Machine learning methods are comparable to logistic regression techniques in predicting severe walking limitation following total knee arthroplasty.

Journal: Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA
PMID: 31832697

Abstract

PURPOSE: Machine-learning methods are flexible prediction algorithms with potential advantages over conventional regression. This study aimed to use machine learning methods to predict post-total knee arthroplasty (TKA) walking limitation, and to compare their performance with that of logistic regression.

Authors

  • Yong-Hao Pua
    Department of Physiotherapy, Singapore General Hospital, Singapore, Singapore. pua.yong.hao@sgh.com.sg.
  • Hakmook Kang
    Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA; Center for Quantitative Sciences, Vanderbilt University Medical Center, Nashville, TN, USA. Electronic address: h.kang@vumc.org.
  • Julian Thumboo
    Department of Rheumatology and Immunology, Singapore General Hospital, Singapore, Singapore.
  • Ross Allan Clark
    Research Health Institute, University of the Sunshine Coast, Sunshine Coast, Australia.
  • Eleanor Shu-Xian Chew
    Department of Physiotherapy, Singapore General Hospital, Singapore, Singapore.
  • Cheryl Lian-Li Poon
    Department of Physiotherapy, Singapore General Hospital, Singapore, Singapore.
  • Hwei-Chi Chong
    Department of Physiotherapy, Changi General Hospital, Singapore, Singapore.
  • Seng-Jin Yeo
    Adult Reconstruction Service, Department of Orthopaedic Surgery, Singapore General Hospital, Singapore, Singapore.

Keywords

External Resources

Popular Topics
Recent Journals