Prediction of elective surgical red blood cell transfusion reveals surgeon-level variation
- 1Finnish Red Cross Blood Service
Abstract
BACKGROUND Preoperative prediction of red blood cell (RBC) transfusion in elective surgery serves two complementary purposes: enabling patient blood management (PBM) interventions before surgery and supporting blood product supply planning for elective lists. Beyond patient risk factors, individual surgeon practice may also contribute to transfusion rates, but this effect has not been fully quantified. STUDY DESIGN AND METHODS In a retrospective cohort of 279,905 elective surgical procedures at Helsinki University Hospital (2021-2025), we trained four gradient-boosted tree (CatBoost) models crossing patient factors with procedure group and pseudonymised surgeon identity. All predictors were restricted to data available seven or more days before scheduled surgery. The primary outcome was any allogeneic RBC transfusion from operating-room entry through seven postoperative days. Discrimination was assessed by the area under the precision-recall curve (AUPRC) on a held-out 20% test set. Surgeon-level effects were characterised by Shapley additive explanation (SHAP) values. RESULTS The transfusion rate was 2.2%. The patient-only model achieved AUPRC 0.261 (no-skill baseline 0.022). Adding surgeon identity to the procedure-adjusted model increased AUPRC from 0.440 to 0.472 (+0.032; 95% CI 0.020-0.044), raising lift from 20.3 to 21.7. Surgeon identity was the third most important of 72 features by permutation importance. DISCUSSION The operating surgeon was associated with RBC transfusion beyond patient and procedure factors, and surgeon identity was the third most important predictor in a deployment-realistic model using only data available a week before surgery. This information is readily available from routine records and could support PBM audit and blood supply planning for elective surgery.
Related
- TRANSFUSION PROFILE AND RED BLOOD CELL CONCENTRATE UTILIZATION IN PATIENTS UNDERGOING ELECTIVE HIP ARTHROPLASTY AT A REFERRAL HOSPITAL IN THE BRAZILIAN AMAZON REGION
- PREOPERATIVE HEMOGLOBIN AS A PREDICTOR OF TRANSFUSION REQUIREMENT IN PATIENTS UNDERGOING ELECTIVE HIP ARTHROPLASTY
- Surgical management of cecal volvulus using endoscopic reduction as a bridge to elective laparoscopic surgery: a three-case series
- Development and multicenter validation of a machine learning model for predicting in-hospital postoperative cardiac arrest in elderly surgical patients: the critical role of intraoperative hemodynamic disturbances and blood transfusion.
- Blood Transfusion Rates and Predictive Factors in Posterior-Based Minimally Invasive Scoliosis Surgery for Idiopathic Scoliosis: A LASSO-Based Prediction Model
BibTeX
@misc{turkulainen2026prediction,
title = {{Prediction of elective surgical red blood cell transfusion reveals surgeon-level variation}},
author = {E. Turkulainen and M. Arvas and M. Koskinen and M. Ilmakunnas},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.03.26364952},
url = {https://www.medrxiv.org/content/10.64898/2026.11.03.26364952v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Prediction of elective surgical red blood cell transfusion reveals surgeon-level variation
AU - E. Turkulainen
AU - M. Arvas
AU - M. Koskinen
AU - M. Ilmakunnas
PY - 2026
DA - 2026/11/03
PB - medRxiv
DO - 10.64898/2026.11.03.26364952
UR - https://www.medrxiv.org/content/10.64898/2026.11.03.26364952v1
AB - BACKGROUND Preoperative prediction of red blood cell (RBC) transfusion in elective surgery serves two complementary purposes: enabling patient blood management (PBM) interventions before surgery and supporting blood product supply planning for elective lists. Beyond patient risk factors, individual surgeon practice may also contribute to transfusion rates, but this effect has not been fully quantified. STUDY DESIGN AND METHODS In a retrospective cohort of 279,905 elective surgical procedures at Helsinki University Hospital (2021-2025), we trained four gradient-boosted tree (CatBoost) models crossing patient factors with procedure group and pseudonymised surgeon identity. All predictors were restricted to data available seven or more days before scheduled surgery. The primary outcome was any allogeneic RBC transfusion from operating-room entry through seven postoperative days. Discrimination was assessed by the area under the precision-recall curve (AUPRC) on a held-out 20% test set. Surgeon-level effects were characterised by Shapley additive explanation (SHAP) values. RESULTS The transfusion rate was 2.2%. The patient-only model achieved AUPRC 0.261 (no-skill baseline 0.022). Adding surgeon identity to the procedure-adjusted model increased AUPRC from 0.440 to 0.472 (+0.032; 95% CI 0.020-0.044), raising lift from 20.3 to 21.7. Surgeon identity was the third most important of 72 features by permutation importance. DISCUSSION The operating surgeon was associated with RBC transfusion beyond patient and procedure factors, and surgeon identity was the third most important predictor in a deployment-realistic model using only data available a week before surgery. This information is readily available from routine records and could support PBM audit and blood supply planning for elective surgery.
ER -