A blood pressure measurement method and device

Abstract

Embodiments of the present invention relate to a blood pressure measurement method and apparatus. The method includes: obtaining a plurality of first cuff pressure data and corresponding first pulse wave sampling data sequences; performing pulse wave feature data extraction processing according to preset first feature type data to generate corresponding first feature data; generating a first trend curve reflecting the change of the feature data with the cuff pressure; performing curve feature parameter extraction processing; using the extracted curve feature parameter to perform systolic blood pressure estimation processing to generate first systolic blood pressure data; using the extracted curve feature parameter to perform diastolic blood pressure estimation processing to generate first diastolic blood pressure data; and forming estimated result data for blood pressure measurement from the first mean pressure data, the first systolic blood pressure data, and the first diastolic blood pressure data. Through the embodiments of the present invention, individual differences can be reflected during blood pressure measurement, and the accuracy of blood pressure measurement can be further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a blood pressure measurement method and device. Background Art

[0002] Blood pressure is an important physiological parameter reflecting the state of the cardiovascular system. The oscillometric method is a common blood pressure measurement technique. This method estimates blood pressure data based on the correspondence between systolic blood pressure, diastolic blood pressure, and cuff pressure. The measurement process of this method is as follows: A cuff that can be inflated is bound to the arm of the test subject, and the cuff pressure is elevated by inflating the cuff. After the cuff pressure is higher than the systolic blood pressure threshold and the arterial blood flow is blocked, the cuff is slowly deflated in stages until the cuff pressure is lower than the diastolic blood pressure. During the entire deflation process, the cuff pressure is detected by a pressure sensing device, and the pulse wave is obtained by a pulse wave sensing device. Finally, the cuff pressure corresponding to the maximum amplitude of the pulse wave during the deflation process is used as the estimation result of the mean pressure data, and then the corresponding systolic blood pressure data and diastolic blood pressure data are further estimated according to the empirical coefficients of the mean pressure, systolic blood pressure, and diastolic blood pressure. In this measurement method, because relatively fixed empirical coefficients are habitually used to calculate systolic blood pressure and diastolic blood pressure, it is not easy to reflect individual differences. Summary of the Invention

[0003] The purpose of the present invention is to provide a blood pressure measurement method, device, electronic device, computer program product, and computer-readable storage medium for the defects of the prior art. Personalized curve feature parameters are extracted from the trend curve reflecting the correspondence between pulse wave feature data and cuff pressure, and the extracted curve feature parameters are used to fine-tune the systolic blood pressure and diastolic blood pressure coefficients. In this way, individual differences can be reflected during blood pressure measurement, and the accuracy of blood pressure measurement can be further improved.

[0004] To achieve the above purpose, a first aspect of an embodiment of the present invention provides a blood pressure measurement method, and the method includes:

[0005] Obtain a plurality of first cuff pressure data and corresponding first pulse wave sampling data sequences;

[0006] According to the preset first feature type data, perform pulse wave feature data extraction processing on each of the first pulse wave sampling data sequences to generate corresponding first feature data;

[0007] Generate a first trend curve reflecting the change of feature data with cuff pressure according to the correspondence between all the first cuff pressure data and all the first feature data;

[0008] Perform curve feature parameter extraction processing on the first trend curve to generate first mean pressure data, first width feature data, and first symmetry feature data;

[0009] Based on the first width feature data, the first symmetry feature data, and the first average pressure data, perform systolic blood pressure estimation processing to generate first systolic blood pressure data;

[0010] Based on the first width feature data, the first symmetry feature data, and the first average pressure data, perform diastolic blood pressure estimation processing to generate first diastolic blood pressure data;

[0011] The first average pressure data, the first systolic blood pressure data, and the first diastolic blood pressure data form the estimated result data of blood pressure measurement.

[0012] Preferably, the extracting of pulse wave feature data from each of the first pulse wave sampling data sequences according to the preset first feature type data to generate corresponding first feature data specifically includes:

[0013] When the first feature type data is of the pulse wave amplitude difference type, perform first pulse wave amplitude difference identification processing on each of the first pulse wave sampling data sequences to generate a plurality of first amplitude difference data; perform feature mean calculation processing according to all the first amplitude difference data to generate the first feature data;

[0014] When the first feature type data is of the maximum slope of the rising edge of the pulse wave type, perform first pulse wave rising edge maximum slope calculation processing on each of the first pulse wave sampling data sequences to generate a plurality of first rising edge maximum slope data; perform feature mean calculation processing according to all the first rising edge maximum slope data to generate the first feature data;

[0015] When the first feature type data is of the pulse wave systolic area type, perform first pulse wave systolic area calculation processing on each of the first pulse wave sampling data sequences to generate a plurality of first pulse wave systolic area data; perform feature mean calculation processing according to all the first pulse wave systolic area data to generate the first feature data.

