Strengths and limitations of early warning scores: A systematic review and narrative synthesis

Background: Early warning scores are widely used to identify deteriorating patients. Whilst their ability to predict clinical outcomes has been extensively reviewed, there has been no attempt to summarise the overall strengths and limitations of these scores for patients, staff and systems. This review aims to address this gap in the literature to guide improvements for the optimization of patient safety. Methods: A systematic review was conducted of MEDLINE., PubMed, CINAHL and The Cochrane Library in September 2016. The citations and reference lists of selected studies were reviewed for completeness. Studies were included if they evaluated vital signs monitoring in adult human subjects. Studies regarding the paediatric population were excluded, as were studies describing the development or validation of monitoring models. A narrative synthesis of qualitative, quantitative and mixed-methods studies was undertaken. Findings: 232 studies met the inclusion criteria. Twelve themes were identified from synthesis of the data: Strengths of early warning scores included their prediction value, influence on clinical outcomes, cross-specialty application, international relevance, interaction with other variables, impact on communication and opportunity for automation. Limitations included their sensitivity, the need for practitioner engagement, the need for reaction to escalation and the need for clinical judgment, and the intermittent nature of recording. Early warning scores are known to have good predictive value for patient deterioration and have been shown to improve patient outcomes across a variety of specialties and international settings. This is partly due to their facilitation of communication between healthcare workers. There is evidence that the prediction value of generic early warning scores suffers in comparison to specialty specific scores, and that their sensitivity can be improved by the addition of other variables. They are also prone to inaccurate recording and user error, which can be partly overcome by automation. Conclusions: Early warning scores provide the right language and environment for the timely escalation of patient care. They are limited by their intermittent and user-dependent nature, which can be partially overcome by automation and new continuous monitoring technologies, although clinical judgment remains paramount.