Advertisement

Modelling MRI enhancing lesion counts in multiple sclerosis using a negative binomial model: implications for clinical trials

      Abstract

      In multiple sclerosis (MS) the number of new enhancing lesions seen on monthly magnetic resonance imaging (MRI) scans is the most widely used response variable in MRI-monitored studies of experimental treatments. However, no statistical model has been proposed to describe the distribution of the number of such lesions across MS patients. This article briefly summarizes the statistical models for counted data. The negative binomial (NB) model is proposed to fit the number of new enhancing lesions counted in a set of 56 untreated MS patients followed for 9 months. It is shown that the large variability present in this data set is better addressed by the NB model (residual deviance=66.6, 54 degrees of freedom) than by the Poisson model (residual deviance=1830.1, 55 degrees of freedom). Applications of the parametrization of lesion counts are discussed, and an example related to computer simulations for the sample size estimation is presented.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Journal of the Neurological Sciences
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Miller D.H.
        • Albert P.S.
        • Barkhof F.
        • Francis G.
        • Frank J.A.
        • Hodgkinson S.
        • Lublin F.D.
        • Paty D.W.
        • Reingold S.C.
        • Simon J.
        Guidelines for the use of magnetic resonance techniques in monitoring the treatment of multiple sclerosis.
        Ann Neurol. 1996; 39: 6-16
        • Filippi M.
        • Miller D.H.
        MRI in the differential diagnosis and monitoring the treatment of multiple sclerosis.
        Curr Opin Neurol. 1996; 9: 176-186
        • Miller D.H.
        • Barkhof F.
        • Berry I.
        • Kappos L.
        • Scotti G.
        • Thompson A.J.
        Magnetic resonance imaging in monitoring the treatment of multiple sclerosis, concerted action guidelines.
        J Neurol Neurosurg Psychiatry. 1991; 54: 683-688
        • Miller D.H.
        • Barkhof F.
        • Nauta J.J.P.
        Gadolinium enhancement increased the sensitivity of MRI in detecting disease activity in MS.
        Brain. 1993; 116: 1077-1094
        • McFarland H.F.
        • Frank J.A.
        • Albert P.S.
        • Smith M.E.
        • Martin R.
        • Harris J.O.
        • Patronas N.
        • Maloni H.
        • McFarlin D.E.
        Using gadolinium-enhanced magnetic resonance imaging to monitor disease activity in multiple sclerosis.
        Ann Neurol. 1992; 32: 758-766
        • Nauta J.J.P.
        • Thompson A.J.
        • Barkhof F.
        • Miller D.H.
        Magnetic resonance imaging in monitoring the treatment of multiple sclerosis patients, statistical power of parallel-groups and crossover designs.
        J Neurol Sci. 1994; 122: 6-14
        • Truyen L.
        • Barkhof F.
        • Tas M.
        • Van Walderveen M.A.A.
        • Frequin S.T.F.M.
        • Hommes O.R.
        • Nauta J.J.P.
        • Pelman C.H.
        • Valk J.
        Specific power calculations for magnetic resonance imaging (MRI) in monitoring active relapsing-remitting multiple sclerosis (MS), implications for phase II therapeutic trials.
        Multiple Sclerosis. 1997; 2: 283-290
        • Tubridy N.
        • Ader H.J.
        • Barkhof F.
        • Thompson A.J.
        • Miller D.H.
        Exploratory treatment trials in multiple sclerosis using MRI, sample size calculations for relapsing remitting and secondary progressive subgroups using placebo controlled parallel groups.
        J Neurol Neurosurg Psychiatry. 1998; 64: 50-55
        • Poser C.M.
        • Paty D.W.
        • Scheinberg L.
        • McDonald W.I.
        • Davis F.A.
        • Ebers G.C.
        • Johnson K.P.
        • Sibley W.A.
        • Silberberg D.H.
        • Tourtellotte W.
        New diagnostic criteria for multiple sclerosis, guidelines for research protocols.
        Ann Neurol. 1983; 13: 227-231
        • Bishop Y.M.M.
        • Fienberg S.E.
        • Holland P.
        Discrete multivariate analysis. MIT Press, Cambridge, MA1988
        • Gardner W.
        • Mulvey E.P.
        • Shaw E.C.
        Regression analysis of counts and rates, Poisson, overdispersed Poisson, and negative binomial models.
        Psychol Bull. 1995; 118: 392-404
        • Miaou S.P.
        The relationship between truck accidents and geometric design of road sections, Poisson versus negative binomial regressions.
        Accid Anal Prev. 1994; 26: 471-482
        • Glynn R.
        • Stukel T.A.
        • Sharp S.A.
        • Bubolz A.
        • Freeman J.L.
        • Fisher E.S.
        Estimating the variance of standardized rates of recurrent events, with application to hospitalizations among the elderly in New England.
        Am J Epidemiol. 1993; 137: 776-786
        • Venables W.N.
        • Ripley B.D.
        Modern applied statistics with S-plus. Springer-Verlag, New York1994
        • Albert P.S.
        • McFarland H.F.
        • Smith M.E.
        • Frank J.A.
        Repeated measures. Time series for modelling counts from a relapsing-remitting disease, application to modelling disease activity in multiple sclerosis.
        Stat Med. 1994; 13: 453-466
        • Kault D.
        The shape of the distribution of the number of sexual partners.
        Stat Med. 1996; 15: 221-230
        • Hougaard P.
        • Ting Lee M.L.
        • Whitmore G.A.
        Analysis of overdispersed count data by mixtures of Poisson variables and Poisson processes.
        Biometrics. 1997; 53: 1225-1238