Using Semantic Technologies to Extract Highlights from Care Notes

摘要

We propose a cognitive system for patient-centric care that leverages and combines natural language processing, semantics, and learning from users over time to support care professionals working with large volumes of patient notes. The proposed methods highlight the entities embedded in the unstructured data to provide a holistic semantic view of an individual. A user-based evaluation is presented, showing consensus between the users and the system. The adoption of electronic health records have contributed to a growing volume of data while promising to improve quality of care and reduce costs. However, in a system of record, insights about a patient with multiple clinical and social issues are often scattered among several notes. New methods are needed to provide automated extraction of highlights and insights to relevant information to care practitioners [2]. Our system captures knowledge from care professionals' observations, often in an unstructured form, to create a holistic patient-centred view, consisting of entities with explicit semantics extracted from notes. Care professionals are then presented with highlights on the most relevant entities, helping them making informed and personalised decisions.