Prediction of red blood cell transfusion after orthopedic surgery using an interpretable machine learning framework

Frontiers in Surgery

Surgery

Jie Lin¹  Yuan Zhuang¹  Deqing Wang¹  Xiaozhen Guan¹  Xiaoyu Cai¹  Feng Jiao²  Xingqiu Xia³  Xiangjun Du⁴  Lehan Xiao⁴  Zicheng Cao⁴  Yifeng Chen⁴  Wenyu Huang⁴  Guozhi Jiang⁵  Ying Wang⁶ 

[1] Department of Transfusion Medicine, The First Medical Center of Chinese PLA General Hospital, Beijing, China;Guangzhou Centre for Applied Mathematics, Guangzhou University, Guangzhou, China;HealSci Technology Co., Ltd, Beijing, China;School of Public Health (Shenzhen), Shenzhen Campus of Sun Yat-sen University, Shenzhen, China;School of Public Health (Shenzhen), Shenzhen Campus of Sun Yat-sen University, Shenzhen, China;Sun Yat-sen University, China;The Second School of Clinical Medicine, Guangdong Medical University, Dongguan, China;

关键词: orthopedic surgery;    RBC transfusion;    prediction model;    machine learning;    interpretability;   

DOI  :  10.3389/fsurg.2023.1047558

 received in 2022-10-13, accepted in 2023-02-13,  发布年份 2023

来源: Frontiers

【 摘 要 】

ObjectivePostoperative red blood cell (RBC) transfusion is widely used during the perioperative period but is often associated with a high risk of infection and complications. However, prediction models for RBC transfusion in patients with orthopedic surgery have not yet been developed. We aimed to identify predictors and constructed prediction models for RBC transfusion after orthopedic surgery using interpretable machine learning algorithms.MethodsThis retrospective cohort study reviewed a total of 59,605 patients undergoing orthopedic surgery from June 2013 to January 2019 across 7 tertiary hospitals in China. Patients were randomly split into training (80%) and test subsets (20%). The feature selection method of recursive feature elimination (RFE) was used to identify an optimal feature subset from thirty preoperative variables, and six machine learning algorithms were applied to develop prediction models. The Shapley Additive exPlanations (SHAP) value was employed to evaluate the contribution of each predictor towards the prediction of postoperative RBC transfusion. For simplicity of the clinical utility, a risk score system was further established using the top risk factors identified by machine learning models.ResultsOf the 59,605 patients with orthopedic surgery, 19,921 (33.40%) underwent postoperative RBC transfusion. The CatBoost model exhibited an AUC of 0.831 (95% CI: 0.824–0.836) on the test subset, which significantly outperformed five other prediction models. The risk of RBC transfusion was associated with old age (>60 years) and low RBC count (<4.0 × 1012/L) with clear threshold effects. Extremes of BMI, low albumin, prolonged activated partial thromboplastin time, repair and plastic operations on joint structures were additional top predictors for RBC transfusion. The risk score system derived from six risk factors performed well with an AUC of 0.801 (95% CI: 0.794–0.807) on the test subset.ConclusionBy applying an interpretable machine learning framework in a large-scale multicenter retrospective cohort, we identified novel modifiable risk factors and developed prediction models with good performance for postoperative RBC transfusion in patients undergoing orthopedic surgery. Our findings may allow more precise identification of high-risk patients for optimal control of risk factors and achieve personalized RBC transfusion for orthopedic patients.

【 授权许可】

Unknown   
© 2023 Chen, Cai, Cao, Lin, Huang, Zhuang, Xiao, Guan, Wang, Xia, Jiao, Du, Jiang and Wang.