[0016] Preferably, the generating of the first trend curve reflecting the change of feature data with the cuff pressure according to the corresponding relationship between all the first cuff pressure data and all the first feature data specifically includes:

[0017] Each of the first cuff pressure data and the corresponding first feature data form a first data group, and all the first data groups constitute a first data group sequence; and perform envelope fitting processing on the first data group sequence to obtain the first trend curve that can reflect the change of feature data with the cuff pressure.

[0018] Preferably, the curve feature parameter extraction process for the first trend curve to generate the first mean pressure data, the first width feature data, and the first symmetry feature data specifically includes:

[0019] On the first trend curve reflecting the change of feature data with cuff pressure, mark the position where the feature data is the maximum as the first feature point position; and use the feature data corresponding to the first feature point position as the first amplitude data; and use the cuff pressure corresponding to the first feature point position as the first mean pressure data;

[0020] According to the preset symmetry point ratio, on the first trend curve, mark the two positions where the feature data is the first amplitude data * symmetry point ratio as the second feature point position and the third feature point position respectively; use the cuff pressure corresponding to the second feature point position as the first reference cuff pressure data, and use the cuff pressure corresponding to the third feature point position as the second reference cuff pressure data, where the first reference cuff pressure data is higher than the second reference cuff pressure data;

[0021] Generate the first width feature data according to the difference between the first reference cuff pressure data and the second reference cuff pressure data;

[0022] Generate the first difference data according to the difference between the first reference cuff pressure data and the first mean pressure data;

[0023] Calculate and generate the first symmetry feature data according to the first difference data and the first width feature data, where the first symmetry feature data = first difference data / first width feature data.

[0024] Preferably, the systolic blood pressure estimation process for generating the first systolic blood pressure data according to the first width feature data, the first symmetry feature data, and the first mean pressure data specifically includes:

[0025] Calculate and generate the first systolic blood pressure coefficient according to the first width feature data, the first symmetry feature data, the first mean pressure data, and the preset systolic blood pressure empirical coefficient, where the first systolic blood pressure coefficient = systolic blood pressure empirical coefficient + (A1 * first mean pressure data + A2 * first width feature data + A3 * first symmetry feature data); (A1 * first mean pressure data + A2 * first width feature data + A3 * first symmetry feature data) is the systolic blood pressure fine-tuning coefficient; A1, A2, and A3 are the preset first, second, and third systolic blood pressure fine-tuning factors;

[0026] On the first trend curve reflecting the change of characteristic data with cuff pressure, mark the position corresponding to the first average pressure data as the first reference point position; and use the characteristic data corresponding to the first reference point position as the first reference point amplitude data; and on the half curve of the cuff pressure higher than the first average pressure data, mark the position where the characteristic data is the first reference point amplitude data * the first systolic pressure coefficient as the first systolic pressure position; and use the cuff pressure corresponding to the first systolic pressure position as the first systolic pressure data.

[0027] Preferably, the estimating and processing of the diastolic blood pressure according to the first width characteristic data, the first symmetry characteristic data and the first average pressure data to generate the first diastolic blood pressure data specifically includes:

[0028] Calculate and generate a first diastolic blood pressure coefficient according to the first width characteristic data, the first symmetry characteristic data, the first average pressure data and a preset diastolic blood pressure empirical coefficient, where the first diastolic blood pressure coefficient = diastolic blood pressure empirical coefficient + (B1 * first average pressure data + B2 * first width characteristic data + B3 * first symmetry characteristic data); (B1 * first average pressure data + B2 * first width characteristic data + B3 * first symmetry characteristic data) is the diastolic blood pressure fine-tuning coefficient; B1, B2 and B3 are preset first, second and third diastolic blood pressure fine-tuning factors;

[0029] On the first trend curve reflecting the change of characteristic data with cuff pressure, mark the position corresponding to the first average pressure data as the second reference point position; and use the characteristic data corresponding to the second reference point position as the second reference point amplitude data; and on the half curve of the cuff pressure lower than the first average pressure data, mark the position where the characteristic data is the second reference point amplitude data * the first diastolic blood pressure coefficient as the first diastolic blood pressure position; and use the cuff pressure corresponding to the first diastolic blood pressure position as the first diastolic blood pressure data.

[0030] A second aspect of the embodiments of the present invention provides a blood pressure measurement device, including:

[0031] An acquisition module is used to acquire a plurality of first cuff pressure data and corresponding first pulse wave sampling data sequences;

[0032] A data processing module is used to perform pulse wave characteristic data extraction processing on each of the first pulse wave sampling data sequences according to preset first characteristic type data to generate corresponding first characteristic data; and generate a first trend curve reflecting the change of characteristic data with cuff pressure according to the corresponding relationship between all the first cuff pressure data and all the first characteristic data;

[0033] The feature extraction module is used to extract curve feature parameters from the first trend curve, and generate first mean pressure data, first width feature data, and first symmetry feature data;

[0034] The blood pressure estimation module is used to perform systolic blood pressure estimation processing based on the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first systolic blood pressure data; and perform diastolic blood pressure estimation processing based on the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first diastolic blood pressure data; and the first mean pressure data, the first systolic blood pressure data, and the first diastolic blood pressure data form the estimated result data of blood pressure measurement.

