
浏览全部资源
扫码关注微信
1.西南医科大学附属医院麻醉科 四川 泸州
2.自贡市第四人民医院麻醉科 四川 自贡
3.四川大学华西医院麻醉科 四川 成都
周 军, E-mail: junzhou@swmu.edu.cn
收稿日期:2025-03-04,
修回日期:2025-04-01,
纸质出版日期:2025-05-30
移动端阅览
李强,母国,王文章,等.术后入ICU肥胖患者AKI风险及其进展为死亡预测研究[J].陆军军医大学学报,2025,47(10):1110-1125.DOI:10.16016/j.2097-0927.202503010.
LI Q,MU G,WANG W Z,et al.Prediction of risk for acute kidney injury and its progression to mortality in obese patients admitted to ICU postoperatively[J].J Army Med Univ,2025,47(10):1110-1125.DOI:10.16016/j.2097-0927.202503010.
李强,母国,王文章,等.术后入ICU肥胖患者AKI风险及其进展为死亡预测研究[J].陆军军医大学学报,2025,47(10):1110-1125.DOI:10.16016/j.2097-0927.202503010. DOI:
LI Q,MU G,WANG W Z,et al.Prediction of risk for acute kidney injury and its progression to mortality in obese patients admitted to ICU postoperatively[J].J Army Med Univ,2025,47(10):1110-1125.DOI:10.16016/j.2097-0927.202503010. DOI:
目的
2
本研究旨在通过机器学习算法构建肥胖患者术后急性肾损伤(acute kidney injury, AKI)风险预测模型及死亡风险预测模型,以提高对肥胖患者术后AKI的预警能力和预后评估水平,为临床医疗提供支持。
方法
2
研究从MIMIC-IV和eICU数据库中收集术后入ICU的肥胖患者相关数据进行统计分析,最终纳入2520例肥胖术后入ICU患者(MIMIC-IV 670例,eICU 1 850例)进行模型构建,包括一般资料、生命体征、实验室检查结果、手术类型、合并症及用药情况等。通过数据清洗和预处理,使用Boruta进行特征筛选,并采用GBM、GLM、KNN、NB、NNET、SVM和XGBoost等7种机器学习算法构建预测模型,通过交叉验证和外部验证评估模型性能。
结果
2
肥胖患者术后AKI风险预测模型中,SVM模型在测试集的AUC值达到0.80,外部验证AUC为0.71;死亡风险预测模型中,GBM模型表现最佳,测试集AUC值达到0.91。
结论
2
本研究成功构建了肥胖患者术后AKI风险及死亡风险预测模型,为临床医生提供了有力的辅助工具,有助于改善患者临床结局。
Objective To develop a machine learning-based risk prediction model for postoperative acute kidney injury (AKI) and a model for mortality in obese patients admitted to intensive care unit (ICU) in order to improve early warning and prognostic evaluation to support clinical decision-making. Methods Data of obese postoperative ICU patients were retrospectively retrieved from the MIMIC-IV and eICU databases for statistical analysis. Ultimately
2 520 patients (670 from MIMIC-IV and 1 850 from eICU databases) were included to build the risk prediction models for AKI and mortality. The data included demographic information
vital signs
laboratory findings
surgical types
comorbidities
and medication use. After data cleaning and preprocessing
Boruta feature selection was applied
followed by the construction of prediction models using 7 machine learning algorithms
that is
Gradient Boosting Machine (GBM)
Generalized Linear Model (GLM)
k-Nearest Neighbors (KNN)
Naïve Bayes (NB)
Neural Network (NNET)
Support Vector Machine (SVM)
and XGBoost. Model performance was evaluated through cross-validation and external validation. Results In the risk prediction models of AKI
the SVM model achieved the highest AUC value of 0.80 in the testing set and 0.71 in the external validation test. For the risk prediction models of mortality
the GBM model outperformed others in the prediction
attaining an AUC value of 0.91 in the testing set. Conclusion Risk predictive models for postoperative AKI and mortality in obese ICU patients are successfully constructed
and are valuable tools for clinicians to optimize early intervention and improve clinical outcomes for the patients.
GOREN O , MATOT I . Perioperative acute kidney injury [J]. Br J Anaesth , 2015 , 115: ii3-ii 14 . DOI: 10.1093/bja/aev380 http://dx.doi.org/10.1093/bja/aev380 .
