Advertisement

Using Machine Learning to Develop a Short-Form Measure Assessing 5 Functions in Patients With Stroke

  • Gong-Hong Lin
    Affiliations
    Master Program in Long-Term Care, College of Nursing, Taipei Medical University, Taipei, Taiwan
    Search for articles by this author
  • Chih-Ying Li
    Affiliations
    Department of Occupational Therapy, School of Health Professions, University of Texas Medical Branch, Galveston, TX
    Search for articles by this author
  • Ching-Fan Sheu
    Affiliations
    Institute of Education, National Cheng Kung University, Tainan, Taiwan
    Search for articles by this author
  • Chien-Yu Huang
    Affiliations
    Department of Occupational Therapy, College of Medicine, I-Shou University, Kaohsiung, Taiwan

    Department of Physical Medicine and Rehabilitation, National Taiwan University Hospital, Taipei, Taiwan

    Department of Occupational Therapy, College of Medicine, I-Shou University, Kaohsiung, Taiwan
    Search for articles by this author
  • Shih-Chieh Lee
    Affiliations
    School of Occupational Therapy, College of Medicine, National Taiwan University, Taipei, Taiwan

    Department of Occupational Therapy, College of Medicine, National Cheng Kung University, Tainan City, Taiwan

    Institute of Long-Term Care, MacKay Medical College, New Taipei City, Taiwan
    Search for articles by this author
  • Yu-Hui Huang
    Affiliations
    School of Medicine, Chung Shan Medical University, Taichung, Taiwan

    Department of Physical Medicine and Rehabilitation, Chung Shan Medical University Hospital, Taichung, Taiwan
    Search for articles by this author
  • Author Footnotes
    ⁎ Huang and Hsieh contributed equally to this work.
    Ching-Lin Hsieh
    Correspondence
    Corresponding author Ching-Lin Hsieh, PhD, Rm. 418, 4F, No. 14, Xuzhou Rd, Taipei, Taiwan and Yu-Hui Huang, No. 110, Sec. 1, Jianguo N. Rd., Taichung City, Taiwan
    Footnotes
    ⁎ Huang and Hsieh contributed equally to this work.
    Affiliations
    School of Occupational Therapy, College of Medicine, National Taiwan University, Taipei, Taiwan

    School of Occupational Therapy, College of Medicine, National Taiwan University, Taipei, Taiwan

    Department of Occupational Therapy, College of Medical and Health Science, Asia University, Taichung, Taiwan
    Search for articles by this author
  • Author Footnotes
    ⁎ Huang and Hsieh contributed equally to this work.
Published:December 30, 2021DOI:https://doi.org/10.1016/j.apmr.2021.12.006

      Abstract

      Objective

      This study aimed to develop and validate a machine learning-based short measure to assess 5 functions (the ML-5F) (activities of daily living [ADL], balance, upper extremity [UE] and lower extremity [LE] motor function, and mobility) in patients with stroke.

      Design

      Secondary data from a previous study. A follow-up study assessed patients with stroke using the Barthel Index (BI), Postural Assessment Scale for Stroke (PASS), and Stroke Rehabilitation Assessment of Movement (STREAM) at hospital admission and discharge.

      Setting

      A rehabilitation unit in a medical center.

      Participants

      Patients (N=307) with stroke.

      Interventions

      Not applicable.

      Main Outcome Measures

      The BI, PASS, and STREAM.

      Results

      A machine learning algorithm, Extreme Gradient Boosting, was used to select 15 items from the BI, PASS, and STREAM, and transformed the raw scores of the selected items into the scores of the ML-5F. The ML-5F demonstrated good concurrent validity (Pearson's r, 0.88-0.98) and responsiveness (standardized response mean, 0.28-1.01).

      Conclusions

      The ML-5F comprises only 15 items but demonstrates sufficient concurrent validity and responsiveness to assess ADL, balance, UE and LE functions, and mobility in patients with stroke. The ML-5F shows great potential as an efficient outcome measure in clinical settings.

      Keywords

      List of abbreviations:

      ADL (activities of daily living), BI (Barthel Index), LE (lower extremity), CAT-5F (computerized adaptive testing system for assessing 5 functions), ML (machine learning), ML-5F (machine learning-based short measure to assess 5 functions), PASS (Postural Assessment Scale for Stroke), SRM (standardized response mean), STREAM (Stroke Rehabilitation Assessment of Movement), UE (upper extremity)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Archives of Physical Medicine and Rehabilitation
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Appelros P
        • Nydevik I
        • Terent A.
        Living setting and utilisation of ADL assistance one year after a stroke with special reference to gender differences.
        Disabil Rehabil. 2006; 28: 43-49
        • Tyson SF
        • Hanley M
        • Chillala J
        • Selley A
        • Tallis RC.
        Balance disability after stroke.
        Phys Ther. 2006; 86: 30-38
        • Bonita R
        • Beaglehole R.
        Recovery of motor function after stroke.
        Stroke. 1988; 19: 1497-1500
        • Carod-Artal FJ
        • González-Gutiérrez JL
        • Herrero JAE
        • Horan T
        • Seijas EVD.
        Functional recovery and instrumental activities of daily living: follow-up 1-year after treatment in a stroke unit.
        Brain Inj. 2002; 16: 207-216
        • Byeon H
        • Koh HW.
        The relationship between communication activities of daily living and quality of life among the elderly suffering from stroke.
        J Phys Ther Sci. 2016; 28: 1450-1453
        • Kim K
        • Kim YM
        • Kim EK.
        Correlation between the activities of daily living of stroke patients in a community setting and their quality of life.
        J Phys Ther Sci. 2014; 26: 417-419
        • Mahoney FI
        • Barthel DW.
        Functional evaluation: the Barthel Index.
        Md State Med J. 1965; 14: 61-65
        • Benaim C
        • Perennou DA
        • Villy J
        • Rousseaux M
        • Pelissier JY.
        Validation of a standardized assessment of postural control in stroke patients: the Postural Assessment Scale for Stroke Patients (PASS).
        Stroke. 1999; 30: 1862-1868
        • Daley K.
        The Stroke Rehabilitation Assessment of Movement (STREAM): refining and validating the content.
        Physiother Can. 1997; 49: 269-278
        • Gor-García-Fogeda MD
        • Molina-Rueda F
        • Cuesta-Gómez A
        • Carratalá-Tejada M
        • Alguacil-Diego IM
        • Miangolarra-Page JC
        Scales to assess gross motor function in stroke patients: a systematic review.
        Arch Phys Med Rehabil. 2014; 95: 1174-1183
        • Sorrentino G
        • Sale P
        • Solaro C
        • Rabini A
        • Cerri CG
        • Ferriero G.
        Clinical measurement tools to assess trunk performance after stroke: a systematic review.
        Eur J Phys Rehabil Med. 2018; 54: 772-784
        • Sangha H
        • Lipson D
        • Foley N
        • et al.
        A comparison of the Barthel Index and the Functional Independence Measure as outcome measures in stroke rehabilitation: patterns of disability scale usage in clinical trials.
        Int J Rehabil Res. 2005; 28: 135-139
      1. Shirley Ryan AbilityLab. Stroke Rehabilitation Assessment of Movement. Available at: https://www.sralab.org/rehabilitation-measures/stroke-rehabilitation-assessment-movement-measure. Accessed April 16, 2020.

      2. Shirley Ryan AbilityLab. Postural Assessment Scale for Stroke. Available at: https://www.sralab.org/rehabilitation-measures/postural-assessment-scale-stroke. Accessed April 16, 2020.

      3. Shirley Ryan AbilityLab. Barthel Index. Available at: https://www.sralab.org/rehabilitation-measures/barthel-index. Accessed April 16, 2020.

