Dynamic categorization of clinical research eligibility criteria by hierarchical clustering

ObjectiveTo semi-automatically induce semantic categories of eligibility criteria from text and to automatically classify eligibility criteria based on their semantic similarity.DesignThe UMLS semantic types and a set of previously developed semantic preference rules were utilized to create an unambiguous semantic feature representation to induce eligibility criteria categories through hierarchical clustering and to train supervised classifiers.MeasurementsWe induced 27 categories and measured the prevalence of the categories in 27,278 eligibility criteria from 1578 clinical trials and compared the classification performance (i.e., precision, recall, and F1-score) between the UMLS-based feature representation and the “bag of words” feature representation among five common classifiers in Weka, including J48, Bayesian Network, Naïve Bayesian, Nearest Neighbor, and instance-based learning classifier.ResultsThe UMLS semantic feature representation outperforms the “bag of words” feature representation in 89% of the criteria categories. Using the semantically induced categories, machine-learning classifiers required only 2000 instances to stabilize classification performance. The J48 classifier yielded the best F1-score and the Bayesian Network classifier achieved the best learning efficiency.ConclusionThe UMLS is an effective knowledge source and can enable an efficient feature representation for semi-automated semantic category induction and automatic categorization for clinical research eligibility criteria and possibly other clinical text.

Graphical abstractThe UMLS semantic types significantly outperform the “bag of words” for feature representation across all criteria categories.Figure optionsDownload full-size imageDownload as PowerPoint slideHighlights► We present a novel method to dynamically categorize clinical research eligibility criteria. ► We demonstrate the value of the UMLS for improving the learning efficiency of semantic classifiers. ► Using the UMLS semantic types is far more effective than using the ‘‘bag of words” for feature representation.