Abstract
The rapidly expanding corpus of medical research literature presents major challenges in the understanding of previous work, the extraction of maximum information from collected data, and the identification of promising research directions. We present a case for the use of advanced machine learning techniques as an aide in this task and introduce a novel methodology that is shown to be capable of extracting meaningful information from large longitudinal corpora and of tracking complex temporal changes within it. Our framework is based on (i) the discretization of time into epochs, (ii) epoch-wise topic discovery using a hierarchical Dirichlet process-based model, and (iii) a temporal similarity graph which allows for the modelling of complex topic changes. More specifically, this is the first work that discusses and distinguishes between two groups of particularly challenging topic evolution phenomena: topic splitting and speciation and topic convergence and merging, in addition to the more widely recognized emergence and disappearance and gradual evolution. The proposed framework is evaluated on a public medical literature corpus.
Highlights
Recent years have witnessed a remarkable convergence of two broad trends
To obtain a quantitative measure, we looked at the number of inter-topic connections formed in respective graphs both when the Bhattacharyya distance (BHD) is used as well as when the Kullback-Leibler divergence (KLD) is applied instead
Our results for the metabolic syndrome (MetS) corpus are summarized in Fig. 2; similar results were obtained for autism spectrum disorder (ASD) data
Summary
Recent years have witnessed a remarkable convergence of two broad trends The first of these concerns information, i.e. data, rapid technological advances coupled with an increased presence of computing in nearly every aspect of daily life, have for the first time made it possible to acquire and store massive amounts of highly diverse types of information. Considering the overarching and global importance of health (to say nothing of practical considerations such as the availability of funding), it is not surprising to observe that the amount of published medical research is immense and its growth is only continuing to accelerate. This presents a clear challenge to a researcher.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
