Modelling physiological deterioration in post-operative patient vital-sign data

• Published in: Medical & biological engineering & computing Vol. 51; no. 8; pp. 869 - 877
• Main Authors: Pimentel, Marco A. F., Clifton, David A., Clifton, Lei, Watkinson, Peter J., Tarassenko, Lionel
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.08.2013; Springer Nature B.V
• Subjects: Aged; Algorithms; Analysis of Variance; Biomedical and Life Sciences; Biomedical engineering; Biomedical Engineering and Bioengineering; Biomedicine; Clinical trials; Computer Applications; Consciousness; Databases, Factual; Datasets; Density; Deterioration; Digestive System Surgical Procedures; Discharge; Female; Glasgow Coma Scale; Human Physiology; Humans; Image Processing, Computer-Assisted; Imaging; Intensive care; Length of stay; Male; Medical; Middle Aged; Models, Biological; Models, Statistical; Monitoring systems; Mortality; Normality; Original; Original Article; Patients; Physiology; Postoperative Period; Radiology; Signal Processing, Computer-Assisted; Signs; Studies; Surgery; Vital signs; Vital Signs - physiology; Warning; United Kingdom > UK; Patient monitoring; Early warning scores; Novelty detection
• ISSN: 0140-0118; 1741-0444
• DOI: 10.1007/s11517-013-1059-0

Patients who undergo upper-gastrointestinal surgery have a high incidence of post-operative complications, often requiring admission to the intensive care unit several days after surgery. A dataset comprising observational vital-sign data from 171 post-operative patients taking part in a two-phase clinical trial at the Oxford Cancer Centre, was used to explore the trajectory of patients’ vital-sign changes during their stay in the post-operative ward using both univariate and multivariate analyses. A model of normality based vital-sign data from patients who had a “normal” recovery was constructed using a kernel density estimate, and tested with “abnormal” data from patients who deteriorated sufficiently to be re-admitted to the intensive care unit. The vital-sign distributions from “normal” patients were found to vary over time from admission to the post-operative ward to their discharge home, but no significant changes in their distributions were observed from halfway through their stay on the ward to the time of discharge. The model of normality identified patient deterioration when tested with unseen “abnormal” data, suggesting that such techniques may be used to provide early warning of adverse physiological events.