29 July 2021 in BMJ Health & Care Informatics
There is much discussion concerning ‘digital transformation’ in healthcare and the potential of artificial intelligence (AI) in healthcare systems. Yet it remains rare to find AI solutions deployed in routine healthcare settings. This is in part due to the numerous challenges inherent in delivering an AI project in a clinical environment. In this article, several UK healthcare professionals and academics reflect on the challenges they have faced in building AI solutions using routinely collected healthcare data. These personal reflections are summarised as 10 practical tips. In our experience, these are essential considerations for an AI healthcare project to succeed. They are organised into four phases: conceptualisation, data management, AI application and clinical deployment. There is a focus on conceptualisation, reflecting our view that initial set-up is vital to success. We hope that our personal experiences will provide useful insights to others looking to improve patient care through optimal data use.
1 January 2015 in Plastic and Reconstructive Surgery
The purpose of this study was to (1) determine risk factors predictive of delayed abdominal healing; (2) determine characteristics that perpetuate progression to chronic abdominal wounds and describe the resultant morbidity; and (3) identify outcomes and cost following two treatment strategies-conservative wound care and early reoperative primary closure. Patients were identified from a database of abdominally based free flaps performed from January of 2005 through July of 2012. One thousand two hundred eighteen abdominal donor sites were reviewed, and 167 cases (13.7 percent) of delayed abdominal wound healing were identified. Obesity (p < 0.0001), smoking (p = 0.043), bilateral reconstruction (p = 0.006), preoperative chemotherapy (p = 0.006), and abdominal mesh (p = 0.028) were independently associated with delayed healing. Initiation of chemotherapy p < 0.0001), wet-to-dry wound care (p = 0.001), negative-pressure wound therapy (p = 0.002), and flap type (p = 0.047) were predictive of chronic wounds, and such wounds generated higher rates of hospital readmission (p = 0.009), mesh complications (p < 0.001), and hernia/bulge (p = 0.006). Patients who underwent delayed primary wound closure were more likely to have a well-healed abdomen within 1 month (90.9 percent versus 24.2 percent; p < 0.0001), resulting in lower cost, fewer hospital readmissions, lower rates of scar revision, and lower rates of mesh complications/hernia/bulge. Chronic abdominal wounds were associated with abdominal wall sequelae, including hernia. Early reoperative primary wound closure has been successfully and selectively implemented, resulting in improved patient outcomes. Risk, III.
1 November 1994 in American Journal of Roentgenology
The purpose of this in vitro study was to determine the value of spiral CT for detecting displacement of fractures of the tibial plateau. The exact amount of inferior plateau depression, if any, is a primary criterion for deciding between surgical management and conservative management.An artificial fracture was produced in a cadaveric tibial plateau. Inferior displacements of 0, 1, 3, and 5 mm were created at the fracture. Spiral CT scans of each displacement were obtained with table speeds of 2, 3, and 5 mm/sec. Section collimation equaled table increment. Coronal image reconstructions were produced by use of standard scanner software. The images were interpreted by six musculoskeletal radiologists.Interpretation accuracy was greatest with coronal images created from the 2 mm/sec scans. For distinguishing 5-mm fracture displacements, the average diagnostic sensitivity and specificity were 96% and 93%, respectively; when a 2-mm depression was used as the criterion for clinical significance, the sensitivi...
2 March 2000 in Emergency Radiology
1 May 2002 in The Journal of Foot and Ankle Surgery
1 September 2021 in Injury