There is an emerging need in clinical research to accurately predict patients' disease status and disease progression by optimally integrating multivariate clinical information. Clinical data are often collected over time for multiple biomarkers of different types (e.g. continuous, binary and counts). In this paper, we present a flexible and dynamic (time-dependent) discriminant analysis approach in which multiple biomarkers of various types are jointly modelled for classification purposes by the multivariate generalized linear mixed model. We propose a mixture of normal distributions for the random effects to allow additional flexibility when modelling the complex correlation between longitudinal biomarkers and to robustify the model and the classification procedure against misspecification of the random effects distribution. These longitudinal models are subsequently used in a multivariate time-dependent discriminant scheme to predict, at any time point, the probability of belonging to a particular risk group. The methodology is illustrated using clinical data from patients with epilepsy, where the aim is to identify patients who will not achieve remission of seizures within a five-year follow-up period.

Charles University Faculty of Mathematics and Physics Department of Probability and Mathematical Statistics Prague Czech Republic

Department of Biostatistics University of Liverpool UK

Department of Eye and Vision Science University of Liverpool UK

Zobrazit více v PubMed

Marson AG, Al-Kharusi AM, Alwaidh M, et al. The SANAD study of effectiveness of valproate, lamotrigine, or topiramate for generalised and unclassifiable epilepsy: an unblinded randomised controlled trial. Lancet 2007; 369: 1016–1026. PubMed PMC

Marson AG, Al-Kharusi AM, Alwaidh M, et al. The SANAD study of effectiveness of carbamazepine, gabapentin, lamotrigine, oxcarbazepine, or topiramate for treatment of partial epilepsy: an unblinded randomised controlled trial. Lancet 2007; 369: 1000–1015. PubMed PMC

Bonnett L, Smith CT, Smith D, et al. Prognostic factors for time to treatment failure and time to 12 months of remission for patients with focal epilepsy: post-hoc, subgroup analyses of data from the SANAD trial. Lancet Neurol 2012; 11: 331–340. PubMed

Bonnett LJ, Smith CT, Smith D, et al. Time to 12-month remission and treatment failure for generalised and unclassified epilepsy. J Neurol Neurosurg Psychiatry 2014; 85: 603–610. PubMed PMC

van Houwelingen H, Putter H. Dynamic prediction in clinical survival analysis, Boca Raton, FL: CRC Press, 2011.

Rizopoulos D. Joint models for longitudinal and time-to-event data: with applications in R, Boca Raton, FL: CRC Press, 2012.

Proust-Lima C, Taylor JMG. Development and validation of a dynamic prognostic tool for prostate cancer recurrence using repeated measures of posttreatment PSA: a joint modeling approach. Biostatistics 2009; 10: 535–549. PubMed PMC

Proust-Lima C, Séne M, Taylor JM, et al. Joint latent class models for longitudinal and time-to-event data: a review. Stat Meth Med Res 2014; 23: 74–90. PubMed PMC

Proust-Lima C, Dartigues JF, Jacqmin-Gadda H. Joint modelling of repeated multivariate cognitive measures and competing risks of dementia and death: a latent process and latent class approach. arXiv preprint arXiv. 14097598 2014. PubMed

Hastie T, Tibshirani R, Friedman J. The elements of statistical learning: data mining, inference, and prediction, 2nd ed New York: Springer-Verlag, 2009.

Tomasko L, Helms RW, Snapinn SM. A discriminant analysis extension to mixed models. Stat Med 1999; 18: 1249–1260. PubMed

Brant LJ, Sheng SL, Morrell CH, et al. Screening for prostate cancer by using random-effects models. J Roy Stat Soc Ser A 2003; 166: 51–62.

Wernecke KD, Kalb G, Schink T, et al. A mixed model approach to discriminant analysis with longitudinal data. Biometrical J 2004; 46: 246–254.

Lix LM, Sajobi TT. Discriminant analysis for repeated measures data: a review. Front Psychol 2010; 1: 1–9. PubMed PMC

Kohlmann M, Held L, Grunert VP. Classification of therapy resistance based on longitudinal biomarker profiles. Biometric J 2009; 51: 610–626. PubMed

Roy A, Khattree R. Discrimination and classification with repeated measures data under different covariance structures. Commun Stat Simul 2005; 34: 167–178.

