A stochastic model to analyse risk factors for emesis in multi-cycle chemotherapies |
| |
| Institution: | 1. Student, Foot & Ankle Unit, Royal National Orthopaedic Hospital, Stanmore, Middlesex, United Kingdom;2. Surgeon, Barking, Havering and Redbridge NHS Trust, Queen''s Hospital, Romford, United Kingdom;3. Surgeon, Robert Jones and Agnes Hunt Orthopaedic Hospital NHS Trust, Oswestry, United Kingdom;4. Surgeon, Northumbria Healthcare NHS Trust, Rake Lane, Tyne and Wear, United Kingdom;5. Surgeon, UCL Institute of Orthopaedics and Musculokeletal Science, RNOH, Brockley Hill, Stanmore, United Kingdom;1. Department of Medicine, Division of Neurology, University of Toronto, Toronto, Ontario, Canada, M4G 3V9;2. Department of Medicine, Division of Physical Medicine and Rehabilitation, Lyndhurst Centre, Toronto, Ontario, Canada, M4G 3V9;3. Lyndhurst Centre, Toronto Rehabilitation Institute, University Health Network, Toronto, Ontario, Canada, M4G 3V9;4. Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada, M4G 3V9;5. Division of Neurology, University Health Network, Toronto, Ontario, Canada, M4G 3V9 |
| |
| Abstract: | We propose a stochastic model to analyse risk factors for emesis in multi-cycle chemotherapies, which allows to describe the effect of a potential risk factor by a single parameter. This model is a hybrid between a random intercept model and a transition model and it is motivated by some medical background knowledge with respect to frequency and course of emesis in cancer patients. We consider maximum likelihood estimation of the parameters of the model and additionally efficient estimation of the marginal risk in the first cycle. Finite sample properties are investigated in a simulation study. The proposed model suffers from a slight overparametrization, such that ML estimates show some poor statistical properties, but estimates of the marginal risk behave quite well. An investigation of alternative, simpler regression models reveals, that in this setting these models allow to define a time-constant regression coefficient only in a somewhat arbitrary manner. Hence we conclude, that the proposed model is valuable in spite of the difficulties with respect to parameter estimation. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
