WO2020114190A1 - 血氧饱和度测量置信度的递推方法、系统及存储介质 - Google Patents
血氧饱和度测量置信度的递推方法、系统及存储介质 Download PDFInfo
- Publication number
- WO2020114190A1 WO2020114190A1 PCT/CN2019/116480 CN2019116480W WO2020114190A1 WO 2020114190 A1 WO2020114190 A1 WO 2020114190A1 CN 2019116480 W CN2019116480 W CN 2019116480W WO 2020114190 A1 WO2020114190 A1 WO 2020114190A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- blood oxygen
- oxygen saturation
- linear regression
- saturation measurement
- confidence
- Prior art date
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7221—Determining signal validity, reliability or quality
Definitions
- the invention relates to the technical field of biomedical signal processing, in particular to a recursive method, system and storage medium for blood oxygen saturation measurement confidence.
- HbO2 oxyhemoglobin
- Oxygen is released through blood to capillaries.
- Sufficient oxygen is the material basis to realize the metabolism of human tissue cells and maintain life activities.
- Blood oxygen saturation is an important physiological parameter that reflects the oxygen content in the blood, and it has a direct relationship with the respiratory system, circulatory system and cardiopulmonary function. At present, blood oxygen saturation is widely used in intensive care, home health care and high-risk occupations such as firefighters, pilots, etc. physical examination.
- the detection methods of blood oxygen saturation can be divided into two types: invasive detection and non-invasive detection.
- the invasive blood oxygen saturation test mainly uses the Van Slyke pressure test method and the oxygen electrode method.
- the main method of noninvasive detection is photoplethysmography (PPG).
- PPG photoplethysmography
- the blood volume of the blood vessel changes with the diastole and contraction of the heart, resulting in different absorption rates of light, and the intensity of the reflected or transmitted light also changes in a pulsating cycle.
- the pulse wave oximeter uses photoelectric volume pulse wave tracing to record the intensity of the reflected or transmitted light of red light at 660 nm and infrared light at 940 nm, and then calculate the hemorrhagic oxygen saturation according to Lambert-Beer law.
- the accurate calculation of the characteristic value R of the pulse blood oxygen signal is the key to the noninvasive detection of blood oxygen saturation based on the photoelectric volume pulse wave tracing method.
- the traditional R value extraction method needs to decompose the pulse wave into two components: DC component, which reflects the absorption of light by HbO2 and Hb in the blood, and DC component reflects the non-blood tissues such as muscle, bone, fat, and water in the fingertips. Equal absorption of light.
- the calculation of the AC component usually uses the peak-valley method, that is, the difference between the peak value and the valley value within a pulse cycle is approximated to be the amplitude of the AC component. In the process of measurement and AC/DC decomposition, the interference and random noise introduced and generated will affect the accuracy of the R value calculated by the peak-to-valley method.
- an object of the present invention is to provide a recursive method, system and storage medium for blood oxygen saturation measurement confidence with high reliability.
- the recursive method of blood oxygen saturation measurement confidence includes the following steps:
- the linear regression model is updated by a recursive algorithm, and the step of performing the confidence of obtaining the blood oxygen saturation measurement result according to the linear regression model is returned.
- step of constructing a linear regression model according to the initial configuration result includes the following steps:
- step of updating the linear regression model through a recursive algorithm according to the update results of the data points includes the following steps:
- the confidence of the blood oxygen saturation measurement result is updated.
- the pulse blood oxygen signal characteristic value is generated.
- Recursion system for blood oxygen saturation measurement confidence including:
- Initialization module used for initial configuration of the number of data points
- Construction module used to construct linear regression model according to the initial configuration results
- the acquisition module is used to obtain the confidence of the blood oxygen saturation measurement result according to the linear regression model
- the judgment module is used to judge whether the confidence level of the blood oxygen saturation measurement result meets the threshold requirement, and if it is, the confidence level of the blood oxygen saturation measurement result is output; otherwise, the next step is performed until the blood oxygen saturation measurement result The confidence level meets the threshold requirements;
- Update module used to update the number of data points
- the recursion module is used to update the linear regression model through the recursive algorithm according to the update results of the data points, and returns to the execution acquisition module.
- the building module includes:
- the first calculation unit is used to calculate intermediate parameters according to the initial configuration result
- the second calculation unit is used to calculate the fitting coefficient of the linear regression equation according to the intermediate parameters to obtain the linear regression equation
- the third calculation unit is used to calculate the sum of squared deviations and the sum of squared residuals according to the linear regression equation
- the fourth calculation unit is used to calculate the confidence of the blood oxygen saturation measurement result based on the sum of squared deviations from the total deviation and the sum of squared residuals.
