Using Structured event to represent complaints of patients: a medical assistant for doctors

Abstract

Extracting relations between entities from complaints of patients is a significant but challenging problem in intelligent medical diagnose. It can help doctors to record the main information from the complaints of patients. As the development of technologies, Doctors need a more effective and convenient way to capture entire information from patients’ complaints and build Electronic Health Records (EHRs). This paper proposes an event generation model which input the complaints of patients directly then output a series of events as complementary to traditional keywords based chief complaint capture. The event generation model adopts an open Chinese Information Extraction (open Chinese IE) and build a part-of-speech tagging to do dependency grammar analysis. Two kinds of evaluations are taken. One is metrics recall-oriented understanding for gusting evaluation (ROUGE). It measures the fitness of the generated events with the standard reference from doctors. The other are accuracy and Matthews Correlation Coefficient (MCC). They test the performance of grammar analysis. The results show our model have an excellent and robust performance.