Fig. 2.

The performance of interpretable shallow learning-based classifiers (using F1 scores) built by different combinations of the clinical feature representation method with supervised learning algorithm. In both sets of clinical notes, the combination of the hybrid features of bag-of-words + UMLS concepts restricted to five semantic groups with tf-idf weighting and linear SVM yielded the optimal performance for clinical note classification based on the medical subdomain of the document. a F1 score of classifiers trained on iDASH dataset, b F1 score of classifiers trained on MGH dataset. The lines connecting data points for different clinical feature representation methods only serve to tie together the visual results from specific algorithms on different sets of features, but should not imply continuity in the horizontal axis features