[0035] A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

[0036] The processor is used to be coupled with the memory, read and execute instructions in the memory to implement the method steps described in the first aspect above;

[0037] The transceiver is coupled with the processor, and the processor controls the transceiver to perform message sending and receiving.

[0038] A fourth aspect of an embodiment of the present invention provides a computer program product, the computer program product includes computer program code, when the computer program code is executed by a computer, the computer is caused to execute the method described in the first aspect above.

[0039] A fifth aspect of an embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores computer instructions, when the computer instructions are executed by a computer, the computer is caused to execute the method described in the first aspect above.

[0040] A blood pressure measurement method, device, electronic device, computer program product, and computer-readable storage medium provided by an embodiment of the present invention extract personalized curve feature parameters from a trend curve reflecting the corresponding relationship between pulse wave feature data and cuff pressure, and use the extracted curve feature parameters to fine-tune the systolic and diastolic blood pressure coefficients, which not only reflects individual differences during blood pressure measurement but also further improves the accuracy of blood pressure measurement. Description of the Drawings

[0041] Figure 1 It is a schematic diagram of a blood pressure measurement method provided by Embodiment 1 of the present invention;

[0042] Figure 2 It is a schematic diagram of cuff pressure and pulse wave provided by Embodiment 1 of the present invention;

[0043] Figure 3 Schematic diagram of the first trend curve provided by the first embodiment of the present invention;

[0044] Figure 4 Schematic diagram of the characteristic parameters of the first trend curve provided by the first embodiment of the present invention;

[0045] Figure 5 Schematic diagram of the positions of the first systolic blood pressure and diastolic blood pressure provided by the first embodiment of the present invention;

[0046] Figure 6 Module structure diagram of a blood pressure measurement device provided by the second embodiment of the present invention;

[0047] Figure 7 Schematic diagram of the structure of an electronic device provided by the third embodiment of the present invention. Detailed implementation manners

[0048] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] Before measuring the blood pressure of a test subject, first bind a cuff that can inflate air to the subject's arm, and raise the cuff pressure by inflating the cuff. Stop inflating after the cuff pressure is higher than the systolic blood pressure threshold and the arterial blood flow is blocked. Then start to slowly deflate the cuff in stages until the cuff pressure is lower than the diastolic blood pressure. During the entire deflation process, the cuff pressure data of each stage, that is, the first cuff pressure data, can be obtained through the pressure sensing device, and the waveform sampling data of the pulse wave, that is, the first pulse wave sampling data sequence corresponding to the first cuff pressure data of each stage, can be obtained through the pulse wave sensing device. After obtaining a plurality of first cuff pressure data and the corresponding first pulse wave sampling data sequences, the blood pressure can be measured by using a blood pressure measurement method provided by the first embodiment of the present invention. Figure 1 Schematic diagram of a blood pressure measurement method provided by the first embodiment of the present invention. As Figure 1 shown, the method mainly includes the following steps:

[0050] Step 1, obtain a plurality of first cuff pressure data and the corresponding first pulse wave sampling data sequences.

[0051] Here, as Figure 2As shown in the schematic diagram of cuff pressure and pulse wave provided in the first embodiment of the present invention, when the cuff is slowly deflated in stages, the cuff pressure within each stage is stable. Therefore, the first cuff pressure data used to characterize the cuff pressure in each stage is a specific pressure value; each first pulse wave sampling data sequence is generated by continuously sampling all pulse waves within the stage time during each deflation stage. This data sequence consists of multiple pulse wave sampling data, and each sampling data corresponds to the amplitude of the pulse wave at a sampling time point.

[0052] Step 2: According to the preset first characteristic type data, perform pulse wave characteristic data extraction processing on each first pulse wave sampling data sequence to generate corresponding first characteristic data.

[0053] Here, the first characteristic type data includes three types: pulse wave amplitude difference type, maximum slope of the rising edge of the pulse wave type, and pulse wave systolic area type. These three types correspond to three different characteristic data; under normal circumstances, we default to using the processing flow of the pulse wave amplitude difference type to extract the amplitude difference data of the pulse wave waveform as the characteristic data, and in subsequent steps, make a trend curve based on the corresponding relationship between this characteristic data and the cuff pressure, and perform personalized characteristic parameter extraction based on the trend curve, and then estimate the relevant data of blood pressure based on the extracted characteristic parameters; however, if we find that the collected pulse wave has obvious baseline drift or waveform deformation due to external interference, we can respectively make three corresponding trend curves based on the three types of characteristic data, then perform personalized characteristic parameter extraction on the three trend curves, and obtain three groups of blood pressure estimation data. Finally, perform normalized comprehensive decision-making on the three groups of blood pressure estimation data to obtain the final blood pressure estimation data.

[0054] Specifically, it includes: Step 21: When the first characteristic type data is the pulse wave amplitude difference type, perform first pulse wave amplitude difference recognition processing on each first pulse wave sampling data sequence to generate multiple first amplitude difference data; according to all the first amplitude difference data, perform characteristic mean calculation processing to generate first characteristic data.