GUMBERT S D , KORK F , JACKSON M L , et al . Perioperative acute kidney injury [J]. Anesthesiology , 2020 , 132 ( 1 ): 180 - 204 . DOI: 10.1097/ALN.0000000000002968 http://dx.doi.org/10.1097/ALN.0000000000002968 .
MACLAUGHLIN H L , BLACKLOCK R M , WRIGHT K , et al . Obesity and recovery from acute kidney injury (Ob AKI): a prospective cohort feasibility study [J]. BMJ Open , 2019 , 9 ( 3 ): e024033 . DOI: 10.1136/bmjopen-2018-024033 http://dx.doi.org/10.1136/bmjopen-2018-024033 .
HAWN M T , BIAN J , LEETH R R , et al . Impact of obesity on resource utilization for general surgical procedures [J]. Ann Surg , 2005 , 241 ( 5 ): 821-826;discussion 826-828 . DOI: 10.1097/01.sla.0000161044.20857.24 http://dx.doi.org/10.1097/01.sla.0000161044.20857.24 .
MULLEN J T , DAVENPORT D L , HUTTER M M , et al . Impact of body mass index on perioperative outcomes in patients undergoing major intra-abdominal cancer surgery [J]. Ann Surg Oncol , 2008 , 15 ( 8 ): 2164 - 2172 . DOI: 10.1245/s10434-008-9990-2 http://dx.doi.org/10.1245/s10434-008-9990-2 .
NTINOPOULOU P , NTINOPOULOU E , PAPATHANASIOU I V , et al . Obesity as a risk factor for venous thromboembolism recurrence: a systematic review [J]. Medicina , 2022 , 58 ( 9 ): 1290 . DOI: 10.3390/medicina58091290 http://dx.doi.org/10.3390/medicina58091290 .
JÄMSEN E , NEVALAINEN P , ESKELINEN A , et al . Obesity, diabetes, and preoperative hyperglycemia as predictors of periprosthetic joint infection: a single-center analysis of 7181 primary hip and knee replacements for osteoarthritis [J]. J Bone Joint Surg Am , 2012 , 94 ( 14 ): e101 . DOI: 10.2106/JBJS.J.01935 http://dx.doi.org/10.2106/JBJS.J.01935 .
WANG W , FENG S , YE Z , et al . Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm [J]. Acta Pharm Sin B , 2022 , 12 ( 6 ): 2950 - 2962 . DOI: 10.1016/j.apsb.2021.11.021 http://dx.doi.org/10.1016/j.apsb.2021.11.021 .
林泰安 , 罗亚梅 , 黄志伟 , 等 . 基于支持向量机的肝外胆管癌术前淋巴结状态预测模型构建 [J]. 西南医科大学学报 , 2023 , 46 ( 4 ): 303 - 307 . DOI: 10.3969/j.issn.2096-3351.2023.04.006 http://dx.doi.org/10.3969/j.issn.2096-3351.2023.04.006 .
LIN T A , LUO Y M , HUANG Z W , et al . The prediction model based on support vector machine for preoperative lymph nodes status in extrahepatic cholangiocarcinoma [J]. J Southwest Med Univ , 2023 , 46 ( 4 ): 303 - 307 . DOI: 10.3969/j.issn.2096-3351.2023.04.006 http://dx.doi.org/10.3969/j.issn.2096-3351.2023.04.006 .
CAO L , HE R M , ZHANG A , et al . Development of a deep learning system for predicting biochemical recurrence in prostate cancer [J]. BMC Cancer , 2025 , 25 ( 1 ): 232 . DOI: 10.1186/s12885-025-13628-9 http://dx.doi.org/10.1186/s12885-025-13628-9 .
孟祥勇 , 秦嘉怡 , 陈文生 . 基于机器学习的早期胃癌淋巴结转移预测模型构建与验证 [J]. 陆军军医大学学报 , 2024 , 46 ( 21 ): 2432 - 2442 . DOI: 10.16016/j.2097-0927.202403126 http://dx.doi.org/10.16016/j.2097-0927.202403126 .
MENG X Y , QIN J Y , CHEN W S . Construction and validation of a prediction model for lymph node metastasis in early gastric cancer based on machine learning [J]. J Army Med Univ , 2024 , 46 ( 21 ): 2432 - 2442 . DOI: 10.16016/j.2097-0927.202403126 http://dx.doi.org/10.16016/j.2097-0927.202403126 .
