CN109171694B - Pulse signal-based diabetes condition evaluation method and system - Google Patents
Pulse signal-based diabetes condition evaluation method and system Download PDFInfo
- Publication number
- CN109171694B CN109171694B CN201810813051.4A CN201810813051A CN109171694B CN 109171694 B CN109171694 B CN 109171694B CN 201810813051 A CN201810813051 A CN 201810813051A CN 109171694 B CN109171694 B CN 109171694B
- Authority
- CN
- China
- Prior art keywords
- sequence
- pprx
- pulse signal
- pulse signals
- pulse
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/42—Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
-
- 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
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
Abstract
The invention discloses a method and a system for evaluating the state of a diabetic patient based on a pulse signal, which are characterized in that the pulse signal is obtained, a characteristic index corresponding to the pulse signal is obtained, and a model function of the corresponding relation between the characteristic index of the pulse signal and the diabetic patient is obtained; and obtaining a diabetes condition evaluation result through obtaining the pulse signal, calculating and according to the characteristic index of the pulse signal and the model function. The system can also obtain a plurality of pulse signals to obtain a plurality of diabetes condition evaluation results, and the results are recorded and analyzed to obtain the diabetes condition development trend evaluation result for daily condition monitoring and control of the diabetic. Compared with the prior art, the method can evaluate the diabetes condition and the development trend through a non-invasive method, has good user experience, low cost and easy operation, and is convenient for the diabetic patient to realize the aim of controlling the condition development and even delaying the condition development.
Description
Technical Field
The invention relates to a diabetes condition evaluation method, in particular to a diabetes condition evaluation method and system based on pulse signals.
Background
Diabetes is a chronic metabolic disease which can cause disability and death, and the severity of the disease and the risk assessment of the diabetes are very concerned by the diabetic and family members. Diabetes is closely related to lifestyle, and at present most of the time patients are in the community and at home unless the condition is severe, and thus the management of diabetes relies largely on the patients' self-management. The method is an important link for self-management of the diabetic patients, and can be used for removing the conditions of glycosylated hemoglobin, liver and kidney functions, retina damage degree, weight, blood pressure and heart in periodic admission examination, knowing the self physical condition by monitoring means and primarily performing self-evaluation, so that the diabetic patients can be treated in time.
In the prior art, daily health management of diabetics mainly depends on self-testing blood sugar. By monitoring the blood sugar of the patient, the blood sugar regulation capability of the patient is only evaluated, and when the condition of the blood sugar is found to be incapable of being controlled by medicines at home, the patient is in time admitted for treatment. However, in addition to hyperglycemia, many diabetics also have a combination of cardiovascular risk factors, such as hypertension, hyperlipidemia, and hyperuricemia, the more these risk factors, the higher the risk of diabetic complications. Because diabetes can cause damage to multiple organs such as heart, brain, kidney, eyes, nerves, limbs, and the like, various chronic complications of diabetes are the main causes of disability and death of the diabetic.
Disclosure of Invention
The invention mainly solves the technical problem that the current diabetes condition evaluation mainly adopts a blood sugar self-test method, and the method has the advantages of single detection parameter, creation, poor user experience and high cost.
In order to solve the above technical problems, the present invention provides a method for evaluating a diabetic condition based on a pulse signal, comprising: acquiring a pulse signal; and acquiring a corresponding diabetes condition evaluation result according to the pulse signal.
In another aspect, the present invention further provides a pulse signal-based diabetes condition assessment system, including: the pulse signal acquisition device is used for acquiring pulse signals of a person to be detected; a processor for performing the method as described above.
In another aspect, the present invention also proposes a computer-readable storage medium containing a program executable by a processor to implement the method as described above.
Compared with the prior art, the method and the system for evaluating the diabetes condition based on the pulse signal can evaluate the diabetes condition and the development trend noninvasively, have good user experience, low cost and easy operation, and are convenient for the diabetic to realize the aim of controlling the condition development and even delaying the condition development.
