Health informatics visualisation engine : HIVE

S : scientific #bd14 | big data conference 30 Norm Good Senior Statistician CSIRO Norm Good is a Statistician within the CSIRO’s Computational Informatics Division. He has been based in the Australian E-Health Research Centre (Brisbane) for the past eight years conducting health related research. Mr Good has considerable expertise in developing and applying variable selection techniques and survival models to health data. Examples of this include novel approaches for estimating optimal colonoscopy screening intervals and developing a risk profiles for patients who are likely to be readmitted to hospital. He has also worked in the field of confidential health data, developing risk and utility measures for regression modelling and promoting the use of remote server statistical querying. Recently Mr Good has exploring the utility of visualisation methods for analysing high-dimensional geometry and multivariate data. Health informatics visualisation engine: HIVE Norm Good, Chris Bain, David Hansen, Simon Gibson The Australian e-Health Research Centre, CSIRO, Queensland Health Informatics, Alfred Health, The Alfred, Victoria SUMMARY This project was designed to integrate, analyse, synthesise and present essential health and hospital information in a highly accessible, agile and visual form – because pictures are worth a thousand words. We developed a prototype software tool that is; • capable of drawing on standardised data files that replicate known industry standard, or are easily derivable from such standards • provides the user (analyst, operational manager, financial manger, executive) with a customisable view of the relative outcomes of, and resources used in, care in a number of dimensionsclinical (LOS, number of adverse events, number of drug doses, attending doctor etc) and financial (surgical, pharmacy, nursing etc) in one setting • and identify outliers using advanced statistical modelling techniques. This tool will generate immediate value for a hospitals’ endeavour in continuous operational improvement and will be of particular interest to potential customers throughout Australia given the move to nationally provided Activity Based Funding for hospital services. The tool is a useful way to harness the power of “big data” through advanced analytics. INTRODUCTION In Australia, there has been a paradigm shift from input to output (activity) based funding for hospital service delivery. A common output based payment system for managing healthcare provisions involves casemix. Casemix systems are information tools used to classify episodes of patient care. Diagnosis-Related Groups (DRGs) are the most popular casemix system. The rationale from going from an input to output based funding are: i) improving cost efficiency in providing healthcare services; ii) promoting equity for all people to access health services; and iii) increasing incentives to hospitals for providing efficient and quality services. This shift in funding type has highlighted a number of issues. The one with a significant impact on the costs of care is focused on outliers. An outlier in this context is an observation for a patient which is outside the “normal” range expected. Current practices of outlier identification involve a case-by-case analysis, which can be very time consuming. Another issue is to assess the relative clinical and financial value of components of care delivery. These components consist of equipment, drugs and specialist staff which are assessed against mortality and measures of morbidity. Once again, current practice is on a case-by-case basis. Significant cost savings and identification of efficient care models can be achieved if an appropriate software tool can be developed and utilised by front line care. DESCRIPTION ANALYTICS ENGINE Behind the software interface are two main analytics modules. In the first module we can develop models of predicted costs for treating individual patients. In addition to the standard cost attached to a specific DRG, extra costs based on clinical and demographic parameters can be estimated. The main purpose of this modeling was to develop a profile for the “average” patient. The second module focused on identifying outliers in a data set. Given the predicted cost of care calculated above, the actual cost of care is calculated. An outlier in this context is the difference between the actual and predicted cost for a patient which is outside the “normal” range expected. The current method for identifying outliers in Victoria is the L3H3 method. It uses three times the average length of stay for a particular DRG as the high cut point for outliers. We will be using a more robust method based on statistical discordancy to identify outliers. What is potentially more informative is the detection of “inliers”. That is, people whose costs are much lower than predicted. Examination of these patients may reveal insights into optimal care models. Given the multivariate nature of the cost and clinical data, dimension reductions tools such as principal components analysis have been employed to project patients and their associated cost of care and clinical status onto a viewable two or three dimensional space. [email protected]