[0055] Here, the first pulse wave sampling data sequence includes the sampling data of multiple consecutive pulse waves. When performing the first pulse wave amplitude difference recognition processing, first identify the waveform data sequences of multiple specific pulse wave waveforms from the first pulse wave sampling data sequence, and then perform peak and trough recognition on each waveform data sequence, and calculate the absolute amplitude difference between the peak and the trough to obtain the first amplitude difference data corresponding to each waveform data sequence; when performing the characteristic mean calculation processing, the characteristic mean of all the first amplitude difference data can be calculated by means such as average processing or weighted average processing, and the calculated result is the first characteristic data.

[0056] Step 22, when the first feature type data is the type of the maximum slope of the ascending edge of the pulse wave, for each first pulse wave sampling data sequence, perform the calculation process of the maximum slope of the ascending edge of the first pulse wave to generate multiple first ascending edge maximum slope data; according to all the first ascending edge maximum slope data, perform the calculation process of the feature mean value to generate the first feature data.

[0057] Here, the first pulse wave sampling data sequence includes the sampling data of multiple consecutive pulse waves. When performing the calculation process of the maximum slope of the ascending edge of the first pulse wave, first identify the ascending edge data sequences of multiple specific pulse wave waveforms from the first pulse wave sampling data sequence, and then calculate the slopes of all ascending edge sampling points in each ascending edge data sequence. The maximum value among them is the first ascending edge maximum slope data of the current pulse wave; when performing the calculation process of the feature mean value, the feature mean value of all the first ascending edge maximum slope data can be calculated by means such as average value processing or weighted average value processing, and the calculated result is the first feature data.

[0058] Step 23, when the first feature type data is the type of the systolic area of the pulse wave, for each first pulse wave sampling data sequence, perform the calculation process of the systolic area of the first pulse wave to generate multiple first pulse wave systolic area data; according to all the first pulse wave systolic area data, perform the calculation process of the feature mean value to generate the first feature data.

[0059] Here, the first pulse wave sampling data sequence includes the sampling data of multiple consecutive pulse waves. When performing the calculation process of the systolic area of the first pulse wave, first identify the waveform data sequences of multiple specific pulse wave waveforms from the first pulse wave sampling data sequence, then deduce the demarcation point between the systolic period and the diastolic period according to each waveform data sequence, and then calculate the area of the systolic period in the pulse wave waveform to obtain the first pulse wave systolic area data of the current pulse wave; when performing the calculation process of the feature mean value, the feature mean value of all the first pulse wave systolic area data can be calculated by means such as average value processing or weighted average value processing, and the calculated result is the first feature data.

[0060] Step 3, generate a first trend curve reflecting the change of the feature data with the cuff pressure according to the corresponding relationship between all the first cuff pressure data and all the first feature data;

[0061] Specifically, it includes: forming a first data group from each first cuff pressure data and the corresponding first feature data, and forming a first data group sequence from all the first data groups; and performing envelope fitting processing on the first data group sequence to obtain a first trend curve that can reflect the change of the feature data with the cuff pressure.

[0062] Here, for the first feature type data corresponding to step 2 in the previous text, if the first feature type data is the pulse wave amplitude difference type, the first feature data is the pulse wave amplitude difference data, and the first trend curve is the trend curve reflecting the corresponding relationship between the pulse wave amplitude difference data and the cuff pressure; if the first feature type data is the maximum slope of the rising edge of the pulse wave type, the first feature data is the maximum slope data of the rising edge of the pulse wave, and the first trend curve is the trend curve reflecting the corresponding relationship between the maximum slope data of the rising edge of the pulse wave and the cuff pressure; if the first feature type data is the systolic area of the pulse wave type, the first feature data is the systolic area feature data of the pulse wave, and the first trend curve is the trend curve reflecting the corresponding relationship between the systolic area feature data of the pulse wave and the cuff pressure.

[0063] For example, as Figure 2 shown, at step 1, the first cuff pressure data of 6 deflation stages and the corresponding 6 first pulse wave sampling data sequences are obtained. Each first pulse wave sampling data sequence can obtain a first feature data. Then the first data group sequence should be [(the first first cuff pressure data, the first first feature data), (the second first cuff pressure data, the second first feature data), (the third first cuff pressure data, the third first feature data), (the fourth first cuff pressure data, the fourth first feature data), (the fifth first cuff pressure data, the fifth first feature data), (the sixth first cuff pressure data, the sixth first feature data)]. Taking the cuff pressure as the horizontal axis and the feature data as the vertical axis, performing envelope fitting processing on the first data group sequence, the obtained fitting curve is the first trend curve that can reflect the change of the feature data with the cuff pressure, as Figure 3 shown in the schematic diagram of the first trend curve provided in Embodiment 1 of the present invention. Among them, the coordinates of point 1 are (the first first cuff pressure data, the first first feature data), the coordinates of point 2 are (the second first cuff pressure data, the second first feature data), and so on. The coordinates of point 6 are (the sixth first cuff pressure data, the sixth first feature data); among them, from the first first cuff pressure data to the sixth first cuff pressure data, the specific cuff pressure values of the cuff pressure data show a decreasing trend in sequence.