- the recursion module includes:
- the first update unit is used to update the intermediate parameters according to the update results of the data points
- the second updating unit is used to update the linear regression equation according to the updated intermediate parameters
- the third updating unit is used to update the sum of squared total deviations and the sum of squared residuals according to the updated linear regression equation
- the confidence of the blood oxygen saturation measurement result is updated.
- the generating module is used to generate the characteristic value of the pulse blood oxygen signal according to the linear regression model.
- Recursion system for blood oxygen saturation measurement confidence including:
- At least one processor At least one processor
- At least one memory for storing at least one program
- the at least one processor When the at least one program is executed by the at least one processor, the at least one processor implements the recursive method of the blood oxygen saturation measurement confidence level.
- the beneficial effects of the present invention are: based on a linear regression model, the present invention updates the linear regression model through a recursive algorithm, and finally obtains the confidence level of the blood oxygen saturation measurement result, thereby achieving the reliability evaluation of the measurement value and avoiding movement
- the conditions of missed detection and false detection caused by interference factors such as artifacts and noise have improved the reliability of the blood oxygen saturation measurement results and are more scientific.
- FIG. 1 is a flowchart of steps in an embodiment of the present invention.
- step numbers in the embodiments of the present invention are set for the convenience of explanation and description, and the order between the steps is not limited, and the execution order of the steps in the embodiments can be performed according to the understanding of those skilled in the art Adaptive adjustment.
- an embodiment of the present invention provides a recursive method for measuring blood oxygen saturation measurement confidence, including the following steps:
- step S2 includes the following steps:
- the sum of s n, 5 represents the sum of squares of y n ;
- the above statistics are essentially the first and second moments of the data, reflecting the overall information in the sample.
- c n,11 , c n,12 , c n,21 and c n,22 represent intermediate parameters in the recursive algorithm implementation process.
- b n,2 c n,21 s n,2 +c n,22 s n,4 .
- the characteristic value R of the pulse blood oxygen signal is the parameter b n,2 .
- b 1 and b 2 are the undetermined parameters of the regression equation; b n,1 and b n,2 are the calculated b 1 and b 2 when n data points, and the pulse blood oxygen signal characteristic value R is the parameter b n, 2 .
- this embodiment calculates the sum of squared deviations
- step S7 it is determined whether the confidence coefficient in step S3 reaches a preset threshold, and if so, step S7 is executed; otherwise, step S5 is returned to for the next recursive calculation.
- n n+1.
- the linear regression model is updated through a recursive algorithm
- step S6 includes the following steps:
- the characteristic value R is updated to the parameter b n+1,2 .
- step S64 Update the confidence of the blood oxygen saturation measurement result according to the updated total squared mean deviation and the residual sum of squares; if the confidence at this time does not meet the threshold, return to step S5 to enter the next step A recursive calculation process.
- the method further includes the following steps:
- step S4 when it is determined in step S4 that the confidence coefficient reaches a preset threshold, the pulse blood oxygen signal characteristic value R is output.
- an embodiment of the present invention further provides a recursion system for measuring blood oxygen saturation measurement confidence, including:
- Initialization module used for initial configuration of the number of data points
- Construction module used to construct linear regression model according to the initial configuration results
- the acquisition module is used to obtain the confidence of the blood oxygen saturation measurement result according to the linear regression model
- the judgment module is used to judge whether the confidence level of the blood oxygen saturation measurement result meets the threshold requirement, and if it is, the confidence level of the blood oxygen saturation measurement result is output; otherwise, the next step is performed until the blood oxygen saturation measurement result The confidence level meets the threshold requirements;
- Update module used to update the number of data points
- the recursion module is used to update the linear regression model through the recursive algorithm according to the update results of the data points, and returns to the execution acquisition module.
- the building module includes:
- the first calculation unit is used to calculate intermediate parameters according to the initial configuration result
- the second calculation unit is used to calculate the fitting coefficient of the linear regression equation according to the intermediate parameters to obtain the linear regression equation
- the third calculation unit is used to calculate the sum of squared deviations and the sum of squared residuals according to the linear regression equation
- the fourth calculation unit is used to calculate the confidence of the blood oxygen saturation measurement result based on the sum of squared deviations from the total deviation and the sum of squared residuals.
- the recursion module includes:
- the first update unit is used to update the intermediate parameters according to the update results of the data points
- the second updating unit is used to update the linear regression equation according to the updated intermediate parameters
- the third updating unit is used to update the sum of squared total deviations and the sum of squared residuals according to the updated linear regression equation
- the confidence of the blood oxygen saturation measurement result is updated.
- it further includes:
- the generating module is used to generate the characteristic value of the pulse blood oxygen signal according to the linear regression model.
