急性高原病风险预测模型的系统评价

职业与健康 ›› 2025, Vol. 41 ›› Issue (18): 2564-2570.

急性高原病风险预测模型的系统评价

商昳婧^1a,2, 杨孝光^1a, 路强^1b, 裴家兴^1a,2, 周鹏飞^1c, 李运明^1a,2

1.西部战区总医院a医疗保障中心医学信息数据室,b医疗保障中心信息科,c卫生经济科,四川成都 610083;
2.西南医科大学公共卫生学院,四川泸州 646000

收稿日期:2025-01-05 修回日期:2025-01-20 出版日期:2025-09-15 发布日期:2025-12-13
通信作者: 李运明,副主任技师,E-mail：lee3082@sina.com
作者简介:商昳婧,女,在读硕士研究生,研究方向为流行病与卫生统计学。
基金资助:
四川省中医药管理局中医药科研专项（25MSZX477, 25MSZX495）

Risk prediction models for acute mountain sickness：a systematic review

SHANG Yijing^1a,2, YANG Xiaoguang^1a, LU Qiang^1b, PEI Jiaxing^1a,2, ZHOU Pengfei^1c, LI Yunming^1a,2

1. a Office of Medical Information and Data Medical Support Center,b Department of Information,Medical Support Center,c Department of Health Economics,General Hospital of Western Theater Command of PLA,Chengdu,Sichuan 610083,China;
2. School of Public Health,Southwest Medical University,Luzhou,Sichuan 646000,China

Received:2025-01-05 Revised:2025-01-20 Online:2025-09-15 Published:2025-12-13
Contact: LI Yunming,Deputy chief technician,E-mail：lee3082@sina.com

摘要/Abstract

摘要： 目的系统评价急性高原病风险预测模型,了解模型的偏倚风险和适用范围。方法检索中国知网、维普、万方、Web of Science、Ovid MEDLINE、PubMed、Embase数据库,收集急性高原病风险预测模型相关研究,检索时限均为建库至2024年3月;由2位研究者独立筛选文献并提取数据,采用预测模型偏倚风险评估工具（prediction model risk of bias assessment tool,PROBAST）评价模型的偏倚风险和适用性。结果共纳入20篇文献,包括27个急性高原病风险预测模型。纳入研究的预测模型AUC为0.593~0.986,研究的样本量为32~4 369例,预测因子数量为1~22个。61.9%的研究仅建立模型但未进行验证,90.5%的研究未进行外部验证,所报告的模型灵敏度范围为0.611~0.998。结论急性高原病风险预测模型预测性能整体较差,且均存在高偏倚风险,半数研究存在适用性不足的风险。

关键词: 急性高原病, 预测模型, 系统评价, 预测性能, 预测模型偏倚风险评估工具

Abstract: Objective To systematically evaluate the risk prediction model of acute altitude sickness,understand the bias risk of and application scope of the model. Methods The CNKI,VIP,WanFang,Web of Science,Ovid MEDLINE,PubMed,and Embase databases were electronically searched to collect studies related to the risk prediction model of acute mountain sickness,and the time frame of the search was from the establishment of the database to March 2024. Two researchers independently screened literature and extracted data,and the risk of bias assessment tool for prediction models（ PROBAST） was used to evaluate the risk of bias and applicability of the models. Results A total of 20 papers were included,including 27 prediction models for acute altitude illness. The AUCs of the predictive models included in the studies were 0.593-0.986,the sample sizes of the studies were 32-4 369 cases,and the number of predictors was 1-22.61.9% of the studies were modeled only without internal validation,and 90.5% of the studies were not externally validated. The reported model sensitivity ranged from 0.611 to 0.998. Conclusion The overall predictive performance of the acute altitude sickness risk prediction model is poor,and all included studies have a high risk of bias,and half of the studies have a high risk of applicability.

Key words: Acute mountain sickness, Prediction model, Systematic review, Prediction performance, Prediction model risk of bias assessment tool

中图分类号:

R181.2

商昳婧, 杨孝光, 路强, 裴家兴, 周鹏飞, 李运明. 急性高原病风险预测模型的系统评价. [J]职业与健康, 2025, 41(18): 2564-2570.

SHANG Yijing, YANG Xiaoguang, LU Qiang, PEI Jiaxing, ZHOU Pengfei, LI Yunming. Risk prediction models for acute mountain sickness：a systematic review. [J]OCCUPATION AND HEALTH, 2025, 41(18): 2564-2570.

