Machine learning-driven personalized tranexamic acid administration recommendations improve perioperative outcomes in orthopedic surgery patients: A large-scale database study

LI Jian; ZHOU Mi; LIU Xiang; ZHU Yiziting; SHU Xin; ZHANG Xuhao; HE Wenquan

doi:10.16016/j.2097-0927.202507025

您当前的位置：

首页 >

文章列表页 >

Machine learning-driven personalized tranexamic acid administration recommendations improve perioperative outcomes in orthopedic surgery patients: A large-scale database study

Biomedical Engineering | 更新时间：2025-11-28

- Machine learning-driven personalized tranexamic acid administration recommendations improve perioperative outcomes in orthopedic surgery patients: A large-scale database study
- Journal of Army Medical University Vol. 47, Issue 22, Pages: 2868-2880(2025)
- 作者机构：
  
  1.重庆市合川区人民医院麻醉科，重庆
  2.陆军军医大学（第三军医大学）第一附属医院麻醉科，重庆
- 作者简介：
  
  HE Wenquan， E-mail： hewenquan7@tmmu.edu.cn
- 基金信息：
- DOI：10.16016/j.2097-0927.202507025
  CLC： R319;R687.3;R973.1
- Received：07 July 2025，
  
  Revised：2025-11-11，
  
  Accepted：11 November 2025，
  
  Published：30 November 2025
- 稿件说明：
移动端阅览
李剑，周秘，刘祥，等.机器学习驱动的个性化氨甲环酸用药推荐改善骨科手术患者围手术期预后：一项基于大样本数据库的研究［J］.陆军军医大学学报，2025，47（22）：2868-2880.DOI：10.16016/j.2097-0927.202507025.

LI J，ZHOU M，LIU X，et al.Machine learning-driven personalized tranexamic acid administration recommendations improve perioperative outcomes in orthopedic surgery patients： A large-scale database study［J］.J Army Med Univ，2025，47（22）：2868-2880.DOI：10.16016/j.2097-0927.202507025.
李剑，周秘，刘祥，等.机器学习驱动的个性化氨甲环酸用药推荐改善骨科手术患者围手术期预后：一项基于大样本数据库的研究［J］.陆军军医大学学报，2025，47（22）：2868-2880.DOI：10.16016/j.2097-0927.202507025. DOI：

LI J，ZHOU M，LIU X，et al.Machine learning-driven personalized tranexamic acid administration recommendations improve perioperative outcomes in orthopedic surgery patients： A large-scale database study［J］.J Army Med Univ，2025，47（22）：2868-2880.DOI：10.16016/j.2097-0927.202507025. DOI：

摘要

目的

基于机器学习构建骨科手术围手术期氨甲环酸使用的个性化推荐策略，以减少围手术期出血及相关并发症，改善患者预后。

方法

从INSPIRE数据库中纳入了11 727例骨科手术患者，通过多重插补方法处理缺失数据，并采用Boruta分析筛选出相关特征变量。构建了多种机器学习模型，包括梯度提升机（gradient boosting machine， GBM）、广义线性模型（generalized linear model， GLM）、极端梯度提升机（eXtreme gradient boosting， XGBoost）、K最近邻（k-nearest neighbors， KNN）、神经网络（neural network， NNET）、朴素贝叶斯（naive bayes， NB）及随机森林（random forest， RF），评估各模型在预测术中出血及术后住院时间延长的效能。筛选最优模型后采用加权集成法进行整合，以达到最佳预后为目标对氨甲环酸使用策略进行推荐。通过测试集验证及与医生决策对比，完成模型性能评估。

结果

针对术中出血，RF模型的受试者操作曲线下面积（area under the subject curve，AUC）达到0.73，显著优于其他模型；而针对术后住院时间延长，XGBoost模型表现得最佳（AUC=0.84）。基于上述最佳模型，实施了集成策略，结果显示符合推荐策略的患者术中出血量降低，术后住院时间缩短。

结论

氨甲环酸的使用与术中出血和术后住院时间相关，应用构建的模型进行个性化决策推荐能有效改善患者预后。

Abstract

Objective

To develop a personalized recommendation strategy for tranexamic acid administration during the perioperative period of orthopedic surgery based on machine learning

aiming to reduce perioperative bleeding and related complications and improving clinical outcomes.

Methods

A total of 11 727 patients undergoing orthopedic surgery from the INSPIRE database were subjected in this study. Missing data were handled using multiple imputation methods

and relevant feature variables were screened using Boruta analysis. We constructed various machine learning models

including Gradient Boosting Machine (GBM)

Generalized Linear Model (GLM)

eXtreme Gradient Boosting (XGBoost)

K-Nearest Neighbors (KNN)

Neural Network (NNET)

Naive Bayes (NB)

and Random Forest (RF)

to evaluate their performance in predicting intraoperative bleeding and prolonged postoperative length of hospital stay. The optimal model was then selected and further integrated using a weighted ensemble

aiming to achieve the best prognosis by recommending usage strategies for tranexamic acid. The predictive performance of the constructed model was then verified against the testing set

and compared with the physician decision-making to complete the evaluation.