- An embodiment of the present invention also provides a recursive system for measuring blood oxygen saturation measurement confidence, including:
- At least one processor At least one processor
- At least one memory for storing at least one program
- the at least one processor When the at least one program is executed by the at least one processor, the at least one processor implements the recursive method of the blood oxygen saturation measurement confidence level.
- an embodiment of the present invention further provides a storage medium in which processor-executable instructions are stored, and when executed by the processor, the processor-executable instructions are used to perform the blood oxygen saturation measurement confidence Degree recursion method.
- the present invention designs a set of recursive algorithms for calculating the pulse blood oxygen signal characteristic value R and the confidence coefficient C.
- the algorithm makes full use of the data of all sampling points, but there is no need to store a large amount of original data during operation, only a few statistics are kept as intermediate variables, and the final calculation result is constantly updated accordingly. Therefore, the recursive algorithm of the present invention avoids the waste of hardware resources caused by storing the original data, and also greatly improves the calculation speed. Therefore, by using the recursive algorithm of the present invention, the calculation of the characteristic value and confidence coefficient of the pulse oximetry signal can be efficiently completed in real time, which provides theoretical support for the hardware system to realize fast and efficient pulse oximetry detection.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Optics & Photonics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
一种血氧饱和度测量置信度的递推方法、系统及存储介质，方法包括：对数据点个数进行初始化配置（S1）；根据初始化配置结果，构建线性回归模型（S2）；根据线性回归模型，获取血氧饱和度测量结果的置信度（S3）；判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行下一步骤，直至血氧饱和度测量结果的置信度满足阈值要求（S4）；对数据点个数进行更新（S5）；根据数据点的更新结果，通过递推算法对线性回归模型进行更新，并返回执行根据线性回归模型，获取血氧饱和度测量结果的置信度的步骤（S6）。血氧饱和度测量置信度的递推方法提高了血氧饱和度测量结果的可靠性，更加科学，可广泛应用于生物医学信号处理技术领域。
Description
本发明涉及生物医学信号处理技术领域，尤其是血氧饱和度测量置信度的递推方法、系统及存储介质。
心脏的舒张与收缩驱动血液流经肺部，使氧气与还原血红蛋白(hemoglobin,Hb)结合成为氧合血红蛋白(Oxyhemoglobin,HbO2)，氧通过血液输送到毛细血管后释放。足够的氧气是实现人体组织细胞的新陈代谢，维持生命活动的物质基础。血氧饱和度是一种反映血液中氧气含量的重要生理参数，其与呼吸系统、循环系统及心肺功能有着直接的关系。目前，血氧饱和度广泛应用于重症监护，家庭保健及高危职业如消防员、飞行员等的体征检测。
血氧饱和度的检测方法可分为有创检测和无创检测两种。其中有创的血氧饱和度检测主要使用Van Slyke压检法和氧电极法。无创检测的主要手段是光电容积脉搏波描记法(photoplethysmography,PPG)。血管血容量随心脏舒张和收缩时变化，导致对光线吸收率的不同，反射或透射的光强度也随之呈脉动性周期变化。脉搏波血氧分析仪利用光电容积脉搏波描记法，通过记录波长为660nm红光和940nm红外光的反射或透射光强度，进而根据Lambert-Beer定律推算出血氧饱和度。在实际测量中，准确计算脉搏血氧信号特征值R是基于光电容积脉搏波描记法实现无创检测血氧饱和度的关键。
