Title : 
BIOSIGN™ : multi-parameter monitoring for early warning of patient deterioration
         
        
            Author : 
Tarassenko, L. ; Hann, A. ; Patterson, A. ; Braithwaite, E. ; Davidson, K. ; Barber, V. ; Young, D.
         
        
            Author_Institution : 
Signal Process. & Neural Networks Group, Oxford Univ., UK
         
        
        
        
        
        
            Abstract : 
Early recognition of abnormalities in the physiological parameters of hospital patients followed by rapid intervention should result in an improvement in functional outcome or mortality rate. We have developed a real-time system, BioSign™, capable of analysing physiological parameters in order to identify adverse trends in multi-parameter space (departure from "normality") and prompt clinical staff to intervene. The model of normality is based on five vital signs, which can all be recorded non-invasively: the heart rate, blood pressure, arterial oxygen saturation, respiration rate and temperature. We have evaluated the trained model of normality in a two-year randomised controlled trial of 405 patients monitored on general medical and surgical wards. Preliminary results show that BioSign™ can provide early warning of changes in clinical status and deterioration in patient condition.
         
        
            Keywords : 
blood pressure measurement; blood vessels; cardiology; medical signal processing; patient monitoring; pneumodynamics; sensor fusion; BIOSIGN™; abnormality recognition; arterial oxygen saturation; blood pressure; catastrophic system; data fusion; heart rate; hospital patient; mortality rate; multiparameter monitoring; normality model; patient deterioration; patient monitoring; physiological parameter; respiration rate;
         
        
        
        
            Conference_Titel : 
Medical Applications of Signal Processing, 2005. The 3rd IEE International Seminar on (Ref. No. 2005-1119)
         
        
            Conference_Location : 
IET
         
        
            Print_ISBN : 
0-86341-570-9