CPC G16H 50/50 (2018.01) [G16H 10/60 (2018.01)] | 20 Claims |
1. Non-transitory computer-readable media having computer-executable instructions embodied thereon that when executed, facilitate a method for determining one or more patient conditions from unstructured text data, the method comprising:
receiving a structured topic modeling (STM) model associating terms with metadata labels;
receiving a set of clusters comprising an association of one or more terms and one or more metadata labels;
receiving a set of candidate conditions associated with each cluster of the set of clusters based on the association of one or more terms and one or more metadata labels;
receiving unstructured clinical narratives associated with a particular patient;
determining, using the STM model and the received unstructured clinical narratives, a likely cluster membership of the particular patient in one or more of a cluster of the set of clusters, wherein the likely cluster membership is determined by calculating a quantitative lexical distance between the unstructured clinical narrative associated with the particular patient and the set of candidate conditions; and
storing the likely cluster membership of the particular patient in a data store.
|