Development and validation of machine learning models for intraoperative blood transfusion prediction in severe lumbar disc herniation

Qiang Liu; An-Tian Chen; Runmin Li; Liang Yan; Xubin Quan; Xiaozhu Liu; Yang Zhang; Tianyu Xiang; Yingang Zhang; Anfa Chen; Hao Jiang; Xuewen Hou; Qizhong Xu; Weiheng He; Liang Chen; Xin Zhou; Qiang Zhang; Wei Huang; Haopeng Luan; Xinghua Song; Xiaolin Yu; Xiangdong Xi; Kai Wang; Shi-Nan Wu; Wencai Liu; Yusi Zhang; Jialiang Zheng; Haizhen Ding; Chan Xu; Chengliang Yin; Zhaohui Hu; Baicheng Qiu; Wenle Li

doi:10.1016/j.isci.2024.111106

Development and validation of machine learning models for intraoperative blood transfusion prediction in severe lumbar disc herniation

iScience. 2024 Oct 5;27(11):111106. doi: 10.1016/j.isci.2024.111106. eCollection 2024 Nov 15.

Authors

Qiang Liu¹, An-Tian Chen^{2

3}, Runmin Li⁴, Liang Yan⁵, Xubin Quan⁶, Xiaozhu Liu^{7

8}, Yang Zhang^{9

10}, Tianyu Xiang¹¹, Yingang Zhang¹², Anfa Chen¹³, Hao Jiang¹⁴, Xuewen Hou¹⁵, Qizhong Xu¹⁶, Weiheng He¹⁷, Liang Chen¹⁸, Xin Zhou¹⁹, Qiang Zhang²⁰, Wei Huang²¹, Haopeng Luan²², Xinghua Song²², Xiaolin Yu²³, Xiangdong Xi²⁴, Kai Wang²⁵, Shi-Nan Wu²⁶, Wencai Liu²⁷, Yusi Zhang^{28

29

30}, Jialiang Zheng³¹, Haizhen Ding³², Chan Xu³², Chengliang Yin³³, Zhaohui Hu⁶, Baicheng Qiu³⁴, Wenle Li^{6

25

32}

Affiliations

¹ Department of Orthopedics, Xianyang Central Hospital, Xianyang, Shannxi, China.
² Department of Cardiology, State Key Laboratory of Cardiovascular Disease, Fuwai Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College/National Center for Cardiovascular Diseases, Beijing, China.
³ Department of Computer Science, University of Texas at Austin, Austin, TX, USA.
⁴ Department of Foot and Ankle Surgery, Honghui Hospital, Xi'an Jiaotong University, Xi'an, Shaanxi Province, China.
⁵ Department of Spinal Surgery, Honghui Hospital of Xi'an Jiaotong University, Xi'an, China.
⁶ Department of Spinal Surgery, Guangxi Medical University Affiliated Liuzhou People's Hospital, Liuzhou, China.
⁷ Department of Critical Care Medicine, Beijing Shijitan Hospital, Capital Medical University, Beijing, China.
⁸ Department of Cardiology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, China.
⁹ College of Medical Informatics, Chongqing Medical University, Chongqing, China.
¹⁰ Medical Data Science Academy, Chongqing Medical University, Chongqing, China.
¹¹ Information Center, The University-Town Hospital of Chongqing Medical University, Chongqing, China.
¹² Department of Orthopaedics of the First Affiliated Hospital, Medical School, Xi' an Jiaotong University, Xi'an, China.
¹³ Department of Orthopedics, Jiangxi Province Hospital of Integrated Chinese & Western Medicine, Nanchang, China.
¹⁴ Spine Tumor Center, Changzheng Hospital, Second Military Medical University, 415 Feng Yang Road, Shanghai 200003, China.
¹⁵ Department of Radiology, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan, China.
¹⁶ Department of Radiology, The First Affiliated Hospital of Shenzhen University, Shenzhen Second People's Hospital, Shenzhen, China.
¹⁷ Department of Radiology, People's Hospital of Ningxia Hui Autonomous Region, Yinchuan, China.
¹⁸ Department of Radiology, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan, China.
¹⁹ Third Hospital of Shanxi Medical University, Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Taiyuan 030032, China.
²⁰ First Department of Orthopaedics, Xi 'an Central Hospital, Xi'an, Shaanxi Province, China.
²¹ Department of Orthopedics, The Sixth Affiliated Hospital, School of Medicine, South China University of Technology, Foshan, Guangdong 528000, China.
²² Department of Spine Surgery, The Six Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China.
²³ Department of Orthopedics, Affiliated Hospital of Guizhou Medical University, Guiyang, China.
²⁴ Department of Joint Surgery, No.215 Hospital of Shaanxi Nuclear Industry, Xianyang, Shannxi, China.
²⁵ Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China.
²⁶ Eye Institute of Xiamen University, School of Medicine, Xiamen University, Xiamen, Fujian, China.
²⁷ Department of Orthopedics, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai 200233, China.
²⁸ Cancer Center, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
²⁹ Precision Medicine Center, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
³⁰ Department of Medical Oncology, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
³¹ Cancer Research Center, School of Medicine, Xiamen University, Xiamen, China.
³² State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics & Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, China.
³³ Faculty of Medicine, Macau University of Science and Technology, Macau, China.
³⁴ Medical Cosmetic Department, Foresea Life Insurance Guangxi Hospital, Nanning, China.

Abstract

Lumbar disc herniation (LDH) is a common cause of lower back pain and sciatica, and posterior lumbar interbody fusion (PLIF) is always employed. This multicenter retrospective study investigates predicting intraoperative blood transfusion for LDH patients undergoing PLIF in China. The research includes 6,241 patients from 22 medical centers and employs 8 feature selection methods and 10 machine learning models, including an integrated stacking model. The optimal predictive model was selected based on the receiver operating characteristic area under the curve, clinical applicability, and computational efficiency. Among the evaluated combinations, the simulated annealing support vector machine recursive + stacking model achieved the highest performance with an area under the curve of 0.884, supported by robust calibration and decision curve analyses. A publicly accessible web calculator was developed to assist clinicians in decision-making. This work significantly enhances intraoperative transfusion predictions, providing valuable tools for improving patient management.

Keywords: Computer science; Health sciences; Natural sciences.