Drawings
FIG. 1 is a schematic diagram of a system for evaluating a condition of diabetes based on pulse signals;
FIG. 2 is a flow chart of a method for evaluating a condition of diabetes based on pulse signals;
FIG. 3 is a flow chart of a method for establishing a model function of a relationship between a characteristic indicator of a pulse signal and a diabetic condition.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
The first embodiment of the invention: referring to fig. 1, a system for evaluating a diabetic condition based on a pulse signal includes:
pulse signal acquisition device a 00: the pulse signal acquisition device is used for acquiring the pulse signal of a person to be detected;
processor a 01: and the device is used for acquiring a corresponding diabetes condition evaluation result according to the acquired pulse signal. On the other hand, the processor a01 obtains the corresponding diabetes condition evaluation result according to the pulse signal, including: and calculating one or more characteristic indexes of the pulse signals according to the pulse signals, and acquiring corresponding diabetes condition evaluation results according to the characteristic indexes of the pulse signals. In addition, the processor a01 may pre-establish a model function of the corresponding relationship between the characteristic index of the pulse signal and the diabetic condition, and input the characteristic index of the pulse signal into the model function to obtain a corresponding diabetic condition evaluation result. The processor A10 acquires physiological parameters of the diabetic patients in different disease stages in advance, and acquires pulse signals before corresponding time points when the physiological parameters are acquired; acquiring characteristic indexes of the pulse signals; and taking the characteristic indexes of the pulse signals and the physiological parameters corresponding to the pulse signals as input, and performing machine learning to obtain a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition. The processor a10 can also obtain the evaluation results of the diabetic condition corresponding to the multiple time points according to the pulse signals obtained at the multiple time points, and record and analyze the evaluation results for evaluating the development trend of the diabetic condition.
Wherein the processor a10 obtains the corresponding diabetic condition assessment result based on the Pulse signal, mainly based on a Pulse Rate (PR) signal sequence in the Pulse signal plethysmogram, the PR signal refers to a time interval between adjacent peaks in the Pulse signal plethysmogram, and the PR signal sequence includes all PR signal intervals in a segment of the Pulse signal.
In one embodiment, the processor a10 calculates the characteristic indicator from the pulse signal, including:
the frequency domain analysis is carried out on any section of pulse signals, and one or more frequency domain characteristic indexes can be obtained:
the freqArea sequence is obtained by calculating the area under the line of at least one frequency band of the pulse signal frequency domain image, the area under the line corresponding to each frequency band is obtained by setting different frequency bands, and the area under the line forms the freqArea sequence; the frequency domain of a typical pulse signal includes: ultra-low frequency band: 0-0.04Hz, low frequency band: 0.04-0.15Hz and high frequency band: 0.15-0.4 Hz. The freqPercent sequence is obtained by calculating the percentage of the area under at least one frequency band line of the pulse signal frequency domain image to the area under the bus, the corresponding percentage of each frequency band is obtained by setting different frequency bands, and the percentages form the freqPercent sequence; the ratio sequence is obtained by calculating the area ratio of the area under the line between different frequency bands of the pulse signal frequency domain image, the area ratio of the area under the line between every two frequency bands is obtained by setting different frequency bands, and the ratios form the ratio sequence.
The pPRx sequence of the pulse signal is linearly analyzed for one or more linear signatures and/or non-linearly analyzed for one or more non-linear signatures. The pPRx sequence of any pulse signal is calculated by the following method: and calculating the ratio of the number of adjacent pulse rate signal intervals in the pulse signal to the number of all pulse rate signal intervals, wherein the difference between the adjacent pulse rate signal intervals is greater than a threshold value x milliseconds, and obtaining the ratio corresponding to each threshold value x by setting different threshold values x, wherein the ratios form the pPRx sequence. In this embodiment, the ratio is expressed as a percentage, as shown in equation (1):
one or more characteristic indicators can be obtained by performing a linear analysis, and/or a nonlinear analysis, and/or a frequency domain analysis on the pPRx sequence of the pulse signal.
For example, the characteristic indicators obtained by the linear analysis may include: mean meanPR of pPRx sequence, standard deviation SDPR of pPRx sequence, standard deviation SDAPR of pPRx sequence mean, and root mean square RMSSD of adjacent pPRx differences in pPRx sequence.
