PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Visualization and Prediction of Disease Interactions with Continuous-Time Hidden Markov Models
Jose Leiva-Murillo, Antonio Artés-Rodríguez and Enrique Baca-García
In: From statistical genetics to predictive models in personalized medicine, 16 Dec 2011, Granada, Spain.


This paper describes a method for discovering disease relationships and the evolution of diseases from medical records. The method makes use of continuous-time Markov chain models that overcome some drawbacks of the more widely used discrete-time chain models. The model addresses uncertainty in the diagnoses, possible diagnosis errors and the existence of multiple alternative diagnoses in the records. A set of experiments, performed on a dataset of psychiatric medical records, shows the capability of the model to visualize maps of comorbidity and causal interactions among diseases as well as to perform predictions of future evolution of diseases.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:9110
Deposited By:Jose Leiva-Murillo
Deposited On:21 February 2012