传统的R值提取方法需要把脉搏波分解成交/直流两种成分，其中交流成分反映血液中HbO2和Hb对光的吸收，直流成分反映了指端中非血液组织如肌肉、骨骼、脂肪和水等对光的吸收。交流成分的计算通常使用峰谷值法，即近似认为一个脉搏周期内峰值和谷值之间的差值为交流成分的幅值。在测量和交直流分解过程中，引入和产生的干扰和随机噪声会影响峰谷值法计算的R值精度，通常需要采用多个周期峰谷值的平均来提高精度，从而影响计算的实时性。有人提出了一种采用线性回归模型的方法来计算R值，该方法充分利用了所有采样点的数据，而非仅仅依赖与脉搏波的峰谷值，提高了计算结果的稳定性。然而，光电检测容易受到外部光照环境的影响以及指端运动伪差造成血液充盈状况及光透射路径的变化。上述因素均会引起测量结果失真，导致漏检和误检的情况。目前，血氧饱和度测试仪缺乏对测量结果的可靠性进行科学分析，如何合理评估测量值的可靠性，是一个业界急需解决的问题。
发明内容
为解决上述技术问题，本发明的目的在于：提供一种可靠性高的血氧饱和度测量置信度的递推方法、系统及存储介质。
本发明一方面所采取的技术方案为：
血氧饱和度测量置信度的递推方法，包括以下步骤：
对数据点个数进行初始化配置；
根据初始化配置结果，构建线性回归模型；
根据线性回归模型，获取血氧饱和度测量结果的置信度；
判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行下一步骤，直至血氧饱和度测量结果的置信度满足阈值要求；
对数据点个数进行更新；
根据数据点的更新结果，通过递推算法对线性回归模型进行更新，并返回执行根据线性回归模型，获取血氧饱和度测量结果的置信度的步骤。
进一步，所述根据初始化配置结果，构建线性回归模型这一步骤，包括以下步骤：
根据初始化配置结果，计算中间参数；
根据中间参数，计算线性回归方程的拟合系数，得到线性回归方程；
根据线性回归方程，计算总离均差平方和以及残差平方和；
根据总离均差平方和以及残差平方和，计算血氧饱和度测量结果的置信度。
进一步，所述根据数据点的更新结果，通过递推算法对线性回归模型进行更新这一步骤，包括以下步骤：
根据数据点的更新结果，对中间参数进行更新；
根据更新后的中间参数，对线性回归方程进行更新；
根据更新后的线性回归方程，对总离均差平方和以及残差平方和进行更新；
根据更新后的总离均差平方和以及残差平方和，对血氧饱和度测量结果的置信度进行更新。
进一步，还包括以下步骤：
根据线性回归模型，生成脉搏血氧信号特征值。
本发明另一方面所采取的技术方案是：
血氧饱和度测量置信度的递推系统，包括：
初始化模块，用于对数据点个数进行初始化配置；
构建模块，用于根据初始化配置结果，构建线性回归模型；
获取模块，用于根据线性回归模型，获取血氧饱和度测量结果的置信度；
判断模块，用于判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行下一步骤，直至血氧饱和度测量结果的置信度满足阈值要求；
更新模块，用于对数据点个数进行更新；
递推模块，用于根据数据点的更新结果，通过递推算法对线性回归模型进行更新，并返回执行获取模块。
进一步，所述构建模块包括：
第一计算单元，用于根据初始化配置结果，计算中间参数；
第二计算单元，用于根据中间参数，计算线性回归方程的拟合系数，得到线性回归方程；
第三计算单元，用于根据线性回归方程，计算总离均差平方和以及残差平方和；
第四计算单元，用于根据总离均差平方和以及残差平方和，计算血氧饱和度测量结果的置信度。
进一步，所述递推模块包括：
第一更新单元，用于根据数据点的更新结果，对中间参数进行更新；
第二更新单元，用于根据更新后的中间参数，对线性回归方程进行更新；
第三更新单元，用于根据更新后的线性回归方程，对总离均差平方和以及残差平方和进行更新；
根据更新后的总离均差平方和以及残差平方和，对血氧饱和度测量结果的置信度进行更新。
进一步，还包括：
生成模块，用于根据线性回归模型，生成脉搏血氧信号特征值。
本发明另一方面所采取的技术方案是：
血氧饱和度测量置信度的递推系统，包括：
至少一个处理器；
至少一个存储器，用于存储至少一个程序；
当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现所述的血氧饱和度测量置信度的递推方法。
本发明另一方面所采取的技术方案是：
一种存储介质，其中存储有处理器可执行的指令，所述处理器可执行的指令在由处理器 执行时用于执行所述的血氧饱和度测量置信度的递推方法。
本发明的有益效果是：本发明基于线性回归模型，通过递推算法对线性回归模型进行更新，最终得到血氧饱和度测量结果的置信度，进而实现对测量值的可靠性评估，避免了运动伪差及噪声等干扰因素影响造成的漏检和误检的情况，提高了血氧饱和度测量结果的可靠性，更加科学。
图1为本发明实施例的步骤流程图。
下面结合说明书附图和具体实施例对本发明作进一步解释和说明。对于本发明实施例中的步骤编号，其仅为了便于阐述说明而设置，对步骤之间的顺序不做任何限定，实施例中的各步骤的执行顺序均可根据本领域技术人员的理解来进行适应性调整。
参照图1，本发明实施例提供了一种血氧饱和度测量置信度的递推方法，包括以下步骤：
S1、对数据点个数进行初始化配置；
本实施例中，数据点个数n初始化配置为n＝2；
S2、根据初始化配置结果，构建线性回归模型；
进一步作为步骤S2的优选实施方式，所述步骤S2，包括以下步骤：
S20、获取红光和红外光的第n个时刻点数据，分别以I
rd(n)和I
ir(n)表示；计算中间变量x(n)＝I
rd(n)(I
ir(n)-I
ir(n-1))和y(n)＝I
rd(n)(I
ir(n)-I
ir(n-1))，为了书写方便，又分别记为x
n和y
n；
S21、根据初始化配置结果，计算中间参数；
其中，本实施例首先根据数据点个数的初始值，计算统计量的初始值，即：s
n,0＝n，
和
s
n,0代表数据点个数；s
n,1代表x
n的和；s