Carrying out nonlinear analysis on the pPRx sequence of each pulse signal by adopting an entropy analysis method, namely: according to the prior art, for a random variable set a of a probability distribution function p (x), the definition of entropy is as shown in equation (2):
H(A)＝-∑pA(x)logpA(x) (2)
the characteristic indicators that can be obtained include:
(1) entropy S of pPRx sequence histogram distribution informationdhIs the numerical distribution information entropy for the pPRx sequence;
(2) pPRx sequence power spectrum vertical distribution information entropy SphPerforming discrete Fourier transform on the pPRx sequence to obtain a power spectrum, and then calculating the information entropy of the pPRx sequence according to the numerical distribution of the power spectrum sequence;
(3) pPRx sequence power spectrum full-band distribution information entropy SpfThe discrete Fourier transform is carried out on the pPRx sequence to obtain a power spectrum in the full frequency band [ fs/N,fs/2](the sampling frequency of the signal is fsThe number of sampling points is N) and i-1 division points f are inserted in1，f2，...，fm-1The full band is divided into i sub-bands. And taking the sum of the power densities in each frequency band as the power density of the frequency band to obtain m power densities. Normalizing the i power densities to obtain the probability p of occurrence of each frequency bandiThen, ΣipiAs 1, the corresponding full-band entropy of the power spectrum is as shown in equation (3):
the pPRx sequence of each pulse signal is subjected to nonlinear analysis, and the following four fractal dimension calculation and analysis methods can be adopted to obtain the following characteristic indexes:
(1) fractal dimension D calculated by structure function methodsfWherein, the structure function method is to define the incremental variance as a structure function for a given sequence z (x), and the relationship is:
for a plurality of scales tau, calculating corresponding S (tau) for discrete values of a sequence z (x), drawing a logS (tau) -log tau function curve, performing linear fitting in a scale-free region to obtain a slope alpha, and corresponding to a fractal dimension DsfThe conversion relation with the slope α is shown in formula (5):
(2) fractal dimension D calculated by correlation function methodcfWherein the correlation function method means that for a given sequence z (x), the correlation function C (τ) is defined as shown in equation (6):
C(τ)＝AVE(z(x+τ)*z(x))，τ＝1,2,3,...,N-1 (6)
where AVE (·) represents the average, and τ represents the two-point distance. At this time, the correlation function is power type, and since there is no characteristic length, the distribution is fractal, with C (tau) alpha tau-α. At this time, a function curve of logC (tau) -log tau is drawn, linear fitting is carried out in a scale-free area to obtain a slope alpha, and the corresponding fractal dimension D is obtainedcfThe conversion relation with the slope α is shown in formula (7):
Dcf＝2-α (7)
(3) fractal dimension D calculated by variation methodvmWherein the variation method uses a width of tauThe fractal curves are covered by the end-to-end connection of the rectangular frames, and the difference between the maximum value and the minimum value of the curve in the ith frame is H (i), namely the height of the rectangle. The height and width of all rectangles are multiplied to obtain the total area S (τ). Varying τ in size results in a series of S (τ). As shown in formula (8):
drawing a logN (tau) -log tau function curve, performing linear fitting in a scale-free region to obtain a slope alpha, and obtaining a corresponding fractal dimension DvmThe conversion relation with the slope α is shown in formula (7).
(4) Fractal dimension D calculated by root mean square methodrmsWherein, the root mean square method covers the fractal curve by connecting the ends of a rectangular frame with the width of tau, and the difference between the maximum value and the minimum value of the curve in the ith frame is H (i), namely the height of the rectangle. The root mean square value S (τ) of the heights of these rectangles is calculated. Varying τ in size results in a series of S (τ). Drawing a logS (tau) -log tau function curve, performing linear fitting in a scale-free region to obtain a slope alpha, and obtaining a corresponding fractal dimension DrmsThe conversion relation with the slope α is shown in formula (7).
The pulse signal characteristic indicators used for evaluating the diabetes condition are one, more or a collection of several of the above-mentioned frequency domain analysis and/or linear and/or nonlinear analysis, and may also be corresponding characteristic indicators obtained by existing analysis methods except those listed in the embodiment.
