The Use of Classification Trees to Determine Criteria Leading to a Total Joint Replacement Recommendation for Patients with Knee or Hip Osteoarthritis
Loading...
Files
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2011-01-01
Type of Work
Department
Mathematics and Statistics
Program
Statistics
Citation of Original Publication
Rights
This item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan through a local library, pending author/copyright holder's permission.
Access limited to the UMBC community. Item may possibly be obtained via Interlibrary Loan through a local library, pending author/copyright holder's permission.
Abstract
There is a need for a nonacceptable symptom state to indicate when a patient with knee or hip osteoarthritis exhibits symptoms severe enough to warrant total joint replacement (TJR). A previous study using logistic regression and ROC curve analysis was unable to determine pain and functional disability cut points leading to a TJR recommendation. Using the datasets from the previous study, classification trees were used to identify predictors and cut points of those predictors leading to a TJR recommendation. From the analysis, a patient's quality of life and joint space narrowing appeared to be the most important predictors, out of those included in the analysis, of a surgeon's recommendation for TJR. Further research and analysis is needed to determine if the generated classification trees accurately predict a surgeon's recommendation for TJR.