Roy A, Khattree R. On discrimination and classification with multivariate repeated measures data. J Stat Plan Inference 2005; 134: 462–485.

Kim Y, Kong L. Classification using longitudinal trajectory of biomarker in the presence of detection limits. Stat Meth Med Res 2016; 25: 458–471. PubMed

Laird NM, Ware JH. Random-effects models for longitudinal data. Biometrics 1982; 38: 963–974. PubMed

Marshall G, De la Cruz-Mesía R, Quintana FA, et al. Discriminant analysis for longitudinal data with multiple continuous responses and possibly missing data. Biometrics 2009; 65: 69–80. PubMed

Komárek A, Hansen BE, Kuiper EMM, et al. Discriminant analysis using a multivariate linear mixed model with a normal mixture in the random effects distribution. Stat Med 2010; 29: 3267–3283. PubMed

Morrell CH, Brant LJ, Sheng S, et al. Screening for prostate cancer using multivariate mixed-effects models. Appl Stat 2012; 39: 1151–1175. PubMed PMC

Fieuws S, Verbeke G, Maes B, et al. Predicting renal graft failure using multivariate longitudinal profiles. Biostatistics 2008; 9: 419–431. PubMed

Verbeke G, Lesaffre E. A linear mixed-effects model with heterogeneity in the random-effects population. J Am Stat Assoc 1996; 91: 217–221.

Litière S, Alonso A, Molenberghs G. The impact of a misspecified random-effects distribution on the estimation and the performance of inferential procedures in generalized linear mixed models. Stat Med 2008; 27: 3125–3144. PubMed

Muthén B, Asparouhov T. Growth mixture modeling: analysis with non-Gaussian random effects. In: Fitzmaurice G, Davidian M, Verbeke G, et al.(eds). Longitudinal data analysis: handbooks of modern statistical methods, Boca Raton, FL: Chapman & Hall/CRC, 2009, pp. 143–165.

McLachlan GJ, Peel D. Finite mixture models, New York: John Wiley & Sons, 2000.

Böhning D, Seidel W, Alfó M, et al. Editorial: advances in mixture models. Comput Stat Data Analysis 2007; 51: 5205–5210.

Komárek A, Komárková L. Clustering for multivariate continuous and discrete longitudinal data. Ann Appl Stat 2013; 7: 177–200.

Komárek A, Komárková L. Capabilities of R package mixAK for clustering based on multivariate continuous and discrete longitudinal data. J Stat Softw 2014; 59: 1–38. PubMed

R Core Team. R: a language and environment for statistical computing. Vienna: R Foundation for Statistical Computing, 2016, http://www.R-project.org/.

Morrell CH, Brant LJ and Sheng S. Comparing approaches for predicting prostate cancer from longitudinal data. In: 2007 Proceedings of the American statistical association (Biometrics Section), pp.127–133. Alexandria: American Statistical Association.

Morrell CH, Sheng SL, Brant LJ. A comparative study of approaches for predicting prostate cancer from longitudinal data. Commun Stat Simul 2011; 40: 1494–1513.

Tanner MA, Wong WH. The calculation of posterior distributions by data augmentation. J Am stat Assoc 1987; 82: 528–540.

Plummer M. Penalized loss functions for Bayesian model comparison. Biostatistics 2008; 9: 523–539. PubMed

Heagerty PJ, Zheng Y. Survival model predictive accuracy and roc curves. Biometrics 2005; 61: 92–105. PubMed

Teixeira L, Cadarso-Surez C, Rodrigues A, et al. Time-dependent ROC methodology to evaluate the predictive accuracy of semiparametric multi-state models in the presence of competing risks: an application to peritoneal dialysis programme. Stat Model 2016; 16: 409–428.

Peyhardi J, Trottier C, Gudon Y. Partitioned conditional generalized linear models for categorical responses. Stat Model 2016; 16: 297–321.

Colombi R, Giordano S. A class of mixture models for multidimensional ordinal data. Stat Model 2016; 16: 322–340.

Personalized risk-based screening for diabetic retinopathy: A multivariate approach versus the use of stratification rules

Identification of patients who will not achieve seizure remission within 5 years on AEDs

Dynamic classification using credible intervals in longitudinal discriminant analysis