Results

In predicting intraoperative bleeding

the RF model achieved an area under the receiver operating characteristic curve (AUC) of 0.73

which was significantly better than other models. In predicting the prolonged postoperative length of hospital stay

the XGBoost model performed the best

with an AUC value of 0.84. Based on the above best-performing models

an ensemble strategy was implemented. The patients who followed the recommended strategy had reduced intraoperative bleeding and shorter postoperative length of hospital stay.

Conclusion

The use of tranexamic acid is associated with intraoperative bleeding and postoperative length of hospital stay. Personalized decision-making recommendation based on our constructed model can effectively improve the outcomes of the patients undergoing orthopedic surgery.

关键词

Keywords

references

FRISCH N B ， WESSELL N M ， CHARTERS M A ， et al . Predictors and complications of blood transfusion in total hip and knee arthroplasty ［J］. J Arthroplasty ， 2014 ， 29 （ 9 Suppl ）： 189 - 192 . DOI： 10.1016/j.arth.2014.03.048 http://dx.doi.org/10.1016/j.arth.2014.03.048 .

LIU K C ， PIPLE A S ， RICHARDSON M K ， et al . Increased risk of venous thromboembolism in patients with postoperative Anemia After total joint arthroplasty： are transfusions to blame？［J］. J Bone Joint Surg Am ， 2023 ， 105 （ 17 ）： 1354 - 1361 . DOI： 10.2106/JBJS.23.00146 http://dx.doi.org/10.2106/JBJS.23.00146 .

HARATIAN A ， SHELBY T ， HASAN L K ， et al . Utilization of tranexamic acid in surgical orthopaedic practice： indications and current considerations ［J］. Orthop Res Rev ， 2021 ， 13 ： 187 - 199 . DOI： 10.2147/ORR.S321881 http://dx.doi.org/10.2147/ORR.S321881 .

LUO W ， SUN R X ， JIANG H ， et al . The efficacy and safety of topical administration of tranexamic acid in spine surgery： a meta-analysis ［J］. J Orthop Surg Res ， 2018 ， 13 （ 1 ）： 96 . DOI： 10.1186/s13018-018-0815-0 http://dx.doi.org/10.1186/s13018-018-0815-0 .

PATEL P A ， WYROBEK J A ， BUTWICK A J ， et al . Update on applications and limitations of perioperative tranexamic acid ［J］. Anesth Analg ， 2022 ， 135 （ 3 ）： 460 - 473 . DOI： 10.1213/ANE.0000000000006039 http://dx.doi.org/10.1213/ANE.0000000000006039 .

GANDHI R ， EVANS H M K ， MAHOMED S R ， et al . Tranexamic acid and the reduction of blood loss in total knee and hip arthroplasty： a meta-analysis ［J］. BMC Res Notes ， 2013 ， 6 ： 184 . DOI： 10.1186/1756-0500-6-184 http://dx.doi.org/10.1186/1756-0500-6-184 .

LUO H ， SHEN C J ， QU T Y ， et al . Tranexamic acid-induced focal convulsions after spinal surgery： a rare case report and literature review on side effects of accidental spinal administration of tranexamic acid ［J］. EFORT Open Rev ， 2023 ， 8 （ 6 ）： 482 - 488 . DOI： 10.1530/EOR-23-0016 http://dx.doi.org/10.1530/EOR-23-0016 .

WONG J ， GEORGE R B ， HANLEY C M ， et al . Tranexamic acid： current use in obstetrics， major orthopedic， and trauma surgery ［J］. Can J Anaesth ， 2021 ， 68 （ 6 ）： 894 - 917 . DOI： 10.1007/s12630-021-01967-7 http://dx.doi.org/10.1007/s12630-021-01967-7 .

NIZAR AHAMED H ， MOHAN S ， KRISHNAN R . Role of tranexamic acid in controlling blood loss in hemiarthroplasty of the hip： a prospective and observational study ［J］. Cureus ， 2024 ， 16 （ 6 ）： e62617 . DOI： 10.7759/cureus.62617 http://dx.doi.org/10.7759/cureus.62617 .

LIM L ， LEE H ， JUNG C W ， et al . INSPIRE， a publicly available research dataset for perioperative medicine ［J］. Sci Data ， 2024 ， 11 ： 655 . DOI： 10.1038/s41597-024-03517-4 http://dx.doi.org/10.1038/s41597-024-03517-4 .