Input device a 02: and the signal connection with the processor is used for receiving the input information of the user.
Case a 03: the shell body encloses to form a containing cavity, the processor A01 and the input device A02 are at least partially contained in the containing cavity of the shell body A03, and a display area is arranged on the shell body A03.
Display device a 04: is connected with the display area and the processor A01 through signals, and displays the diabetes condition and/or the evaluation result of the diabetes condition trend according to the instructions of the input device A02 and the processor A01.
Memory a 05: is connected with the processor A01 through signals and is used for storing programs, the evaluation result of the diabetes condition and the evaluation result of the trend of the diabetes condition.
In one embodiment, a diabetic patient is 65 years old with type 2 diabetes mellitus, 8.5 mm fasting glucose/l, 14.2 mm glucose/l 2 hours after breakfast, 8.5% glycated hemoglobin (HbA1 c); body mass index 29 (normal below 24), abdominal obesity, blood pressure 165/100 mmhg (high blood pressure), triacylglycerol 4.8 mmol/l, low density lipoprotein-cholesterol (LDL-C)4.5 mmol/l, high density lipoprotein-cholesterol (HDL-C)0.85 mmol/l (dyslipidemia), uric acid 580 mmol/l (hyperuricemia), ocular fundus normal, 24 hours urine microalbumin quantification 210 mg/24 hours (elevated liver function), normal, electrocardiogram normal. The overall evaluation of the diabetic condition of this patient was type 2 diabetes and early stage diabetic nephropathy, accompanied by a high risk of cardiovascular disease. Specifically, in this embodiment, the patient can acquire pulse signals at different times through the pulse signal acquisition device a00, and complete the evaluation results and records of the diabetes condition at corresponding time points through the a01 processor and the a05 memory, so as to perform trend evaluation of the development of the diabetes condition of the patient, receive the patient instruction through the input device a02, and conveniently and accurately acquire the obtained diabetes condition evaluation results and corresponding diabetes condition development trend evaluation results through the display area on the housing a03 with the support of the display device a 04. The results may be used for self-health management by diabetic patients, including: fully discussing individual diabetes condition control objectives with a physician; reviewing daily diabetes condition monitoring and trend results together with doctors; explain and communicate with the doctor the daily diabetic condition; according to the diabetes condition and doctor feedback, the daily life behaviors are actively changed, so that the aim of controlling the diabetes condition development and even delaying the condition development is fulfilled.
In this embodiment, the processor a10 adopts the method for evaluating the condition of diabetes based on the pulse signal shown in fig. 2, which is low in cost, safe and effective, and specifically includes steps B00 through B10, as described in detail below:
b00: pulse signals of a plurality of time periods are acquired.
B10: and acquiring a corresponding diabetes condition evaluation result according to the pulse signal.
In one embodiment, step B10 includes: and calculating one or more characteristic indexes of the pulse signals according to the pulse signals, and acquiring corresponding diabetes condition evaluation results according to the characteristic indexes of the pulse signals. The calculation method of the characteristic index of the pulse signal and the evaluation result of the diabetic condition is as described above.
In an embodiment, in the step B10, when the evaluation result corresponding to the diabetes condition is obtained according to the characteristic indicator of the pulse signal, a model function of a corresponding relationship between the characteristic indicator of the pulse signal and the diabetes condition may be pre-established, and the characteristic indicator of the pulse signal is input into the model function to obtain the evaluation result corresponding to the diabetes condition. For example, in the step B10, a model function of the correspondence between the characteristic index of the pulse signal and the diabetic condition can be established through machine learning, as shown in fig. 3.
As shown in FIG. 3, the step B10 of building the model function may include steps B11-B13, which are described in detail below.