n,2代表y
n的和；s
n,3代表x
n的平方和；s
n,4代表x
ny
n的和；s
n,5代表y
n的平方和；
另外，上述统计量本质上是数据的一阶和二阶矩，反映了样本中的总体信息。
然后，根据计算得到的统计量的值，计算线性回归方程的中间参数，即：
其中，c
n,11、c
n,12、c
n,21和c
n,22代表递推算法实现过程中的中间参数。
S22、根据中间参数，计算线性回归方程的拟合系数，得到线性回归方程；
具体地，本实施例计算线性回归方程Y＝b
1+b
2X的在n个数据点的拟合系数b
n,1＝c
n,11s
n,2+c
n,12s
n,4和b
n,2＝c
n,21s
n,2+c
n,22s
n,4。其中，脉搏血氧信号特征值R即为参数b
n,2。其中，b
1和b
2是回归方程的待定参数；b
n,1与b
n,2为n个数据点时计算的b
1和b
2，脉搏血氧信号特征值R即为参数b
n,2。
S23、根据线性回归方程，计算总离均差平方和以及残差平方和；
S24、根据总离均差平方和以及残差平方和，计算血氧饱和度测量结果的置信度。
具体地，本实施例计算总离均差平方和
残差平方和SSE
n＝b
n,1s
n,2+b
n,2s
n,4，置信度系数C
n＝1-SSE
n/SST
n。
S3、根据线性回归模型，获取血氧饱和度测量结果的置信度；
本实施例获取的置信度即为步骤S24中计算得到的置信度系数C
n＝1-SSE
n/SST
n。
S4、判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行步骤S5，直至血氧饱和度测量结果的置信度满足阈值要求。
具体地，本实施例判断步骤S3中的置信度系数是否达到预设阈值，若是，则执行步骤S7；反之，则返回步骤S5，以进行下一次递推计算。
S5、对数据点个数进行更新；
具体地，本实施例的数据点个数增加后为：n＝n+1。
S6、根据数据点的更新结果，通过递推算法对线性回归模型进行更新；
进一步作为步骤S6的优选实施方式，所述步骤S6包括以下步骤：
S61、根据数据点的更新结果，对中间参数进行更新；
具体地，本实施例根据更新结果n＝n+1，进一步计算中间参数：
首先，利用递推公式，更新统计量的值如下：
s
n+1,0＝s
n+1，s
n+1,1＝s
n,1+x
n+1，s
n+1,2＝s
n,2+y
n+1，
s
n+1,4＝s
n,4+x
n+1y
n+1和
接着，利用递推公式，更新中间参数的值如下：
S62、根据更新后的中间参数，对线性回归方程进行更新；
具体地，本实施例根据更新后的中间参数，进一步计算线性回归方程Y＝b
1+b
2X的系数b
n+1,1＝c
n+1,11s
n+1,2+c
n+1,12s
n+1,4和b
n+1,2＝c
n+1,21s
n+1,2+c
n+1,22s
n+1,4，其中，脉搏血氧信号特征值R更新为参数b
n+1,2。
S63、根据更新后的线性回归方程，对总离均差平方和以及残差平方和进行更新；
S64、根据更新后的总离均差平方和以及残差平方和，对血氧饱和度测量结果的置信度进行更新；如果此时的置信度未满足阈值，则返回执行步骤S5，以进入下一次的递推计算流程。
具体地，本实施例根据更新后的线性回归方程，进一步计算总离均差平方和
残差平方和SSE
n+1＝b
n+1,1s
n+1,2+b
n+1,2s
n+1,4，置信度系数C
n+1＝1-SSE
n+1/SST
n+1。
进一步作为优选的实施方式，所述还包括以下步骤：
S7、根据线性回归模型，生成脉搏血氧信号特征值。
在本实施例中，当步骤S4中判断得到置信度系数达到预设阈值时，输出脉搏血氧信号特征值R。
与图1的方法相对应，本发明实施例还提供了一种血氧饱和度测量置信度的递推系统，包括：
初始化模块，用于对数据点个数进行初始化配置；
构建模块，用于根据初始化配置结果，构建线性回归模型；
获取模块，用于根据线性回归模型，获取血氧饱和度测量结果的置信度；
判断模块，用于判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行下一步骤，直至血氧饱和度测量结果的置信度满足阈值要求；
更新模块，用于对数据点个数进行更新；
递推模块，用于根据数据点的更新结果，通过递推算法对线性回归模型进行更新，并返回执行获取模块。
进一步作为优选的实施方式，所述构建模块包括：
第一计算单元，用于根据初始化配置结果，计算中间参数；
第二计算单元，用于根据中间参数，计算线性回归方程的拟合系数，得到线性回归方程；
第三计算单元，用于根据线性回归方程，计算总离均差平方和以及残差平方和；
第四计算单元，用于根据总离均差平方和以及残差平方和，计算血氧饱和度测量结果的置信度。
进一步作为优选的实施方式，所述递推模块包括：
第一更新单元，用于根据数据点的更新结果，对中间参数进行更新；
第二更新单元，用于根据更新后的中间参数，对线性回归方程进行更新；
第三更新单元，用于根据更新后的线性回归方程，对总离均差平方和以及残差平方和进行更新；
根据更新后的总离均差平方和以及残差平方和，对血氧饱和度测量结果的置信度进行更新。
进一步作为优选的实施方式，还包括：
生成模块，用于根据线性回归模型，生成脉搏血氧信号特征值。
本发明实施例还提供了一种血氧饱和度测量置信度的递推系统，包括：
至少一个处理器；
至少一个存储器，用于存储至少一个程序；
当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现所述的血氧饱和度测量置信度的递推方法。
上述方法实施例中的内容均适用于本系统实施例中，本系统实施例所具体实现的功能与上述方法实施例相同，并且达到的有益效果与上述方法实施例所达到的有益效果也相同。
此外，本发明实施例还提供了一种存储介质，其中存储有处理器可执行的指令，所述处理器可执行的指令在由处理器执行时用于执行所述的血氧饱和度测量置信度的递推方法。
综上所述，本发明设计了一套计算脉搏血氧信号特征值R和置信度系数C的递推算法。该算法充分利用了所有采样点的数据，但运行中无需存储大量的原始数据，仅仅保留若干个统计量作为中间变量，并以此不断更新最后的计算结果。由此可得，本发明的递推算法避免 了为了存储原始数据而造成的硬件资源浪费，同时也极大的提高了运算速度。因此，通过使用本发明的递推算法能实时高效的完成计算脉搏血氧信号特征值及置信度系数的运算，为硬件系统实现快速高效脉搏血氧检测提供了理论支持。
