Literature DB >> 35147666

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

Sunny S Lou1, Hanyang Liu2, Chenyang Lu2, Troy S Wildes1, Bruce L Hall3, Thomas Kannampallil4.   

Abstract

BACKGROUND: Accurate estimation of surgical transfusion risk is essential for efficient allocation of blood bank resources and for other aspects of anesthetic planning. This study hypothesized that a machine learning model incorporating both surgery- and patient-specific variables would outperform the traditional approach that uses only procedure-specific information, allowing for more efficient allocation of preoperative type and screen orders.
METHODS: The American College of Surgeons National Surgical Quality Improvement Program Participant Use File was used to train four machine learning models to predict the likelihood of red cell transfusion using surgery-specific and patient-specific variables. A baseline model using only procedure-specific information was created for comparison. The models were trained on surgical encounters that occurred at 722 hospitals in 2016 through 2018. The models were internally validated on surgical cases that occurred at 719 hospitals in 2019. Generalizability of the best-performing model was assessed by external validation on surgical cases occurring at a single institution in 2020.
RESULTS: Transfusion prevalence was 2.4% (73,313 of 3,049,617), 2.2% (23,205 of 1,076,441), and 6.7% (1,104 of 16,053) across the training, internal validation, and external validation cohorts, respectively. The gradient boosting machine outperformed the baseline model and was the best- performing model. At a fixed 96% sensitivity, this model had a positive predictive value of 0.06 and 0.21 and recommended type and screens for 36% and 30% of the patients in internal and external validation, respectively. By comparison, the baseline model at the same sensitivity had a positive predictive value of 0.04 and 0.144 and recommended type and screens for 57% and 45% of the patients in internal and external validation, respectively. The most important predictor variables were overall procedure-specific transfusion rate and preoperative hematocrit.
CONCLUSIONS: A personalized transfusion risk prediction model was created using both surgery- and patient-specific variables to guide preoperative type and screen orders and showed better performance compared to the traditional procedure-centric approach.
Copyright © 2022, the American Society of Anesthesiologists. All Rights Reserved.

Entities:  

Mesh:

Year:  2022        PMID: 35147666      PMCID: PMC9177553          DOI: 10.1097/ALN.0000000000004139

Source DB:  PubMed          Journal:  Anesthesiology        ISSN: 0003-3022            Impact factor:   8.986


  32 in total

1.  Safety of uncrossmatched type-O red cells for resuscitation from hemorrhagic shock.

Authors:  Richard P Dutton; Diane Shih; Bennett B Edelman; John Hess; Thomas M Scalea
Journal:  J Trauma       Date:  2005-12

2.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms.

Authors: 
Journal:  Neural Comput       Date:  1998-09-15       Impact factor: 2.026

3.  Toward robust information: data quality and inter-rater reliability in the American College of Surgeons National Surgical Quality Improvement Program.

Authors:  Mira Shiloach; Stanley K Frencher; Janet E Steeger; Katherine S Rowell; Kristine Bartzokis; Majed G Tomeh; Karen E Richards; Clifford Y Ko; Bruce L Hall
Journal:  J Am Coll Surg       Date:  2009-11-22       Impact factor: 6.113

4.  The ASA Physical Status Classification: inter-observer consistency. American Society of Anesthesiologists.

Authors:  P H K Mak; R C H Campbell; M G Irwin
Journal:  Anaesth Intensive Care       Date:  2002-10       Impact factor: 1.669

5.  Physician understanding, explainability, and trust in a hypothetical machine learning risk calculator.

Authors:  William K Diprose; Nicholas Buist; Ning Hua; Quentin Thurier; George Shand; Reece Robinson
Journal:  J Am Med Inform Assoc       Date:  2020-04-01       Impact factor: 4.497

6.  Machine Learning Applied to Registry Data: Development of a Patient-Specific Prediction Model for Blood Transfusion Requirements During Craniofacial Surgery Using the Pediatric Craniofacial Perioperative Registry Dataset.

Authors:  Ali Jalali; Hannah Lonsdale; Lillian V Zamora; Luis Ahumada; Anh Thy H Nguyen; Mohamed Rehman; James Fackler; Paul A Stricker; Allison M Fernandez
Journal:  Anesth Analg       Date:  2020-06-30       Impact factor: 5.108

7.  Reducing unnecessary cross-matching: a patient-specific blood ordering system is more accurate in predicting who will receive a blood transfusion than the maximum blood ordering system.

Authors:  Thalia Palmer; Joyce A Wahr; Michael O'Reilly; Mary Lou V H Greenfield
Journal:  Anesth Analg       Date:  2003-02       Impact factor: 5.108

8.  Calibration: the Achilles heel of predictive analytics.

Authors:  Ben Van Calster; David J McLernon; Maarten van Smeden; Laure Wynants; Ewout W Steyerberg
Journal:  BMC Med       Date:  2019-12-16       Impact factor: 8.775

9.  Prediction of perioperative transfusions using an artificial neural network.

Authors:  Steven Walczak; Vic Velanovich
Journal:  PLoS One       Date:  2020-02-24       Impact factor: 3.240

10.  Predictors for blood loss and transfusion frequency to guide blood saving programs in primary knee- and hip-arthroplasty.

Authors:  Christina Pempe; Robert Werdehausen; Philip Pieroh; Martin Federbusch; Sirak Petros; Reinhard Henschler; Andreas Roth; Christian Pfrepper
Journal:  Sci Rep       Date:  2021-02-23       Impact factor: 4.379

View more
  1 in total

1.  Selective type & screen for elective colectomy based on a transfusion risk score may generate substantial cost savings.

Authors:  Alexander T Booth; Shelby Allen; Vlad V Simianu; Christine C Jensen; Marc L Schermerhorn; Virgilio V George; Thomas Curran
Journal:  Surg Endosc       Date:  2022-05-26       Impact factor: 4.584

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.