查看更多>>摘要：Introduction: This article explores how measures of semantic similarity and relatedness are impacted by the semantic groups to which the concepts they are measuring belong. Our goal is to determine if there are distinctions between homogeneous comparisons (where both concepts belong to the same group) and heterogeneous ones (where the concepts are in different groups). Our hypothesis is that the similarity measures will be significantly affected since they rely on hierarchical is-a relations, whereas relatedness measures should be less impacted since they utilize a wider range of relations. In addition, we also evaluate the effect of combining different measures of similarity and relatedness. Our hypothesis is that these combined measures will more closely correlate with human judgment, since they better reflect the rich variety of information humans use when assessing similarity and relatedness. Method: We evaluate our method on four reference standards. Three of the reference standards were annotated by human judges for relatedness and one was annotated for similarity. Results: We found significant differences in the correlation of semantic similarity and relatedness measures with human judgment, depending on which semantic groups were involved. We also found that combining a definition based relatedness measure with an information content similarity measure resulted in significant improvements in correlation over individual measures. (C) 2014 Elsevier Inc. All rights reserved.
Mattingly, William A.Wiemken, Timothy L.Khan, MohammadKelley, Robert R....
8页
查看更多>>摘要：Missing data arise in clinical research datasets for reasons ranging from incomplete electronic health records to incorrect trial data collection. This has an adverse effect on analysis performed with the data, but it can also affect the management of a clinical trial itself. We propose two graphical visualization schemes to aid in managing the completeness of a clinical research dataset: the binary completeness grid (BCG) for single patient observation, and the gradient completeness grid (GCG) for an entire dataset. We use these tools to manage three clinical trials. Two are ongoing observational trials, while the other is a cohort study that is complete. The completeness grids revealed unexpected patterns in our data and enabled us to identify records that should have been purged and identify missing follow-up data from sets of observations thought to be complete. Binary and gradient completeness grids provide a rapid, convenient way to visualize missing data in clinical datasets. (C) 2015 Elsevier Inc. All rights reserved.
NSTL
Elsevier