Blood pressure is an important physiological parameter to reflect human vital signs.In order to achieve the non-contact dynamic blood pressure acquisition based on ordinary optical camera,a theoretical understanding o...Blood pressure is an important physiological parameter to reflect human vital signs.In order to achieve the non-contact dynamic blood pressure acquisition based on ordinary optical camera,a theoretical understanding of the functional relationship between blood pressure and pulse wave signal conduction time.And through imaging photoelectric plethysmography(IPPG),pulse wave signal conduction time of forehead and hand was obtained with ordinary optical camera.First,the pulse wave conduction time was obtained by recording the video with an ordinary optical camera.Second,real-time blood pressure values were collected.Finally,based on the relationship between blood pressure and pulse wave conduction time,a non-contact blood pressure measurement prediction model was obtained through neural network fitting.So that non-contact blood pressure measurement with optical camera could be completed.The method in this paper has several advantages,such as low requirements on measuring equipment,low cost,and simple operation.It can let people get rid of the discomfort caused by measuring equipment such as cuff and can measure blood pressure at any time.The predicted blood pressure results were compared with an Omron wrist electronic sphygmomanometer.The calculated error of systolic blood pressure is-9.28%~3.16%,and the error of diastolic blood pressure is-9.84~4.35%.展开更多
Failure of an automated blood pressure cuff to deflate when a patient is under general anesthesia can lead to catastrophic consequences if unnoticed for more than three hours [1]. We present this as a hearsay case in ...Failure of an automated blood pressure cuff to deflate when a patient is under general anesthesia can lead to catastrophic consequences if unnoticed for more than three hours [1]. We present this as a hearsay case in which an automated blood pressure cuff of the Spacelabs Ultraview Clinical Workstation monitor (model No. 90385) applied pressure for about five hours resulting in limb thrombosis. In order to analyze this catastrophe, simulation scenarios were tested to elucidate the possible errors and malfunctions that may have led to this injury. We present the analysis of the advantages and validity of the hearsay case report. We also include our proposed criteria that should be required when a hearsay case is considered for publication.展开更多
目的直接动脉血压(arterial blood pressure,ABP)连续监测是侵入式的,传统袖带式的间接血压测量法无法实现连续监测。既往利用光学体积描记术(photoplethysmography,PPG)实现了连续无创血压监测,但其为收缩压和舒张压的离散值,而非ABP...目的直接动脉血压(arterial blood pressure,ABP)连续监测是侵入式的,传统袖带式的间接血压测量法无法实现连续监测。既往利用光学体积描记术(photoplethysmography,PPG)实现了连续无创血压监测,但其为收缩压和舒张压的离散值,而非ABP波的连续值,本研究期望基于卷积神经网络-长短期记忆神经网络(CNN-LSTM)利用PPG信号波重建ABP波信号,实现连续无创血压监测。方法构建CNN-LSTM混合神经网络模型,利用重症监护医学信息集(medical information mart for intensive care,MIMIC)中的PPG与ABP波同步记录信号数据,将PPG信号波经预处理降噪、归一化、滑窗分割后输入该模型,重建与之同步对应的ABP波信号。结果使用窗口长度312的CNN-LSTM神经网络时,重建ABP值与实际ABP值间误差最小,平均绝对误差(mean absolute error,MAE)和均方根误差(root mean square error,RMSE)分别为2.79 mmHg和4.24 mmHg,余弦相似度最大,重建ABP值与实际ABP值一致性和相关性情况良好,符合美国医疗器械促进协会(Association for the Advancement of Medical Instrumentation,AAMI)标准。结论CNN-LSTM混合神经网络可利用PPG信号波重建ABP波信号,实现连续无创血压监测。展开更多
基金The work of this paper is supported by the National Natural Science Foundation of China under Grant No.61572038,the Innovation Project Foundation NCUT.
文摘Blood pressure is an important physiological parameter to reflect human vital signs.In order to achieve the non-contact dynamic blood pressure acquisition based on ordinary optical camera,a theoretical understanding of the functional relationship between blood pressure and pulse wave signal conduction time.And through imaging photoelectric plethysmography(IPPG),pulse wave signal conduction time of forehead and hand was obtained with ordinary optical camera.First,the pulse wave conduction time was obtained by recording the video with an ordinary optical camera.Second,real-time blood pressure values were collected.Finally,based on the relationship between blood pressure and pulse wave conduction time,a non-contact blood pressure measurement prediction model was obtained through neural network fitting.So that non-contact blood pressure measurement with optical camera could be completed.The method in this paper has several advantages,such as low requirements on measuring equipment,low cost,and simple operation.It can let people get rid of the discomfort caused by measuring equipment such as cuff and can measure blood pressure at any time.The predicted blood pressure results were compared with an Omron wrist electronic sphygmomanometer.The calculated error of systolic blood pressure is-9.28%~3.16%,and the error of diastolic blood pressure is-9.84~4.35%.
文摘Failure of an automated blood pressure cuff to deflate when a patient is under general anesthesia can lead to catastrophic consequences if unnoticed for more than three hours [1]. We present this as a hearsay case in which an automated blood pressure cuff of the Spacelabs Ultraview Clinical Workstation monitor (model No. 90385) applied pressure for about five hours resulting in limb thrombosis. In order to analyze this catastrophe, simulation scenarios were tested to elucidate the possible errors and malfunctions that may have led to this injury. We present the analysis of the advantages and validity of the hearsay case report. We also include our proposed criteria that should be required when a hearsay case is considered for publication.
文摘目的直接动脉血压(arterial blood pressure,ABP)连续监测是侵入式的,传统袖带式的间接血压测量法无法实现连续监测。既往利用光学体积描记术(photoplethysmography,PPG)实现了连续无创血压监测,但其为收缩压和舒张压的离散值,而非ABP波的连续值,本研究期望基于卷积神经网络-长短期记忆神经网络(CNN-LSTM)利用PPG信号波重建ABP波信号,实现连续无创血压监测。方法构建CNN-LSTM混合神经网络模型,利用重症监护医学信息集(medical information mart for intensive care,MIMIC)中的PPG与ABP波同步记录信号数据,将PPG信号波经预处理降噪、归一化、滑窗分割后输入该模型,重建与之同步对应的ABP波信号。结果使用窗口长度312的CNN-LSTM神经网络时,重建ABP值与实际ABP值间误差最小,平均绝对误差(mean absolute error,MAE)和均方根误差(root mean square error,RMSE)分别为2.79 mmHg和4.24 mmHg,余弦相似度最大,重建ABP值与实际ABP值一致性和相关性情况良好,符合美国医疗器械促进协会(Association for the Advancement of Medical Instrumentation,AAMI)标准。结论CNN-LSTM混合神经网络可利用PPG信号波重建ABP波信号,实现连续无创血压监测。
