A classification algorithm to predict chronic pain using both regression and machine learning – A stepwise approach.

This secondary data analysis study aimed to (1) investigate the use of two sense-based parameters (movement and sleep hours) as predictors of chronic pain when controlling for patient demographics and depression, and (2) identify a classification model with accuracy in predicting chronic pain. Data...

Full description

Bibliographic Details
Published in:Applied Nursing Research Vol. 62
Main Authors: Tsai, Pao-Feng, Wang, Chih-Hsuan, Zhou, Yang, Ren, Jiaxiang, Jones, Alisha, Watts, Sarah O., Chou, Chiahung, Ku, Wei-Shinn
Format: research Journal Article
Published: Elsevier B.V. Dec2021
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=153682439&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 153682439
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        08971897
        44Z
      jtl: Applied Nursing Research
      issn: 08971897
      maglogo: N
    pubinfo:
      dt: Dec2021
      vid: 62
      pid: 82545
      pub: Elsevier B.V.
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        153682439
        153682439
        153682439
        10.1016/j.apnr.2021.151504
        153682439
      ppct: 1
      formats:
      tig:
        atl: A classification algorithm to predict chronic pain using both regression and machine learning – A stepwise approach.
      aug:
        au:
          Tsai, Pao-Feng
          Wang, Chih-Hsuan
          Zhou, Yang
          Ren, Jiaxiang
          Jones, Alisha
          Watts, Sarah O.
          Chou, Chiahung
          Ku, Wei-Shinn
        affil: School of Nursing, Auburn University, Auburn, AL 36849, United States of America
      sug:
        subj:
          Classification Algorithms
          Chronic Pain Risk Factors
          Risk Assessment
          Machine Learning
          Depression Prevention and Control
          Sensitivity and Specificity
          Human
          Step-Wise Multiple Regression
          Secondary Analysis
          Questionnaires
          Community Living In Old Age
          Neural Networks (Computer)
          Step
          Descriptive Statistics
          Prediction Models
          Aged
          Movement
          Sleep
          Aged: 65+ years
      ab: This secondary data analysis study aimed to (1) investigate the use of two sense-based parameters (movement and sleep hours) as predictors of chronic pain when controlling for patient demographics and depression, and (2) identify a classification model with accuracy in predicting chronic pain. Data collected by Oregon Health & Science University between March 2018 and December 2019 under the Collaborative Aging Research Using Technology Initiative were analyzed in two stages. Data were collected by sensor technologies and questionnaires from older adults living independently or with a partner in the community. In Stage 1, regression models were employed to determine unique sensor-based behavioral predictors of pain. These sensor-based parameters were used to create a classification model to predict the weekly recalled pain intensity and interference level using a deep neural network model, a machine learning approach, in Stage 2. Daily step count was a unique predictor for both pain intensity (75% Accuracy, F1 = 0.58) and pain interference (82% Accuracy, F1 = 0.59). The developed classification model performed well in this dataset with acceptable accuracy scores. This study demonstrated that machine learning technique can be used to identify the relationship between patients' pain and the risk factors. • Chronic pain disproportionally affects older adults, but their pains are not adequately treated. • Existing non-verbal tools or advanced sensor technologies for pain detection are not feasible in community clinics. • Daily step count is a unique predictor for levels of pain, but additional parameters are needed to improve the prediction. • Combining statistical and machine learning approaches provides a powerful method to develop a predictive model.
      pubtype: Academic Journal
      doctype:
        research
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N