ObjectivesMost patients are unaware they have liver cirrhosis until they present with a decompensating event. We therefore aimed to develop and validate an algorithm to predict advanced liver disease (AdvLD) using data widely available in primary care.Design, setting and participantsLogistic regression was performed on routinely collected blood result data from the University Hospital Southampton (UHS) information systems for 16 967 individuals who underwent an upper gastrointestinal endoscopy (2005–2016). Data were used to create a model aimed at detecting AdvLD: ‘CIRRhosis Using Standard tests’ (CIRRUS). Prediction of a first serious liver event (SLE) was then validated in two cohorts of 394 253 (UHS: primary and secondary care) and 183 045 individuals (Care and Health Information Exchange (CHIE): primary care).Primary outcome measuresModel creation dataset: cirrhosis or portal hypertension. Validation datasets: SLE (gastro-oesophageal varices, liver-related ascites or cirrhosis).ResultsIn the model creation dataset, 931 SLEs were recorded (5.5%). CIRRUS detected cirrhosis or portal hypertension with an area under the curve (AUC) of 0.90 (95% CI 0.88 to 0.92). Overall, 3044 (0.8%) and 1170 (0.6%) SLEs were recorded in the UHS and CHIE validation cohorts, respectively. In the UHS cohort, CIRRUS predicted a first SLE within 5 years with an AUC of 0.90 (0.89 to 0.91) continuous, 0.88 (0.87 to 0.89) categorised (crimson, red, amber, green grades); and AUC 0.84 (0.82 to 0.86) and 0.83 (0.81 to 0.85) for the CHIE cohort. In patients with a specified liver risk factor (alcohol, diabetes, viral hepatitis), a crimson/red cut-off predicted a first SLE with a sensitivity of 72%/59%, specificity 87%/93%, positive predictive value 26%/18% and negative predictive value 98%/99% for the UHS/CHIE validation cohorts, respectively.ConclusionIdentification of individuals at risk of AdvLD within primary care using routinely available data may provide an opportunity for earlier intervention and prevention of liver-related morbidity and mortality.

Abstract. This paper presents a case study of using data mining techniques in the analysis of diagnosis and treatment events related to Breast Cancer disease. Data from over 16,000 patients has been pre-processed and several data mining techniques have been implemented by using Weka (Waikato Environment for Knowledge Analysis). In particular, Generalized Sequential Patterns mining has been used to discover frequent patterns from disease event sequence profiles based on groups of living and deceased patients. Furthermore, five models have been evaluated in Classification with the objective to classify the patients based on selected attributes. This research showcases the data mining process and techniques to transform large amounts of patient data into useful information and potentially valuable patterns to help understand cancer outcomes.

BackgroundConventional electronic screen visualisation formats, which use tabs, dropdown menus, lists and multiple windows, present huge navigation challenges to health professionals. A unifying and intuitive interface for the electronic patient record (EPR) has been an elusive goal for software developers for decades.MethodsSince 2009, by working in an agile way, we have built and implemented a fully operational and dynamic system, the University Hospital Southampton Lifelines (UHSL), within our clinical data estate, in a UK university hospital. UHSL permits the continuously updated display of the EPR on a single desktop computer screen in an intuitive format. During this iterative evolution, we have resolved a number of practical challenges in data display, while maintaining our core aims of end-user optimisation and radical simplification of the interface. Concurrently, we have upcycled a significant volume of clinical e-content, some from as far back as 1991, into UHSL, and at a marginal cost.OutcomesUHSL went live in 2017 for all authorised staff at the hospital. It displays all e-records for 2.5 million patients and for more than 100 million documents and reports. It significantly reduces the screen time to navigate the individual EPR, and it offers substantial productivity gains in designated clinical services.ConclusionsUHSL has considerable further development potential as a National Health Service EPR interface, for the integration, display and ease of understanding of medical records across primary, secondary and community care.

Abstract. This research presents a methodology for health data analytics through a case study for modelling cancer patient records. Timeline-structured clinical data systems represent a new approach to the understanding of the relationship between clinical activity, disease pathologies and health outcomes. The novel Southampton Breast Cancer Data System contains episode and timeline-structured records on >17,000 patients who have been treated in University Hospital Southampton and affiliated hospitals since the late 1970s. The system is under continuous development and validation. Modern data mining software and visual analytics tools permit new insights into temporallystructured clinical data. The challenges and outcomes of the application of such software-based systems to this complex data environment are reported here. The core data was anonymised and put through a series of pre-processing exercises to identify and exclude anomalous and erroneous data, before restructuring within a remote data warehouse. A range of approaches was tested on the resulting dataset including multi-dimensional modelling, sequential patterns mining and classification. Visual analytics software has enabled the comparison of survival times and surgical treatments. The systems tested proved to be powerful in identifying episode sequencing patterns which were consistent with real-world clinical outcomes. It is concluded that, subject to further refinement and selection, modern data mining techniques can be applied to large and heterogeneous clinical datasets to inform decision making.