Change-point detection for monitoring clinical decision support systems with a multi-process dynamic linear model

Siqi Liu, Adam Wright, Dean F. Sittig, Milos Hauskrecht
2017 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)  
A clinical decision support system and its components may malfunction due to different reasons. The objective of this work is to develop computational methods that can help us to monitor the system and assure its proper operation by promptly detecting and analyzing changes in its behavior. We develop a new change-point detection method using the Multi-Process Dynamic Linear Model. The experiments on real and simulated data show that our method outperforms existing change-point detection
more » ... leading to higher accuracy and shorter delay in the detection. To detect changes of the monitoring and alerting component, it would be ideal to have measurements on different components of the CDSS. However, in reality, it is not feasible to
doi:10.1109/bibm.2017.8217712 pmid:29302379 pmcid:PMC5749419 dblp:conf/bibm/LiuWSH17 fatcat:ve2zru6wwng5vn3dxijwduqvay