B11: the method comprises the steps of acquiring physiological parameters of the diabetic patients in different disease states in advance, and acquiring pulse signals before corresponding time points when the physiological parameters are acquired. Wherein, the physiological parameters of the diabetes patients in different disease stages are acquired in advance, such as: blood glucose value, body mass index, blood pressure value, cholesterol, blood uric acid, disease type, stage, complication quantity and severity and the like; the method for acquiring physiological parameters in this step may adopt a method commonly used in the prior art and high in accuracy, and meanwhile, corresponding to the acquisition of physiological parameters of each patient, pulse signals corresponding to time points before the physiological parameters need to be acquired, and due to differences in individual metabolism conditions, the time lengths of the pulse signals required by each sampler are different, and based on an actual modeling effect, the embodiment selects the pulse signals of different time lengths in 1-30 minutes.
B12: characteristic indicators of the pulse signals are obtained.
B13: and taking the characteristic indexes of the pulse signals and the physiological parameters corresponding to the pulse signals as input, and performing machine learning to obtain a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition.
And D, after obtaining a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition according to the steps, inputting the pulse signals of the person to be detected obtained in the step B00 into the model function, and obtaining the diabetes condition evaluation result.
In an embodiment, the evaluation results of the diabetes condition of the same patient at a plurality of time points can be obtained according to the above method, and the evaluation results of the development trend of the diabetes condition of the patient can be obtained through table recording and further analysis.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (3)
1. A pulse signal based diabetic condition assessment system, comprising:
the pulse signal acquisition device is used for acquiring pulse signals of a person to be detected;
a processor for performing a diabetes condition assessment method;
the method for evaluating the diabetic condition comprises the following steps:
acquiring a pulse signal;
acquiring a corresponding diabetes condition evaluation result according to the pulse signal;
according to the pulse signals, acquiring corresponding diabetes condition evaluation results, including:
calculating one or more characteristic indexes of the pulse signals according to the pulse signals;
according to the characteristic indexes of the pulse signals, acquiring corresponding diabetes condition evaluation results, wherein the diabetes condition evaluation results comprise:
pre-establishing a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes conditions, and inputting the characteristic indexes of the pulse signals into the model function to obtain a corresponding diabetes condition evaluation result;
the characteristic indicators of the pulse signal include:
performing frequency domain analysis on the pulse signal to obtain one or more frequency domain characteristics, and/or performing linear analysis on the pPRx sequence of the pulse signal to obtain one or more linear characteristic indexes, and/or performing nonlinear analysis to obtain one or more nonlinear characteristic indexes; wherein, the pPRx sequence of any section of pulse signal is calculated by the following method:
calculating the ratio of the number of adjacent pulse rate signal intervals in the pulse signal to the number of all pulse rate signal intervals, wherein the difference between the adjacent pulse rate signal intervals is larger than a threshold value x milliseconds, and obtaining the ratio corresponding to each threshold value x by setting different threshold values x, wherein the ratios form the pPRx sequence;
the characteristic indicators of the pulse signal further include:
the frequency domain features obtained by the frequency domain analysis comprise a freqArea sequence, a freqPercent sequence and a ratio sequence; the freqArea sequence is obtained by calculating the area under the line of at least one frequency band of the pulse signal frequency domain image, the area under the line corresponding to each frequency band is obtained by setting different frequency bands, and the area under the line forms the freqArea sequence; the freqPercent sequence is obtained by calculating the percentage of the area under at least one frequency band line of the pulse signal frequency domain image to the area under the bus, the corresponding percentage of each frequency band is obtained by setting different frequency bands, and the percentages form the freqPercent sequence; the ratio sequence is obtained by calculating the area ratio of the area under the line between different frequency bands of the pulse signal frequency domain image, the area ratio of the area under the line between every two frequency bands is obtained by setting different frequency bands, and the ratios form at least one of the ratio sequences;
and/or the characteristic indexes obtained by the linear analysis comprise:
at least one of a mean value meanPR of the pPRx sequence, a standard deviation SDPR of the pPRx sequence, a standard deviation SDAPR of the pPRx sequence mean, a root mean square RMSSD of adjacent pPRx differences in the pPRx sequence;
and/or the nonlinear characteristic index comprises a characteristic index obtained by performing entropy analysis on the pPRx sequence, and comprises the following steps:
entropy S of pPRx sequence histogram distribution informationdhpPRx sequence power spectrum vertical distribution information entropy SdhpPRx sequence power spectrum full-band distribution information entropy SpfAt least one of (a);
and/or the nonlinear characteristic index comprises a characteristic index obtained by fractal dimension calculation analysis of the pPRx sequence, and comprises the following steps:
fractal dimension D calculated by structure function methodsfCalculating the fractal dimension D by a correlation function methodcfCalculating the obtained fractal dimension D by a variation methodvmFractal dimension D calculated by root mean square methodrmsAt least one of (a);
the pre-established model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition comprises the following steps:
acquiring physiological parameters of the diabetic patients in different disease stages in advance, and acquiring pulse signals before corresponding time points when the physiological parameters are acquired;
acquiring characteristic indexes of the pulse signals;
the method comprises the following steps of taking the characteristic indexes of the pulse signals and the physiological parameters corresponding to the pulse signals as characteristic input, and performing machine learning to obtain a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition, wherein the model function comprises the following steps:
acquiring pulse signals of a plurality of time points;
obtaining diabetes condition evaluation results corresponding to a plurality of time points;
the evaluation results are recorded and analyzed for evaluating the development trend of the diabetic condition.
