An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery

Abstract Aim The study aimed to develop a predictive model with machine learning (ML) algorithm, to predict and manage the need for red blood cell (RBC) transfusion during hip fracture surgery. Methods Data of 2785 cases that underwent hip fracture surgery from April 2016 to May 2022 were collected,...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongchang Zhou, Suo Wang, Zhikun Wu, Weixing Chen, Dong Yang, Chaojin Chen, Gaofeng Zhao, Qingxiong Hong
Format: Article
Language:English
Published: BMC 2024-12-01
Series:BMC Anesthesiology
Subjects:
Online Access:https://doi.org/10.1186/s12871-024-02832-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850100606591565824
author Yongchang Zhou
Suo Wang
Zhikun Wu
Weixing Chen
Dong Yang
Chaojin Chen
Gaofeng Zhao
Qingxiong Hong
author_facet Yongchang Zhou
Suo Wang
Zhikun Wu
Weixing Chen
Dong Yang
Chaojin Chen
Gaofeng Zhao
Qingxiong Hong
author_sort Yongchang Zhou
collection DOAJ
description Abstract Aim The study aimed to develop a predictive model with machine learning (ML) algorithm, to predict and manage the need for red blood cell (RBC) transfusion during hip fracture surgery. Methods Data of 2785 cases that underwent hip fracture surgery from April 2016 to May 2022 were collected, covering demographics, medical history and comorbidities, type of surgery and preoperative laboratory results. The primary outcome was the intraoperative RBC transfusion. The predicting performance of six algorithms were respectively evaluated with the area under the receiver operating characteristic (AUROC). The SHapley Additive exPlanations (SHAP) package was applied to interpret the Random Forest (RF) model. Data from 122 patients at The Third Affiliated Hospital of Sun Yat-sen University were collected for external validation. Results 1417 patients (50.88%) were diagnosed with preoperative anemia (POA) and 209 patients (7.5%) received intraoperative RBC transfusion. Longer estimated duration of surgery, POA, older age, hypoproteinemia, and surgery of internal fixation were revealed as the top 5 important variables contributing to intraoperative RBC transfusion. Among the six ML models, the RF model performed the best, which achieved the highest AUC (0.887, CI 0.838 to 0.926) in the internal validation set. Further, it achieved a comparable AUC of 0.834(0.75, 0.911) in the external validation set. Conclusion Our study firstly demonstrated that the RF model with 10 common variables might predict intraoperative RBC transfusion in hip fracture patients.
format Article
id doaj-art-861f940b706d4ad59deeac8a06e7431d
institution DOAJ
issn 1471-2253
language English
publishDate 2024-12-01
publisher BMC
record_format Article
series BMC Anesthesiology
spelling doaj-art-861f940b706d4ad59deeac8a06e7431d2025-08-20T02:40:15ZengBMCBMC Anesthesiology1471-22532024-12-0124111210.1186/s12871-024-02832-yAn explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgeryYongchang Zhou0Suo Wang1Zhikun Wu2Weixing Chen3Dong Yang4Chaojin Chen5Gaofeng Zhao6Qingxiong Hong7Department of Anesthesiology, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong Provincial Hospital of Chinese MedicineGuangzhou University of Chinese MedicineDepartment of Anesthesiology, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong Provincial Hospital of Chinese MedicineDepartment of Data Science, Guangzhou AID Cloud TechnologyDepartment of Data Science, Guangzhou AID Cloud TechnologyDepartment of Anesthesiology, The Third Affiliated Hospital of Sun Yat-Sen UniversityDepartment of Anesthesiology, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong Provincial Hospital of Chinese MedicineDepartment of Anesthesiology, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong Provincial Hospital of Chinese MedicineAbstract Aim The study aimed to develop a predictive model with machine learning (ML) algorithm, to predict and manage the need for red blood cell (RBC) transfusion during hip fracture surgery. Methods Data of 2785 cases that underwent hip fracture surgery from April 2016 to May 2022 were collected, covering demographics, medical history and comorbidities, type of surgery and preoperative laboratory results. The primary outcome was the intraoperative RBC transfusion. The predicting performance of six algorithms were respectively evaluated with the area under the receiver operating characteristic (AUROC). The SHapley Additive exPlanations (SHAP) package was applied to interpret the Random Forest (RF) model. Data from 122 patients at The Third Affiliated Hospital of Sun Yat-sen University were collected for external validation. Results 1417 patients (50.88%) were diagnosed with preoperative anemia (POA) and 209 patients (7.5%) received intraoperative RBC transfusion. Longer estimated duration of surgery, POA, older age, hypoproteinemia, and surgery of internal fixation were revealed as the top 5 important variables contributing to intraoperative RBC transfusion. Among the six ML models, the RF model performed the best, which achieved the highest AUC (0.887, CI 0.838 to 0.926) in the internal validation set. Further, it achieved a comparable AUC of 0.834(0.75, 0.911) in the external validation set. Conclusion Our study firstly demonstrated that the RF model with 10 common variables might predict intraoperative RBC transfusion in hip fracture patients.https://doi.org/10.1186/s12871-024-02832-yHip fractureRed blood cell transfusionMachine learningPredictive modelSHapley Additive exPlanations
spellingShingle Yongchang Zhou
Suo Wang
Zhikun Wu
Weixing Chen
Dong Yang
Chaojin Chen
Gaofeng Zhao
Qingxiong Hong
An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
BMC Anesthesiology
Hip fracture
Red blood cell transfusion
Machine learning
Predictive model
SHapley Additive exPlanations
title An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
title_full An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
title_fullStr An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
title_full_unstemmed An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
title_short An explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
title_sort explainable and supervised machine learning model for prediction of red blood cell transfusion in patients during hip fracture surgery
topic Hip fracture
Red blood cell transfusion
Machine learning
Predictive model
SHapley Additive exPlanations
url https://doi.org/10.1186/s12871-024-02832-y
work_keys_str_mv AT yongchangzhou anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT suowang anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT zhikunwu anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT weixingchen anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT dongyang anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT chaojinchen anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT gaofengzhao anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT qingxionghong anexplainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT yongchangzhou explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT suowang explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT zhikunwu explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT weixingchen explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT dongyang explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT chaojinchen explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT gaofengzhao explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery
AT qingxionghong explainableandsupervisedmachinelearningmodelforpredictionofredbloodcelltransfusioninpatientsduringhipfracturesurgery