Literature DB >> 28850152

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

Dieter Hayn1, Karl Kreiner, Hubert Ebner, Peter Kastner, Nada Breznik, Angelika Rzepka, Axel Hofmann, Hans Gombotz, Günter Schreier.   

Abstract

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.

Entities:  

Keywords:  Predictive modelling; benchmarking; blood transfusion; machine learning; patient blood management; random forests

Mesh:

Year:  2017        PMID: 28850152      PMCID: PMC6241749          DOI: 10.4338/ACI-2016-11-RA-0195

Source DB:  PubMed          Journal:  Appl Clin Inform        ISSN: 1869-0327            Impact factor:   2.342


  16 in total

1.  Impact of hierarchies of clinical codes on predicting future days in hospital.

Authors:  Sandra Neubauer; Gunter Schreier; Stephen J Redmond; Nigel H Lovell
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2015

2.  Blood use in elective surgery: the Austrian benchmark study.

Authors:  Hans Gombotz; Peter H Rehak; Aryeh Shander; Axel Hofmann
Journal:  Transfusion       Date:  2007-08       Impact factor: 3.157

3.  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.

Authors:  Michael F Leahy; Axel Hofmann; Simon Towler; Kevin M Trentino; Sally A Burrows; Stuart G Swain; Jeffrey Hamdorf; Trudi Gallagher; Audrey Koay; Gary C Geelhoed; Shannon L Farmer
Journal:  Transfusion       Date:  2017-02-02       Impact factor: 3.157

4.  Evidence-based medicine: Save blood, save lives.

Authors:  Emily Anthes
Journal:  Nature       Date:  2015-04-02       Impact factor: 49.962

5.  Restrictive blood transfusion practices are associated with improved patient outcomes.

Authors:  Lawrence T Goodnough; Paul Maggio; Eric Hadhazy; Lisa Shieh; Tina Hernandez-Boussard; Paul Khari; Neil Shah
Journal:  Transfusion       Date:  2014-07-04       Impact factor: 3.157

6.  Predicting the need for blood transfusion in patients with hip fractures.

Authors:  Assaf Kadar; Ofir Chechik; Ely Steinberg; Evgeny Reider; Amir Sternheim
Journal:  Int Orthop       Date:  2013-02-05       Impact factor: 3.075

7.  The second Austrian benchmark study for blood use in elective surgery: results and practice change.

Authors:  Hans Gombotz; Peter H Rehak; Aryeh Shander; Axel Hofmann
Journal:  Transfusion       Date:  2014-05-08       Impact factor: 3.157

Review 8.  Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): the TRIPOD Statement.

Authors:  G S Collins; J B Reitsma; D G Altman; K G M Moons
Journal:  Br J Surg       Date:  2015-02       Impact factor: 6.939

9.  Bias in random forest variable importance measures: illustrations, sources and a solution.

Authors:  Carolin Strobl; Anne-Laure Boulesteix; Achim Zeileis; Torsten Hothorn
Journal:  BMC Bioinformatics       Date:  2007-01-25       Impact factor: 3.169

10.  Intraoperative transfusion practices in Europe.

Authors:  J Meier; D Filipescu; S Kozek-Langenecker; J Llau Pitarch; S Mallett; P Martus; I Matot
Journal:  Br J Anaesth       Date:  2016-02       Impact factor: 9.166

View more
  3 in total

1.  Personalized Surgical Transfusion Risk Prediction Using Machine Learning to Guide Preoperative Type and Screen Orders.

Authors:  Sunny S Lou; Hanyang Liu; Chenyang Lu; Troy S Wildes; Bruce L Hall; Thomas Kannampallil
Journal:  Anesthesiology       Date:  2022-07-01       Impact factor: 8.986

2.  Machine learning-based prediction of transfusion.

Authors:  Andreas Mitterecker; Axel Hofmann; Kevin M Trentino; Adam Lloyd; Michael F Leahy; Karin Schwarzbauer; Thomas Tschoellitsch; Carl Böck; Sepp Hochreiter; Jens Meier
Journal:  Transfusion       Date:  2020-06-28       Impact factor: 3.157

3.  A novel model forecasting perioperative red blood cell transfusion.

Authors:  Yawen Zhang; Xiangjie Fu; Xi Xie; Danyang Yan; Yanjie Wang; Wanting Huang; Run Yao; Ning Li
Journal:  Sci Rep       Date:  2022-09-27       Impact factor: 4.996

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.