Despite the vast quantities of published artificial intelligence (AI) algorithms that target trauma and orthopaedic applications, very few progress to inform clinical practice. One key reason for this is the lack of a clear pathway from development to deployment. In order to assist with this process, we have developed the Clinical Practice Integration of Artificial Intelligence (CPI-AI) framework – a five-stage approach to the clinical practice adoption of AI in the setting of trauma and orthopaedics, based on the IDEAL principles ( Cite this article:
As of April 2010 all NHS institutions in the United Kingdom are required to publish data on surgical site infection, but the method for collecting this has not been decided. We examined 7448 trauma and orthopaedic surgical wounds made in patients staying for at least two nights between 2000 and 2008 at our institution and calculated the rate of surgical site infection using three definitions: the US Centers for Disease Control, the United Kingdom Nosocomial Infection National Surveillance Scheme and the ASEPSIS system. On the same series of wounds, the infection rate with outpatient follow-up according to Centre for Disease Control was 15.45%, according to the UK Nosocomial infection surveillance was 11.32%, and according to ASEPSIS was 8.79%. These figures highlight the necessity for all institutions to use the same method for diagnosing surgical site infection. If different methods are used, direct comparisons will be invalid and published rates of infection will be misleading.
