOG episodes predicted on average 3.1 s (1.3 s) before the actual onset in the main (independent) data set. Around 50% of FOG was detected with an average delay of 0.8 s (1.1 s) in the main (independent) data set. Moreover, a specificity above 88% (93%) was obtained when testing the algorithm on the main (independent) test set, while 100% specificity was obtained on healthy elderly subjects.Conclusion: The algorithm proved robust, with low computational complexity and processing time, thus paving the way to a real-time implementation in a stand-alone device that can be used in non-supervised environments.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] A Real-Time Detection Algorithm for Freezing of Gait in Parkinson's Disease
    Chang, Yi-Fan
    Ding, Jian-Jiun
    Hu, Hao
    Yang, Wen-Chieh
    Lin, Kwan-Hwa
    Wu, Po-Hung
    2014 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2014, : 1312 - 1315
  • [2] Evaluation of deep convolutional neural networks for detection of freezing of gait in Parkinson's disease patients
    Xia, Yi
    Zhang, Jun
    Ye, Qiang
    Cheng, Nan
    Lu, Yixiang
    Zhang, Dexiang
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2018, 46 : 221 - 230
  • [3] Detection of freezing of gait for Parkinson's disease patients with multi-sensor device and Gaussian neural networks
    Saad, Ali
    Zaarour, Iyad
    Guerin, Francois
    Bejjani, Paul
    Ayache, Mohammad
    Lefebvre, Dimitri
    INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2017, 8 (03) : 941 - 954
  • [4] Detection of freezing of gait for Parkinson’s disease patients with multi-sensor device and Gaussian neural networks
    Ali Saad
    Iyad Zaarour
    François Guerin
    Paul Bejjani
    Mohammad Ayache
    Dimitri Lefebvre
    International Journal of Machine Learning and Cybernetics, 2017, 8 : 941 - 954
  • [5] Inertial Sensor Based Detection of Freezing of Gait for On-Demand Cueing in Parkinson's Disease
    Dvorani, A.
    Jochner, M. C. E.
    Seel, T.
    Salchow-Hoemmen, C.
    Meyer-Ohle, J.
    Wiesener, C.
    Voigt, H.
    Kuehn, A.
    Wenger, N.
    Schauer, T.
    IFAC PAPERSONLINE, 2020, 53 (02): : 16004 - 16009
  • [6] Real-Time Gait Event Detection Using a Single Head-Worn Inertial Measurement Unit
    Hwang, Tong-Hun
    Reh, Julia
    Effenberg, Alfred
    Blume, Holger
    2016 IEEE 6TH INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - BERLIN (ICCE-BERLIN), 2016,
  • [7] Real-time arrhythmia detection using convolutional neural networks
    Vu, Thong
    Petty, Tyler
    Yakut, Kemal
    Usman, Muhammad
    Xue, Wei
    Haas, Francis M.
    Hirsh, Robert A.
    Zhao, Xinghui
    FRONTIERS IN BIG DATA, 2023, 6
  • [8] Real-Time Pedestrian Detection Using Convolutional Neural Networks
    Kuang, Ping
    Ma, Tingsong
    Li, Fan
    Chen, Ziwei
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2018, 32 (11)
  • [9] Real-Time Grasp Detection Using Convolutional Neural Networks
    Redmon, Joseph
    Angelova, Anelia
    2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2015, : 1316 - 1322
  • [10] Fast Spectrogram Inversion Using Multi-Head Convolutional Neural Networks
    Arik, Sercan O.
    Jun, Heewoo
    Diamos, Gregory
    IEEE SIGNAL PROCESSING LETTERS, 2019, 26 (01) : 94 - 98