CN114145722A - Pulse pathological feature mining method for pancreatitis patient - Google Patents
Pulse pathological feature mining method for pancreatitis patient Download PDFInfo
- Publication number
- CN114145722A CN114145722A CN202111484127.1A CN202111484127A CN114145722A CN 114145722 A CN114145722 A CN 114145722A CN 202111484127 A CN202111484127 A CN 202111484127A CN 114145722 A CN114145722 A CN 114145722A
- Authority
- CN
- China
- Prior art keywords
- curve
- pancreatitis
- period
- pulse signal
- peak
- 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.)
- Granted
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
-
- 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
- A61B5/4222—Evaluating particular parts, e.g. particular organs
- A61B5/425—Evaluating particular parts, e.g. particular organs pancreas
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4857—Indicating the phase of biorhythm
-
- 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
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides a pulse pathological feature mining method for pancreatitis patients, which comprises the following steps: obtaining a labeled pulse signal curve sample, wherein the label is used for distinguishing a sample pulse signal curve as that of a normal person or a pancreatitis patient, then carrying out periodic division on the signal curve, extracting basic time domain characteristics, stability indexes and dual-peak index characteristics to form an input characteristic vector, inputting the input characteristic vector into a classification model, carrying out supervision by using labels corresponding to all samples, carrying out training to obtain a trained classification model, and then diagnosing that all persons to be diagnosed are sick. The double-peak index extracted by the invention represents two peak values in the single-period curve and an obvious concave arc structure, the stability index is used for representing the change rate of the latter half part of the single-period curve, can well indicate patients suffering from pancreatitis, provides case characteristic vectors for a subsequently trained classification model, and the obtained trained classification model has positive significance for classifying the patients.
Description
Technical Field
The invention belongs to the technical field of pulse condition acquisition systems in traditional Chinese medicine, and particularly relates to a pulse pathological characteristic mining method for patients suffering from pancreatitis.
Background
Chinese medicine occupies a very important position in the world medical system, and Chinese pulse-taking science has been summarized with two thousand years of experience in the medical field, accumulates abundant experience, and becomes one of the most representative diagnosis modes in Chinese medicine 'inspection, auscultation, inquiry and cutting'. At present, the pulse feeling diagnosis is mainly carried out by touching the veins of patients by doctors of traditional Chinese medicine, but the diagnosis mode has great influence on the diagnosis result due to different subjects and objects, and the diagnosis of pulse conditions has no quantitative data and lacks of objectivity. With the development of sensors and artificial intelligence technologies, computer-assisted medical treatment is widely applied.
More human body information is used for accurately analyzing and diagnosing pulse conditions, and multi-mode information acquisition is carried out, so that the method has important significance for pulse condition diagnosis of traditional Chinese medicine.
Blood flows through the whole body of a human body, physiological changes of the human body can influence the change of blood vessel pressure in an artery of an arm, and in the traditional Chinese medicine theory, pulse contains various information of the human body. The pulse is a quasi-periodic signal, and after the pulse signal is preprocessed and periodically divided, the single-period pulse can reflect various physiological and pathological information of human bodies, such as age, sex, physical conditions, health conditions and the like. However, at present, physicians of traditional Chinese medicine use manual measurement to conduct pulse diagnosis only by experience, which causes uncertainty of diagnosis result.
Disclosure of Invention
The invention aims to solve the technical problem that aiming at the defects of the prior art, the invention provides a pulse pathological feature mining algorithm for patients with pancreatitis, the algorithm provides a feature design formula of the patients with pancreatitis by comparing the pulse of the patients with pancreatitis with the pulse of the patients with non-pancreatitis, the feature design formula comprises a stability index and a double-peak index, compared with the patients with non-pancreatitis, the pulse of the patients with pulse condition pancreatitis has two peak values and an obvious concave arc structure, the two features can well describe the stability of a pulse single-cycle signal, the two pathological features are fused with a basic time domain feature for training a classification model, the preliminary classification of the patients with suspected pancreatitis is realized, and the classification effect is better.
In order to solve the technical problems, the invention adopts the technical scheme that: a pathological feature mining method for pancreatitis patients is characterized by comprising the following steps:
obtaining a labeled sample pulse signal curve, wherein the label is used for distinguishing individuals corresponding to the sample pulse signal curve from non-pancreatitis patients or pancreatitis patients;
dividing the sample pulse signal curve according to periods to obtain each single-period curve;
extracting the basic time domain characteristics of each single-period curve;
extracting a stability index and a double-peak index of each single-period curve as a case characteristic of pancreatitis of the corresponding single-period curve, wherein the double-peak index represents two peak values and an obvious concave arc structure in the single-period curve; the stability index is used for representing the change rate of the second half part of the single-period curve;
and (3) forming input feature vectors by the basic time domain features of the pulse signal curves of all samples and the case features of pancreatitis, inputting the input feature vectors into the classification model, supervising by using the labels corresponding to all samples, and training to obtain the trained classification model.
Preferably, the tags are classified into patient tags and non-patient tags;
the trained classification model further comprises:
acquiring a pulse signal curve of a person to be diagnosed;
inputting the feature vectors composed of the basic time domain features of all the single-period curves and the case features of pancreatitis into a trained classification model in the pulse signal curve of the person to be diagnosed to obtain a diagnosis label set; each label in the diagnosis label set corresponds to the monocycle curve one by one;
and if the occurrence frequency of the patient labels in the diagnosis label set is greater than a preset threshold, determining that the person to be diagnosed is a suspected pancreatitis patient.
Preferably, the stability index for extracting each monocycle curve is specifically: the method comprises the following steps of selecting a plurality of sampling points in a single-period curve, and calculating through a first formula to obtain the variance of each sampling point, wherein the variances of all the sampling points are used for expressing the stability index of the pulse single-period signal of each single-period curve, and the first formula is as follows:
in the first formula, N represents the number of sampling points in a single-period curve, N represents the number of sampling points in the whole period of a sample pulse signal curve, and SFDenotes the sampling frequency, t denotes the start position of the sampling point, DiRepresents the variance of the sample point at i, where i is a positive integer from 0 to N, and the parameter XiAbsolute coordinate value, x, representing a sample point on the abscissa iiAbscissa, y, representing the sample point at iiThe ordinate of the sample point at i is indicated.
Preferably, the sampling frequency is 2 times of the beating frequency of the human body pulse.
Preferably, the two-peak index for extracting each monocycle curve is specifically: selecting a plurality of sampling points in a single-period curve, obtaining the mean value of the longitudinal coordinate values of each sampling point of a non-pancreatitis patient through calculation, calculating the sum of the differences of the longitudinal coordinate values of the sampling points between two peaks in the single-period curve and the mean value of the longitudinal coordinate values of the same sampling points of the non-pancreatitis patient through a second formula, and using the sum as a double-peak index; the second formula is as follows:
in the second formula, Y represents a data set of longitudinal coordinates of sampling points, N represents the number of the sampling points in the whole period of the sample pulse signal curve, N represents the number of the sampling points in the single-period curve, T represents the point with the highest numerical value of the longitudinal coordinates in the single-period pulse signal curve, T represents the point with the second highest numerical value of the longitudinal coordinates in the single-period curve, and SFRepresenting the sampling frequency, A representing the mean value of the ordinate values of each sampling point of a normal person, BiRepresents the sum of the difference of the value of the ordinate of the sampling point at i of the pancreatitis patient and A.
Preferably, the basic time domain features of each monocycle pulse signal curve include a first peak height, a second peak height, a third peak height, a time interval from the first peak to the second peak, a time interval from the second peak to the third peak, a time interval from a pulse start point to a first trough, a time interval from a first trough to a second trough, and a time interval from a second trough to a pulse start point.
Preferably, the pulse signal curve of the person to be diagnosed is at least one single-cycle pulse signal curve.
Preferably, the classification model is trained by using an SVM kernel method.
Compared with the prior art, the invention has the following advantages:
1. based on the principle of traditional Chinese medicine, the invention discovers the unique pathological characteristics of pulse images of patients with pancreatitis compared with normal people, designs two algorithms for embodying the two pathological characteristics of pancreatitis through data in order to enable the characteristics and the differentiation to be visualized, the two pathological characteristics are stability indexes and double-peak indexes and are combined with the basic time domain characteristics of a single-cycle pulse signal curve to train a classification model, and the trained classification model is used for preliminarily diagnosing whether a person to be diagnosed is sick or not.
2. The invention is characterized in that a computer is used for detecting pancreatitis for the first time based on the principle of traditional Chinese medicine, the pulse signal curve of a person to be diagnosed is input into a trained classification model to judge whether the person to be diagnosed is a suspected pancreatitis patient, the accuracy of classification is up to more than 95%, wherein the accuracy of the classification is even close to 100% for young patients. The elderly subjects have older age, the elasticity of blood vessels is reduced, the peak structure of the typical pulse image features is less obvious, and therefore the diagnosis accuracy is reduced compared with that of the young subjects.
The technical solution of the present invention is further described in detail by the accompanying drawings and examples.
Drawings
FIG. 1 is a block diagram of a process for training a classification model according to an embodiment of the present invention.
Fig. 2 is a graph of a normal person's single-cycle pulse signal.
FIG. 3 is a graph of pulse signals from patients with pancreatitis.
Fig. 4 is a basic time domain characteristic of the single-cycle pulse signal curve of the present invention.
Detailed Description
The embodiment discloses a pulse pathological feature mining method for pancreatitis patients, which comprises the following steps:
s101, obtaining a labeled sample pulse signal curve, wherein the label is used for distinguishing pulse signal curves of patients with non-pancreatitis and patients with pancreatitis, and the label can be defined as: non-pancreatitis patients were labeled "1", pancreatitis patients were labeled "0";
the specific steps for obtaining the labeled sample pulse signal curve are as follows: collecting pulse data of a plurality of patients without pancreatitis and a plurality of patients with pancreatitis, respectively preprocessing the collected pulse data, and drawing a pulse signal curve by taking the collected time as an abscissa and the pulse amplitude of the pulse as an ordinate, thereby obtaining a labeled sample pulse signal curve; the pulse data is preprocessed based on the prior art, for example, a Butterworth algorithm is adopted to filter signals, baseline drift of the filtered signals is removed, and a smooth function is adopted to process the signals again, so that a curve for drawing the pulse signals is smooth;
s102, pulse data period division: the human body pulse is a quasi-periodic signal, each pulse period has similar period, amplitude and waveform, but the characteristics are different from person to person, so that pulse signal curves drawn by patients without pancreatitis and patients with pancreatitis are subjected to period division to obtain each single-period curve, and the pulse curve characteristics representing the curve acquirer can be obtained by researching each single-period pulse signal curve;
s103, extracting the basic time domain characteristics of each single-period curve; the basic time domain features comprise a first peak height, a second peak height, a third peak height, a time interval from the first peak to the second peak, a time interval from the second peak to the third peak, a time interval from a pulse starting point to a first trough, a time interval from a first trough to a second trough and a time interval from the second trough to the pulse starting point of a monocycle curve;
s104, extracting a stability index of each single-period curve, wherein the stability index is used for expressing the change rate of the latter half part of the single-period curve and has classification significance for distinguishing patients suffering from pancreatitis from patients suffering from non-pancreatitis;
s105, extracting a double-peak index of each single-period curve, wherein the double-peak index represents two peak values and an obvious concave arc structure in the single-period curve; since the twin peak index of normal persons is greater than that of patients with pancreatitis,
extracting the stability index and the double-peak index of each single-period curve as the case characteristics of pancreatitis of the corresponding single-period curve;
and S106, forming input feature vectors by the basic time domain features of the pulse signal curves of all samples and the case features of pancreatitis, inputting the input feature vectors into a classification model, supervising the classification model by using labels corresponding to all samples, and training the classification model by using an SVM kernel method to obtain the trained classification model.
In this example, the non-pancreatitis patients were healthy, normal without any disease; the pulse data acquisition is to measure the pulse of a non-pancreatitis patient or a pancreatitis patient through a pulse sensor and other similar instruments, collect and acquire the pulse data, and upload the acquired pulse data to a computer for disease detection research. 57 patients without pancreatitis and 7 patients with pancreatitis are selected during collection, and are respectively measured in several time periods every day, and pulse data are obtained by continuous measurement for several days, wherein the pulse data are provided by the 211 th hospital of the people's liberation military in China.
In this embodiment, the extracting the stability index of each monocycle curve specifically includes: the method comprises the following steps of selecting a plurality of sampling points in a single-period curve, and calculating through a first formula to obtain the variance of each sampling point, wherein the variances of all the sampling points are used for expressing the stability index of the pulse single-period signal of each single-period curve, and the first formula is as follows:
in the first formula, N represents the number of sampling points in a single-period curve, N represents the number of sampling points in the whole period of a sample pulse signal curve, and SFDenotes the sampling frequency, t denotes the start position of the sampling point, DiRepresents the variance of the sample point at i, where i is a positive integer from 0 to N, and the parameter XiAbsolute coordinate value, x, representing a sample point on the abscissa iiAbscissa, y, representing the sample point at iiThe ordinate of the sample point at i is indicated.
As shown in fig. 2 and 3, compared with the normal pulse of a human, the pulse condition (within the considered area) of a patient with pancreatitis has two peaks and a remarkable concave arc structure, and the characteristic can well describe the stability of a pulse monocycle signal and can describe the number of peaks and the concave arc degree in the pulse. Therefore, in this embodiment, the specific steps for extracting the double-peak index of each monocycle curve are as follows: selecting a plurality of sampling points in a single-period curve, obtaining the mean value of the longitudinal coordinate values of each sampling point of a non-pancreatitis patient through calculation, calculating the sum of the differences of the longitudinal coordinate values of the sampling points between two peaks in the single-period curve and the mean value of the longitudinal coordinate values of the same sampling points of the non-pancreatitis patient through a second formula, and using the sum as a double-peak index; the second formula is as follows:
in the second formula, Y represents a data set of longitudinal coordinates of sampling points, N represents the number of the sampling points in the whole period of the sample pulse signal curve, N represents the number of the sampling points in the single-period curve, T represents the point with the highest numerical value of the longitudinal coordinates in the single-period pulse signal curve, T represents the point with the second highest numerical value of the longitudinal coordinates in the single-period curve, and SFRepresenting the sampling frequency, A representing the mean value of the ordinate values of each sampling point of a normal person, BiRepresents the sum of the difference of the value of the ordinate of the sampling point at i of the pancreatitis patient and A.
As shown in fig. 4, the basic time domain features of the monocycle pulse signal include: the first peak height h of the pulse is started from the starting point of the pulse1Second peak height h2A third peak height h3Time interval t from first peak to second peakaTime interval t from second peak to third peakbTime interval t from pulse start to first trough2-t1Time interval t from first trough to second trough3-t2Time interval t from the second trough to the start of the pulse3-t1。
In this embodiment, the trained classification model further includes:
s201, acquiring a pulse signal curve of a person to be diagnosed;
s202, inputting feature vectors formed by basic time domain features of all single-period curves and case features of pancreatitis in a pulse signal curve of a person to be diagnosed into a trained classification model to obtain a diagnosis label set; each label in the diagnosis label set corresponds to the monocycle curve one by one;
s203, if the occurrence frequency of the patient labels in the diagnosis label set is greater than a preset threshold, determining that the person to be diagnosed is a suspected pancreatitis patient.
In this embodiment, the pulse signal curve of the person to be diagnosed is a pulse signal curve of at least one single cycle.
The trained classification model is verified by selecting the diagnosed patients and non-patients, and the verification result shows that the accuracy rate of the pancreatitis patients finally diagnosed by the personnel to be diagnosed which are preliminarily classified by the method disclosed by the invention is more than 95%, and especially the accuracy rate of the pancreatitis patients for young patients is even close to 100%. The elderly subjects have older age, the elasticity of blood vessels is reduced, the peak structure of the typical pulse image features is less obvious, the diagnosis accuracy is reduced compared with that of the young subjects, and the experimental model has a very good experimental effect on pancreatitis and is extremely high in accuracy.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way. Any simple modification, change and equivalent changes of the above embodiments according to the technical essence of the invention are still within the protection scope of the technical solution of the invention.
Claims (8)
1. A pathological feature mining method for pancreatitis patients is characterized by comprising the following steps:
obtaining a labeled sample pulse signal curve, wherein the label is used for distinguishing individuals corresponding to the sample pulse signal curve from non-pancreatitis patients or pancreatitis patients;
dividing the sample pulse signal curve according to periods to obtain each single-period curve;
extracting the basic time domain characteristics of each single-period curve;
extracting a stability index and a double-peak index of each single-period curve as a case characteristic of pancreatitis of the corresponding single-period curve, wherein the double-peak index represents two peak values and an obvious concave arc structure in the single-period curve; the stability index is used for representing the change rate of the second half part of the single-period curve;
and (3) forming input feature vectors by the basic time domain features of the pulse signal curves of all samples and the case features of pancreatitis, inputting the input feature vectors into the classification model, supervising by using the labels corresponding to all samples, and training to obtain the trained classification model.
2. The method for mining pathological features of pancreatitis patients according to claim 1, wherein said tags are classified into patient tags and non-patient tags;
the trained classification model further comprises:
acquiring a pulse signal curve of a person to be diagnosed;
inputting the feature vectors composed of the basic time domain features of all the single-period curves and the case features of pancreatitis into a trained classification model in the pulse signal curve of the person to be diagnosed to obtain a diagnosis label set; each label in the diagnosis label set corresponds to the monocycle curve one by one;
and if the occurrence frequency of the patient labels in the diagnosis label set is greater than a preset threshold, determining that the person to be diagnosed is a suspected pancreatitis patient.
3. The method for mining pathological features of patients with pancreatitis according to claim 1 or 2, characterized in that the stability index for extracting each monocycle curve is specifically: the method comprises the following steps of selecting a plurality of sampling points in a single-period curve, and calculating through a first formula to obtain the variance of each sampling point, wherein the variances of all the sampling points are used for expressing the stability index of the pulse single-period signal of each single-period curve, and the first formula is as follows:
in the first formula, N represents the number of sampling points in a single-period curve, N represents the number of sampling points in the whole period of a sample pulse signal curve, and SFDenotes the sampling frequency, t denotes the start position of the sampling point, DiRepresents the variance of the sample point at i, where i is a positive integer from 0 to N, and the parameter XiAbsolute coordinate value, x, representing a sample point on the abscissa iiAbscissa, y, representing the sample point at iiThe ordinate of the sample point at i is indicated.
4. The pathological feature mining method for pancreatitis patients according to claim 1 or 2, characterized in that the sampling frequency is 2 times of the beating frequency of human pulse.
5. The method for mining pathological features of patients with pancreatitis according to claim 1 or 2, characterized in that the extraction of the double-peaked index of each monocycle curve specifically comprises: selecting a plurality of sampling points in a single-period curve, obtaining the mean value of the longitudinal coordinate values of each sampling point of a non-pancreatitis patient through calculation, calculating the sum of the differences of the longitudinal coordinate values of the sampling points between two peaks in the single-period curve and the mean value of the longitudinal coordinate values of the same sampling points of the non-pancreatitis patient through a second formula, and using the sum as a double-peak index; the second formula is as follows:
in the second formula, Y represents a data set of longitudinal coordinates of sampling points, N represents the number of the sampling points in the whole period of the sample pulse signal curve, N represents the number of the sampling points in the single-period curve, T represents the point with the highest numerical value of the longitudinal coordinates in the single-period pulse signal curve, T represents the point with the second highest numerical value of the longitudinal coordinates in the single-period curve, and SFRepresenting the sampling frequency, A representing the mean value of the ordinate values of each sampling point of a normal person, BiRepresents the sum of the difference of the value of the ordinate of the sampling point at i of the pancreatitis patient and A.
6. The method of claim 1 or 2, wherein the basic temporal features of each monocycle pulse signal curve comprise a first peak height, a second peak height, a third peak height, a first peak to second peak time interval, a second peak to third peak time interval, a pulse onset to first trough time interval, a first trough to second trough time interval, and a second trough to pulse onset time interval.
7. The pathological feature mining method for pancreatitis patients of claim 2, wherein the pulse signal curve of the person to be diagnosed is at least one single-cycle pulse signal curve.
8. The pancreatitis patient-oriented pathological feature mining method of claim 1, wherein the classification model is trained by using an SVM kernel method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111484127.1A CN114145722B (en) | 2021-12-07 | 2021-12-07 | Pulse pathological feature mining method for pancreatitis patients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111484127.1A CN114145722B (en) | 2021-12-07 | 2021-12-07 | Pulse pathological feature mining method for pancreatitis patients |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114145722A true CN114145722A (en) | 2022-03-08 |
| CN114145722B CN114145722B (en) | 2023-08-01 |
Family
ID=80452959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111484127.1A Active CN114145722B (en) | 2021-12-07 | 2021-12-07 | Pulse pathological feature mining method for pancreatitis patients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114145722B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2482793C1 (en) * | 2012-01-11 | 2013-05-27 | Учреждение Российской академии наук Институт химической биологии и фундаментальной медицины Сибирского отделения РАН (ИХБФМ СО РАН) | Method of differential diagnostics of acute pancreatitis forms in experiment |
| US20140073966A1 (en) * | 2012-09-11 | 2014-03-13 | Nellcor Puritan Bennett Llc | Methods and systems for determining algorithm settings for use in determining physiological information |
| US20140081152A1 (en) * | 2012-09-14 | 2014-03-20 | Nellcor Puritan Bennett Llc | System and method for determining stability of cardiac output |
| CN103932686A (en) * | 2014-04-22 | 2014-07-23 | 北京印刷学院 | Method and device for extracting pulse condition signal |
| US20200211707A1 (en) * | 2018-12-28 | 2020-07-02 | National Cheng Kung University | System and method for predicting types of pathogens in patients with septicemia |
| CN112842288A (en) * | 2021-01-29 | 2021-05-28 | 清华大学深圳国际研究生院 | Pulse data classification model establishing device, classification recognition device and measurement system |
-
2021
- 2021-12-07 CN CN202111484127.1A patent/CN114145722B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2482793C1 (en) * | 2012-01-11 | 2013-05-27 | Учреждение Российской академии наук Институт химической биологии и фундаментальной медицины Сибирского отделения РАН (ИХБФМ СО РАН) | Method of differential diagnostics of acute pancreatitis forms in experiment |
| US20140073966A1 (en) * | 2012-09-11 | 2014-03-13 | Nellcor Puritan Bennett Llc | Methods and systems for determining algorithm settings for use in determining physiological information |
| US20140081152A1 (en) * | 2012-09-14 | 2014-03-20 | Nellcor Puritan Bennett Llc | System and method for determining stability of cardiac output |
| CN103932686A (en) * | 2014-04-22 | 2014-07-23 | 北京印刷学院 | Method and device for extracting pulse condition signal |
| US20200211707A1 (en) * | 2018-12-28 | 2020-07-02 | National Cheng Kung University | System and method for predicting types of pathogens in patients with septicemia |
| CN112842288A (en) * | 2021-01-29 | 2021-05-28 | 清华大学深圳国际研究生院 | Pulse data classification model establishing device, classification recognition device and measurement system |
Non-Patent Citations (1)
| Title |
|---|
| CHOW WH 等: "Wrist Pulse Signal Classification for Inflammation of Appendix, Pancreas, and Duodenum", ECON 2014 - 40TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, pages 2479 - 2483 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114145722B (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Altan et al. | Deep learning with 3D-second order difference plot on respiratory sounds | |
| Rong et al. | A multi-type features fusion neural network for blood pressure prediction based on photoplethysmography | |
| Susam et al. | Automated pain assessment using electrodermal activity data and machine learning | |
| CN111067503A (en) | Sleep staging method based on heart rate variability | |
| CN113499035B (en) | Pain identification system based on confidence interval fusion threshold criterion | |
| Liu et al. | Motion artifact detection in ppg signals based on gramian angular field and 2-d-cnn | |
| Rajput et al. | Automated detection of hypertension using wavelet transform and nonlinear techniques with ballistocardiogram signals | |
| Benchekroun et al. | Comparison of Stress Detection through ECG and PPG signals using a Random Forest-based Algorithm | |
| Lu et al. | Pulse feature extraction based on improved gaussian model | |
| Meng et al. | Deep learning-based arrhythmia detection in electrocardiograph | |
| Wang et al. | Single-lead ECG based multiscale neural network for obstructive sleep apnea detection | |
| CN114145722B (en) | Pulse pathological feature mining method for pancreatitis patients | |
| CN115836847A (en) | Blood pressure prediction device and equipment | |
| CN115089145A (en) | Intelligent blood pressure prediction method based on multi-scale residual error network and PPG signal | |
| JP7216408B2 (en) | Device for determining sleep apnea syndrome, method for determining sleep apnea syndrome, and program for determining sleep apnea syndrome | |
| Zhang et al. | Computerized radial artery pulse signal classification for lung cancer detection | |
| CN113425298A (en) | Method for analyzing depression degree by collecting data through wearable equipment | |
| Shilvya et al. | Obstructive Sleep Apnea Detection from ECG Signals with Deep Learning | |
| Kumar et al. | INSOMNet: Automated insomnia detection using scalogram and deep neural networks with ECG signals | |
| Chen et al. | A novel real-time depth of anaesthesia monitoring method using detrended fluctuation analysis and ann | |
| Savostin et al. | DEVISING A METHOD FOR PREDICTING A BLOOD PRESSURE LEVEL BASED ON ELECTROCARDIOGRAM AND PHOTOPLETHYSMOGRAM SIGNALS. | |
| Kim et al. | Untact Abnormal Heartbeat Wave Detection Using Non-Contact Sensor through Transfer Learning | |
| Vyas et al. | Sleep Stage Classification Using Non-Invasive Bed Sensing and Deep Learning | |
| Lin et al. | Research on feature mining algorithm and disease diagnosis of pulse signal based on piezoelectric sensor | |
| Kandukuri et al. | Constant Q–Transform–Based Deep Learning Architecture for Detection of Obstructive Sleep Apnea |
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 |