Classification of Parkinson’s disease and its stages using machine learning

被引:0
|
作者
John Michael Templeton
Christian Poellabauer
Sandra Schneider
机构
[1] Florida International University,Department of Computing and Information Sciences
[2] Saint Mary’s College,Department of Communicative Sciences and Disorders
来源
关键词
D O I
暂无
中图分类号
学科分类号
摘要
As digital health technology becomes more pervasive, machine learning (ML) provides a robust way to analyze and interpret the myriad of collected features. The purpose of this preliminary work was to use ML classification to assess the benefits and relevance of neurocognitive features both tablet-based assessments and self-reported metrics, as they relate to Parkinson’s Disease (PD) and its stages [Hoehn and Yahr (H&Y) Stages 1–5]. Further, this work aims to compare perceived versus sensor-based neurocognitive abilities. In this study, 75 participants (n=50\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n = 50$$\end{document} PD; n=25\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$n = 25$$\end{document} control) completed 14 tablet-based neurocognitive functional tests (e.g., motor, memory, speech, executive, and multifunction), functional movement assessments (e.g., Berg Balance Scale), and standardized health questionnaires (e.g., PDQ-39). Decision tree classification of sensor-based features allowed for the discrimination of PD from healthy controls with an accuracy of 92.6%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$92.6\%$$\end{document}, and early and advanced stages of PD with an accuracy of 73.7%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$73.7\%$$\end{document}; compared to the current gold standard tools [e.g., standardized health questionnaires (78.3%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$78.3\%$$\end{document} accuracy) and functional movement assessments (70%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$70\%$$\end{document} accuracy)]. Significant features were also identified using decision tree classification. Device magnitude of acceleration was significant in 12 of 14 tests (85.7%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$85.7\%$$\end{document}), regardless of test type. For classification between diagnosed and control populations, 17 motor (e.g., device magnitude of acceleration), 9 accuracy (e.g., number of correct/incorrect interactions), and 8 timing features (e.g., time to between interactions) were significant. For classification between early (H&Y Stages 1 and 2) and advanced (H&Y Stages 3, 4, and 5) stages of PD, 7 motor, 12 accuracy, and 14 timing features were significant. Finally, this work depicts that perceived functionality of individuals with PD differed from sensor-based functionalities. In early-stage PD was shown to be 21.6%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$21.6\%$$\end{document} lower than sensor-based scores with notable perceived deficits in memory and executive function. However, individuals in advanced stages had elevated perceptions (1.57x) for executive and behavioral functions compared to early-stage populations. Machine learning in digital health systems allows for a more comprehensive understanding of neurodegenerative diseases and their stages and may also depict new features that influence the ways digital health technology should be configured.
引用
收藏
相关论文
共 50 条
  • [21] Diagnosis of Parkinson's Disease Using Machine Learning Algorithms
    Thakur, Khushal
    Kapoor, Divneet Singh
    Singh, Kiran Jot
    Sharma, Anshul
    Malhotra, Janvi
    THIRD CONGRESS ON INTELLIGENT SYSTEMS, CIS 2022, VOL 1, 2023, 608 : 205 - 217
  • [22] Early Detection of Parkinson's Disease Using Machine Learning
    Salunkhe, Shweta S.
    Ganveer, Samita
    Bire, Himani
    Deshmukh, Rutuja
    JOURNAL OF ELECTRICAL SYSTEMS, 2024, 20 (02) : 2255 - 2266
  • [23] Predicting Parkinson's Disease Progression: Analyzing Prodromal Stages Through Machine Learning
    Martinez-Eguiluz, Maitane
    Muguerz, Javier
    Arbelaitz, Olatz
    Gurrutxaga, Ibai
    Carlos Gomez-Esteban, Juan
    Murueta-Goyena, Ane
    Gabilondo, Inigo
    ADVANCES IN ARTIFICIAL INTELLIGENCE, CAEPIA 2024, 2024, : 61 - 70
  • [24] Detecting Sensitive Mobility Features for Parkinson's Disease Stages Via Machine Learning
    Mirelman, Anat
    Ben Or Frank, Mor
    Melamed, Michal
    Granovsky, Lena
    Nieuwboer, Alice
    Rochester, Lynn
    Del Din, Silvia
    Avanzino, Laura
    Pelosin, Elisa
    Bloem, Bastiaan R.
    Della Croce, Ugo
    Cereatti, Andrea
    Bonato, Paolo
    Camicioli, Richard
    Ellis, Theresa
    Hamilton, Jamie L.
    Hass, Chris J.
    Almeida, Quincy J.
    Inbal, Maidan
    Thaler, Avner
    Shirvan, Julia
    Cedarbaum, Jesse M.
    Giladi, Nir
    Hausdorff, Jeffrey M.
    MOVEMENT DISORDERS, 2021, 36 (09) : 2144 - 2155
  • [25] Machine learning for early detection and severity classification in people with Parkinson's disease
    Hwang, Juseon
    Youm, Changhong
    Park, Hwayoung
    Kim, Bohyun
    Choi, Hyejin
    Cheon, Sang-Myung
    SCIENTIFIC REPORTS, 2025, 15 (01):
  • [26] Machine Learning Algorithms for Classification Patients with Parkinson's Disease and Hereditary Ataxias
    Escamilla-Luna, Osiris
    Wister, Miguel A.
    Hernandez-Torruco, Jose
    JOURNAL OF COMMUNICATIONS SOFTWARE AND SYSTEMS, 2023, 19 (01) : 9 - 18
  • [27] Parkinson's Disease Detection by Using Machine Learning Method based on Local Classification on Class Boundary
    Du, Qiuyang
    Shen, Jinan
    Wen, Pengcheng
    Chen, Xinpeng
    DISCOVER APPLIED SCIENCES, 2024, 6 (11)
  • [28] Efficient Classification of Parkinson's Disease Using Extreme Learning Machine and Hybrid Particle Swarm Optimization
    Shahsavari, Marziye Keshavarz
    Bakhsh, Hajar Rajabi
    Rashidi, Hasan
    2016 4TH INTERNATIONAL CONFERENCE ON CONTROL, INSTRUMENTATION, AND AUTOMATION (ICCIA), 2016, : 148 - 154
  • [29] Machine Learning Smart System for Parkinson Disease Classification Using the Voice as a Biomarker
    Tougui, Ilias
    Jilbab, Abdelilah
    El Mhamdi, Jamal
    HEALTHCARE INFORMATICS RESEARCH, 2022, 28 (03) : 210 - 221
  • [30] Early Detection of Parkinson's Disease Using Deep Learning and Machine Learning
    Wang, Wu
    Lee, Junho
    Harrou, Fouzi
    Sun, Ying
    IEEE ACCESS, 2020, 8 : 147635 - 147646