GAO F Q ， LI Z J ， ZHANG K ， et al . Four methods for calculating blood-loss after total knee arthroplasty ［J］. Chin Med J ， 2015 ， 128 （ 21 ）： 2856 - 2860 . DOI： 10.4103/0366-6999.168041 http://dx.doi.org/10.4103/0366-6999.168041 .

NADLER S B ， HIDALGO J H ， BLOCH T . Prediction of blood volume in normal human adults ［J］. Surgery ， 1962 ， 51 （ 2 ）： 224 - 232 .

DANG T ， NGUYEN T T ， FRANCISCO MORENO-GARCÍA C ， et al . Weighted ensemble of deep learning models based on comprehensive learning particle swarm optimization for medical image segmentation ［C］// 2021 IEEE Congress on Evolutionary Computation （CEC） . June 28 - July 1 ， 2021 ， Kraków， Poland . IEEE ， 2021： 744 - 751 . DOI： 10.1109/CEC45853.2021.9504929 http://dx.doi.org/10.1109/CEC45853.2021.9504929 .

DAI Z Q ， XU S M ， WU X ， et al . Knowledge mapping of multicriteria decision analysis in healthcare： a bibliometric analysis ［J］. Front Public Health ， 2022 ， 10 ： 895552 . DOI： 10.3389/fpubh.2022.895552 http://dx.doi.org/10.3389/fpubh.2022.895552 .

FOUCHE P F ， STEIN C ， NICHOLS M ， et al . Tranexamic acid for traumatic injury in the emergency setting： a systematic review and bias-adjusted meta-analysis of randomized controlled trials ［J］. Ann Emerg Med ， 2024 ， 83 （ 5 ）： 435 - 445 . DOI： 10.1016/j.annemergmed.2023.10.004 http://dx.doi.org/10.1016/j.annemergmed.2023.10.004 .

AL-JEABORY M ， SZARPAK L ， ATTILA K ， et al . Efficacy and safety of tranexamic acid in emergency trauma： a systematic review and meta-analysis ［J］. J Clin Med ， 2021 ， 10 （ 5 ）： 1030 . DOI： 10.3390/jcm10051030 http://dx.doi.org/10.3390/jcm10051030 .

RELKE N ， CHORNENKI N L J ， SHOLZBERG M . Tranexamic acid evidence and controversies： an illustrated review ［J］. Res Pract Thromb Haemost ， 2021 ， 5 （ 5 ）： e12546 . DOI： 10.1002/rth2.12546 http://dx.doi.org/10.1002/rth2.12546 .

LIU J ， XIE Y H ， SHU X ， et al . Value function assessment to different RL algorithms for heparin treatment policy of patients with sepsis in ICU ［J］. Artif Intell Med ， 2024 ， 147 ： 102726 . DOI： 10.1016/j.artmed.2023.102726 http://dx.doi.org/10.1016/j.artmed.2023.102726 .

WALKER I S ， VLOK A J ， ESTERHUIZEN T M ， et al . Prediction of hematocrit decline and the impact of peri-operative fluid use in lumbar spinal fusion surgery ［J］. Eur Spine J ， 2024 ， 33 （ 1 ）： 307 - 313 . DOI： 10.1007/s00586-023-07977-x http://dx.doi.org/10.1007/s00586-023-07977-x .

RANUCCI M ， LADDOMADA T ， RANUCCI M ， et al . Blood viscosity during coagulation at different shear rates ［J］. Physiol Rep ， 2014 ， 2 （ 7 ）： e12065 . DOI： 10.14814/phy2.12065 http://dx.doi.org/10.14814/phy2.12065 .

TAN Z L ， SUN Z J ， MU ER TI ZHA M E A L M ， et al . Personalized tourniquet pressure versus uniform tourniquet pressure in trauma orthopedic surgery of extremities： a prospective randomized controlled study ［J］. J Orthop Surg Res ， 2024 ， 19 （ 1 ）： 721 . DOI： 10.1186/s13018-024-05217-6 http://dx.doi.org/10.1186/s13018-024-05217-6 .

HOFFMAN J F . Chapter 5 Functional Roles of lntracellular Potassium in Red Blood Cells ［M］//GIEBISCH G. Current Topics in Membranes and Transport . Academic Press . 1987 ： 87 - 96 .

AL BALUSHI H ， HANNEMANN A ， REES D ， et al . The effect of antioxidants on the properties of red blood cells from patients with sickle cell anemia ［J］. Front Physiol ， 2019 ， 10 ： 976 . DOI： 10.3389/fphys.2019.00976 http://dx.doi.org/10.3389/fphys.2019.00976 .

