Speed up health research through topic modeling of coded clinical data

Although random control trial is the gold standard in medical research, researchers are increasingly looking to alternative data sources for hypothesis generation and early-stage evidence collection. Coded clinical data are collected routinely in most hospitals. While they contain rich information directly related to the real clinical setting, they are both noisy and semantically diverse, making them difficult to analyze with conventional statistical tools. This paper presents a novel application of Bayesian nonparametric modeling to uncover latent information in coded clinical data. For a patient cohort, a Bayesian nonparametric model is used to reveal the common comorbidity groups shared by the patients and the proportion that each comorbidity group is reflected individual patient. To demonstrate the method, we present a case study based on hospitalization coding from an Australian hospital. The model recovered 15 comorbidity groups among 1012 patients hospitalized during a month. When patients from two areas of unequal socio-economic status were compared, it reveals higher prevalence of diverticular disease in the region of lower socio-economic status. The study builds a convincing case for routine coded data to speed up hypothesis generation.

Translating research for evidence-based public health: key concepts and future directions

Applying research to guide evidence-based practice is an ongoing and significant challenge for public health. Developments in the emerging field of ‘translation’ have focused on different aspects of the problem, resulting in competing frameworks and terminology. In this paper the scope of ‘translation’ in public health is defined, and four related but conceptually different ‘translation processes’ that support evidence-based practice are outlined: (1) reviewing the transferability of evidence to new settings, (2) translation research, (3) knowledge translation, and (4) knowledge translation research. Finally, an integrated framework is presented to illustrate the relationship between these domains, and priority areas for further development and empirical research are identified.