[Ml-stat-talks] bayesian nonparametric modeling of psychiatric disorders

David Blei blei at CS.Princeton.EDU
Sat Oct 19 14:05:24 EDT 2013


ml-stat-talks

francisco ruiz, who has been visiting princeton for a few months, will
be speaking on wednesday 10/23 at 2:00PM in CS room 302.  he will
discuss his recent research on bayesian nonparametric modeling of
psychiatric survey data.  it should be very interesting.  see below.

best
dave

---

Bayesian nonparametric analysis of psychiatric disorders.
Francisco Ruiz

Wed 10/23, 2:00PM
CS Room 302

Abstract: The analysis of comorbidity is an open and complex research
field in the branch of psychiatry, where clinical experience and
several studies suggest that the relation among the psychiatric
disorders may have etiological and treatment implications. In this
paper, we are interested in applying latent feature modeling to find
the latent structure behind the psychiatric disorders that can help to
examine and explain the relationships among them. To this end, we use
the large amount of information collected in the National Epidemio-
logic Survey on Alcohol and Related Conditions (NESARC) database and
propose to model these data using a nonparametric latent model based
on the Indian Buffet Process (IBP). Due to the discrete nature of the
data, we first need to adapt the observation model for discrete random
variables. We propose a generative model in which the observations are
drawn from either a softmax distribution or a multinomial probit
likelihood, given the IBP matrix. The implementation of an efficient
Gibbs sampler is accomplished using the Laplace approximation or the
nested expectation propagation (nEP) algorithm, which allows
integrating out the weighting factors of the model. We also provide a
variational inference algorithm for the model with the softmax
likelihood, which provides a complementary (and less expensive in
terms of computational complexity) alternative to the Gibbs sampler
allowing us to deal with a larger number of data. Finally, we use the
model to analyze comorbidity among the psychiatric disorders diagnosed
by experts for the NESARC database.


More information about the Ml-stat-talks mailing list