David Engler

In multiple sclerosis, the primary clinical measure of disability level is an ordinal score, the expanded disability severity scale score. In relapsing-remitting multiple sclerosis, measures of relapse are additionally of interest. Multiple sclerosis patients are typically assessed with regard to both the expanded disability severity scale and relapse state at each follow-up visit. As both are discrete measures, the two can be viewed as jointly dependent Markov processes. One of the main goals of multiple sclerosis research is to accurately model, over time, both transitions between expanded disability severity scale states and change in relapse state. This objective requires a number of significant modeling decisions, including decisions about whether or not the combination of specific disease states is warranted and assessment of the dependence structure between the two disease processes. Historically, such decisions are often made in an ad hoc manner and are not formally justified. We propose novel use of Bayes factors and Bayesian variable selection in the assessment of jointly dependent Markovian processes in multiple sclerosis. Methods are assessed using both simulated data and data collected from the Partners Multiple Sclerosis Center in Boston, MA.

Background: Meningiomas may occur either as familial tumors in two distinct disorders, familial multiple meningioma and neurofibromatosis 2 (NF2), or sporadically, as either single or multiple tumors in individuals with no family history. Meningiomas in NF2 and approximately 60% of sporadic meningiomas involve inactivation of the NF2 locus, encoding the tumor suppressor merlin on chromosome 22q. This study was undertaken to establish whether genomic profiling could distinguish familial multiple meningiomas from sporadic solitary and sporadic multiple meningiomas. Methods: We compared 73 meningiomas presenting as sporadic solitary (64), sporadic multiple (5) and familial multiple (4) tumors using genomic profiling by array comparative genomic hybridization (array CGH). Results: Sporadic solitary meningiomas revealed genomic rearrangements consistent with at least two mechanisms of tumor initiation, as unsupervised cluster analysis readily distinguished tumors with chromosome 22 deletion (associated with loss of the NF2 tumor suppressor) from those without chromosome 22 deletion. Whereas sporadic meningiomas without chromosome 22 loss exhibited fewer chromosomal imbalance events overall, tumors with chromosome 22 deletion further clustered into two major groups that largely, though not perfectly, matched with their benign (WHO Grade I) or advanced (WHO Grades II and III) histological grade, with the latter exhibiting a significantly greater degree of genomic imbalance (P < 0.001). Sporadic multiple meningiomas showed a frequency of genomic imbalance events comparable to the atypical grade solitary tumors. By contrast, familial multiple meningiomas displayed no imbalances, supporting a distinct mechanism for the origin for these tumors. Conclusion: Genomic profiling can provide an unbiased adjunct to traditional meningioma classification and provides a basis for exploring the different genetic underpinnings of tumor initiation and progression. Most importantly, the striking difference observed between sporadic and familial multiple meningiomas indicates that genomic profiling can provide valuable information for differential diagnosis of subjects with multiple meningiomas and for considering the risk for tumor occurrence in their family members.

In many diseases, Markov transition models are useful in describing transitions between discrete disease states. Often the probability of transitioning from one state to another varies widely across subjects. This heterogeneity is driven, in part, by a possibly unknown number of previous disease states and by potentially complex relationships between clinical data and these states. We propose use of Bayesian variable selection in Markov transition models to allow estimation of subject‐specific transition probabilities. Our approach simultaneously estimates the order of the Markov process and the transition‐specific covariate effects. The methods are assessed using simulation studies and applied to model disease‐state transition on the expanded disability status scale (EDSS) in multiple sclerosis (MS) patients from the Partners MS Center in Boston, MA. The proposed methodology is shown to accurately identify complex covariate–transition relationships in simulations and identifies a clinically significant interaction between relapse history and EDSS history in MS patients. Copyright © 2009 John Wiley & Sons, Ltd.

Use of microarray technology often leads to high-dimensional and low-sample size (HDLSS) data settings. A variety of approaches have been proposed for variable selection in this context. However, only a small number of these have been adapted for time-to-event data where censoring is present. Among standard variable selection methods shown both to have good predictive accuracy and to be computationally efficient is the elastic net penalization approach. In this paper, adaptations of the elastic net approach are presented for variable selection both under the Cox proportional hazards model and under an accelerated failure time (AFT) model. Assessment of the two methods is conducted through simulation studies and through analysis of microarray data obtained from a set of patients with diffuse large B-cell lymphoma where time to survival is of interest. The approaches are shown to match or exceed the predictive performance of a Cox-based and an AFT-based variable selection method. The methods are moreover shown to be much more computationally efficient than their respective Cox- and AFT-based counterparts.