Hospital Alerting Via Electronic Noticeboard (HAVEN) (360G-Wellcome-103703_Z_14_Z)

Deterioration in hospital patients frequently goes unrecognised, despite widespread introduction of vital sign-based early warning scores . All electronically recorded patient data including demographics, laboratory results and vital signs may better identify patients who will deteriorate. However, these different data classes are not integrated and displayed to support decision-making or to quantify a patient's risk. Consequently, patients deteriorate because they are not reliably identified to clinical teams equipped to deliver timely, often life-saving treatments. A hospital- wide surveillance system using electronically-available patient data to provide a continuously-updated risk index is required. We will identify records of inpatients who have experienced unchecked deterioration until they require intensive care unit (ICU) admission and use their data to develop and validate risk-prediction algorithms based on all classes of patient data available within electronic records. We will use these algorithms to deliver a prototype hospital-wide system allowing clinicians to identify, rank, review and treat patients who without acute medical intervention will deteriorate and require ICU admission. Information will be optimally presented to support decision-making and ease of interpretation. If early recognition of deterioration reduced the ~40,000 UK ward patients admitted to ICU annually by only 10% nearly £40m of ICU bed capacity would become available.