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

Summary

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.

Citation: Hayn D, Kreiner K, Ebner H, Kastner P, Breznik N, Rzepka A, Hofmann A, Gombotz H, Schreier G. Development of multivariable models to predict and benchmark transfusion in elective surgery supporting patient blood management. Appl Clin Inform 2017; 8: 617–631 https://doi.org/10.4338/ACI-2016-11-RA-0195

Keywords

Predictive modelling - random forests - machine learning - benchmarking - blood transfusion - patient blood management

Human Subjects Protections

The studies were approved by the regional board of ethics commission (15/07/1999) and performed in compliance with the World Medical Association Declaration of Helsinki on Ethical Principles for Medical Research Involving Human Subjects.

• References

• 1 Anthes E. Evidence-based medicine: Save blood, save lives. Nature 2015; 520 7545 24-26.
• 2 Gombotz H, Zacharowski K, Spahn DR. Patient Blood Management –Individuelles Behandlungskonzept zur Reduktion und Vermeidung von Anämie und Blutverlust sowie zum rationalen Einsatz von Blutprodukten. Georg Thieme Verlag; 2013: 214
• 3 Gombotz H, Rehak PH, Shander A, Hofmann A. Blood use in elective surgery: the Austrian benchmark study. Transfusion 2007; 47 (08) 1468-1480.
• 4 Leahy MF, Hofmann A, Towler S, Trentino KM, Burrows SA, Swain SG, Hamdorf J, Gallagher T, Koay A, Geelhoed GC, Farmer SL. Improved outcomes and reduced costs associated with a health-system-wide patient blood management program: a retrospective observational study in four major adult tertiary-care hospitals. Transfusion. 2017 Epub 2017/02/02. doi: 10.1111/trf.14006.
• 5 Gombotz H, Rehak PH, Shander A, Hofmann A. The second Austrian benchmark study for blood use in elective surgery: results and practice change. Transfusion 2014; 54 10 Pt 2 2646-2657. Epub 2014/05/09. doi: 10.1111/trf.12687.
• 6 Gombotz H, Rehak PH, Hofmann A. Fortsetzung der Studie „Maßnahmen zur Optimierung des Verbrauchs von Blutkomponenten bei ausgewählten operativen Eingriffen in österreichischen Krankenanstalten“ 2008–2010. 2012
• 7 Mercuriali F, Inghilleri G. Proposal of an algorithm to help the choice of the best transfusion strategy. Curr Med Res Opin. 1996; 13 (08) 465-478.
• 8 Kadar A, Chechik O, Steinberg E, Reider E, Sternheim A. Predicting the need for blood transfusion in patients with hip fractures. Int Orthop 2013; 37 (04) 693-700.
• 9 Goodnough LT, Maggio P, Hadhazy E, Shieh L, Hernandez-Boussard T, Khari P, Shah N. Restrictive blood transfusion practices are associated with improved patient outcomes. Transfusion 2014; 54 10 Pt 2 2753-2759.
• 10 Goodnough LT, Murphy MF. Do liberal blood transfusions cause more harm than good?. BMJ. 2014 349. g6897.
• 11 Murphree D, Ngufor C, Upadhyaya S, Madde N, Clifford L, Kor DJ, Pathak J. Ensemble Learning Approaches to Predicting Complications of Blood Transfusion. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Scociety. Milan: IEEE; 2015: 7222-7225.
• 12 Hayn D, Kreiner K, Kastner P, Breznik N, Hofmann A, Gombotz H, Schreier G. Data Driven Methods for Predicting Blood Transfusion Needs in Elective Surgery. Stud Health Technol Inform 2016; 223: 9-16.
• 13 Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): the TRIPOD Statement. Br J Surg 2015; 102 (03) 148-158.
• 14 Xie Y, Schreier G, Chang DC, Neubauer S, Liu Y, Redmond SJ, Lovell NH. Predicting Days in Hospital Using Health Insurance Claims. IEEE J Biomed Health Inform 2015; 19 (04) 1224-1233.
• 15 Xie Y, Neubauer S, Schreier G, Redmond S, Lovell N. editors. Impact of Hierarchies of Clinical Codes on Predicting Future Days in Hospital. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2015. Milan: IEEE;
• 16 Xie Y, Schreier G, Hoy M, Liu Y, Neubauer S, Chang DC, Redmond SJ. Lovell NH Analyzing health insurance claims on different timescales to predict days in hospital. J Biomed Inform. 2016 doi: 10.1016/j.jbi.2016.01.002.
• 17 Breiman L, Cutler A. Random forests. 2014 Available from: http://www.stat.berkeley.edu/breiman/RandomForests/cchome.htm
• 18 Meier J, Filipescu D, Kozek-Langenecker S, Llau Pitarch J, Mallett S, Martus P, Matot I, collaborators E. Intraoperative transfusion practices in Europe. Br J Anaesth 2016; 116 (02) 255-261.
• 19 Tolosi L, Lengauer T. Classification with correlated features: unreliability of feature ranking and solutions. Bioinformatics 2011; 27 (14) 1986-1994.
• 20 Strobl C, Boulesteix AL, Zeileis A, Hothorn T. Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinformatics 2007; 8: 25.
• 21 Gombotz H, Schreier G, Neubauer S, Kastner P, Hofmann A. Gender disparities in red blood cell transfusion in elective surgery: a post hoc multicentre cohort study. BMJ Open 2016; 6 (12) e012210.
• 22 AIT Austrian Institute of Technology GmbH. EU-PBM Patient Blood Management. http://www.europe-pbm.eu/n.d [cited 2016 Feb 8]. Available from: http://www.europe-pbm.eu