参考文献

[1] 曹煜隆,单娇,龚志忠,等.个体预后与诊断预测模型研究报告规范——TRIPOD声明解读[J].中国循证医学杂志,2020,20(4):492-496.
[2] 孙新甫,朱世楣,王云.关于高原病的命名、临床分型和诊断标准的建议[J].高原医学杂志,1993,3(2):4-7.
[3] 马捷,李峰,刘晶,等.高原反应的研究初探[J].中国医学工程,2012,20(12):183-184.
[4] 邹子扬,刘俊双,耿文娟,等.玉树抗震救灾官兵快速进驻高原急性高原反应发生情况调查[J].解放军医药杂志,2011,23(5):61-65.
[5] 魏婧韬. 高寒低氧环境下旅游人群急性高原病发病率调查[J].社区医学杂志,2017,15(7):22-24.
[6] 张晓馨,丁魁,孟新珍,等.首次急进高原士兵急性高原反应发生率及与训练倦怠的相关分析[J].职业与健康,2017,33(19):2670-2673.
[7] 张蕊,郑黎强,潘国伟.疾病发病风险预测模型的应用与建立[J].中国卫生统计,2015,32(4):724-726.
[8] MOONS K G,DE GROOT J A,BOUWMEESTER W,et al.Critical appraisal and data extraction for systematic reviews of prediction modelling studies:The CHARMS checklist[J].PLoS Med,2014,11(10):e1001744.
[9] MOONS K,WOLFF R F,RILEY R D,et al.PROBAST:A tool to assess risk of bias and applicability of prediction model studies:Explanation and elaboration[J].Ann Intern Med,2019,170(1):W1-W33.
[10] WOLFF R F,MOONS K,RILEY R D,et al.PROBAST:A tool to assess the risk of bias and applicability of prediction model studies[J].Ann Intern Med,2019,170(1):51-58.
[11] 陈香萍,张奕,庄一渝,等.PROBAST:诊断或预后多因素预测模型研究偏倚风险的评估工具[J].中国循证医学杂志,2020,20(6):737-744.
[12] ROACH R C,HACKETT P H,OELZ O,et al.The 2018 lake louise acute mountain sickness score[J].High Alt Med Biol,2018,19(1):4-6.
[13] 中华医学会.我国高原病命名、分型及诊断标准[J].高原医学杂志,1996(1):2-4.
[14] SAMPSON J B,KOBRICK J L.The environmental symptoms questionnaire:Revisions and new filed data[J].Aviat Space Environ Med,1980,51(9 Pt 1):872-877.
[15] HACKETT P H,RENNIE D,LEVINE H D.The incidence,importance,and prophylaxis of acute mountain sickness[J].Lancet,1976,2(7996):1149-1155.
[16] 郑然. 急性高原病易感人群预测模型、方法研究[D].重庆:第三军医大学,2003.
[17] 黄庆愿,高钰琪,刘福玉,等.急性高原反应相关因素的多元线性回归分析[J].第三军医大学学报,2006,28(12):1269-1272.
[18] 游海燕,高钰琪,黄朝晖.急性高原病易感性LVQ神经网络模型预测研究[J].局解手术学杂志,2015,24(6):627-629.
[19] LI X,TAO F,PEI T,et al.Population level determinants of acute mountain sickness among young men:A retrospective study[J].BMC Public Health,2011,11:740.
[20] BEIDLEMAN B A,TIGHIOUART H,SCHMID C H,et al.Predictive models of acute mountain sickness after rapid ascent to various altitudes[J].Med Sci Sports Exerc,2013,45(4):792-800.
[21] YOU H,LI X,PEI T,et al.Predictive value of basal exhaled nitric oxide and carbon monoxide for acute mountain sickness[J].Wilderness Environ Med,2012,23(4):316-324.
[22] CANOUI-POITRINE F,VEERABUDUN K,LARMIGNAT P,et al.Risk prediction score for severe high altitude illness:A cohort study[J].PLoS One,2014,9(7):e100642.
[23] 冯丽. 重型急性高原病影响因素探索与预测模型构建[D].武汉:华中科技大学,2015.
[24] LI X,TAO F,YOU H,et al.Factors associated with acute mountain sickness in young Chinese men on entering highland areas[J].Asia Pac J Public Health,2015,27(2):NP116-NP131.
[25] BAO L.A signature of circulating microRNAs predicts the susceptibility of acute mountain sickness[J].Front Physiol,2017,8:55.
[26] 方露. 急性高原反应影响因素探讨和分类模型初建[D].北京:北京协和医学院,2018.
[27] BEIDLEMAN B A,FULCO C S,CYMERMAN A,et al.New metric of hypoxic dose predicts altitude acclimatization status following various ascent profiles[J].Physiol Rep,2019,7(20):e14263.
[28] LI ZB,LIU CW,GUO J,et al.Early warning of acute altitude sickness by physiological variables and noninvasive cardiovascular indicators[J].Chin Med Sci J,2020,35(1):13-19.
[29] 肖军,李小薇,高瞻,等.基于径向基函数神经网络的高原适应人群预测模型构建及应用研究[J].临床输血与检验,2021,23(5):574-577.
[30] COBB A B,LEVETT D Z H,MITCHELL K,et al.Physiological responses during ascent to high altitude and the incidence of acute mountain sickness[J].Physiol Rep,2021,9(7):e14809.
[31] WEI C Y,CHEN P N,LIN S S,et al.Using machine learning to determine the correlation between physiological and environmental parameters and the induction of acute mountain sickness[J].BMC Bioinformatics,2022,22(Suppl 5):628.
[32] YANG M,WU Y,YANG X B,et al.Establishing a prediction model of severe acute mountain sickness using machine learning of support vector machine recursive feature elimination[J].Sci Rep,2023,13(1):4633.
[33] SUONA Y,GESANG L,DANZENG Z,et al.Predictive model for estimating the risk of high-altitude pulmonary edema:A single-centre retrospective outcome-reporting study[J].BMJ Open,2023,13(11):e074161.
[34] ZHAO Y,ZOU H,FAN W,et al.Patterns of structural changes in the fundus measured by optical coherence tomography angiography as potential markers of acute mountain sickness[J].Transl Vis Sci Technol,2023,12(12):15.
[35] WANG L,XIAO R,CHEN J,et al.A slow feature based LSTM network for susceptibility assessment of acute mountain sickness with heterogeneous data[J].Biomed. Signal Process Control,2023,80:104355.
[36] 吴薇,秦晓洪,曾宪容.急性高原病的诊断研究进展[J].西北国防医学杂志,2018,39(7):488-491.
[37] 陈姝宇,刑年路,周英凤.妊娠期糖尿病风险预测模型的系统评价[J].中国循证医学杂志,2023,23(11):1253-1258.
[38] 谢永宏. 急性高山病及高原脑水肿研究进展[J].高原医学杂志,2004(1):61-64.
[39] 王岩飞. 急性高原病各型之间的相互关系[J].西藏医药杂志,2008, 29(3):1-2.