[0064] Step 4: Perform curve feature parameter extraction processing on the first trend curve to generate the first mean pressure data, the first width feature data, and the first symmetry feature data;

[0065] Specifically, it includes: Step 41: On the first trend curve reflecting the change of the feature data with the cuff pressure, mark the position where the feature data is the maximum value as the position of the first feature point; and use the feature data corresponding to the position of the first feature point as the first amplitude data; and use the cuff pressure corresponding to the position of the first feature point as the first mean pressure data;

[0066] Here, as Figure 4As shown in the schematic diagram of the first trend curve characteristic parameters provided in the first embodiment of the present invention, the first amplitude data is the characteristic data Y corresponding to the first characteristic point, and the first average pressure data is the cuff pressure X corresponding to the first characteristic point;

[0067] Step 42: According to a preset symmetry point ratio, on the first trend curve, mark the two positions where the characteristic data is the first amplitude data * the symmetry point ratio as the second characteristic point position and the third characteristic point position respectively; use the cuff pressure corresponding to the second characteristic point position as the first reference cuff pressure data, and use the cuff pressure corresponding to the third characteristic point position as the second reference cuff pressure data, where the first reference cuff pressure data is higher than the second reference cuff pressure data;

[0068] Here, the symmetry point ratio is a preset empirical threshold, defaulting to 80%; as Figure 4 shown, the first reference cuff pressure data is the cuff pressure X1 corresponding to the second characteristic point position, the second reference cuff pressure data is the cuff pressure X2 corresponding to the third characteristic point position, and X1>X2;

[0069] Step 43: Generate the first width characteristic data according to the difference between the first reference cuff pressure data and the second reference cuff pressure data;

[0070] Here, as Figure 4 shown, the first width characteristic data is the first width in the figure, that is, the first width characteristic data = the first reference cuff pressure data - the second reference cuff pressure data = X1 - X2;

[0071] Step 44: Generate the first difference data according to the difference between the first reference cuff pressure data and the first average pressure data;

[0072] Here, as Figure 4 shown, the first difference data is the second width in the figure, that is, the first difference data = the first reference cuff pressure data - the first average pressure data = X1 - X;

[0073] Step 45: Calculate and generate the first symmetry characteristic data according to the first difference data and the first width characteristic data, and the first symmetry characteristic data = the first difference data / the first width characteristic data.

[0074] Here, as Figure 4 shown, the first symmetry characteristic data = the first difference data / the first width characteristic data = the second width / the first width = (X1 - X) / (X1 - X2).

[0075] Step 5: Perform systolic blood pressure estimation processing according to the first width characteristic data, the first symmetry characteristic data and the first average pressure data to generate the first systolic blood pressure data;

[0076] Specifically, it includes: Step 51, calculate and generate a first systolic pressure coefficient according to the first width characteristic data, the first symmetry characteristic data, the first average pressure data, and a preset systolic pressure empirical coefficient. The first systolic pressure coefficient = systolic pressure empirical coefficient + (A1 * first average pressure data + A2 * first width characteristic data + A3 * first symmetry characteristic data);

[0077] Among them, (A1 * first average pressure data + A2 * first width characteristic data + A3 * first symmetry characteristic data) is the systolic pressure fine-tuning coefficient; A1, A2, and A3 are preset first, second, and third systolic pressure fine-tuning factors;

[0078] Here, the systolic pressure empirical coefficient is the empirical coefficient used in the conventional oscillometric detection method and can be obtained by querying a preset blood pressure coefficient table; based on the use of the empirical coefficient in this step, a fine-tuning coefficient is added to it through (A1 * first average pressure data + A2 * first width characteristic data + A3 * first symmetry characteristic data). The characteristic parameters of the trend curve may be different for each person or even for the same person in different states. The fine-tuning coefficient incorporates the three characteristic parameters of the trend curve to achieve personalized fine-tuning of the relatively fixed empirical coefficient; the first, second, and third systolic pressure fine-tuning factors A1, A2, and A3 are learned through statistical methods based on a large number of clinical samples;

[0079] Step 52, on the first trend curve reflecting the change of characteristic data with cuff pressure, mark the position corresponding to the first average pressure data as the first reference point position; and use the characteristic data corresponding to the first reference point position as the first reference point amplitude data; and on the half curve where the cuff pressure is higher than the first average pressure data, mark the position where the characteristic data is the first reference point amplitude data * first systolic pressure coefficient as the first systolic pressure position; and use the cuff pressure corresponding to the first systolic pressure position as the first systolic pressure data.

[0080] Here, the above-mentioned first reference point position, first reference point amplitude data, first systolic pressure position, and first systolic pressure data are respectively as Figure 5 shown in the schematic diagram of the first systolic pressure and diastolic pressure positions provided in Embodiment 1 of the present invention.

