[1]彭福来,水圆圆,张宁玲,等.基于支持向量回归的血红蛋白浓度无创检测模型[J].中国医学物理学杂志,2024,41(5):594-599.[doi:DOI:10.3969/j.issn.1005-202X.2024.05.010]
 PENG Fulai,SHUI Yuanyuan,ZHANG Ningling,et al.Non-invasive detection model for hemoglobin concentration based on support vector regression[J].Chinese Journal of Medical Physics,2024,41(5):594-599.[doi:DOI:10.3969/j.issn.1005-202X.2024.05.010]
点击复制

基于支持向量回归的血红蛋白浓度无创检测模型()
分享到:

《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]

卷:
41卷
期数:
2024年第5期
页码:
594-599
栏目:
医学信号处理与医学仪器
出版日期:
2024-05-23

文章信息/Info

Title:
Non-invasive detection model for hemoglobin concentration based on support vector regression
文章编号:
1005-202X(2024)05-0594-06
作者:
彭福来1水圆圆2张宁玲1陈财1王卫东3
1.山东中科先进技术有限公司, 山东 济南 250000; 2.山东大学数学学院, 山东 济南 250100; 3.中国人民解放军总医院医疗器械研发与临床评价中心, 北京 100853
Author(s):
PENG Fulai1 SHUI Yuanyuan2 ZHANG Ningling1 CHEN Cai1 WANG Weidong3
1. Shandong Zhongke Advanced Technology Co., Ltd., Jinan 250000, China 2. School of Mathematics, Shandong University, Jinan 250100, China 3. Medical Device R&D and Clinical Evaluation Center of Chinese Peoples Liberation Army General Hospital, Beijing 100853, China
关键词:
血红蛋白浓度无创检测光电容积脉搏波描记法支持向量回归
Keywords:
Keywords: hemoglobin concentration non-invasive detection photoplethysmography support vector regression
分类号:
R318;R331
DOI:
DOI:10.3969/j.issn.1005-202X.2024.05.010
文献标志码:
A
摘要:
为实现血红蛋白浓度的无创检测,设计基于支持向量回归的血红蛋白浓度检测方法。首先,基于Beer-Lambert定律建立血红蛋白无创检测数学模型;然后,对采集的光电容积脉搏波描记法(PPG)信号进行降噪和滤除基线漂移处理后提取出血红蛋白浓度特征信息,并使用递归特征消除算法对提取的特征信息进行选择,以去除冗余特征;最后,将筛选出的29个特征信息作为回归模型的输入特征,并采用支持向量回归算法构建血红蛋白预测回归模型。通过对249例临床数据进行试验验证(其中199例作为训练数据集,50例作为测试数据集),得出预测值与参考值的均方根误差为1.83 g/dL,相关系数为0.75(P<0.01),试验结果表明本文方法与传统有创检测方法具有较强的一致性。
Abstract:
Abstract: To achieve non-invasive detection of hemoglobin concentration, a hemoglobin concentration detection method based on support vector regression is designed. A mathematical model for non-invasive hemoglobin detection is established based on the Beer-Lambert law. After removing the noise and baseline drift from the collected photoplethysmography signals, hemoglobin concentration information is extracted, and a recursive feature elimination algorithm is used to select the extracted information and eliminate redundant features. Finally, 29 key features are identified as input to construct a hemoglobin prediction model using support vector regression algorithm. Experimental validation is conducted on 249 clinical data samples (199 cases in training dataset and 50 in test dataset), resulting in a root mean square error of 1.83 g/dL between predicted values and references, with a correlation coefficient of 0.75 (P<0.01), demonstrating the high consistency of the proposed method and traditional invasive detection methods.

相似文献/References:

[1]冯驰,陈文建,付威威,等.基于AFE4403模拟前端新生儿经皮黄疸测量模块设计[J].中国医学物理学杂志,2016,33(10):1069.[doi:10.3969/j.issn.1005-202X.2016.10.018]
 [J].Chinese Journal of Medical Physics,2016,33(5):1069.[doi:10.3969/j.issn.1005-202X.2016.10.018]
[2]董放. 基于冠脉造影图像的无创血流储备分数检测[J].中国医学物理学杂志,2017,34(3):251.[doi:10.3969/j.issn.1005-202X.2017.03.007]
 [J].Chinese Journal of Medical Physics,2017,34(5):251.[doi:10.3969/j.issn.1005-202X.2017.03.007]

备注/Memo

备注/Memo:
【收稿日期】2023-12-11 【基金项目】山东省自然科学基金(ZR2020QF024,ZR2021ZD40) 【作者简介】彭福来,博士,高级工程师,研究方向:医学信号处理与分析,E-mail: pengfulai1112@163.com 【通信作者】王卫东,博士,研究员,研究方向:医学电子与仪器,E-mail: wangwd301@126.com
更新日期/Last Update: 2024-05-24