No abstract

No abstract

The biggest challenge for text and data mining is to truly impact the biomedical discovery process, enabling scientists to generate novel hypothesis to address the most crucial questions. Among a number of worthy submissions, we have selected six papers that exemplify advances in text and data mining methods that have a demonstrated impact on a wide range of applications. Work presented in this session includes data mining techniques applied to the discovery of 3-way genetic interactions and to the analysis of genetic data in the context of electronic medical records (EMRs), as well as an integrative approach that combines data from genetic (SNP) and transcriptomic (microarray) sources for clinical prediction. Text mining advances include a classification method to determine whether a published article contains pharmacological experiments relevant to drug-drug interactions,

IntroductionAcute gastrointestinal bleeding is a medical emergency. Some 44% of bleeds are caused by peptic ulcer disease but the most severe haemorrhage and highest mortality is seen amongst those with bleeding oesophageal or gastric varices.1 Competent triage and assessment are cornerstones of its initial management, with emphasis on identifying sick patients with life threatening haemodynamic compromise, and then initiating appropriate and timely resuscitation being of paramount importance in the patient’s outcome. In a national audit, variceal bleeding accounted for just over 10% of all UK admissions, with just fewer than 50% presenting outside normal working hours.2 The average mortality for a variceal bleed is reported to be up to 20%, with studies confirming a 2–3 fold increase in mortality amongst inpatients.2 Therefore it is paramount that all junior are able to recognise and manage suspected variceal bleeds appropriately.MethodsAn initial questionnaire was distributed and completed by 67 junior doctors (FY1-FY2) at the University Hospitals of Leicester in November 2015, all with jobs involving the acute medical take and providing ward cover. Junior doctors perceived confidence and knowledge was sampled in a range of key areas i.e. management pre and post endoscopy, senior support and escalation, blood transfusion targets and use of risk stratification tools such as the Blatchford score. Following evaluation of the initial questionnaire a dedicated teaching programme was delivered to 65 junior doctors, whom were subsequently re-surveyed.ResultsFollowing introduction of the teaching session all junior doctors expressed improved confidence in managing variceal UGIB’s- improved from 8% to 41% of junior doctors feeling confident. Additionally there were significant improvements identified in all areas. Notably; correct pre-endoscopic management improved to 94% (from 36%), appropriate transfusion targets improved from 45% to 76%, knowledge and use of risk stratification scores improved to 88% (from 3%). With inappropriate pre-endoscopic use of proton pump inhibitors falling from 25% to 0%.ConclusionAdopting a focused teaching programme for junior doctors on the management of acute variceal bleeds designed around pre-identified areas of weakness has proven to increase both knowledge and confidence in its specific management. Junior doctor teaching on core medical emergencies such as UGIB’s should perhaps be incorporated into trust induction programmes to ensure junior doctors are as prepared as possible on their first day in clinical practice.References1 Management of acute upper and lower gastrointestinal bleeding. A national clinical guideline. SIGN. September 2009.2 UK comparartive audit of upper gastrointestinal bleeding and the use of blood. British.Disclosure of InterestNone Declared

Using evidence derived from previously collected medical records to guide patient care has been a long-standing vision of clinicians and informaticians, and one with the potential to transform medical practice. We offered an on-demand consultation service to derive evidence from millions of other patients' data to answer clinician questions and support their bedside decision making. We describe the design and implementation of the service as well as a summary of our experience in responding to the first 100 requests. We will also review a new paradigm for a scalable time-aware clinical data search, and to describe the design, implementation, and use of a search engine realizing this paradigm.