Development of Multivariable Models to Predict and Benchmark Transfusion in Elective Surgery Supporting Patient Blood Management.

BACKGROUND: Blood transfusion is a highly prevalent procedure in hospitalized patients and in some clinical scenarios it has lifesaving potential. However, in most cases transfusion is administered to hemodynamically stable patients with no benefit, but increased odds of adverse patient outcomes and substantial direct and indirect cost. Therefore, the concept of Patient Blood Management has increasingly gained importance to pre-empt and reduce transfusion and to identify the optimal transfusion volume for an individual patient when transfusion is indicated. OBJECTIVES: It was our aim to describe, how predictive modeling and machine learning tools applied on pre-operative data can be used to predict the amount of red blood cells to be transfused during surgery and to prospectively optimize blood ordering schedules. In addition, the data derived from the predictive models should be used to benchmark different hospitals concerning their blood transfusion patterns. METHODS: 6,530 case records obtained for elective surgeries from 16 centers taking part in two studies conducted in 2004-2005 and 2009-2010 were analyzed. Transfused red blood cell volume was predicted using random forests. Separate models were trained for overall data, for each center and for each of the two studies. Important characteristics of different models were compared with one another. RESULTS: Our results indicate that predictive modeling applied prior surgery can predict the transfused volume of red blood cells more accurately (correlation coefficient cc = 0.61) than state of the art algorithms (cc = 0.39). We found significantly different patterns of feature importance a) in different hospitals and b) between study 1 and study 2. CONCLUSION: We conclude that predictive modeling can be used to benchmark the importance of different features on the models derived with data from different hospitals. This might help to optimize crucial processes in a specific hospital, even in other scenarios beyond Patient Blood Management.

Data Driven Methods for Predicting Blood Transfusion Needs in Elective Surgery.

Research in blood transfusions mainly focuses on Donor Blood Management, including donation, screening, storage and transport. However, the last years saw an increasing interest in recipient related optimizations, i.e. Patient Blood Management (PBM). Although PBM already aims at reducing transfusion rates by pre- and intra-surgical optimization, there is still a high potential of improvement on an individual level. The present paper investigates the feasibility of predicting blood transfusions needs based on datasets from various treatment phases, using data which have been collected in two previous studies. Results indicate that prediction of blood transfusions can be further improved by predictive modelling including individual pre-surgical parameters. This also allows to identify the main predictors influencing transfusion practice. If confirmed in a prospective dataset, these or similar predictive methods could be a valuable tool to support PBM with the ultimate goal to reduce costs and improve patient outcomes.

Implementation and validation of a conceptual benchmarking framework for patient blood management.

BACKGROUND: Public health authorities and healthcare professionals are obliged to ensure high quality health service. Because of the high variability of the utilisation of blood and blood components, benchmarking is indicated in transfusion medicine. OBJECTIVES: Implementation and validation of a benchmarking framework for Patient Blood Management (PBM) based on the report from the second Austrian Benchmark trial. METHODS: Core modules for automatic report generation have been implemented with KNIME (Konstanz Information Miner) and validated by comparing the output with the results of the second Austrian benchmark trial. RESULTS: Delta analysis shows a deviation <0.1% for 95% (max. 1.4%). CONCLUSION: The framework provides a reliable tool for PBM benchmarking. The next step is technical integration with hospital information systems.