Automated prediction of deterioration of infants in paediatric intensive care using SpO2. (1st January 2013)

• Record Type: Journal Article
• Authors: Matam, B. Rajeswari; Duncan, Heather; Lowe, David
• Is Part Of: International journal of biomedical engineering and technology. Volume 13:Number 4(2013)
• Page Start: 341
• Page End: 356
• Publication Date: 2013-01-01
• Subjects: biomedical time series -- critical event inference -- feature space embedding -- paediatric intensive care; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

Acute life-threatening events are mostly predictable in adults and children. Despite real-time monitoring these events still occur at a rate of 4%. This paper describes an automated prediction system based on the feature space embedding and time series forecasting methods of the SpO2 signal; a pulsatile signal synchronised with heart beat. We develop an age-independent index of abnormality that distinguishes patient-specific normal to abnormal physiology transitions. Two different methods were used to distinguish between normal and abnormal physiological trends based on SpO2 behaviour. The abnormality index derived by each method is compared against the current gold standard of clinical prediction of critical deterioration.