检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:金钇圳 刘博 毕涛 苗戎利 冯树理 JIN Yi-zhen;LIU Bo;BI Tao(Department of radiotherapy,Beijing Shijitan Hospital,Capital Medical University,Beijing 100038,China;不详)
机构地区:[1]首都医科大学附属北京世纪坛医院放射治疗科,北京100038 [2]首都医科大学附属北京世纪坛医院医学工程处,北京100038 [3]北京大学国际医院医学设备科,北京102206
出 处:《中国医学装备》2022年第5期39-43,共5页China Medical Equipment
基 金:北京市科技计划(Z191100000215022)“医用注射泵和输液泵计量校准方法研究与价值分析”。
摘 要:目的:研究基于线性拟合算法的医用输液泵计量校准方法,以降低医用输液泵计量校准误差。方法:根据输液泵输液多种参数有序数据点,采用线性拟合算法,研究数据点所处位置,判断医用输液泵计量是否为失配状态;当医用输液泵计量处于失配状态时,确定医用输液泵计量数学模型,分析数学模型中患者体重、药剂计量、输液瓶容量等变量的不确定度;依据医用输液泵失配和不确定度计算结果,利用反向传播(BP)神经网络的反向传播特点,建立医用输液泵计量校准模型,通过神经网络的正向传播和BP并修正模型权值,校准医用输液泵计量。结果:对比结果表明,本研究方法较甲醇气体检测仪校准方法和药品强光稳定性试验箱校准方法相比,药液滴数不确定度分别减少0.094和0.079;输液稳定性不确定度分别减少0.088和0.054;输液泵参数不确定度分别减少0.118和0.069。结论:基于线性拟合算法的医用输液泵计量校准方法与甲醇气体检测仪校准方法和药品强光稳定性试验箱校准方法相比,其输液泵计量校准误差较小,可满足医用输液泵计量校准需求。Objective:To reduce the metrological calibration error of medical infusion pump through proposed metrological calibration method of medical infusion pump based on linear fitting algorithm.Methods:According to the ordered data points of various infusion parameters of infusion pump,the linear fitting algorithm was adopted to study the position of the data points,so as to judge whether the metering of medical infusion pump was in mismatch state.When the metering of medical infusion pump was in the mismatch state,the mathematical model of the metering of medical infusion pump was determined,and the uncertainties of a series of variables included weight of patients,medicament metering,volume of infusion bottle of this mathematical model were analyzed.Depended on the computed results of mismatch and uncertainty of medical infusion pump,the characteristics of back propagation(BP)of BP neural network were used to establish the metrological calibration model of medical infusion pump.And then,the metering of medical infusion pump was calibrated through the forward-propagation and BP of neural network,and the modification of the weight of the model.Result:Compared with the calibration method of methanol gas detector and the calibration method of test chamber of hard light stability of drug,the uncertainty of drop number of medicine liquid of this research was 0.094 and 0.079 smaller than those of them,respectively,and the uncertainty of infusion stability of this research was 0.088 and 0.054 smaller than those of them,respectively.And the uncertainty of infusion pump parameters of this research was 0.118 and 0.069 smaller than those of them,respectively.Conclusion:Compared with the calibration method of methanol gas detector and that of test chamber of hard light stability,the calibration error of the metering of infusion pump of this research method is smaller,which can meet the metrological calibration requirements of medical infusion pump.
关 键 词:线性拟合算法 输液泵 计量校准 神经网络 甲醇气体检测仪
分 类 号:R197.39[医药卫生—卫生事业管理]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:3.145.52.101