Application of Multiple-Imputation-Based Generalized Estimating Equations Method to Compare Two Treatment Methods Among Women Aged +50 Years With Knee Osteoarthritis

Abstract

Objectives: Elderly people with knee Osteoarthritis are more likely to become disabled than others. The aim of the present study was to explore the association between two treatments and pain severity in women aged 50-75 who suffered from knee Osteoarthritis. Methods & Materials: A total of 40 women with knee Osteoarthritis were randomized into two groups: to either received common treatment or received common treatment accompanied by knee traction. Participants were followed up for 10 times. Due to missing data, the multiple-imputation-based generalized estimating equations (MI-GEE) method was used to estimate the odds of a pain as a function of the treatment groups adjusted for age and body mass index. Adjusted odds ratios and 95% confidence intervals were estimated. Data were analyzed by SPSS and SAS version 9.1. Results: Using common treatment as the reference group, the pain odds ratios was .28 (95%CI: 0.12-0.65) for common treatment accompanied by knee traction group. Conclusion: The pain was found to be lower among patients treated with common treatment accompanied by knee traction than patients treated with common treatment.

Keywords

• GEE
• Odds ratio
• Osteoarthritis