摘要
无效吸气努力(Ineffective Inspiratory Effort during Expiration,IEE)是使用机械通气抢救危重病人过程中最常见的一种人机不同步问题。针对该问题缺乏检测手段的现状,提出基于机械通气波形,采用K最邻近法(K-Nearest Neighbors,KNN)结合动态时间规整(Dynamic time warping,DTW)实现IEE检测。在临床采集的数据集上进行测试发现,基于DTW-KNN的方法得到96.5%的特异性和97.2%的灵敏度,优于传统的基于规则的方法和机器学习方法。研究表明,该方法有望用于临床IEE检测,提示医护人员调整呼吸机参数设置,改善病人与呼吸机的同步性,优化重症呼吸治疗。
Ineffective inspiratory effort during expiration(IEE)is one of the most common types of patient-ventilator asynchrony in treating critical ill patients using mechanical ventilation(MV).To solve the problem of lacking methods to detect IEE,an algorithm based on dynamic time warping(DTW)and K-Nearest Neighbors(KNN)was proposed for IEE detection based on the MV waveforms.It was tested on the dataset collected from clinic.It is found that the proposed method obtained a sensitivity of 97.2%and a specificity of 96.5%,which is superior to the traditional rule-based methods and machine learning methods.The results indicate that the proposed approach is promising to be applied in clinic to detect IEE to prompt the medical staff to adjust the ventilator parameter settings so as to improve the patient-ventilator interaction and optimize the critical respiratory care.
作者
潘清
龚强
陆飞
方路平
葛慧青
Pan Qing;Gong Qiang;Lu Fei;Fang Luping;Ge Huiqing(College of Information Engineering,Zhejiang University of Technology,Hangzhou 310023,Zhejiang,China;Department of Respiratory Care,Sir Run Run Shaw Hospital,School of Medicine,Zhejiang University,Hangzhou 310016,Zhejiang,China)
出处
《计算机应用与软件》
北大核心
2022年第8期331-337,共7页
Computer Applications and Software
基金
浙江省自然科学基金项目(LY19H010005)
浙江省教育厅一般科研项目(Y201636066)。
关键词
机械通气
无效吸气努力
K-最邻近法
动态时间规整
Mechanical ventilation
Ineffective inspiratory effort during expiration
K-nearest neighbor
Dynamic time warping