舒欣 , 李昊洋 , 李雨捷 , 等 . 基于机器学习建立腹部手术术后脓毒症患者死亡风险预测模型 [J]. 陆军军医大学学报 , 2023 , 45 ( 8 ): 732 - 738 . DOI: 10.16016/j.2097-0927.202212045 http://dx.doi.org/10.16016/j.2097-0927.202212045 .
SHU X , LI H Y , LI Y J , et al . Prediction of postoperative sepsis mortality risk based on machine learning in patients undergoing abdominal surgery [J]. J Army Med Univ , 2023 , 45 ( 8 ): 732 - 738 . DOI: 10.16016/j.2097-0927.202212045 http://dx.doi.org/10.16016/j.2097-0927.202212045 .
SU Y , WANG P , HU Y , et al . AKI-Pro score for predicting progression to severe acute kidney injury or death in patients with early acute kidney injury after cardiac surgery [J]. J Transl Med , 2024 , 22 ( 1 ): 571 . DOI: 10.1186/s12967-024-05279-4 http://dx.doi.org/10.1186/s12967-024-05279-4 .
ZHANG Y H , XU D M , GAO J W , et al . Development and validation of a real-time prediction model for acute kidney injury in hospitalized patients [J]. Nat Commun , 2025 , 16 ( 1 ): 68 . DOI: 10.1038/s41467-024-55629-5 http://dx.doi.org/10.1038/s41467-024-55629-5 .
JOHNSON A E W , BULGARELLI L , SHEN L , et al . MIMIC-IV, a freely accessible electronic health record dataset [J]. Sci Data , 2023 , 10 ( 1 ): 1 . DOI: 10.1038/s41597-022-01899-x http://dx.doi.org/10.1038/s41597-022-01899-x .
POLLARD T J , JOHNSON A E W , RAFFA J D , et al . The eICU Collaborative Research Database, a freely available multi-center database for critical care research [J]. Sci Data , 2018 , 5 : 180178 . DOI: 10.1038/sdata.2018.178 http://dx.doi.org/10.1038/sdata.2018.178 .
WELSH A , HAMMAD M , PIÑA I L , et al . Obesity and cardiovascular health [J]. Eur J Prev Cardiol , 2024 , 31 ( 8 ): 1026 - 1035 . DOI: 10.1093/eurjpc/zwae025 http://dx.doi.org/10.1093/eurjpc/zwae025 .
YOON S Y , KIM J S , JEONG K H , et al . Acute kidney injury: biomarker-guided diagnosis and management [J]. Medicina , 2022 , 58 ( 3 ): 340 . DOI: 10.3390/medicina 58030340 http://dx.doi.org/10.3390/medicina58030340 .
LIEBERMAN O J , LAHUE S C . Extracorporeal blood purification and acute kidney injury in cardiac surgery [J]. JAMA , 2025 , 333 ( 8 ): 722 - 723 . DOI: 10.1001/jama.2024.26219 http://dx.doi.org/10.1001/jama.2024.26219 .
TOYONAGA Y , ASAYAMA K , MAEHARA Y . Impact of systemic inflammatory response syndrome and surgical Apgar score on post-operative acute kidney injury [J]. Acta Anaesthesiol Scand , 2017 , 61 ( 10 ): 1253 - 1261 . DOI: 10.1111/aas.12965 http://dx.doi.org/10.1111/aas.12965 .
BALONOV K . Intraoperative protective lung ventilation strategies in patients with morbid obesity [J]. Saudi J Anaesth , 2022 , 16 ( 3 ): 327 - 331 . DOI: 10.4103/sja.sja_386_22 http://dx.doi.org/10.4103/sja.sja_386_22 .
KAW R , WONG J , MOKHLESI B . Obesity and obesity hypoventilation, sleep hypoventilation, and postoperative respiratory failure [J]. Anesth Analg , 2021 , 132 ( 5 ): 1265 - 1273 . DOI: 10.1213/ANE.0000000000005352 http://dx.doi.org/10.1213/ANE.0000000000005352 .
MARK A L , SOMERS V K . Obesity, hypoxemia, and hypertension: mechanistic insights and therapeutic implications [J]. Hypertension , 2016 , 68 ( 1 ): 24 - 26 . DOI: 10.1161/HYPERTENSIONAHA.116.07338 http://dx.doi.org/10.1161/HYPERTENSIONAHA.116.07338 .
