10105013Connecting the dots: Improved (Personalised) Risk Prediction and Reduction in Perioperative Care through joined-up dataClosedCollaborative R&DInnovate UKEvery year, the NHS performs \>10m surgical procedures (Hospital\_Episodes\_Statistics). The elective surgery backlog has grown from 4m pre-Covid to 7.3m in May 2023 pre-Covid (UKgov). NHS England aims to increase surgical activity to 129% of 2019-20 levels in 2024-25 (Elective Recovery Plan). However, numerous challenges -- particularly resource limitations -- make this difficult or even impossible to achieve. Current patient surgical risk prediction (anticipating care needs post-operation) is managed through homogenised risk prediction strategies which miss the nuances of the individualised care a patient might require, and the wider risk factors beyond their direct surgical intervention. There is a clear and urgent need for highly individualised, mass-application tools and services that can support the NHS in increasing surgical efficiency, improving resource planning and reducing waiting lists. In answer, Ultramed is building a novel perioperative digital patient assessment, clinical risk assessment and workflow management tool. Our tool utilises a ground-breaking AI-enabled, personalised clinical risk model to anticipate individual patient requirements from pre-operative data collection and national database. This allows for a more consistent, personalised and effective approach to every patient across the full surgical journey. Ultramed has already developed MyPreOp, a cloud-hosted pre-operative assessment platform for patients and hospitals. Combining clinical data collection with service analytics, it is currently used by \>25 NHS trusts, reducing patient visits by 50% and clinical effort by 40%. This project significantly extends this tool into a much-needed perioperative management tool, which bases hospital resource planning on patient-centric risk analysis while providing a suite of data collection/presentation tools to support clinicians directly. Risk predictions based on our unique, extensive patient dataset will enable creation of a highly sophisticated predictive model, while on-going digital outcome capture will enable long-term improvements in individual and system-wide care. Our solution will ultimately apply across postoperative specialisms, but our initial focus will be via diabetic/obesity centred pathways to prove efficacy and establish a robust case study for wider use. 63.8% of adults in England are overweight (37.9%) or obese (25.9%), while 6% of the UK population has diabetes (diabetesUK). Both diabetes and obesity present higher levels of risk during and after surgery, with potential complications including infection, kidney problems, and heart problems (MacMillan,2023). This project will bring a sorely needed tool closer to market, developing fundamental algorithmic and data structures necessary to develop a usable perioperative system that can support NHS priorities around improved surgical efficiencies and reduced waiting lists.