摘要
目的探索高海拔暴露前急性高原病(AMS)易感指标与AMS的关系,实现对AMS易感预测。方法进入高原期前,检测314例健康成年人22项生理、心理指标,进入高原后按照国际通用急性高原病判断标准(LLS)进行AMS诊断。利用神经网络强大的容错性,基于选定的易感指标特征,建立了AMS易感预测的LVQ模型。结果模型预测将研究对象判断为不出现AMS的灵敏度较高(95.00%),平均预测正确率达到72.22%,预测结果可信度较好。结论该预测模型的建立为进入高海拔人群筛选提供了可用的方法,能够初步实现对AMS易感人群的筛选。
Objective The purpose of this study was to examine the relationship between acute mountain sickness （AMS） and AMS susceptibility indices before ascent to high altitude and to evaluate their predictive value for AMS. Methods A total of 314 healthy male a- dults were voluntarily enrolled. Their 22 physiological and mental indices of AMS susceptibility were obtained before exposure high altitude. The diagnoses of AMS were based on the Lake Louise score （LLS）, an international standard scoring system for AMS. According to the char- acteristics of selected AMS susceptibility indices and the strong fault tolerance of neural network theory, the learning vector quantization （LVQ） neural network method was adopted to build the prediction model of susceptibility to AMS. Results The results showed the sensitiv- ity of the LVQ model which distinguishes subjects with no-AMS reached 95.00% ,the average correct-prediction precision ultimately reached 72.22%. The result of prediction is believable. Conclusion The builded LVQ model provide a scientific method for screening crowd who quickly ascend to high altitude, and also can lead to an effective preliminary screening of susceptibility to AMS.
出处
《局解手术学杂志》
2015年第6期627-629,共3页
Journal of Regional Anatomy and Operative Surgery
基金
重庆市社会科学规划培育项目(2013PYGL01)
全军医学科研计划面上项目(CWS12J091)
关键词
急性高原病
易感性
LVQ神经网络模型
预测
acute mountain sickness
susceptibility
LVQ neural-network model
prediction
