Can Machine Learning Algorithms Predict Which Patients Will Achieve Minimally Clinically Important Differences From Total Joint Arthroplasty?

Journal: Clinical orthopaedics and related research
PMID:

Abstract

BACKGROUND: Identifying patients at risk of not achieving meaningful gains in long-term postsurgical patient-reported outcome measures (PROMs) is important for improving patient monitoring and facilitating presurgical decision support. Machine learning may help automatically select and weigh many predictors to create models that maximize predictive power. However, these techniques are underused among studies of total joint arthroplasty (TJA) patients, particularly those exploring changes in postsurgical PROMs. QUESTION/PURPOSES: (1) To evaluate whether machine learning algorithms, applied to hospital registry data, could predict patients who would not achieve a minimally clinically important difference (MCID) in four PROMs 2 years after TJA; (2) to explore how predictive ability changes as more information is included in modeling; and (3) to identify which variables drive the predictive power of these models.

Authors

  • Mark Alan Fontana
    M. A. Fontana, S. Lyman, G. K. Sarker, D. E. Padgett, C. H. MacLean, Hospital for Special Surgery, Center for the Advancement of Value in Musculoskeletal Care, New York, NY, USA M. A. Fontana, S. Lyman, Weill Cornell Medical College, Department of Healthcare Policy and Research, New York, NY, USA.
  • Stephen Lyman
  • Gourab K Sarker
  • Douglas E Padgett
  • Catherine H MacLean