Journal of Preventive Medicine and Public Health

The Korean Society for Preventive Medicine (대한예방의학회)
권호 표지

Analysis of Repeated Measured VAS in a Clinical Trial for Evaluating a New NSAID with GEE Method

퇴행성 관절염 환자를 대상으로 새로운 진통제 평가를 위한 임상시험자료의 GEE 분석

  • Lim, Hoi-Jeong (Department of Preventive Medicine, Seoul National University, Institute of Radiation Effect & Epidemiology, Medical Research Center, Seoul National University) ;
  • Kim, Yoon-I (Department of Preventive Medicine, Seoul National University) ;
  • Jung, Young-Bok (Department of Orthopaedic Surgery, Chung-Ang University) ;
  • Seong, Sang-Cheol (Department of Orthopaedic Surgery, Seoul National University) ;
  • Ahn, Jin-Hwan (Department of Orthopaedic Surgery, Sungkyunkwan University and Samsung Medical Center) ;
  • Roh, Kwon-Jae (Department of Orthopaedic Surgery, Ewha Woman's University Hospital) ;
  • Kim, Jung-Man (Department of Orthopaedic Surgery, The Catholic University of Korea) ;
  • Park, Byung-Joo (Department of Preventive Medicine, Seoul National University, Institute of Radiation Effect & Epidemiology, Medical Research Center, Seoul National University, Clinical Trial Center, Clinical Research Institute, Seoul National University Hospital)
  • 임회정 (서울대학교 의과대학 예방의학교실, 서울대학교 의학연구원 원자력영양역학연구소) ;
  • 김윤이 (서울대학교 의과대학 예방의학교실) ;
  • 정영복 (중앙대학교 의과대학 정형외과학교실) ;
  • 성상철 (서울대학교 의과대학 정형외과학교실) ;
  • 안진환 (성균관대학교 의과대학 정형외과학교실) ;
  • 노권재 (이화여자대학교 의과대학 정형외과학교실) ;
  • 김정만 (가톨릭대학교 의과대학 정형외과학교실) ;
  • 박병주 (서울대학교 의과대학 예방의학교실, 서울대학교 의학연구원 원자력영향역학연구소, 서울대학교병원 임상시험센터)
  • Published : 2004.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective : To compare the efficacy between SKI306X and Diclofenac by using generalized estimating equations (GEE) methodology in the analysis of correlated bivariate binary outcome data in Osteoarthritis (OA) diseases. Methods : A randomized, double-blind, active comparator-controlled, non-inferiority clinical trial was conducted at 5 institutions in Korea with the random assignment of 248 patients aged 35 to 75 years old with OA of the knee and clinical evidence of OA. Patients were enrolled in this study if they had at least moderate pain in the affected knee joint and a score larger than 35mm as assessed by VAS (Visual Analog Scale). The main exposure variable was treatment (SKI 306X vs. Diclofenac) and other covariates were age, sex, BMI, baseline VAS, center, operation history (Yes/No), NSAIDS (Y/N), acupuncture (Y/N), herbal medicine (Y/N), past history of musculoskeletal disease (Y/N), and previous therapy related with OA (Y/N). The main study outcome was the change of VAS pain scores from baseline to the 2nd and 4th weeks after treatment. Pain scores were obtained as baseline, 2nd and 4th weeks after treatment. We applied GEE approach with empirical covariance matrix and independent(or exchangeable) working correlation matrix to evaluate the relation of several risk factors to the change of VAS pain scores with correlated binary bivariate outcomes. Results : While baseline VAS, age, and acupuncture variables had protective effects for reducing the OA pain, its treatment (Joins/Diclofenac) was not statistically significant through GEE methodology (ITT:aOR=1.37, 95% CI=(0.8200, 2.26), PP:aOR=1.47, 95% CI=(0.73, 2.95)). The goodness-of-fit statistic for GEE (6.55, p=0.68) was computed to assess the adequacy of the fitted final model. Conclusions : Both ANCOVA and GEE methods yielded non statistical significance in the evaluation of non-inferiority of the efficacy between SKI306X and Diclofenac. While VAS outcome for each visit was applied in GEE, only VAS outcome for the fourth visit was applied in ANCOVA. So the GEE methodology is more accurate for the analysis of correlated outcomes.

Keywords

References

  1. Liang KY, Zeger S1. Longitudinal data analysis using generalized linear models. Biometrika 1986; 73: 13-22 https://doi.org/10.1093/biomet/73.1.13
  2. Zeger SL, Liang KY. Longitudinal data analysis for dicrete and continuous outcomes. Biometrics 1986; 42: 121-130 https://doi.org/10.2307/2531248
  3. Shin DY, Park TS, A Study on the Use of Working Correlation Matrices in the GEE Approach to the Analysis of Repeated Binary Data, Appl Statistic 1996; M: 15-27 (Korean)
  4. Heimendinger J, Feng Z, Emmons K, Stoddard A, Kinne S, Biener L, Sorensen G, Abrams D, Varnes J, Boutwell B. The working well trial: baseline dietary and smoking behaviors of employees and related worksite characteristics. The working well research group, Prev Med 1995;24: 180-193 https://doi.org/10.1006/pmed.1995.1032
  5. aston JF, Gustafasson M, Rheumatoid arthritis: determination of pain characteristics and comparison of RAJ and VAS in its measurement. Pain 1990; 41: 35-40 https://doi.org/10.1016/0304-3959(90)91106-S
  6. Jung YB, Seong SC, Lee MC et al. A four-week, randomized, double-blind trial of the efficacy and safety of SKI306X, a herbal anti-arthritic agent versus diclofenac in osteoarhritis of the knee. Clinical Trial Report of SK Pharm 2000; M-74I(Korean)
  7. Bendel RB, Afifi AA. Comparison of stopping rules in forward regression. JASA 1977; 72: 4653
  8. Mickey J, Greenland S. A study of the impact of confounder-selection criteria on effect estimation. Am J Epidemiol 1989; 129: 125-137 https://doi.org/10.1093/oxfordjournals.aje.a115101
  9. Horton NJ, Bebchuk JD, Jones CL et al. Goodness-of-fit for GEE: An example with mental health service utilization. Statist Med 1999; 18: 213-222 https://doi.org/10.1002/(SICI)1097-0258(19990130)18:2<213::AID-SIM999>3.0.CO;2-E
  10. SAS/STAT User' s Guide, Versoion 8, Cary, NC, USA: SAS Instiute lnc.; 1999
  11. Zhang Y, Glynn RJ, Fekson DT. Misculoskeletal disease research: should we analyze the joint or the person? J Rheumatol 1996; 23: 1130-1134
  12. Koo HW, Kwark M, Lee Y, Park BJ. Comparison of Efficiency between Individual Randomization and Ouster Randomization in the Field Trial. Korean J Prev Med 2000; 33(1):51-55