Accepted author manuscript, 718 KB, PDF document
Final published version
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - ConCarE
T2 - Personalized Clinical Feature Embedding via Capturing the Healthcare Context
AU - Ma, Liantao
AU - Zhang, Chaohe
AU - Wang, Yasha
AU - Ruan, Wenjie
AU - Wang, Jiangtao
AU - Tang, Wen
AU - Ma, Xinyu
AU - Gao, Xin
AU - Gao, Junyi
PY - 2020/4/3
Y1 - 2020/4/3
N2 - Predicting the patient’s clinical outcome from the historical electronic medical records (EMR) is a fundamental research problem in medical informatics. Most deep learning-based solutions for EMR analysis concentrate on learning the clinical visit embedding and exploring the relations between vis- its. Although those works have shown superior performances in healthcare prediction, they fail to thoroughly explore the personal characteristics during the clinical visits. Moreover, existing work usually assumes that a more recent record has a larger weight in the prediction, but this assumption is not true for certain clinical features. In this paper, we propose ConCare to handle the irregular EMR data and extract feature interrelationship to perform individualized healthcare prediction. Our solution can embed the feature sequences separately by modeling the time-aware distribution. ConCare further improves the multi-head self-attention via the cross-head decorrelation, so that the inter-dependencies among dynamic features and static baseline information can be diversely captured to form the personal health context. Experimental results on two real-world EMR datasets demonstrate the effectiveness of ConCare. More importantly, ConCare is able to extract medical findings which can be confirmed by human experts and medical literature.
AB - Predicting the patient’s clinical outcome from the historical electronic medical records (EMR) is a fundamental research problem in medical informatics. Most deep learning-based solutions for EMR analysis concentrate on learning the clinical visit embedding and exploring the relations between vis- its. Although those works have shown superior performances in healthcare prediction, they fail to thoroughly explore the personal characteristics during the clinical visits. Moreover, existing work usually assumes that a more recent record has a larger weight in the prediction, but this assumption is not true for certain clinical features. In this paper, we propose ConCare to handle the irregular EMR data and extract feature interrelationship to perform individualized healthcare prediction. Our solution can embed the feature sequences separately by modeling the time-aware distribution. ConCare further improves the multi-head self-attention via the cross-head decorrelation, so that the inter-dependencies among dynamic features and static baseline information can be diversely captured to form the personal health context. Experimental results on two real-world EMR datasets demonstrate the effectiveness of ConCare. More importantly, ConCare is able to extract medical findings which can be confirmed by human experts and medical literature.
U2 - 10.1609/aaai.v34i01.5428
DO - 10.1609/aaai.v34i01.5428
M3 - Conference contribution/Paper
SN - 9781577358350
T3 - Proceedings of the AAAI Conference on Artificial Intelligence
SP - 833
EP - 840
BT - The Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
PB - AAAI
ER -