[0081] Step 6, perform diastolic pressure estimation processing according to the first width characteristic data, the first symmetry characteristic data, and the first average pressure data to generate the first diastolic pressure data;

[0082] Specifically, it includes: Step 61, calculate and generate a first diastolic pressure coefficient according to the first width characteristic data, the first symmetry characteristic data, the first average pressure data, and a preset diastolic pressure empirical coefficient. The first diastolic pressure coefficient = diastolic pressure empirical coefficient + (B1 * first average pressure data + B2 * first width characteristic data + B3 * first symmetry characteristic data);

[0083] Among them, (B1*first average pressure data+B2*first width characteristic data+B3*first symmetry characteristic data) is the diastolic pressure fine-tuning coefficient; B1, B2 and B3 are the preset first, second and third diastolic pressure fine-tuning factors;

[0084] Here, the diastolic pressure empirical coefficient is the empirical coefficient used in the conventional oscillometric detection method, which can be obtained by querying the preset blood pressure coefficient table; this step, on the basis of using the empirical coefficient, also adds a fine-tuning coefficient through (B1*first average pressure data+B2*first width characteristic data+B3*first symmetry characteristic data), and the characteristic parameters of the trend curve of each person or even the same person in different states may be different. The fine-tuning coefficient incorporates the three characteristic parameters of the trend curve into it, so as to realize personalized fine-tuning of the relatively solidified empirical coefficient; the first, second and third systolic pressure fine-tuning factors B1, B2 and B3 are learned by statistical methods based on a large number of clinical samples;

[0085] Step 62, on the first trend curve reflecting the change of characteristic data with cuff pressure, mark the position corresponding to the first average pressure data as the second reference point position; and use the characteristic data corresponding to the second reference point position as the second reference point amplitude data; and on the half-side curve where the cuff pressure is lower than the first average pressure data, mark the position where the characteristic data is the second reference point amplitude data * the first diastolic pressure coefficient as the first diastolic pressure position; and use the cuff pressure corresponding to the first diastolic pressure position as the first diastolic pressure data.

[0086] Here, the second reference point position, the second reference point amplitude data, the first diastolic pressure position, and the first diastolic pressure data are respectively as follows: Figure 5 shown.

[0087] Step 7, forming estimated result data of blood pressure measurement from the first average pressure data, the first systolic pressure data and the first diastolic pressure data.

[0088] Here, corresponding to the first characteristic type data in step 2 above, under normal circumstances, we use the pulse wave amplitude difference type processing flow by default to extract the amplitude difference data of the pulse wave waveform as characteristic data, and estimate it according to the first trend curve reflecting the corresponding relationship between the pulse wave amplitude characteristic data and the cuff pressure, and use the final estimated result data as the output result of the blood pressure measurement; but if we find that the collected pulse wave has obvious baseline drift or waveform deformation due to external interference, we can also make corresponding three trend curves based on the three characteristic type data, and then use the three trend curves for estimation respectively, and obtain three groups of estimated result data, and then perform normalized comprehensive decision processing on the three groups of estimated result data, and use the decision processing result as the output result of the final blood pressure measurement.

[0089] Figure 6 This is a module structure diagram of a blood pressure measurement device provided in the second embodiment of the present invention. This device can be a terminal device or a server for implementing the method of the embodiment of the present invention, or can be a device for implementing the method of the embodiment of the present invention connected to the above terminal device or server. For example, this device can be a device or a chip system of the above terminal device or server. As Figure 6 shown, this device includes: an acquisition module 201, a data processing module 202, a feature extraction module 203, and a blood pressure estimation module 204.

[0090] The acquisition module 201 is used to acquire a plurality of first cuff pressure data and corresponding first pulse wave sampling data sequences.

[0091] The data processing module 202 is used to perform pulse wave feature data extraction processing on each first pulse wave sampling data sequence according to preset first feature type data to generate corresponding first feature data; and generate a first trend curve reflecting the change of feature data with cuff pressure according to the correspondence between all first cuff pressure data and all first feature data.

[0092] The feature extraction module 203 is used to perform curve feature parameter extraction processing on the first trend curve to generate first mean pressure data, first width feature data, and first symmetry feature data.

[0093] The blood pressure estimation module 204 is used to perform systolic blood pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first systolic blood pressure data; and perform diastolic blood pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first diastolic blood pressure data; and the first mean pressure data, the first systolic blood pressure data, and the first diastolic blood pressure data form the estimated result data of blood pressure measurement.

[0094] A blood pressure measurement device provided in the embodiment of the present invention can execute the method steps in the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here.

[0095] It should be noted that it should be understood that the division of each module of the above device is only a division of logical functions. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also all be implemented in the form of hardware; or some modules can be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the acquisition module can be a separately established processing element, or can be integrated in a certain chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and the function of the above determination module can be called and executed by a certain processing element of the above device. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together or can be independently implemented. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the processor element or the instruction in the form of software.

[0096] For example, the above modules can be one or more integrated circuits configured to implement the above method, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), etc. Again, when a certain module above is implemented in the form of a processing element scheduling program code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program code. Again, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0097] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The above computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The above computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired manner (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, Bluetooth, microwave, etc.). The above computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The above available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0098] Figure 7 FIG. 4 is a schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention. The electronic device can be the aforementioned terminal device or server, or a terminal device or server connected to the aforementioned terminal device or server to implement the method of the embodiments of the present invention. As Figure 7 shown, the electronic device may include: a processor 31 (such as a CPU), a memory 32, and a transceiver 33; the transceiver 33 is coupled to the processor 31, and the processor 31 controls the transceiver operations of the transceiver 33. Various instructions can be stored in the memory 32 to complete various processing functions and implement the methods and processing procedures provided in the above embodiments of the present invention. Preferably, the electronic device related to the embodiments of the present invention further includes: a power supply 34, a system bus 35, and a communication port 36. The system bus 35 is used to realize communication connections between components. The above communication port 36 is used for the electronic device to connect and communicate with other peripherals.

[0099] In Figure 7The system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, only a thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The communication interface is used to implement communication between the database access device and other devices (such as clients, read-write libraries, and read-only libraries). The memory may include Random Access Memory (RAM), and may also include non-volatile memory, such as at least one disk memory.

[0100] The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0101] It should be noted that the embodiments of the present invention also provide a computer-readable storage medium, in which instructions are stored. When it runs on a computer, it enables the computer to execute the methods and processing procedures provided in the above embodiments.

[0102] The embodiments of the present invention also provide a chip for running instructions. The chip is used to execute the methods and processing procedures provided in the above embodiments.

[0103] The embodiments of the present invention also provide a program product, which includes a computer program. The computer program is stored in a storage medium. At least one processor can read the above computer program from the above storage medium, and the at least one processor executes the methods and processing procedures provided in the above embodiments.

[0104] A blood pressure measurement method, device, electronic device, computer program product, and computer-readable storage medium provided by the embodiments of the present invention extract personalized curve characteristic parameters from a trend curve reflecting the correspondence between pulse wave characteristic data and cuff pressure, and use the extracted curve characteristic parameters to finely adjust the systolic blood pressure and diastolic blood pressure coefficients, which not only reflects individual differences during blood pressure measurement but also further improves the accuracy of blood pressure measurement.

[0105] Those skilled in the art should further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0106] The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be implemented by hardware, software modules executed by a processor, or a combination of the two. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0107] The specific embodiments described above have further elaborated on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A blood pressure measurement method, characterized in that, The method includes: Obtaining a plurality of first cuff pressure data and corresponding first pulse wave sampling data sequences; Performing pulse wave feature data extraction processing on each of the first pulse wave sampling data sequences according to preset first feature type data to generate corresponding first feature data; Generating a first trend curve reflecting the change of feature data with cuff pressure according to the correspondence between all the first cuff pressure data and all the first feature data; Performing curve feature parameter extraction processing on the first trend curve to generate first mean pressure data, first width feature data, and first symmetry feature data; Performing systolic blood pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first systolic blood pressure data; Performing diastolic blood pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first diastolic blood pressure data; Composing estimated result data of blood pressure measurement from the first mean pressure data, the first systolic blood pressure data, and the first diastolic blood pressure data; Wherein, the first feature type data is of the pulse wave amplitude difference type, the maximum slope type of the pulse wave rising edge, or the pulse wave systolic area type; The performing curve feature parameter extraction processing on the first trend curve to generate first mean pressure data, first width feature data, and first symmetry feature data specifically includes: On the first trend curve reflecting the change of feature data with cuff pressure, marking the position where the feature data is the maximum value as the first feature point position; and taking the feature data corresponding to the first feature point position as the first amplitude data; and taking the cuff pressure corresponding to the first feature point position as the first mean pressure data; According to a preset symmetry point ratio, on the first trend curve, marking the two positions where the feature data is the first amplitude data * symmetry point ratio as the second feature point position and the third feature point position respectively; taking the cuff pressure corresponding to the second feature point position as the first reference cuff pressure data, and taking the cuff pressure corresponding to the third feature point position as the second reference cuff pressure data, wherein the first reference cuff pressure data is higher than the second reference cuff pressure data; Generating the first width feature data according to the difference between the first reference cuff pressure data and the second reference cuff pressure data; Generating a first difference data according to the difference between the first reference cuff pressure data and the first mean pressure data; Calculating and generating the first symmetry feature data according to the first difference data and the first width feature data, the first symmetry feature data = first difference data / first width feature data.

