Nurse Staffing Levels Linked to Patient Outcomes

The secondary aim of the study was to develop the use of ‘big data’ techniques, commonly used in industry, to this area of healthcare.

The researchers collected data from the United Kingdom National Health Service (NHS, London), which included physiological signs and symptom data from the clinical database, that were then extracted, imported, and mined alongside a bespoke staffing and outcomes database. The physiological data consisted of 120 million patient entries over six years, while the bespoke database consisted of nine years of daily data on staffing levels and safety factors.

The results revealed 40 correlations between safety, physiological, and staffing factors, including several inter-related elements that demonstrated a correlation between nurse availability and outcomes. The researchers also used the large volumes of data to analyze possible scenarios. One example scenario suggested that replacing six healthcare support workers with six registered nurses on wards with highest incidences of falls could decrease the monthly total number of falls by 15%. The study was published on December 16, 2016, in BMJ Open.

“This was a very exciting project to work on, as it's a different way of thinking about the contribution nurses make to patient safety,” said Professor Alison Leary, RN, PhD, of the LSB School of Health and Social Care. “We were very surprised that so many signals emerged from the data, and it is useful that we were able to feed the new knowledge back to the Trust, who then used it in many different ways to look at patient safety.”

Previous studies examining the relationship between nursing numbers and outcomes highlighted the non-linear relationships between staffing and length of stay. While data are increasingly collected, they are rarely mined within the context of nursing to explore variables associated with the complex work of specialist nurses. The researchers anticipate that such approaches could develop nursing knowledge through the identification of patterns and important links between data, nursing interventions, and patient outcomes.

Related Links:
Birmingham City University
London South Bank University
United Kingdom National Health Service