Research on Search Ranking Technology of Chinese Electronic Medical Record Based on Adarank

Abstract

Electronic Medical Records (EMR) run through every link in the whole medical activities. How to find the required EMR quickly and accurately has become a difficult point in the process of EMR retrieval. This paper introduces a method to optimize the sorting of search results in Chinese electronic medical record search engine system by using the sorting learning AdaRank retrieval algorithm. In 248 Chinese electronic medical records manually annotated, five sorting learning methods were used for training and testing. Our AdaRank sorting algorithm achieved NDCG@10 of 0.28178, ERR@10 of 0.38038 and MAP@10 of 0.59368. Compared with RankNet, the sorting learning model, LambdaRank, ListNet and LambdaMART, AdaRank methods have better sorting effect.