2. The system of claim 1, further comprising:
the input device is connected with the processor through signals and used for receiving input information of a user;
the processor and the input device are at least partially accommodated in the accommodating cavity of the shell, and a display area is arranged on the shell;
the display device is in signal connection with the display area and the processor and sends the diabetes condition and/or the diabetes condition trend evaluation result to the display area for displaying according to the instructions of the input device and the processor;
and the memory is in signal connection with the processor and is used for storing the program, the diabetes condition evaluation result and the diabetes condition trend evaluation result.
3. A computer-readable storage medium characterized by comprising a program executable by a processor to implement a diabetes condition assessment method;
the method for evaluating the diabetic condition comprises the following steps:
acquiring a pulse signal;
acquiring a corresponding diabetes condition evaluation result according to the pulse signal;
the acquiring of the corresponding diabetes condition evaluation result according to the pulse signal comprises:
calculating one or more characteristic indexes of the pulse signals according to the pulse signals, and calculating one or more characteristic indexes of the pulse signals according to the characteristic indexes of the pulse signals;
obtaining a corresponding diabetes condition assessment result, comprising:
pre-establishing a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes conditions, and inputting the characteristic indexes of the pulse signals into the model function to obtain a corresponding diabetes condition evaluation result;
characteristic indicators of pulse signals, including:
performing frequency domain analysis on the pulse signal to obtain one or more frequency domain characteristics, and/or performing linear analysis on the pPRx sequence of the pulse signal to obtain one or more linear characteristic indexes, and/or performing nonlinear analysis to obtain one or more nonlinear characteristic indexes; wherein, the pPRx sequence of any section of pulse signal is calculated by the following method:
calculating the ratio of the number of adjacent pulse rate signal intervals in the pulse signal to the number of all pulse rate signal intervals, wherein the difference between the adjacent pulse rate signal intervals is larger than a threshold value x milliseconds, and obtaining the ratio corresponding to each threshold value x by setting different threshold values x, wherein the ratios form the pPRx sequence;
characteristic indicators of the pulse signal, further comprising:
the frequency domain features obtained by the frequency domain analysis comprise a freqArea sequence, a freqPercent sequence and a ratio sequence; the freqArea sequence is obtained by calculating the area under the line of at least one frequency band of the pulse signal frequency domain image, the area under the line corresponding to each frequency band is obtained by setting different frequency bands, and the area under the line forms the freqArea sequence; the freqPercent sequence is obtained by calculating the percentage of the area under at least one frequency band line of the pulse signal frequency domain image to the area under the bus, the corresponding percentage of each frequency band is obtained by setting different frequency bands, and the percentages form the freqPercent sequence; the ratio sequence is obtained by calculating the area ratio of the area under the line between different frequency bands of the pulse signal frequency domain image, the area ratio of the area under the line between every two frequency bands is obtained by setting different frequency bands, and the ratios form at least one of the ratio sequences;
and/or, the characteristic index obtained by the linear analysis is: at least one of a mean value meanPR of the pPRx sequence, a standard deviation SDPR of the pPRx sequence, a standard deviation SDAPR of the pPRx sequence mean, a root mean square RMSSD of adjacent pPRx differences in the pPRx sequence;