以上是对本发明的较佳实施进行了具体说明，但本发明并不限于所述实施例，熟悉本领域的技术人员在不违背本发明精神的前提下还可做作出种种的等同变形或替换，这些等同的变形或替换均包含在本申请权利要求所限定的范围内。
Claims (10)
- 血氧饱和度测量置信度的递推方法，其特征在于：包括以下步骤：对数据点个数进行初始化配置；根据初始化配置结果，构建线性回归模型；根据线性回归模型，获取血氧饱和度测量结果的置信度；判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行下一步骤，直至血氧饱和度测量结果的置信度满足阈值要求；对数据点个数进行更新；根据数据点的更新结果，通过递推算法对线性回归模型进行更新，并返回执行根据线性回归模型，获取血氧饱和度测量结果的置信度的步骤。
- 根据权利要求1所述的血氧饱和度测量置信度的递推方法，其特征在于：所述根据初始化配置结果，构建线性回归模型这一步骤，包括以下步骤：根据初始化配置结果，计算中间参数；根据中间参数，计算线性回归方程的拟合系数，得到线性回归方程；根据线性回归方程，计算总离均差平方和以及残差平方和；根据总离均差平方和以及残差平方和，计算血氧饱和度测量结果的置信度。
- 根据权利要求1所述的血氧饱和度测量置信度的递推方法，其特征在于：所述根据数据点的更新结果，通过递推算法对线性回归模型进行更新这一步骤，包括以下步骤：根据数据点的更新结果，对中间参数进行更新；根据更新后的中间参数，对线性回归方程进行更新；根据更新后的线性回归方程，对总离均差平方和以及残差平方和进行更新；根据更新后的总离均差平方和以及残差平方和，对血氧饱和度测量结果的置信度进行更新。
- 根据权利要求1所述的血氧饱和度测量置信度的递推方法，其特征在于：还包括以下步骤：根据线性回归模型，生成脉搏血氧信号特征值。
- 血氧饱和度测量置信度的递推系统，其特征在于：包括：初始化模块，用于对数据点个数进行初始化配置；构建模块，用于根据初始化配置结果，构建线性回归模型；获取模块，用于根据线性回归模型，获取血氧饱和度测量结果的置信度；判断模块，用于判断血氧饱和度测量结果的置信度是否满足阈值要求，若是，则输出血氧饱和度测量结果的置信度；反之，则执行下一步骤，直至血氧饱和度测量结果的置信度满足阈值要求；更新模块，用于对数据点个数进行更新；递推模块，用于根据数据点的更新结果，通过递推算法对线性回归模型进行更新，并返回执行获取模块。
- 根据权利要求5所述的血氧饱和度测量置信度的递推系统，其特征在于：所述构建模块包括：第一计算单元，用于根据初始化配置结果，计算中间参数；第二计算单元，用于根据中间参数，计算线性回归方程的拟合系数，得到线性回归方程；第三计算单元，用于根据线性回归方程，计算总离均差平方和以及残差平方和；第四计算单元，用于根据总离均差平方和以及残差平方和，计算血氧饱和度测量结果的置信度。
- 根据权利要求5所述的血氧饱和度测量置信度的递推系统，其特征在于：所述递推模块包括：第一更新单元，用于根据数据点的更新结果，对中间参数进行更新；第二更新单元，用于根据更新后的中间参数，对线性回归方程进行更新；第三更新单元，用于根据更新后的线性回归方程，对总离均差平方和以及残差平方和进行更新；根据更新后的总离均差平方和以及残差平方和，对血氧饱和度测量结果的置信度进行更新。
- 根据权利要求5所述的血氧饱和度测量置信度的递推系统，其特征在于：还包括：生成模块，用于根据线性回归模型，生成脉搏血氧信号特征值。
- 血氧饱和度测量置信度的递推系统，其特征在于：包括：至少一个处理器；至少一个存储器，用于存储至少一个程序；当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-4中任一项所述的血氧饱和度测量置信度的递推方法。
- 一种存储介质，其中存储有处理器可执行的指令，其特征在于：所述处理器可执行的指 令在由处理器执行时用于执行如权利要求1-4中任一项所述的血氧饱和度测量置信度的递推方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811482852.3 | 2018-12-05 | ||
| CN201811482852.3A CN109512393B (zh) | 2018-12-05 | 2018-12-05 | 血氧饱和度测量置信度的递推方法、系统及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020114190A1 true WO2020114190A1 (zh) | 2020-06-11 |
Family
ID=65794907
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/116480 WO2020114190A1 (zh) | 2018-12-05 | 2019-11-08 | 血氧饱和度测量置信度的递推方法、系统及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109512393B (zh) |
| WO (1) | WO2020114190A1 (zh) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109512393B (zh) * | 2018-12-05 | 2021-03-02 | 深圳技术大学 | 血氧饱和度测量置信度的递推方法、系统及存储介质 |
| CN112545461A (zh) * | 2020-12-05 | 2021-03-26 | 深圳市美的连医疗电子股份有限公司 | 一种无创血红蛋白浓度值的检测方法、装置、系统及计算机可读存储介质 |
