Systems, methods, and software for assessing ambiguity of medical terms

摘要

Some known medical terms may function as non-medical terms depending on their particular context. Accordingly, the present inventors devised systems, methods, and software that facilitate determining whether a term that is found in a medical corpus is likely to be a medical term when found in another corpus. An exemplary embodiment receives a term and computes an ambiguity score based on language models for a medical and a non-medical corpus.

主权项

1. A computer-implemented method comprising:
receiving a term; determining by the computer an ambiguity score for the term, wherein the ambiguity score is on ratio of a probability of the term and at least first, second and third language models of a plurality of language models, and wherein the first language model is based on a medical corpus of documents and the second language model is based on a general news corpus of documents and the third language model is based on a legal corpus of documents,
wherein the ambiguity score for the term is determined using the function:Stn=λ1⁢log⁡(P⁡(tn|M2))log⁡(P⁡(tn|M1))+λ2⁢log⁡(P⁡(tn|M3))log⁡(P⁡(tn|M1)) where Stnis the ambiguity score for term tn,λ1 is a first constant, λ2 is a second constant, P is a function of probability, M1 is the first language model, M2 is the second language model, and M3 is a third language model; and outputting by the computer the ambiguity score for the term, wherein the ambiguity score for the term is outputted as ranked list, with each score associated with corresponding terms.