Identifying Patterns of Associated-Conditions through Topic Models of Electronic Medical Records

摘要

Multiple adverse health conditions co-occurring in a patient are typicallyassociated with poor prognosis and increased office or hospital visits.Developing methods to identify patterns of co-occurring conditions can assistin diagnosis. Thus identifying patterns of associations among co-occurringconditions is of growing interest. In this paper, we report preliminary resultsfrom a data-driven study, in which we apply a machine learning method, namely,topic modeling, to electronic medical records, aiming to identify patterns ofassociated conditions. Specifically, we use the well established latentdirichlet allocation, a method based on the idea that documents can be modeledas a mixture of latent topics, where each topic is a distribution over words.In our study, we adapt the LDA model to identify latent topics in patients'EMRs. We evaluate the performance of our method both qualitatively, and showthat the obtained topics indeed align well with distinct medical phenomenacharacterized by co-occurring conditions.