Time-sensitive clinical concept embeddings learned from large electronic health records

• Published in: BMC medical informatics and decision making 2019-04, Vol.19 (Suppl 2), p.58-58, Article 58
• Main Authors: Xiang, Yang, Xu, Jun, Si, Yuqi, Li, Zhiheng, Rasmy, Laila, Zhou, Yujia, Tiryaki, Firat, Li, Fang, Zhang, Yaoyun, Wu, Yonghui, Jiang, Xiaoqian, Zheng, Wenjin Jim, Zhi, Degui, Tao, Cui, Xu, Hua
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Clinical concept embedding; Concept learning; Concept similarity; Data mining; Databases, Factual; Datasets; Deep Learning; Distributional representation; Electronic Health Records; Electronic medical records; Electronic records; Embedding; Evaluation; Health aspects; Heart failure; Humans; Information Storage and Retrieval; Machine learning; Machine translation; Medical coding; Medical records; Medical research; Methods; Natural language processing; Neural networks; Patients; Performance enhancement; Predictive modeling; Similarity; Similarity measures; Technology application; Time Factors; Time sensitive concept embedding; Windows (intervals)
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-019-0766-3

Learning distributional representation of clinical concepts (e.g., diseases, drugs, and labs) is an important research area of deep learning in the medical domain. However, many existing relevant methods do not consider temporal dependencies along the longitudinal sequence of a patient's records, which may lead to incorrect selection of contexts. To address this issue, we extended three popular concept embedding learning methods: word2vec, positive pointwise mutual information (PPMI) and FastText, to consider time-sensitive information. We then trained them on a large electronic health records (EHR) database containing about 50 million patients to generate concept embeddings and evaluated them for both intrinsic evaluations focusing on concept similarity measure and an extrinsic evaluation to assess the use of generated concept embeddings in the task of predicting disease onset. Our experiments show that embeddings learned from information within one visit (time window zero) improve performance on the concept similarity measure and the FastText algorithm usually had better performance than the other two algorithms. For the predictive modeling task, the optimal result was achieved by word2vec embeddings with a 30-day sliding window. Considering time constraints are important in training clinical concept embeddings. We expect they can benefit a series of downstream applications.