题 目: Estimating the association of bivariate survival data through copula models: Applications to head and neck cancer and HIV/AIDS studies
摘要：Radiation therapy has become the primary treatment modality for cancer of the pharynx and larynx in many institutions in the United States. In patients with recurrent head and neck cancer that have failed radiation with or without chemotherapy, salvage surgery is the preferred treatment modality for curative intent. Salvage surgery in the post radiation setting is a significant undertaking frequently requiring major ablative and reconstructive efforts. We hypothesize the initial-disease free interval is positively associated with the overall survival after salvage surgery. In another study, forty-nine patients with AIDS-related non-Hodgkin’s lymphoma in East Africa were treated with lomustine, VP-16, cyclophosphamide and procarbazine. There is a strong interest in the association of overall survival (OS) and progression-free survival (PFS) in the area of biomarkers and surrogate endpoints research. We hypothesize there is a positive association between OS and PFS in this specific disease setting. Due to censoring, the estimation and inference of the association parameter of bivariate survival data based on methods developed recently, namely, a semi-parametric normal copula-based approach, in particular Spearman correlation coefficient, as the dependence of such times is assumed monotonic, is used. A simulation study was conducted to explore which copula is optimal for such task under various scenarios. Based the simulation study, the correlation of the two times with censoring for the clinical study, rs = 0.91 (95% CI: 0.02 – 0.46, p < 0.0001), shows that there was a strong positive association between OS and PFS.
个人简历：Pingfu Fu, The-professor-of-the-year (2010), a tenured Associate Professor of Department of Epidemiology and Biostatistics at Case Western Reserve University, Member and Editorial board of Reviews on Recent Clinical Trials and Member of American Statistical Association. He has worked extensively in cancer research ever since receiving his doctoral degree in Biostatistics in 2001 and has the record of working together with numerous investigators at Case Western Reserve medical school and Case Comprehensive Cancer Center (Case CCC) in particular. He has a broad training in mathematics, statistics/biostatistics, and computer science. He has worked on numerous cancer projects including lung cancer, breast cancer, prostate cancer, leukemia among others, and applied many novel statistical methods in data from clinical studies. Specifically, he has helped investigators in protocol development regarding to study design and clinical trial conducting/monitoring, in grant development, in data analysis and scientific reporting. He has been serving in the Data Safety and Toxicity Committee, Tissue Utilization Review Committee and Protocol Review and Monitoring Committee at Case CCC. He has had interest in developing statistical methods to design clinical trials and to analyze data related to a wide range of health outcomes. Besides cancer research, he has got involved in other subject areas in medical research including dermatology, HIV/AIDS. He also teaches survival data analysis annually and mentors/advises graduate students in biostatistics.