Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study

作者全名："Li, Wenle; Zhang, Yusi; Zhou, Xin; Quan, Xubin; Chen, Binghao; Hou, Xuewen; Xu, Qizhong; He, Weiheng; Chen, Liang; Liu, Xiaozhu; Zhang, Yang; Xiang, Tianyu; Li, Runmin; Liu, Qiang; Wu, Shi-Nan; Wang, Kai; Liu, Wencai; Zheng, Jialiang; Luan, Haopeng; Yu, Xiaolin; Chen, Anfa; Xu, Chan; Luo, Tongqing; Hu, Zhaohui"

作者地址："[Li, Wenle; Xu, Chan] Xiamen Univ, Diagnost & Ctr Mol Imaging & Translat Med, Sch Publ Hlth, State Key Lab Mol Vaccinol & Mol, Xiamen, Peoples R China; [Li, Wenle; Wang, Kai] Xuzhou Med Univ, Affiliated Hosp 2, Key Lab Neurol Dis, Xuzhou, Jiangsu, Peoples R China; [Li, Wenle; Quan, Xubin; Chen, Binghao; Luo, Tongqing; Hu, Zhaohui] Guangxi Med Univ, Liuzhou Peoples Hosp, Dept Spinal Surg, Liuzhou, Peoples R China; [Zhang, Yusi] Xi An Jiao Tong Univ, Affiliated Hosp 1, Canc Ctr, Xian, Peoples R China; [Zhang, Yusi] Xi An Jiao Tong Univ, Affiliated Hosp 1, Precis Med Ctr, Xian, Peoples R China; [Zhang, Yusi] Xi An Jiao Tong Univ, Affiliated Hosp 1, Dept Med Oncol, Xian, Peoples R China; [Zhou, Xin] Shanxi Med Univ, Shanxi Bethune Hosp, Shanxi Acad Med Sci,Hosp 3, Tongji Shanxi Hosp, Taiyuan 030032, Peoples R China; [Hou, Xuewen] Guangdong Med Univ, Dongguan Affiliated Hosp 1, Dept Radiol, Dongguan, Peoples R China; [Xu, Qizhong] Shenzhen Univ, Shenzhen Peoples Hosp 2, Affiliated Hosp 1, Dept Radiol, Shenzhen, Peoples R China; [He, Weiheng] Peoples Hosp Ningxia Hui Autonomous Reg, Dept Radiol, Yinchuan, Peoples R China; [Chen, Liang] Hubei Prov Hosp Tradit Chinese Med, Dept Radiol, Wuhan, Peoples R China; [Liu, Xiaozhu] Capital Med Univ, Beijing Shijitan Hosp, Dept Crit Care Med, Beijing, Peoples R China; [Liu, Xiaozhu] Chongqing Med Univ, Affiliated Hosp 2, Dept Cardiol, Chongqing, Peoples R China; [Zhang, Yang] Chongqing Med Univ, Coll Med Informat, Chongqing, Peoples R China; [Zhang, Yang] Chongqing Med Univ, Med Data Sci Acad, Chongqing, Peoples R China; [Xiang, Tianyu] Chongqing Med Univ, Univ Town Hosp, Informat Ctr, Chongqing, Peoples R China; [Li, Runmin] Xi An Jiao Tong Univ, Honghui Hosp, Dept Foot & Ankle Surg, Xian, Shaanxi, Peoples R China; [Liu, Qiang] Xianyang Cent Hosp, Dept Orthoped, Xianyang, Shannxi, Peoples R China; [Wu, Shi-Nan] Xiamen Univ, Eye Inst, Sch Med, Xiamen, Fujian, Peoples R China; [Liu, Wencai] Shanghai Jiao Tong Univ, Shanghai Sixth Peoples Hosp, Dept Orthoped, Sch Med, Shanghai 200233, Peoples R China; [Zheng, Jialiang] Xiamen Univ, Canc Res Ctr, Sch Med, Xiamen, Peoples R China; [Luan, Haopeng] Xinjiang Med Univ, Affiliated Hosp 6, Dept Spine Surg, Urumqi, Xinjiang, Peoples R China; [Yu, Xiaolin] Guizhou Med Univ, Affiliated Hosp, Dept Orthoped, Guiyang, Guizhou, Peoples R China; [Chen, Anfa] Jiangxi Prov Hosp Integrated Chinese & Western Med, Dept Orthoped, Nanchang, Peoples R China"

通信作者："Li, WL (通讯作者)，Xiamen Univ, Diagnost & Ctr Mol Imaging & Translat Med, Sch Publ Hlth, State Key Lab Mol Vaccinol & Mol, Xiamen, Peoples R China.; Li, WL (通讯作者)，Xuzhou Med Univ, Affiliated Hosp 2, Key Lab Neurol Dis, Xuzhou, Jiangsu, Peoples R China.; Li, WL; Luo, TQ; Hu, ZH (通讯作者)，Guangxi Med Univ, Liuzhou Peoples Hosp, Dept Spinal Surg, Liuzhou, Peoples R China."

来源：JOURNAL OF ORTHOPAEDIC SURGERY AND RESEARCH

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001156559800002

JCR分区：Q1

影响因子：2.8

年份：2024

卷号：19

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Spinal deformity; Posterior spinal deformity surgery; Postoperative length of stay; Multimodal; Machine learning

摘要："PurposeThis research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management.MethodsPatients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction.ResultsOf the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability.ConclusionsOur study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians.Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic.clinicaltrials.gov/ct2/show/NCT05867732.ConclusionsOur study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians.Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic.clinicaltrials.gov/ct2/show/NCT05867732."

基金机构：Shaanxi Provincial Health and Health Research Fund Project

基金资助正文：Not applicable.