Two complementary AI approaches for predicting UMLS semantic group assignment: heuristic reasoning and deep learning

Objective: Use heuristic, deep learning (DL), and hybrid AI methods to predict semantic group (SG) assignments for new UMLS Metathesaurus atoms, with target accuracy ≥ 95%.
Materials and Methods: We used train-test datasets from successive 2020AA-2022AB UMLS Metathesaurus releases. Our heuristic “waterfall\" approach employed a sequence of seven different SG prediction methods. Atoms not qualifying for a method were passed on to the next method. The DL approach generated BioWordVec and SapBERT embeddings for atom names, BioWordVec embeddings for source vocabulary names, and BioWordVec embeddings for atom names of the second-to-top nodes of an atom’s source hierarchy. We fed a concatenation of the four embeddings into a fully connected multi-layer neural network with an output layer of 15 nodes (one for each SG). Both methods were capable of estimating the probability that their predicted SG for an atom would be correct. We developed two hybrid SG prediction methods combining the strength..., , A pipe delimited text file is provided which can be opened in any text editor or imported into any spreadsheet software. The attached README.txt file explains each column.