Citations

We consider the problem of model‐based clustering in the presence of many correlated, mixed continuous, and discrete variables, some of which may have missing values. Discrete variables are treated with a latent continuous variable approach, and the Dirichlet process is used to construct a mixture model with an unknown number of components. Variable selection is also performed to identify the variables that are most influential for determining cluster membership. The work is motivated by the need to cluster patients thought to potentially have autism spectrum disorder on the basis of many cognitive and/or behavioral test scores. There are a modest number of patients (486) in the data set along with many (55) test score variables (many of which are discrete valued and/or missing). The goal of the work is to (1) cluster these patients into similar groups to help identify those with similar clinical presentation and (2) identify a sparse subset of tests that inform the clusters in order to eliminate unnecessary testing. The proposed approach compares very favorably with other methods via simulation of problems of this type. The results of the autism spectrum disorder analysis suggested 3 clusters to be most likely, while only 4 test scores had high (>0.5) posterior probability of being informative. This will result in much more efficient and informative testing. The need to cluster observations on the basis of many correlated, continuous/discrete variables with missing values is a common problem in the health sciences as well as in many other disciplines.

A large cohort consisting of all children born to mothers from community provides ‘natural’ selection into different exposures and is a powerful resource for epidemiological research. A large population-based birth cohort with detailed systematic information already recorded, as part of longitudinal medical care, historical and current school data, detailed birth certificate data and all three resources available for every member of the birth cohort, are extremely rare. Our population-based birth cohort consists of all children born between 1976 and 2000 to mothers residing in Olmsted County, Minnesota, at the time of child's birth (N=39 890). In this paper, we provide a comprehensive report of the method describing the identification, the characteristics and longitudinal follow-up of each child (and family members) from the birth cohort, wealth of complementary resources of data and study measures and designs (retrospective, combined retrospective/prospective). In the last decade or so, we obtained scientific and clinically needed answers for incidence rates, potential risk/protective factors, treatment, comorbidities, outcomes, cost/usage and potential biases (that are always assessed and clinically interpreted) of many developmental learning and behavioural disorders (DLBDs) including learning and attention-deficit/hyperactivity disorders, intellectual disability, speech-language impairment and autism spectrum disorder. Many current and future questions related to DLBDs are remaining to be answered. The Olmsted County Birth Cohort (OCBC) is an example of a comprehensive, contemporary epidemiological research model for the development of similar research infrastructures, and its current and future results are important for replication and comparison with other population-based retrospective and prospective birth cohort studies.