| CN112603287B (zh) * | 2020-12-16 | 2022-11-11 | 南昌逸勤科技有限公司 | 应用于可穿戴设备的心率曲线修正方法及装置 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101347334A (zh) * | 2007-07-19 | 2009-01-21 | 深圳迈瑞生物医疗电子股份有限公司 | 血氧饱和度测量方法和装置 |
| US20090324033A1 (en) * | 2008-06-30 | 2009-12-31 | Nellcor Puritan Bennett Ireland | Signal Processing Systems and Methods for Determining Slope Using an Origin Point |
| CN101872444A (zh) * | 2010-05-21 | 2010-10-27 | 杭州电子科技大学 | 一种结合中期修正策略的间歇过程批到批优化方法 |
| CN106837305A (zh) * | 2016-12-28 | 2017-06-13 | 中国石油天然气股份有限公司 | 确定抽油井井下液面深度的方法和装置 |
| CN108464836A (zh) * | 2018-02-09 | 2018-08-31 | 重庆东渝中能实业有限公司 | 一种面向社区医疗的血氧饱和度检测系统及方法 |
| CN109512393A (zh) * | 2018-12-05 | 2019-03-26 | 深圳技术大学（筹） | 血氧饱和度测量置信度的递推方法、系统及存储介质 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5934277A (en) * | 1991-09-03 | 1999-08-10 | Datex-Ohmeda, Inc. | System for pulse oximetry SpO2 determination |
| US8064975B2 (en) * | 2006-09-20 | 2011-11-22 | Nellcor Puritan Bennett Llc | System and method for probability based determination of estimated oxygen saturation |
| CN102095526B (zh) * | 2011-01-30 | 2012-07-25 | 中南大学 | 一种基于烧结热量损失计算的环冷机烟气温度预测方法 |
| US10092226B2 (en) * | 2011-12-23 | 2018-10-09 | General Electric Company | Method, arrangement, sensor, and computer program product for non-invasively measuring hemoglobin concentrations in blood |
| CN105962949A (zh) * | 2016-06-14 | 2016-09-28 | 上海理工大学 | 一种基于近红外光能量守恒法的无创血糖计算方法以及信号采集装置 |
-
2018
- 2018-12-05 CN CN201811482852.3A patent/CN109512393B/zh active Active
-
2019
- 2019-11-08 WO PCT/CN2019/116480 patent/WO2020114190A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101347334A (zh) * | 2007-07-19 | 2009-01-21 | 深圳迈瑞生物医疗电子股份有限公司 | 血氧饱和度测量方法和装置 |
| US20090324033A1 (en) * | 2008-06-30 | 2009-12-31 | Nellcor Puritan Bennett Ireland | Signal Processing Systems and Methods for Determining Slope Using an Origin Point |
| CN101872444A (zh) * | 2010-05-21 | 2010-10-27 | 杭州电子科技大学 | 一种结合中期修正策略的间歇过程批到批优化方法 |
| CN106837305A (zh) * | 2016-12-28 | 2017-06-13 | 中国石油天然气股份有限公司 | 确定抽油井井下液面深度的方法和装置 |
| CN108464836A (zh) * | 2018-02-09 | 2018-08-31 | 重庆东渝中能实业有限公司 | 一种面向社区医疗的血氧饱和度检测系统及方法 |
| CN109512393A (zh) * | 2018-12-05 | 2019-03-26 | 深圳技术大学（筹） | 血氧饱和度测量置信度的递推方法、系统及存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109512393B (zh) | 2021-03-02 |
| CN109512393A (zh) | 2019-03-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ding et al. | Continuous cuffless blood pressure estimation using pulse transit time and photoplethysmogram intensity ratio | |
| Zhang et al. | An empirical study on predicting blood pressure using classification and regression trees | |
| WO2020114190A1 (zh) | 血氧饱和度测量置信度的递推方法、系统及存储介质 | |
| WO2020114191A1 (zh) | 血氧饱和度测量置信度的计算方法、系统及存储介质 | |