        • Lin GH
        • Huang CY
        • Lee SC
        • et al.
        A 10-item Fugl-Meyer Motor Scale based on machine learning.
        Phys Ther. 2021; 101 (pzab036)
        • Chien CW
        • Lin JH
        • Wang CH
        • Hsueh IP
        • Sheu CF
        • Hsieh CL.
        Developing a short form of the postural assessment scale for people with stroke.
        Neurorehabil Neural Repair. 2007; 21: 81-90
        • Lin GH
        • Huang YJ
        • Lee YC
        • Lee SC
        • Chou CY
        • Hsieh CL.
        Development of a computerized adaptive testing system for assessing 5 functions in patients with stroke: a simulation and validation study.
        Arch Phys Med Rehabil. 2019; 100: 899-907
        • Abbas H
        • Garberson F
        • Glover E
        • Wall DP.
        Machine learning approach for early detection of autism by combining questionnaire and home video screening.
        J Am Med Inform Assoc. 2018; 25: 1000-1007
        • MacIsaac RL
        • Ali M
        • Taylor-Rowan M
        • Rodgers H
        • Lees KR
        • Quinn TJ.
        Use of a 3-item short-form version of the Barthel Index for use in stroke: systematic review and external validation.
        Stroke. 2017; 48: 618-623
        • Hsueh IP
        • Wang WC
        • Wang CH
        • et al.
        A simplified stroke rehabilitation assessment of movement instrument.
        Phys Ther. 2006; 86: 936-943
        • Wang YL
        • Lin GH
        • Huang YJ
        • Chen MH
        • Hsieh CL.
        Refining 3 measures to construct an efficient functional assessment of stroke.
        Stroke. 2017; 48: 1630-1635
        • Huang YJ
        • Lin GH
        • Lee SC
        • Chen YM
        • Huang SL
        • Hsieh CL.
        Group- and individual-level responsiveness of the 3-point Berg Balance Scale and 3-point Postural Assessment Scale for Stroke Patients.
        Arch Phys Med Rehabil. 2018; 99: 529-533
        • Baghaei P.
        The application of multidimensional Rasch models in large scale assessment and validation: an empirical example.
        Rev Electron Investig Psicoeduc Psigopedag. 2012; 10: 233-252
        • Hou WH
        • Shih CL
        • Chou YT
        • et al.
        Development of a computerized adaptive testing system of the Fugl-Meyer motor scale in stroke patients.
        Arch Phys Med Rehabil. 2012; 93: 1014-1020
        • Wall DP
        • Dally R
        • Luyster R
        • Jung J-Y
        • DeLuca TF.
        Use of artificial intelligence to shorten the behavioral diagnosis of autism.
        PLoS One. 2012; 7: e43855
        • Thabtah F
        • Kamalov F
        • Rajab K.
        A new computational intelligence approach to detect autistic features for autism screening.
        Int J Med Inform. 2018; 117: 112-124
        • Sahdra BK
        • Ciarrochi J
        • Parker P
        • Scrucca L.
        Using genetic algorithms in a large nationally representative American sample to abbreviate the Multidimensional Experiential Avoidance Questionnaire.
        Front Psychol. 2016; 7: 189
        • Koh CL
        • Pan SL
        • Jeng JS
        • et al.
        Predicting recovery of voluntary upper extremity movement in subacute stroke patients with severe upper extremity paresis.
        PLoS One. 2015; 10e0126857
        • Chen T
        • Guestrin C.
        XGBoost: a scalable tree boosting system.
        (Paper presented at:)in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA2016 (August 13-17)
        • Hsueh IP
        • Lee MM
        • Hsieh CL.
        Psychometric characteristics of the Barthel activities of daily living index in stroke patients.
        J Formos Med Assoc. 2001; 100: 526-532
        • Hsueh IP
        • Lin JH
        • Jeng JS
        • Hsieh CL.
        Comparison of the psychometric characteristics of the functional independence measure, 5 item Barthel index, and 10 item Barthel index in patients with stroke.
        J Neurol Neurosurg Psychiatry. 2002; 73: 188-190
        • Mao HF
        • Hsueh IP
        • Tang PF
        • Sheu CF
        • Hsieh CL.
        Analysis and comparison of the psychometric properties of three balance measures for stroke patients.
        Stroke. 2002; 33: 1022-1027
        • Yao G
        • Chung CW
        • Yu CF
        • Wang JD.
        Development and verification of validity and reliability of the WHOQOL-BREF Taiwan version.
        J Formos Med Assoc. 2002; 101: 342-351
        • Hsueh IP
        • Hsu MJ
        • Sheu CF
        • Lee S
        • Hsieh CL
        • Lin JH.
        Psychometric comparisons of 2 versions of the Fugl-Meyer Motor Scale and 2 versions of the Stroke Rehabilitation Assessment of Movement.
        Neurorehabil Neural Repair. 2008; 22: 737-744
        • Salter K
        • Jutai J
        • Teasell R
        • Foley N
        • Bitensky J
        • Bayley M.
        Issues for selection of outcome measures in stroke rehabilitation: ICF activity.
        Disabil Rehabil. 2005; 27: 315-340
        • Bartolo M
        • De Nunzio AM
        • Sebastiano F
        • et al.
        Arm weight support training improves functional motor outcome and movement smoothness after stroke.
        Funct Neurol. 2014; 29: 15-21
        • Rao N
        • Zielke D
        • Keller S
        • et al.
        Pregait balance rehabilitation in acute stroke patients.
        Int J Rehabil Res. 2013; 36: 112-117
        • Mohan U
        • Kumar KV
        • Suresh B
        • Misri Z
        • Chakrapani M.
        Effectiveness of mirror therapy on lower extremity motor recovery, balance and mobility in patients with acute stroke: a randomized sham-controlled pilot trial.
        Ann Indian Acad Neurol. 2013; 16: 634-639
        • El-Helow M
        • Zamzam M
        • Fathalla M
        • et al.
        Efficacy of modified constraint-induced movement therapy in acute stroke.
        Eur J Phys Rehabil Med. 2015; 51: 371-379
        • Kojović J
        • Djurić-Jovičić M
        • Došen S
        • Popović MB
        • Popović DB.
        Sensor-driven four-channel stimulation of paretic leg: functional electrical walking therapy.
        J Neurosci Methods. 2009; 181: 100-105
        • Gonzalez O.
        Psychometric and machine learning approaches to reduce the length of scales.
        Multivariate Behavioral Research. 2020 Aug 4; ([Epub ahead of print])
        • De Vet HC
        • Terwee CB
        • Mokkink LB
        • Knol DL.
        Measurement in medicine: a practical guide.
        Cambridge University Press, 2011