and/or the nonlinear characteristic index comprises a characteristic index obtained by performing entropy analysis on the pPRx sequence, and comprises the following steps: entropy S of pPRx sequence histogram distribution informationdhpPRx sequence power spectrum vertical distribution information entropy SdhpPRx sequence power spectrum full-band distribution information entropy SpfAt least one of (a); and/or the nonlinear characteristic index comprises a characteristic index obtained by fractal dimension calculation analysis of the pPRx sequence, and comprises the following steps: fractal dimension D calculated by structure function methodsfCalculating the fractal dimension D by a correlation function methodcfCalculating the obtained fractal dimension D by a variation methodvmFractal dimension D calculated by root mean square methodrmsAt least one of (a);
the pre-established model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition comprises the following steps:
acquiring physiological parameters of the diabetic patients in different disease stages in advance, and acquiring pulse signals before corresponding time points when the physiological parameters are acquired;
acquiring characteristic indexes of the pulse signals;
the method comprises the following steps of taking the characteristic indexes of the pulse signals and the physiological parameters corresponding to the pulse signals as characteristic input, and performing machine learning to obtain a model function of the corresponding relation between the characteristic indexes of the pulse signals and the diabetes condition, wherein the model function comprises the following steps:
acquiring pulse signals of a plurality of time points;
obtaining diabetes condition evaluation results corresponding to a plurality of time points;
recording and analyzing the evaluation results;
and evaluating the development trend of the diabetes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810813051.4A CN109171694B (en) | 2018-07-23 | 2018-07-23 | Pulse signal-based diabetes condition evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810813051.4A CN109171694B (en) | 2018-07-23 | 2018-07-23 | Pulse signal-based diabetes condition evaluation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109171694A CN109171694A (en) | 2019-01-11 |
| CN109171694B true CN109171694B (en) | 2021-04-06 |
Family
ID=64937170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810813051.4A Active CN109171694B (en) | 2018-07-23 | 2018-07-23 | Pulse signal-based diabetes condition evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109171694B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1422591A (en) * | 2001-12-05 | 2003-06-11 | 丽台科技股份有限公司 | Sensor capable of synchronously measuring electrocardio, pulse and sound-wave signals from neck |
| WO2005032653A1 (en) * | 2003-10-01 | 2005-04-14 | Medtronic, Inc | Device and method for attenuating an immune response |
| CN103153175A (en) * | 2010-05-14 | 2013-06-12 | 先进计算发展中心 | Diagnostic classifications of pulse signal waveform data |
| EP3056141A1 (en) * | 2015-02-10 | 2016-08-17 | Politechnika Gdanska | A method of non-invasive measurement of blood glucose and optoelectronic system to non-invasive measurement of blood glucose |
| CN106061373A (en) * | 2011-01-28 | 2016-10-26 | 巴伊兰大学 | Method and system for non-invasively monitoring biological or biochemical parameters of individual |
| WO2016205558A1 (en) * | 2015-06-18 | 2016-12-22 | Ultradian Diagnostics Llc | Methods and devices for determining metabolic states |
| CN107028603A (en) * | 2015-11-20 | 2017-08-11 | 塔塔咨询服务有限公司 | The apparatus and method that the diabetes in human body are detected using pulse palpation signal |
| CN107945874A (en) * | 2017-11-15 | 2018-04-20 | 北京军秀咨询有限公司 | A kind of senior health and fitness's evaluation system based on internet |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7729734B2 (en) * | 2006-03-07 | 2010-06-01 | Andreas Mandelis | Non-invasive biothermophotonic sensor for blood glucose monitoring |
| EP2219518B1 (en) * | 2007-10-12 | 2012-08-22 | Cardiac Pacemakers, Inc. | Decompensation detection based on heart failure co-morbidities |