| Addison et al. | A novel time–frequency-based 3D Lissajous figure method and its application to the determination of oxygen saturation from the photoplethysmogram | |
| US20210330203A1 (en) | Blood pressure measuring apparatus, blood pressure measuring method, electronic device, and computer readable storage medium | |
| Sahoo et al. | Wavelet based pulse rate and Blood pressure estimation system from ECG and PPG signals | |
| US20110196244A1 (en) | System and apparatus for the non-invasive measurement of blood pressure | |
| US20100274102A1 (en) | Processing Physiological Sensor Data Using a Physiological Model Combined with a Probabilistic Processor | |
| Yan et al. | Novel deep convolutional neural network for cuff-less blood pressure measurement using ECG and PPG signals | |
| CN108261190B (zh) | 连续血压估计方法、装置以及设备 | |
| US10405762B2 (en) | System and method for noninvasively measuring ventricular stroke volume and cardiac output | |
| Yang et al. | Estimation and validation of arterial blood pressure using photoplethysmogram morphology features in conjunction with pulse arrival time in large open databases | |
| Sola et al. | Parametric estimation of pulse arrival time: a robust approach to pulse wave velocity | |
| Solem et al. | Prediction of intradialytic hypotension using photoplethysmography | |
| CN114145724A (zh) | 基于ecg和ppg多生理特征参数动态监测血压的方法 | |
| Girčys et al. | Wearable system for real-time monitoring of hemodynamic parameters: Implementation and evaluation | |
| Gupta et al. | Dynamic large artery stiffness index for cuffless blood pressure estimation | |
| US9554712B2 (en) | Systems and methods for generating an artificial photoplethysmograph signal | |
| US20200065649A1 (en) | Method for robust and noise-tolerant SpO2 determination | |
| WO2011110491A1 (en) | A non-invasive system and method for diagnosing and eliminating white coat hypertention and white coat effect in a patient | |
| Xu et al. | Analysis for the Influence of ABR Sensitivity on PTT‐Based Cuff‐Less Blood Pressure Estimation before and after Exercise | |
| Yang et al. | respiratory rate estimation from the photoplethysmogram combining multiple respiratory-induced variations based on SQI | |
| Poon et al. | Using the changes in hydrostatic pressure and pulse transit time to measure arterial blood pressure | |
| Sannino et al. | Non-invasive estimation of blood pressure through genetic programming-preliminary results |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19893350 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19893350 Country of ref document: EP Kind code of ref document: A1 |