Probabilistic patient monitoring using extreme value theory: A multivariate, multimodal methodology for detecting patient deterioration

Journal article

Conventional patient monitoring is performed by generating alarms when vital signs exceed pie-determined thresholds, but the false-alarm rate of such monitors in hospitals is so high that alarms are typically ignored. We propose a principled, probabilistic method for combining vital signs into a multivariate model of patient state, using extreme value theory (EVT) to generate robust alarms if a patient's vital signs are deemed to have become sufficiently "extreme". Our proposed formulation operates many orders of magnitude faster than existing methods, allowing on-line learning of models, leading ultimately to patient-specific monitoring.

Authors: Hugueny, S; Clifton, D; Tarassenko, L

• Journal: BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings
• Pages: 5-12
• Publication date: 2010-01-01
• Language: English
• Keywords: Telemetry; Patient monitoring; Multivariate extreme value theory; Novelty detection