HODGSON L E , MURPHY P B , HART N . Respiratory management of the obese patient undergoing surgery [J]. J Thorac Dis , 2015 , 7 ( 5 ): 943 - 952 . DOI: 10.3978/j.issn.2072-1439.2015.03.08 http://dx.doi.org/10.3978/j.issn.2072-1439.2015.03.08 .
MAFORT T T , RUFINO R , COSTA C H , et al . Obesity: systemic and pulmonary complications, biochemical abnormalities, and impairment of lung function [J]. Multidiscip Respir Med , 2016 , 11 : 28 . DOI: 10.1186/s40248-016-0066-z http://dx.doi.org/10.1186/s40248-016-0066-z .
DE CASTILHO F M , RIBEIRO A L P , NOBRE V , et al . Heart rate variability as predictor of mortality in sepsis: a systematic review [J]. PLoS One , 2018 , 13 ( 9 ): e0203487 . DOI: 10.1371/journal.pone.0203487 http://dx.doi.org/10.1371/journal.pone.0203487 .
LIAU M Y Q , LIAU J Y J , SELVAKUMAR S V , et al . Heart rate variability in acute pancreatitis: a narrative review [J]. Transl Gastroenterol Hepatol , 2024 , 9 : 68 . DOI: 10.21037/tgh-24-22 http://dx.doi.org/10.21037/tgh-24-22 .
MARGRAF A , LUDWIG N , ZARBOCK A , et al . Systemic inflammatory response syndrome after surgery: mechanisms and protection [J]. Anesth Analg , 2020 , 131 ( 6 ): 1693 - 1707 . DOI: 10.1213/ANE.0000000000005175 http://dx.doi.org/10.1213/ANE.0000000000005175 .
YU S M , BONVENTRE J V . Acute kidney injury and maladaptive tubular repair leading to renal fibrosis [J]. Curr Opin Nephrol Hypertens , 2020 , 29 ( 3 ): 310 - 318 . DOI: 10.1097/MNH.0000000000000605 http://dx.doi.org/10.1097/MNH.0000000000000605 .
陈晓媚 , 马圆媛 , 聂静 , 等 . 急性肾损伤向慢性肾脏病转化中肾小管上皮细胞损伤修复机制的研究进展 [J]. 首都医科大学学报 , 2022 , 43 ( 5 ): 720 - 727 .
CHEN X M , MA Y Y , NIE J , et al . Progress on the injury and repair mechanism of renal tubular epithelial cells in the transition of acute kidney injury to chronic kidney disease [J]. J Cap Med Univ , 2022 , 43 ( 5 ): 720 - 727 .
BONVENTRE J V , YANG L . Cellular pathophysiology of ischemic acute kidney injury [J]. J Clin Invest , 2011 , 121 ( 11 ): 4210 - 4221 . DOI: 10.1172/JCI45161 http://dx.doi.org/10.1172/JCI45161 .
PAIS T , JORGE S , LOPES J A . Acute kidney injury in sepsis [J]. Int J Mol Sci , 2024 , 25 ( 11 ): 5924 . DOI: 10.3390/ijms25115924 http://dx.doi.org/10.3390/ijms25115924 .
HOSTE E A J , BAGSHAW S M , BELLOMO R , et al . Epidemiology of acute kidney injury in critically ill patients: the multinational AKI-EPI study [J]. Intensive Care Med , 2015 , 41 ( 8 ): 1411 - 1423 . DOI: 10.1007/s00134-015-3934-7 http://dx.doi.org/10.1007/s00134-015-3934-7 .
LEE J M , KIM H L , LIM M N , et al . Acute kidney injury as a prognostic marker in severe fever with thrombocytopenia syndrome [J]. Sci Rep , 2024 , 14 ( 1 ): 20651 . DOI: 10.1038/s41598-024-71438-8 http://dx.doi.org/10.1038/s41598-024-71438-8 .
SCHUURMANS J , VAN ROSSEM B T B , RELLUM S R , et al . Hypotension during intensive care stay and mortality and morbidity: a systematic review and meta-analysis [J]. Intensive Care Med , 2024 , 50 ( 4 ): 516 - 525 . DOI: 10.1007/s00134-023-07304-4 http://dx.doi.org/10.1007/s00134-023-07304-4 .
INKER L A , ENEANYA N D , CORESH J , et al . New creatinine- and cystatin C-based equations to estimate GFR without race [J]. N Engl J Med , 2021 , 385 ( 19 ): 1737 - 1749 . DOI: 10.1056/NEJMoa2102953 http://dx.doi.org/10.1056/NEJMoa2102953 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621