Format

Send to

Choose Destination
Neural Comput. 2016 Feb;28(2):354-81. doi: 10.1162/NECO_a_00805. Epub 2015 Dec 14.

Infinite Continuous Feature Model for Psychiatric Comorbidity Analysis.

Author information

1
Max Planck Institute for Software Systems, 67663 Kaiserslautern, Germany ivalera@mpi-sws.org.
2
Department of Signal Processing and Communications, University Carlos III in Madrid, 28911 Leganes, Spain; Gregorio Marañón Health Research Institute, 28007 Madrid, Spain; and Department of Computer Science, Columbia University, New York, NY 10027, U.S.A. franrruiz@columbia.edu.
3
Department of Signal Processing and Communications, University Carlos III in Madrid, 28911 Leganes, Madrid, and Gregorio Marañón Health Research Institute, 28007 Madrid, Spain olmos@tsc.uc3m.es.
4
Department of Psychiatry, New York State Psychiatric Institute, Columbia University, New York, NY 10032, U.S.A. cblanco@nyspi.columbia.edu.
5
Department of Signal Processing and Communications, University Carlos III in Madrid, 28911 Leganes, Madrid; Gregorio Marañón Health Research Institute, 28007 Madrid, Spain; and Bell Labs, Alcatel-Lucent, New Providence, NJ 07974, U. S. A. Fernando.Perez-Cruz@Alcatel-Lucent.com.

Abstract

We aim at finding the comorbidity patterns of substance abuse, mood and personality disorders using the diagnoses from the National Epidemiologic Survey on Alcohol and Related Conditions database. To this end, we propose a novel Bayesian nonparametric latent feature model for categorical observations, based on the Indian buffet process, in which the latent variables can take values between 0 and 1. The proposed model has several interesting features for modeling psychiatric disorders. First, the latent features might be off, which allows distinguishing between the subjects who suffer a condition and those who do not. Second, the active latent features take positive values, which allows modeling the extent to which the patient has that condition. We also develop a new Markov chain Monte Carlo inference algorithm for our model that makes use of a nested expectation propagation procedure.

PMID:
26654208
DOI:
10.1162/NECO_a_00805
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Atypon
Loading ...
Support Center