2. The blood pressure measurement method according to claim 1, wherein The performing pulse wave feature data extraction processing on each of the first pulse wave sampling data sequences according to preset first feature type data to generate corresponding first feature data specifically includes: When the first feature type data is of the pulse wave amplitude difference type, perform first pulse wave amplitude difference recognition processing on each of the first pulse wave sampling data sequences to generate a plurality of first amplitude difference data; based on all the first amplitude difference data, perform feature mean calculation processing to generate the first feature data; When the first feature type data is of the maximum slope of the rising edge of the pulse wave type, perform first maximum slope calculation processing of the rising edge of the pulse wave on each of the first pulse wave sampling data sequences to generate a plurality of first maximum slope data of the rising edge; based on all the first maximum slope data of the rising edge, perform feature mean calculation processing to generate the first feature data; When the first feature type data is of the systolic area of the pulse wave type, perform first systolic area calculation processing of the pulse wave on each of the first pulse wave sampling data sequences to generate a plurality of first systolic area data of the pulse wave; based on all the first systolic area data of the pulse wave, perform feature mean calculation processing to generate the first feature data.

3. The blood pressure measurement method according to claim 1, wherein Generating a first trend curve reflecting the change of the feature data with the cuff pressure according to the corresponding relationship between all the first cuff pressure data and all the first feature data specifically includes: Each of the first cuff pressure data and the corresponding first feature data form a first data group, and all the first data groups constitute a first data group sequence; and perform envelope fitting processing on the first data group sequence to obtain the first trend curve that can reflect the change of the feature data with the cuff pressure.

4. The blood pressure measurement method according to claim 1, characterized in that, Performing systolic blood pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first systolic blood pressure data specifically includes: Calculate and generate a first systolic blood pressure coefficient according to the first width feature data, the first symmetry feature data, the first mean pressure data, and a preset systolic blood pressure empirical coefficient, the first systolic blood pressure coefficient = systolic blood pressure empirical coefficient + (A1 * first mean pressure data + A2 * first width feature data + A3 * first symmetry feature data); (A1 * first mean pressure data + A2 * first width feature data + A3 * first symmetry feature data) is the systolic blood pressure fine-tuning coefficient; A1, A2, and A3 are preset first, second, and third systolic blood pressure fine-tuning factors; On the first trend curve reflecting the change of the feature data with the cuff pressure, mark the position corresponding to the first mean pressure data as the first reference point position; and use the feature data corresponding to the first reference point position as the first reference point amplitude data; and on the half curve where the cuff pressure is higher than the first mean pressure data, mark the position where the feature data is the first reference point amplitude data * first systolic blood pressure coefficient as the first systolic blood pressure position; and use the cuff pressure corresponding to the first systolic blood pressure position as the first systolic blood pressure data.

5. The blood pressure measurement method according to claim 1, characterized in that, Performing diastolic blood pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first mean pressure data to generate first diastolic blood pressure data specifically includes: Calculate and generate a first diastolic pressure coefficient according to the first width feature data, the first symmetry feature data, the first average pressure data, and a preset diastolic pressure empirical coefficient. The first diastolic pressure coefficient = diastolic pressure empirical coefficient + (B1 * first average pressure data + B2 * first width feature data + B3 * first symmetry feature data); (B1 * first average pressure data + B2 * first width feature data + B3 * first symmetry feature data) is the diastolic pressure fine-tuning coefficient; B1, B2, and B3 are preset first, second, and third diastolic pressure fine-tuning factors. On the first trend curve reflecting the change of feature data with cuff pressure, mark the position corresponding to the first average pressure data as the second reference point position; and use the feature data corresponding to the second reference point position as the second reference point amplitude data; and on the half curve where the cuff pressure is lower than the first average pressure data, mark the position where the feature data is the second reference point amplitude data * first diastolic pressure coefficient as the first diastolic pressure position; and use the cuff pressure corresponding to the first diastolic pressure position as the first diastolic pressure data.

6. An apparatus for implementing the blood pressure measurement method according to any one of claims 1-5, characterized in that, The device includes: An acquisition module for acquiring a plurality of first cuff pressure data and corresponding first pulse wave sampling data sequences; A data processing module for performing pulse wave feature data extraction processing on each of the first pulse wave sampling data sequences according to preset first feature type data to generate corresponding first feature data; and generating a first trend curve reflecting the change of feature data with cuff pressure according to the corresponding relationship between all the first cuff pressure data and all the first feature data; A feature extraction module for performing curve feature parameter extraction processing on the first trend curve to generate first average pressure data, first width feature data, and first symmetry feature data; A blood pressure estimation module for performing systolic pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first average pressure data to generate first systolic pressure data; and performing diastolic pressure estimation processing according to the first width feature data, the first symmetry feature data, and the first average pressure data to generate first diastolic pressure data; and forming the estimated result data of blood pressure measurement from the first average pressure data, the first systolic pressure data, and the first diastolic pressure data.

7. An electronic device, characterized in that, Including: A memory, a processor, and a transceiver; The processor is used to be coupled with the memory, read and execute instructions in the memory to implement the method according to any one of claims 1 - 5; The transceiver is coupled with the processor, and the processor controls the transceiver to perform message sending and receiving.

8. A computer program product, characterized in that, The computer program product includes computer program code, and when the computer program code is executed by a computer, the computer is caused to execute the method according to any one of claims 1 - 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and when the computer instructions are executed by a computer, the computer is caused to execute the method according to any one of claims 1 - 5.

Images