Abstract
Using natural language processing tools, we investigate the semantic differences in medical guidelines for three decision problems: breast cancer screening, lower back pain and hypertension management. The recommendation differences may cause undue variability in patient treatments and outcomes. Therefore, having a better understanding of their causes can contribute to a discussion on possible remedies. We show that these differences in recommendations are highly correlated with the knowledge brought to the problem by different medical societies, as reflected in the conceptual vocabularies used by the different groups of authors. While this article is a case study using three sets of guidelines, the proposed methodology is broadly applicable. Technically, our method combines word embeddings and a novel graph-based similarity model for comparing collections of documents. For our main case study, we use the CDC summaries of the recommendations (very short documents) and full (long) texts of guidelines represented as bags of concepts. For the other case studies, we compare the full text of guidelines with their abstracts and tables, summarizing the differences between recommendations. The proposed approach is evaluated using different language models and different distance measures. In all the experiments, the results are highly statistically significant. We discuss the significance of the results, their possible extensions, and connections to other domains of knowledge. We conclude that automated methods, although not perfect, can be applicable to conceptual comparisons of different medical guidelines and can enable their analysis at scale.
Highlights
We evaluate our approach on three sets of medical guidelines: for breast cancer screening, lower back pain management guidelines and hypertension management guidelines
Besides breast cancer screening disagreements, which we model in this article, controversies over PSA screening, hypertension and other treatment and prevention guidelines are well-known
Since the creation of such accurate models is beyond the current state of the art, in this article, we focused on an approximation, i.e., a model that is simple and general enough to be potentially applicable in other situations, and which was useful for the question at hand, namely, whether conceptual vocabulary determines recommendations
Summary
The purpose of this article is to present such a computational method and use a collection of case studies to evaluate its performance. Our objective is to create a graph of conceptual distances between the documents
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have