Open AccessCan Machine Learning Methods Produce Accurate and Easy-to-use Prediction Models of 30-day Complications and Mortality After Knee or Hip Arthroplasty?
Author(s) -
Alex H. S. Harris,
Alfred C. Kuo,
Yingjie Weng,
Amber W. Trickey,
Thomas Bowe,
Nicholas J. Giori
Publication year - 2019
Publication title -
clinical orthopaedics and related research
Language(s) - English
Resource type - Journals
eISSN - 1528-1132
pISSN - 0009-921X
DOI - 10.1097/corr.0000000000000601
Subject(s) - medicine , generalizability theory , lasso (programming language) , arthroplasty , predictive modelling , reimbursement , sports medicine , veterans affairs , physical therapy , machine learning , surgery , health care , statistics , mathematics , world wide web , computer science , economics , economic growth
Existing universal and procedure-specific surgical risk prediction models of death and major complications after elective total joint arthroplasty (TJA) have limitations including poor transparency, poor to modest accuracy, and insufficient validation to establish performance across diverse settings. Thus, the need remains for accurate and validated prediction models for use in preoperative management, informed consent, shared decision-making, and risk adjustment for reimbursement.