Abstract | ||
---|---|---|
Late onset neonatal sepsis is one of the major clinical concerns when premature babies receive intensive care. Current practice relies on slow laboratory testing of blood cultures for diagnosis. A valuable research question is whether sepsis can be reliably detected before the blood sample is taken. This paper investigates the extent to which physiological events observed in the patient's monitoring traces could be used for the early detection of neonatal sepsis. We model the distribution of these events with an autoregressive hidden Markov model (AR-HMM). Both learning and inference carefully use domain knowledge to extract the baby's true physiology from the monitoring data. Our model can produce real-time predictions about the onset of the infection and also handles missing data. We evaluate the effectiveness of the AR-HMM for sepsis detection on a dataset collected from the Neonatal Intensive Care Unit at the Royal Infirmary of Edinburgh. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/JBHI.2013.2294692 | Biomedical and Health Informatics, IEEE Journal of |
Keywords | Field | DocType |
autoregressive processes,blood,diseases,hidden Markov models,neurophysiology,paediatrics,patient diagnosis,patient monitoring,AR-HMM,autoregressive hidden Markov models,blood sample,data monitoring,domain knowledge,early detection,infection,intensive care,learning,neonatal sepsis,patient diagnosis,patient monitoring,physiological events,premature babies,slow laboratory testing,Autoregressive hidden Markov model (AR-HMM),intensive care,neonatal sepsis,real-time inference | Autoregressive model,Neonatal intensive care unit,Remote patient monitoring,Intensive care medicine,Missing data,Sepsis,Hidden Markov model,Intensive care,Medicine,Neonatal sepsis | Journal |
Volume | Issue | ISSN |
18 | 5 | 2168-2194 |
Citations | PageRank | References |
11 | 0.71 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ioan Stanculescu | 1 | 11 | 0.71 |
Christopher K. I. Williams | 2 | 6807 | 631.16 |
Yvonne Freer | 3 | 139 | 9.97 |