@inproceedings{ede5028250264b4cb38ed120a0a4e9e6,
title = "CAMP: Co-Attention Memory Networks for Diagnosis Prediction in Healthcare",
abstract = "Diagnosis prediction, which aims to predict future health information of patients from historical electronic health records (EHRs), is a core research task in personalized healthcare. Although some RNN-based methods have been proposed to model sequential EHR data, these methods have two major issues. First, they cannot capture fine-grained progression patterns of patient health conditions. Second, they do not consider the mutual effect between important context (e.g., patient demographics) and historical diagnosis. To tackle these challenges, we propose a model called Co-Attention Memory networks for diagnosis Prediction (CAMP), which tightly integrates historical records, fine-grained patient conditions, and demographics with a three-way interaction architecture built on co-attention. Our model augments RNNs with a memory network to enrich the representation capacity. The memory network enables analysis of fine-grained patient conditions by explicitly incorporating a taxonomy of diseases into an array of memory slots. We instantiate the READ/WRITE operations of the memory network so that the memory cooperates effectively with the patient demographics through co-attention mechanism. Experiments on real-world datasets demonstrate that CAMP consistently performs better than state-of-the-art methods.",
keywords = "Attention mechanism, Diagnosis prediction, Healthcare informatics, Memory networks",
author = "Jingyue Gao and Xiting Wang and Yasha Wang and Zhao Yang and Junyi Gao and Jiangtao Wang and Wen Tang and Xing Xie",
year = "2019",
month = nov,
doi = "10.1109/ICDM.2019.00120",
language = "English",
isbn = "9781728146058",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
publisher = "IEEE",
pages = "1036--1041",
editor = "Jianyong Wang and Kyuseok Shim and Xindong Wu",
booktitle = "Proceedings - 19th IEEE International Conference on Data Mining, ICDM 2019",
address = "United States",
}