Multi-Classification of Clinical Guidelines in Concept Hierarchies

Clinical practice guidelines (CPGs) are increasingly common in clinical medicine for prescribing a set of rules that a physician should follow. Recent interest is in accurate retrieval of CPGs at the point of care. Examples are the CPGs digital libraries National Guideline Clearinghouse (NGC) or Vaidurya (DeGeL), which are organized along predefined concept hierarchies, like MeSH and UMLS. In this case, both browsing and concept-based search can be applied. Mandatory step in enabling both ways to CPGs retrieval is manual classification of CPGs along the concepts hierarchy. This task is extremely time consuming. Supervised learning approaches, where a classifier is trained based on a meaningful set of labeled examples is not a satisfying solution, because usually too few or no CPGs are provided as training set for each class. In this paper we present how to apply the Tax- SOM model for multi-classification. TaxSOM is an unsupervised technique that supports the physician in the classification of CPGs along the concepts hierarchy, even when no labeled examples are available. This model exploits lexical and topological information on the hierarchy to elaborate a classification hypothesis for any given CPG. We argue that such a kind of unsupervised classification can support a physician to classify CPGs by recommending the most probable classes. An experimental evaluation on various concept hierarchies with hundreds of CPGs and categories provides the empirical evidence of the proposed technique