Physiological trajectory of patients pre and post ICU discharge1

The intensive care unit (ICU) admits the most severely ill patients, and the goal of the unit can be interpreted as stabilizing patient physiology. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff. Early detection of physiological deterioration has been highlighted as a key step to reduce ICU readmission and improve patient outcomes. Vital signs were collected for a dataset of 98 patients admitted to an ICU and who survived to hospital discharge after their stay on a step-down ward. A model of physiological normality was developed using data from the day of hospital discharge, and patients were retrospectively evaluated throughout their stay using this model. We show that the physiology of patients being cared for in the ICU improves very rapidly in the three days prior to discharge, and furthermore, that this recovery continues during their stay on the ward, albeit at a slower rate.

[1]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[2]  K. Hillman,et al.  A comparison of Antecedents to Cardiac Arrests, Deaths and EMergency Intensive care Admissions in Australia and New Zealand, and the United Kingdom—the ACADEMIA study , 2004 .

[3]  Toni Tan,et al.  Rehabilitation after critical illness: summary of NICE guidance , 2009, BMJ : British Medical Journal.

[4]  F. Ismail,et al.  Integrated monitoring and analysis for early warning of patient deterioration. , 2007, British journal of anaesthesia.

[5]  D. Harrison,et al.  Systematic review and evaluation of physiological track and trigger warning systems for identifying at-risk patients on the ward , 2007, Intensive Care Medicine.

[6]  David A. Clifton,et al.  Modelling physiological deterioration in post-operative patient vital-sign data , 2013, Medical & Biological Engineering & Computing.

[7]  M. Cowie National Institute for Health and Care Excellence. , 2015, European heart journal.

[8]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[9]  Giles Morgan,et al.  Confidential inquiry into quality of care before admission to intensive care , 1998, BMJ.

[10]  T. Hodgetts,et al.  Incidence, location and reasons for avoidable in-hospital cardiac arrest in a district general hospital. , 2002, Resuscitation.

[11]  C. Vincent,et al.  Adverse events in British hospitals: preliminary retrospective record review , 2001, BMJ : British Medical Journal.