TY - GEN
T1 - Fine-grained Patient Similarity Measuring using Contrastive Graph Similarity Networks
AU - Liu, Yuxi
AU - Zhang, Zhenhao
AU - Qin, Shaowen
AU - Salim, Flora D.
AU - Bian, Jiang
AU - Yepes, Antonio Jimeno
PY - 2024/8/22
Y1 - 2024/8/22
N2 - Predictive analytics using Electronic Health Records (EHRs) have become an active research area in recent years, especially with the development of deep learning techniques. A popular EHR data analysis paradigm in deep learning is patient representation learning, which aims to learn a condensed mathematical representation of individual patients. However, EHR data are often inherently irregular, i.e., data entries were captured at different times as well as with different contents due to the individualized needs of each patient. Most of the work focused on the provision of deep neural networks with attention mechanisms that generate complete patient representations that can be readily used for downstream prediction tasks. However, such approaches fail to take patient similarity into account, which is generally used in clinical reasoning scenarios. This study presents a new Contrastive Graph Similarity Network for similarity calculation among patients in large EHR datasets. Particularly, we apply graph-based similarity analysis that explicitly extracts the clinical characteristics of each patient and aggregates the information of similar patients to generate rich patient representations. Experimental results on real-world EHR databases demonstrate the effectiveness and superiority of our method for the task of vital signs imputation and ICU patient deterioration prediction.
AB - Predictive analytics using Electronic Health Records (EHRs) have become an active research area in recent years, especially with the development of deep learning techniques. A popular EHR data analysis paradigm in deep learning is patient representation learning, which aims to learn a condensed mathematical representation of individual patients. However, EHR data are often inherently irregular, i.e., data entries were captured at different times as well as with different contents due to the individualized needs of each patient. Most of the work focused on the provision of deep neural networks with attention mechanisms that generate complete patient representations that can be readily used for downstream prediction tasks. However, such approaches fail to take patient similarity into account, which is generally used in clinical reasoning scenarios. This study presents a new Contrastive Graph Similarity Network for similarity calculation among patients in large EHR datasets. Particularly, we apply graph-based similarity analysis that explicitly extracts the clinical characteristics of each patient and aggregates the information of similar patients to generate rich patient representations. Experimental results on real-world EHR databases demonstrate the effectiveness and superiority of our method for the task of vital signs imputation and ICU patient deterioration prediction.
KW - Graph Contrastive Learning
KW - Patient Representation Learning
KW - Patient Similarity Calculation
UR - http://www.scopus.com/inward/record.url?scp=85203678775&partnerID=8YFLogxK
U2 - 10.1109/ICHI61247.2024.00009
DO - 10.1109/ICHI61247.2024.00009
M3 - Conference contribution
AN - SCOPUS:85203678775
T3 - Proceedings - 2024 IEEE 12th International Conference on Healthcare Informatics, ICHI 2024
SP - 1
EP - 10
BT - Proceedings - 2024 IEEE 12th International Conference on Healthcare Informatics, ICHI 2024
PB - Institute of Electrical and Electronics Engineers
T2 - 12th IEEE International Conference on Healthcare Informatics, ICHI 2024
Y2 - 3 June 2024 through 6 June 2024
ER -