TRUONG A ， HANNA M H ， MOGHADAMYEGHANEH Z ， et al . Implications of preoperative hypoalbuminemia in colorectal surgery ［J］. World J Gastrointest Surg ， 2016 ， 8 （ 5 ）： 353 - 362 . DOI： 10.4240/wjgs.v8.i5.353 http://dx.doi.org/10.4240/wjgs.v8.i5.353 .

GRIFFIN F S ， STEAD T S ， ZEYL V G ， et al . Low preoperative albumin levels significantly associated with increased risk of wound infection and bleeding after panniculectomy ［J］. Plast Surg （Oakv）， 2024 ： 2292550 3241292350 . DOI： 10.1177/22925503241292350 http://dx.doi.org/10.1177/22925503241292350 .

WANG Y F ， GONG Y ， CHEN D ， et al . C-reactive protein/albumin ratio is associated with mortality in patients with moderate to severe traumatic brain injury ［J］. World Neurosurg ， 2023 ， 173 ： e234 - e240 . DOI： 10.1016/j.wneu.2023.02.037 http://dx.doi.org/10.1016/j.wneu.2023.02.037 .

GUO J L ， HE Q H ， LI Y H . Development and validation of machine learning models to predict perioperative transfusion risk for hip fractures in the elderly ［J］. Ann Med ， 2024 ， 56 （ 1 ）： 2357225 . DOI： 10.1080/07853890.2024.2357225 http://dx.doi.org/10.1080/07853890.2024.2357225 .

MORA D ， MATEO J ， NIETO J A ， et al . Machine learning to predict major bleeding during anticoagulation for venous thromboembolism： possibilities and limitations ［J］. Br J Haematol ， 2023 ， 201 （ 5 ）： 971 - 981 . DOI： 10.1111/bjh.18737 http://dx.doi.org/10.1111/bjh.18737 .

HUI V ， LITTON E ， EDIBAM C ， et al . Using machine learning to predict bleeding after cardiac surgery ［J］. Eur J Cardiothorac Surg ， 2023 ， 64 （ 6 ）： ezad297 . DOI： 10.1093/ejcts/ezad297 http://dx.doi.org/10.1093/ejcts/ezad297 .

WANG H H ， OUYANG Y H ， CHEN Y L ， et al . Clinical application of tranexamic acid in arthroscopic rotator cuff repair surgery： a randomized controlled trial ［J］. Medicine ， 2024 ， 103 （ 26 ）： e38515 . DOI： 10.1097/MD.000000000 0038515 http://dx.doi.org/10.1097/MD.0000000000038515 .

CHOI W S ， IRWIN M G ， SAMMAN N . The effect of tranexamic acid on blood loss during orthognathic surgery： a randomized controlled trial ［J］. J Oral Maxillofac Surg ， 2009 ， 67 （ 1 ）： 125 - 133 . DOI： 10.1016/j.joms.2008.08.015 http://dx.doi.org/10.1016/j.joms.2008.08.015 .

ALVAREZ J C ， SANTIVERI F X ， RAMOS I ， et al . Tranexamic acid reduces blood transfusion in total knee arthroplasty even when a blood conservation program is applied ［J］. Transfusion ， 2008 ， 48 （ 3 ）： 519 - 525 . DOI： 10.1111/j.1537-2995.2007.01564.x http://dx.doi.org/10.1111/j.1537-2995.2007.01564.x .

GAUSDEN E B ， QUDSI R ， BOONE M D ， et al . Tranexamic acid in orthopaedic trauma surgery： a meta-analysis ［J］. J Orthop Trauma ， 2017 ， 31 （ 10 ）： 513 - 519 . DOI： 10.1097/BOT.0000000000000913 http://dx.doi.org/10.1097/BOT.0000000000000913 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Efficacy of robotic renal transplantation in perioperative period

Clinical analysis on perioperative blood coagulation status in lung cancer patients by thrombelastography

Pre-emptive analgesia of parecoxib sodium in peri-operative nasal endoscopic surgery under local anesthesia: a clinical study of 280 cases

Study of plasma concentration of tranexamic acid during cardiopulmonary bypass in infants with tetralogy of Fallot

Perioperative differences in open radical prostatectomy versus laparoscopic radical prostatectomy

Related Author

JIANG Jun

ZHONG Xiao

LAN Weihua

WANG Luofu

ZHANG Yao

ZHANG Jun

NIE Zhilin

LI Ke

Related Institution

Department of Urology, Army Medical Center of PLA

Institute of Thoracic Surgery, Institute of Surgery Research, Daping Hospital, Third Military Medical University

Department of Otolaryngology, Head and Neck Surgery, Chongqing People’s Hospital

Department of Cardiovascular Surgery, Xinqiao Hospital, Third Military Medical University

Department of Anesthesia, Qingdao Children Hospital

⁰