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*

doi:10.3969/j.issn.1671-2587.2021.05.007

临床输血与检验 ›› 2021, Vol. 23 ›› Issue (5): 574-577.DOI: 10.3969/j.issn.1671-2587.2021.05.007

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^*

肖军, 李小薇, 高瞻, 孟方园, 卢江敏, 候杜娟, 李翠莹

100142 北京空军特色医学中心

收稿日期:2021-05-25 发布日期:2021-10-20
通讯作者: 李翠莹,女,主任技师,硕士研究生导师,主要从事临床输血及高原输血研究,（E-mail）licuiying2013@qq.com。
作者简介:肖军（1987-）,男,主管技师,博士,主要从事临床输血及高原输血研究,（E-mail） ammsxj@126.com。
基金资助:
*本课题由全军后勤科研重大专项子项（No.AWS13J004）; 国家自然科学基金（No.81971778）; 空军特色医学中心助推计划（No.2020KTC19）资助

A Prediction Model for Altitude Adaptation Population on Plateau Based on Radial Basis Function Neural Network

XIAO Jun, LI Xiao-wei, GAO Zhan, et al

Department of Blood Transfusion, Air force Medical Center, PLA, Beijing 100142

Received:2021-05-25 Published:2021-10-20

摘要/Abstract

摘要： 目的建立基于径向基函数神经网络的急性高原病（acute mountain sickness,AMS）预测模型。方法在平原对需要急进高原的98名人员测定血红蛋白,P₅₀,身体质量指数,EPAS1基因和EGLN1基因的单核苷酸多态性（single nucleotide polymorphism, SNP）位点。急进高原后,按照急性高原反应（AMS）诊断标准进行判断是否发生AMS,然后基于径向基函数神经网络建立AMS疾病诊断预测模型。结果神经网络学习训练结果正确百分比为88.0%,用所构建的神经网络进行预测,其结果与实际诊断结果的符合率为88.9%。对预测模型诊断能力进行检验,其ROC曲线下面积为0.917,具有较好的诊断能力。结论基于径向基函数神经网络的预测模型可为早期AMS诊断提供一种有效的方法。

关键词: 急性高原病, 神经网络, 预测模型

Abstract: Objective To establish prediction model of acute mountain sickness (AMS) based on radial basis function (RBF) neural network. Methods The hemoglobin, P₅₀, body mass index (BMI), single nucleotide polymorphism (SNP) of the EPAS1 and EGLN1 genes were detected in 98 people who urgent need to enter the plateau. According to the diagnostic criteria, AMS was judged after rapid ascent to high altitude. The diagnostic prediction model was established using RBF neural network. Results The correct percentage of the neural network learning training was 88.0%. The constructed neural network was used for prediction, and the coincidence rate between the results and the actual diagnosis results was 88.9%. The diagnostic ability of the prediction model was tested, and the area under the receiver operating characteristic (ROC) curve was 0.917, suggesting a good diagnostic ability. Conclusion The prediction model based on RBF neural network can provide an effective method for early diagnosis of AMS.

Key words: Acute mountain sickness, Neural network, Prediction model

中图分类号:

TP183

肖军, 李小薇, 高瞻, 孟方园, 卢江敏, 候杜娟, 李翠莹. 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.

XIAO Jun, LI Xiao-wei, GAO Zhan, et al. A Prediction Model for Altitude Adaptation Population on Plateau Based on Radial Basis Function Neural Network[J]. JOURNAL OF CLINICAL TRANSFUSION AND LABORATORY MEDICINE, 2021, 23(5): 574-577.

参考文献

[1] 高钰琪. 高原军事医学[M].重庆:重庆出版社.2005.
[2] 李相俊,李平,史连胜,等.健康青年男性进驻更高海拔地区急性高原病分析[J].西北国防医学杂志,2018,39(6): 360-364.
[3] 叶文. 高原寒区作战卫勤保障应把握的几个问题[J].西南国防医药,2001,11(6):438-439.
[4] LI C Y,LI X W,XIAO J,et al.Genetic changes in the EPAS1 gene between Tibetan and Han ethnic groups and adaptation to the plateau hypoxic environment[J].PeerJ,2019,7:e7943.
[5] 邹慧琴,李硕,陶欧,等.RBF神经网络在中医药领域中的应用及其在SPSS 17.0软件中的实现[J].中华中医药学刊,2015,33(2):336-338.
[6] 方露,徐成丽.超重及肥胖与急性高原反应关系的meta分析[J].医学研究杂志,2018,47(4):28-31.
[7] 周其全,高钰琪,黄庆愿,等.肺功能测定对急性高原反应易感者预测价值的初步探讨[J].西北国防医学杂志,2004,25(1):13-15.
[8] HUANG H H,TSENG C Y,FAN J S,et al.Alternations of heart rate variability at lower altitude in the predication of trekkers with acute mountain sickness at high altitude[J].Clin J Sport Med,2010,20(1):58-63.
[9] 周波,周其全,杨景义.血液酸碱度对急性高原病易感人群预测价值的初步探讨[J].华西医学,2006,21(2):284-285.
[10] KOEHLE M S,GUENETTE J A,WARBURTON D E R.Oximetry,heart rate variability,and the diagnosis of mild-to-moderate acute mountain sickness[J].Eur J Emerg Med,2010,17(2):119-122.
[11] 刘晓东,祁玉曙,周波.急进高原人群肾上腺皮质机能状态与急性高原病的相关性探讨[J].西南国防医药,2010,20(2):141-143.
[12] 黄庆愿,高钰琪,刘福玉,等.低氧反应和屏气反应在急性高原反应预测中的作用[J].中国应用生理学杂志,2004,20(2):142-145.
[13] 曾颖,覃军,高旭滨,等.EPAS1基因多态性与急性高原病关联性研究[J].军事医学,2013,37(5):332-335.
[14] BURTSCHER M,SZUBSKI C,FAULHABER M.Prediction of the susceptibility to AMS in simulated altitude[J].Sleep Breath,2008,12(2):103-108.
[15] VANN R D,POLLOCK N W,PIEPER C F,et al.Statistical models of acute mountain sickness[J].High Alt Med Biol,2005,6(1):32-42.
[16] 何晓,冯丽,杜玉开.914例重型急性高原病危险因素分析[J].中国社会医学杂志,2019,36(2):142-145.

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^*

A Prediction Model for Altitude Adaptation Population on Plateau Based on Radial Basis Function Neural Network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价

关于本刊

作者中心

在线期刊

访问统计

联系我们