-
2018
- 2018-07-23 CN CN201810813051.4A patent/CN109171694B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1422591A (en) * | 2001-12-05 | 2003-06-11 | 丽台科技股份有限公司 | Sensor capable of synchronously measuring electrocardio, pulse and sound-wave signals from neck |
| WO2005032653A1 (en) * | 2003-10-01 | 2005-04-14 | Medtronic, Inc | Device and method for attenuating an immune response |
| CN103153175A (en) * | 2010-05-14 | 2013-06-12 | 先进计算发展中心 | Diagnostic classifications of pulse signal waveform data |
| CN106061373A (en) * | 2011-01-28 | 2016-10-26 | 巴伊兰大学 | Method and system for non-invasively monitoring biological or biochemical parameters of individual |
| EP3056141A1 (en) * | 2015-02-10 | 2016-08-17 | Politechnika Gdanska | A method of non-invasive measurement of blood glucose and optoelectronic system to non-invasive measurement of blood glucose |
| WO2016205558A1 (en) * | 2015-06-18 | 2016-12-22 | Ultradian Diagnostics Llc | Methods and devices for determining metabolic states |
| CN107028603A (en) * | 2015-11-20 | 2017-08-11 | 塔塔咨询服务有限公司 | The apparatus and method that the diabetes in human body are detected using pulse palpation signal |
| CN107945874A (en) * | 2017-11-15 | 2018-04-20 | 北京军秀咨询有限公司 | A kind of senior health and fitness's evaluation system based on internet |
Non-Patent Citations (2)
| Title |
|---|
| 2型糖尿病患者踝肱脉搏波传导速度与尿蛋白的相关性;张倩倩 等;《医学研究生学报》;20151231;第1-3页 * |
| Application and performance analysis of a two-pulse synthesis model on Photoplethysmograph signals of diabetic subjects;Dharitri Goswami,et al;《Biomedical Engineering and Technology》;20111231;第1-23页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109171694A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1383424B1 (en) | Method for monitoring pressure in body cavities | |
| US4974598A (en) | EKG system and method using statistical analysis of heartbeats and topographic mapping of body surface potentials | |
| US9220437B2 (en) | Diagnostic classifications of pulse signal waveform data | |
| US10512408B2 (en) | System and method for characterizing circulatory blood flow | |
| AU2002251604A1 (en) | Device, method and system for monitoring pressure in body cavities | |
| US9002440B2 (en) | System and method for characterizing circulatory blood flow | |
| EP2734103A1 (en) | Hemodynamic reserve monitor and hemodialysis control | |
| CN113727638A (en) | Method and system for automatically quantizing signal quality | |
| CN108403107B (en) | Arrhythmia discrimination method and system | |
| CN108652614B (en) | A kind of cardiovascular disease condition assessment method and system | |
| EP3065631A1 (en) | Noninvasive predictive and/or estimative blood pressure monitoring | |
| Rodriguez et al. | Detrended fluctuation analysis of heart intrabeat dynamics | |
| CN108461146B (en) | A kind of diabetic condition appraisal procedure and system based on electrocardiosignal | |
| WO2014143962A2 (en) | System and method for characterizing circulatory blood flow | |
| Howorka et al. | Modified orthostatic load for spectral analysis of short-term heart rate variability improves the sensitivity of autonomic dysfunction assessment | |
| DE102010061580A1 (en) | Use of the frequency spectrum of an artifact in oscillometry | |
| CN109171694B (en) | Pulse signal-based diabetes condition evaluation method and system | |
| Gravel et al. | Categorization and theoretical comparison of quantitative methods for assessing QT/RR hysteresis | |
| EP2339953B1 (en) | Methods for evaluating glycemic control | |
| CN113243898B (en) | Cerebral apoplexy data processing equipment and method | |
| Iqbal et al. | Real-time signal processing of data from an ECG | |
| US20230116132A1 (en) | Hemodynamic Reserve Monitor and Hemodialysis Control | |
| Howes et al. | Effects of regular alcohol consumption on 24 hour ambulatory blood pressure recordings | |
| KR20110094177A (en) | Method and system for measuring parameters of autonomic dysfunction tests | |
| Goovaerts et al. | Analysis of changes in ECG morphology prior to in-hospital cardiac arrest using weighted tensor decompositions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |