CN118098492A - Administration return visit task management method and system for chronic obstructive pulmonary disease patient - Google Patents
Administration return visit task management method and system for chronic obstructive pulmonary disease patient Download PDFInfo
- Publication number
- CN118098492A CN118098492A CN202410487374.4A CN202410487374A CN118098492A CN 118098492 A CN118098492 A CN 118098492A CN 202410487374 A CN202410487374 A CN 202410487374A CN 118098492 A CN118098492 A CN 118098492A
- Authority
- CN
- China
- Prior art keywords
- patient
- medication
- value
- portrait
- time
- 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
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 title claims abstract description 25
- 238000007726 management method Methods 0.000 title description 12
- 239000003814 drug Substances 0.000 claims abstract description 150
- 229940079593 drug Drugs 0.000 claims abstract description 107
- 238000000034 method Methods 0.000 claims abstract description 59
- 238000010276 construction Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 2
- 208000017667 Chronic Disease Diseases 0.000 description 4
- 238000011084 recovery Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013123 lung function test Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of intelligent service, and particularly discloses a method and a system for managing medication return visit tasks of chronic obstructive pulmonary disease patients, wherein the method comprises the steps of acquiring time-containing physical parameters of the patients according to authority granted by the patients, and constructing patient portraits according to the physical parameters; inquiring medication information of each patient, and assigning a value to the patient portrait according to the medication information; clustering the assigned patient portraits, and synchronously extracting the mean value portraits of each type of patient portraits; for any patient, the body parameters of the patient are recorded in real time according to the authority granted to the patient, the mean portrait is matched according to the body parameters, and a medication prompt is generated according to the assignment condition of the mean portrait. According to the invention, a large number of physical data and medication conditions of patients are counted, a patient portrait is constructed, when a new patient needs to be evaluated, a short-time portrait is constructed, and the short-time portrait is matched with a counted sample to obtain medication references, so that the working pressure of a medication scheme provider is greatly relieved.
Description
Technical Field
The invention relates to the technical field of intelligent service, in particular to a medication return visit task management method and system for chronic obstructive pulmonary disease patients.
Background
Chronic obstructive pulmonary disease (Chronic Obstructive Pulmonary Disease, COPD) is a common chronic disease that has a great impact on the daily life and health status of the patient and therefore requires regular revisits.
In the recovery process of chronic diseases, different physical conditions and different medication histories can influence the final medication result, which puts forward high requirements on medication scheme providers, the recovery process of chronic diseases has high similarity, and the recovery process of chronic diseases can relieve the pressure of the medication scheme providers, and how to assist the medication scheme providers and relieve the working pressure of the medication scheme providers is a technical problem to be solved by the technical scheme of the invention.
Disclosure of Invention
The invention aims to provide a medication return visit task management method and system for chronic obstructive pulmonary disease patients, so as to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A method of administration return visit task management for a patient with chronic obstructive pulmonary disease, the method comprising:
Acquiring a time-containing body parameter of a patient according to the authority granted by the patient, and constructing a patient portrait according to the body parameter; the patient representation is a curve set;
inquiring medication information of each patient, and assigning a value to the patient portrait according to the medication information;
clustering the assigned patient portraits, and synchronously extracting the mean value portraits of each type of patient portraits;
for any patient, the body parameters of the patient are recorded in real time according to the authority granted to the patient, the mean portrait is matched according to the body parameters, and a medication prompt is generated according to the assignment condition of the mean portrait.
As a further scheme of the invention: the step of obtaining a temporal-containing body parameter of the patient according to the rights granted by the patient and constructing a representation of the patient according to said body parameter comprises:
Receiving a return visit management request uploaded by a patient, and applying for inquiry data acquisition permission to the patient;
when receiving the inquiry data acquisition permission granted by the patient, acquiring the physical index containing the time stamp of the patient and the numerical value thereof;
forward-converting the numerical value based on the body index, and inserting the forward-converted numerical value into the same coordinate system; the horizontal axis of the coordinate system is time, the vertical axis is a numerical value, and each body index corresponds to a unique vertical axis section; the corresponding relation between the body index and the vertical axis section is preset by staff;
Fitting the inserted values in time sequence at each vertical axis segment to generate a curve; when all values of the vertical axis segments are fit, the curve set is taken as a patient representation.
As a further scheme of the invention: the forward direction process is as follows:
；
In the method, in the process of the invention, Is a numerical value after forward conversion,/>For the value before correction,/>For the optimal interval corresponding to the body index,/>；/>Is the minimum value of all the values corresponding to the body index,/>The maximum value of all the values corresponding to the body index;
the fitting process is as follows:
sequentially connecting adjacent coordinates according to time sequence to obtain N folding lines;
fitting the N fold lines to obtain a curve;
wherein, the fitting process is a recursion process, and the recursion rule is:
; in the/> A position on the curve is indicated,The initial point is indicated when the value is 0, and the end point is indicated when the value is 1.
As a further scheme of the invention: the step of inquiring the medication information of each patient and assigning the patient portrait according to the medication information comprises the following steps:
Acquiring medication information of a patient, wherein the medication information contains a time stamp;
marking the medication point in the horizontal axis of the patient representation according to the time stamp;
Determining characteristic values at other moments based on the administration points, and assigning values to the corresponding positions of all curves at the moments based on the characteristic values;
the determination process of the characteristic value is as follows:
; in the/> N is the number of the administration points and is the characteristic value at the time t/(The medicine taking value is the medicine taking value of the kth medicine taking point, the medicine taking value is determined by medicine taking information, and the corresponding relation between the medicine taking information and the medicine taking value is preset by staff; /(I)Is the time difference between the kth administration point and the time t.
As a further scheme of the invention: the step of clustering the assigned patient portraits and synchronously extracting the mean value portraits of each type of patient portraits comprises the following steps:
Converting the format of the assigned patient portrait into a picture;
obtaining a histogram of the picture, comparing the histogram, and clustering the picture according to the comparison result;
calculating the numerical value average value of each curve at each moment for each type of patient portrait, and calculating the assigned average value of each curve at each moment to obtain an average value curve;
Counting a mean curve to obtain a mean portrait;
The comparison process of the histograms is as follows:
And converting the histogram into an array, calculating the Euclidean distance of the array, and determining the similarity of the histogram based on the Euclidean distance according to the Euclidean distance, wherein the similarity is inversely proportional to the Euclidean distance.
As a further scheme of the invention: the step of recording the physical parameters of any patient in real time according to the granted authority of the patient, matching the mean portrait according to the physical parameters, and generating a medication prompt according to the assignment condition of the mean portrait comprises the following steps:
when acquiring the acquisition right of the inquiry data granted to any patient, recording the physical index and the numerical value thereof in a time period;
Constructing a short-term representation of the patient based on a construction process of the patient representation;
traversing the existing average value portrait according to the short-time portrait to match the target portrait;
And extracting an assignment in the next time period from the target portrait, generating a medication prompt according to the assignment result, and sending the medication prompt to the patient.
The technical scheme of the invention also provides a medication return visit task management system for patients with chronic obstructive pulmonary disease, which comprises the following steps:
The patient portrait construction module is used for acquiring time-containing body parameters of a patient according to rights granted by the patient and constructing a patient portrait according to the body parameters; the patient representation is a curve set;
The patient portrait assignment module is used for inquiring the medication information of each patient and assigning values to the patient portraits according to the medication information;
the mean value portrait extraction module is used for clustering the assigned patient portraits and synchronously extracting the mean value portraits of each type of patient portraits;
The information matching module is used for recording the physical parameters of any patient in real time according to the granted authority of the patient, matching the mean portrait according to the physical parameters and generating a medication prompt according to the assignment condition of the mean portrait.
As a further scheme of the invention: the patient representation construction module comprises:
The right acquisition unit is used for receiving a return visit management request uploaded by a patient and applying inquiry data acquisition right to the patient;
the system comprises a value acquisition unit, a time stamp acquisition unit and a data processing unit, wherein the value acquisition unit is used for acquiring a physical index containing a time stamp of a patient and a value thereof when receiving inquiry data acquisition permission granted by the patient;
The forward unit is used for forward converting the numerical value based on the body index and inserting the forward numerical value into the same coordinate system; the horizontal axis of the coordinate system is time, the vertical axis is a numerical value, and each body index corresponds to a unique vertical axis section; the corresponding relation between the body index and the vertical axis section is preset by staff;
The numerical fitting unit is used for fitting the inserted numerical values in time sequence when each vertical axis section is used for generating a curve; when all values of the vertical axis segments are fit, the curve set is taken as a patient representation.
As a further scheme of the invention: the patient representation assignment module includes:
the medication information acquisition unit is used for acquiring medication information of a patient, wherein the medication information contains a time stamp;
A medication point marking unit for marking medication points in a horizontal axis of the patient representation based on the time stamps;
the assignment execution unit is used for determining the characteristic values of other moments based on the medication points and assigning the corresponding positions of all curves at the moments based on the characteristic values;
the determination process of the characteristic value is as follows:
; in the/> N is the number of the administration points and is the characteristic value at the time t/(The medicine taking value is the medicine taking value of the kth medicine taking point, the medicine taking value is determined by medicine taking information, and the corresponding relation between the medicine taking information and the medicine taking value is preset by staff; /(I)Is the time difference between the kth administration point and the time t.
As a further scheme of the invention: the mean value portrait extraction module comprises:
The format conversion unit is used for carrying out format conversion on the assigned patient portrait and converting the patient portrait into a picture;
the clustering unit is used for acquiring the histogram of the picture, comparing the histogram and clustering the picture according to the comparison result;
the average value calculation unit is used for calculating the numerical average value of each curve at each moment for each type of patient portrait, and calculating the assigned average value of each curve at each moment to obtain an average value curve;
The statistics unit is used for counting the mean curve to obtain a mean portrait;
The comparison process of the histograms is as follows:
And converting the histogram into an array, calculating the Euclidean distance of the array, and determining the similarity of the histogram based on the Euclidean distance according to the Euclidean distance, wherein the similarity is inversely proportional to the Euclidean distance.
Compared with the prior art, the invention has the beneficial effects that: on the premise of having authority, the invention counts the body data and the medication condition of a large number of patients, constructs the patient portrait, constructs the short-term patient portrait by adopting the same process when a new patient needs to be evaluated, and then matches the short-term patient portrait with the counted sample to obtain medication references, and at the moment, the medication scheme provider only needs to carry out fine adjustment, thereby greatly relieving the working pressure.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a flow chart of a method for managing medication return visit tasks for patients with chronic obstructive pulmonary disease.
Fig. 2 is a block diagram showing the construction of a medication return visit task management system for patients with chronic obstructive pulmonary disease.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flow chart of a method for managing a medication return visit task for a patient with chronic obstructive pulmonary disease, in an embodiment of the present invention, a method for managing a medication return visit task for a patient with chronic obstructive pulmonary disease, the method includes:
Step S100: acquiring a time-containing body parameter of a patient according to the authority granted by the patient, and constructing a patient portrait according to the body parameter; the patient representation is a curve set;
Step S200: inquiring medication information of each patient, and assigning a value to the patient portrait according to the medication information;
Step S300: clustering the assigned patient portraits, and synchronously extracting the mean value portraits of each type of patient portraits;
Step S400: for any patient, the body parameters of the patient are recorded in real time according to the authority granted to the patient, the mean portrait is matched according to the body parameters, and a medication prompt is generated according to the assignment condition of the mean portrait.
The physical parameters of the patient and the medicine information belong to the privacy of the patient, and the rights granted definitely by the patient must be obtained to carry out the subsequent steps; under the framework of the technical scheme, when a patient needs to prompt the execution main body of the method according to actual conditions, the permission is granted, and the execution main body of the method can provide services, which is equivalent to building a data sharing platform.
Specifically, after receiving the authority granted by the patient, acquiring body parameters at each return visit, wherein the body parameters are various indexes and specific values thereof, and the conventional indexes mainly comprise lung function test indexes including vital capacity (Forced VITAL CAPACITY, FVC): the patient exhales the expelled air volume as soon as possible after maximum inhalation. One second effort exhalation volume (Forced Expiratory Volume in one second, FEV 1): the patient exhales the air volume expelled after 1 second as soon as possible after maximum inhalation. FEV1/FVC ratio: the ratio of FEV1 to FVC is used to evaluate the percentage of expiratory flow. Maximum expiratory flow-pulmonary function check (Maximal Expiratory Flow, MEF): the expiratory flow rate at maximum effort expiration is evaluated. In addition, there are other indexes, such as blood indexes or imaging indexes, and the method execution body converts the data into numerical values according to preset rules in consideration of the processing difficulty of the data, no matter what the indexes are.
And each moment corresponds to a plurality of body indexes and numerical values thereof, the numerical values are counted according to a time sequence, the numerical values of the same index are fitted into curves, so that a plurality of curves are obtained, the curves are counted according to the same time axis, and the obtained curve set is called a patient image.
On the basis, the medication information of the patient at each moment is queried, the medication information is filled into the patient image according to a preset rule, at the moment, the patient information simultaneously comprises the medication information and the physical parameters after medication, the two pieces of information can be used for summarizing similar patients into one type, the more the number of patients is, the more the samples are, the more the number of classified types is, and the more the follow-up matching process is accurate. In the classifying process, mean portraits of each class are synchronously calculated.
Finally, to the application stage, for each patient, a short-time portrait is constructed by adopting a patient portrait construction scheme in a period of time, such as one week or one month, the short-time portrait has the same data structure as the patient portrait, the difference is the data quantity, various patient portraits are traversed by the short-time portrait, the best matched patient portraits are determined, and medication information in the patient portraits generates medication prompts.
In addition, in the process of traversing various patient portraits by short-time portraits, only the body indexes and the numerical values thereof can be compared, namely, the medication information is not considered.
As a preferred embodiment of the present invention, step S100 is specifically described, where the step of obtaining the physical parameter of the patient including the time according to the authority granted by the patient, and constructing the representation of the patient according to the physical parameter includes:
Receiving a return visit management request uploaded by a patient, and applying for inquiry data acquisition permission to the patient;
when receiving the inquiry data acquisition permission granted by the patient, acquiring the physical index containing the time stamp of the patient and the numerical value thereof;
forward-converting the numerical value based on the body index, and inserting the forward-converted numerical value into the same coordinate system; the horizontal axis of the coordinate system is time, the vertical axis is a numerical value, and each body index corresponds to a unique vertical axis section; the corresponding relation between the body index and the vertical axis section is preset by staff;
Fitting the inserted values in time sequence at each vertical axis segment to generate a curve; when all values of the vertical axis segments are fit, the curve set is taken as a patient representation.
Receiving a return visit management request uploaded by a patient means that the patient needs an execution subject of the method to provide services for the patient, at the moment, the patient is applied with inquiry data acquisition rights, and the patient directly or indirectly grants the inquiry data acquisition rights.
The method and the device are used for acquiring the physical index and the numerical value thereof of the patient in each inquiry process based on the inquiry data acquisition permission, and for enabling the image of the patient to be more practical, all the numerical values are forward-oriented, namely, the closer the numerical value is to a certain range, the more normal the physical index is indicated.
And determining coordinates according to the time and the forward numerical value, and fitting all the coordinates to obtain curves corresponding to each body index, thereby obtaining a curve set serving as a patient portrait. In order to ensure that different curves are mutually independent, the longitudinal axis is segmented in advance by a worker, so that each body index corresponds to a certain section of the longitudinal axis.
As a preferred embodiment of the technical scheme of the invention, the forward direction process is as follows:
；
In the method, in the process of the invention, Is a numerical value after forward conversion,/>For the value before correction,/>For the optimal interval corresponding to the body index,/>；/>Is the minimum value of all the values corresponding to the body index,/>The maximum value of all the values corresponding to the body index;
the fitting process is as follows:
sequentially connecting adjacent coordinates according to time sequence to obtain N folding lines;
fitting the N fold lines to obtain a curve;
wherein, the fitting process is a recursion process, and the recursion rule is:
; in the/> A position on the curve is indicated,The initial point is indicated when the value is 0, and the end point is indicated when the value is 1.
With respect to step S200 in the foregoing, the step of querying medication information of each patient and assigning a value to the patient portrait according to the medication information includes:
Acquiring medication information of a patient, wherein the medication information contains a time stamp;
marking the medication point in the horizontal axis of the patient representation according to the time stamp;
And determining characteristic values at other moments based on the administration points, and assigning corresponding positions of all curves at the moments based on the characteristic values.
The purpose of assigning the patient portrait by using the medication information is very simple, namely, parameters reflecting the medication conditions are introduced into the patient portrait, the introduction mode is to adjust the display process of the curves, different display values correspond to different medication conditions, and in order to simplify the operation, the characteristic values in the content are generally converted into single gray values, and then each curve is assigned.
The determination process of the characteristic value is as follows:
; in the/> N is the number of the administration points and is the characteristic value at the time t/(The medicine taking value is the medicine taking value of the kth medicine taking point, the medicine taking value is determined by medicine taking information, and the corresponding relation between the medicine taking information and the medicine taking value is preset by staff; /(I)Is the time difference between the kth administration point and the time t.
With respect to step S300 in the foregoing, the step of clustering the assigned patient portraits and synchronously extracting the mean portraits of each type of patient portraits includes:
Converting the format of the assigned patient portrait into a picture;
obtaining a histogram of the picture, comparing the histogram, and clustering the picture according to the comparison result;
calculating the numerical value average value of each curve at each moment for each type of patient portrait, and calculating the assigned average value of each curve at each moment to obtain an average value curve;
Counting a mean curve to obtain a mean portrait;
The comparison process of the histograms is as follows:
And converting the histogram into an array, calculating the Euclidean distance of the array, and determining the similarity of the histogram based on the Euclidean distance according to the Euclidean distance, wherein the similarity is inversely proportional to the Euclidean distance.
The application provides a scheme which is characterized in that the patient portraits are pictures, then the similarity condition is judged by means of a similarity evaluation scheme of the pictures, and then the patient portraits with higher similarity are classified.
Specifically, the picture similarity evaluation scheme adopts a histogram comparison principle, firstly extracts a histogram at the picture, compares the histograms, and calculates the similarity of the histograms as the similarity of the pictures.
For the same type of patient portraits, calculating the average value of the curves of each body index at each moment, and then counting the average value to obtain an average value curve; in addition, for each point on each curve at each moment, the assigned result is read, and the average value is synchronously calculated and used as the assigned average value. Since the assignment of different curves is synchronous, the assignment of the mean value can be performed after the generation of the mean value curve.
It should be noted that the above average means the average of different images in the same type of patient image.
As a preferred embodiment of the technical scheme of the present invention, step S400 is specifically described, wherein the step of recording the physical parameters of any patient in real time according to the authority granted to the patient, matching the mean portrait according to the physical parameters, and generating the medication prompt according to the assignment condition of the mean portrait comprises:
when acquiring the acquisition right of the inquiry data granted to any patient, recording the physical index and the numerical value thereof in a time period;
Constructing a short-term representation of the patient based on a construction process of the patient representation;
traversing the existing average value portrait according to the short-time portrait to match the target portrait;
And extracting an assignment in the next time period from the target portrait, generating a medication prompt according to the assignment result, and sending the medication prompt to the patient.
Step S400 is an application process, wherein for each patient, a patient portrait in a time period is constructed by adopting the schemes from step S101 to step S104, which is called a short-time portrait, and then the patient portrait is compared with the average portraits of various patient portraits to determine the most matched average portraits, which is called a target portrait; and then, reading the assignment condition of the curve in the next time period, wherein the assignment condition represents the medication information, and sending medication prompts to patients according to the medication information obtained by reverse pushing, so that a prompt framework of similar patients to the current patients can be constructed, and the accuracy is high.
Fig. 2 is a block diagram of a system for managing a medication return visit task for a patient with chronic obstructive pulmonary disease, in which the system 10 includes:
A patient portrayal construction module 11 for acquiring a time-containing body parameter of a patient according to rights granted by the patient and constructing a patient portrayal according to the body parameter; the patient representation is a curve set;
a patient representation assignment module 12 for querying medication information of each patient and assigning a value to the patient representation based on the medication information;
the mean value portrait extraction module 13 is used for clustering the assigned patient portraits and synchronously extracting the mean value portraits of each type of patient portraits;
The information matching module 14 is used for recording the physical parameters of any patient in real time according to the granted authority of the patient, matching the mean portrait according to the physical parameters, and generating a medication prompt according to the assignment condition of the mean portrait.
Further, the patient portrait construction module 11 includes:
The right acquisition unit is used for receiving a return visit management request uploaded by a patient and applying inquiry data acquisition right to the patient;
the system comprises a value acquisition unit, a time stamp acquisition unit and a data processing unit, wherein the value acquisition unit is used for acquiring a physical index containing a time stamp of a patient and a value thereof when receiving inquiry data acquisition permission granted by the patient;
The forward unit is used for forward converting the numerical value based on the body index and inserting the forward numerical value into the same coordinate system; the horizontal axis of the coordinate system is time, the vertical axis is a numerical value, and each body index corresponds to a unique vertical axis section; the corresponding relation between the body index and the vertical axis section is preset by staff;
The numerical fitting unit is used for fitting the inserted numerical values in time sequence when each vertical axis section is used for generating a curve; when all values of the vertical axis segments are fit, the curve set is taken as a patient representation.
Specifically, the patient representation assignment module 12 includes:
the medication information acquisition unit is used for acquiring medication information of a patient, wherein the medication information contains a time stamp;
A medication point marking unit for marking medication points in a horizontal axis of the patient representation based on the time stamps;
the assignment execution unit is used for determining the characteristic values of other moments based on the medication points and assigning the corresponding positions of all curves at the moments based on the characteristic values;
the determination process of the characteristic value is as follows:
; in the/> N is the number of the administration points and is the characteristic value at the time t/(The medicine taking value is the medicine taking value of the kth medicine taking point, the medicine taking value is determined by medicine taking information, and the corresponding relation between the medicine taking information and the medicine taking value is preset by staff; /(I)Is the time difference between the kth administration point and the time t.
In addition, the mean value image extraction module 13 includes:
The format conversion unit is used for carrying out format conversion on the assigned patient portrait and converting the patient portrait into a picture;
the clustering unit is used for acquiring the histogram of the picture, comparing the histogram and clustering the picture according to the comparison result;
the average value calculation unit is used for calculating the numerical average value of each curve at each moment for each type of patient portrait, and calculating the assigned average value of each curve at each moment to obtain an average value curve;
The statistics unit is used for counting the mean curve to obtain a mean portrait;
The comparison process of the histograms is as follows:
And converting the histogram into an array, calculating the Euclidean distance of the array, and determining the similarity of the histogram based on the Euclidean distance according to the Euclidean distance, wherein the similarity is inversely proportional to the Euclidean distance.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. A method for managing medication return visit tasks for patients with chronic obstructive pulmonary disease, the method comprising:
Acquiring a time-containing body parameter of a patient according to the authority granted by the patient, and constructing a patient portrait according to the body parameter; the patient representation is a curve set;
inquiring medication information of each patient, and assigning a value to the patient portrait according to the medication information;
clustering the assigned patient portraits, and synchronously extracting the mean value portraits of each type of patient portraits;
for any patient, the body parameters of the patient are recorded in real time according to the authority granted to the patient, the mean portrait is matched according to the body parameters, and a medication prompt is generated according to the assignment condition of the mean portrait.
2. A method of managing medication return visit tasks for patients with chronic obstructive pulmonary disease according to claim 1, wherein said step of obtaining a patient's temporal-containing physical parameters based on rights granted by the patient, and constructing a patient representation based on said physical parameters comprises:
Receiving a return visit management request uploaded by a patient, and applying for inquiry data acquisition permission to the patient;
when receiving the inquiry data acquisition permission granted by the patient, acquiring the physical index containing the time stamp of the patient and the numerical value thereof;
forward-converting the numerical value based on the body index, and inserting the forward-converted numerical value into the same coordinate system; the horizontal axis of the coordinate system is time, the vertical axis is a numerical value, and each body index corresponds to a unique vertical axis section; the corresponding relation between the body index and the vertical axis section is preset by staff;
Fitting the inserted values in time sequence at each vertical axis segment to generate a curve; when all values of the vertical axis segments are fit, the curve set is taken as a patient representation.
3. The method for managing medication return visit tasks of patients with chronic obstructive pulmonary disease according to claim 2, wherein the forward direction is as follows:
；
In the method, in the process of the invention, Is a numerical value after forward conversion,/>For the value before correction,/>For the optimal interval corresponding to the physical index,；/>Is the minimum value of all the values corresponding to the body index,/>The maximum value of all the values corresponding to the body index;
the fitting process is as follows:
sequentially connecting adjacent coordinates according to time sequence to obtain N folding lines;
fitting the N fold lines to obtain a curve;
wherein, the fitting process is a recursion process, and the recursion rule is:
; in the/> Representing a position on the curve,/>The initial point is indicated when the value is 0, and the end point is indicated when the value is 1.
4. The method for managing medication return visit tasks for patients with chronic obstructive pulmonary disease according to claim 1, wherein the step of querying medication information of each patient and assigning a value to a patient representation based on the medication information comprises:
Acquiring medication information of a patient, wherein the medication information contains a time stamp;
marking the medication point in the horizontal axis of the patient representation according to the time stamp;
Determining characteristic values at other moments based on the administration points, and assigning values to the corresponding positions of all curves at the moments based on the characteristic values;
the determination process of the characteristic value is as follows:
; in the/> N is the number of the administration points and is the characteristic value at the time t/(The medicine taking value is the medicine taking value of the kth medicine taking point, the medicine taking value is determined by medicine taking information, and the corresponding relation between the medicine taking information and the medicine taking value is preset by staff; /(I)Is the time difference between the kth administration point and the time t.
5. The method for managing medication return visit tasks for patients with chronic obstructive pulmonary disease according to claim 1, wherein the step of clustering the assigned patient portraits and synchronously extracting the mean portraits of each type of patient portraits comprises:
Converting the format of the assigned patient portrait into a picture;
obtaining a histogram of the picture, comparing the histogram, and clustering the picture according to the comparison result;
calculating the numerical value average value of each curve at each moment for each type of patient portrait, and calculating the assigned average value of each curve at each moment to obtain an average value curve;
Counting a mean curve to obtain a mean portrait;
The comparison process of the histograms is as follows:
And converting the histogram into an array, calculating the Euclidean distance of the array, and determining the similarity of the histogram based on the Euclidean distance according to the Euclidean distance, wherein the similarity is inversely proportional to the Euclidean distance.
6. The method for managing medication return visit tasks of chronic obstructive pulmonary disease patients according to claim 1, wherein the step of recording the physical parameters of any patient in real time according to the rights granted to the patient, matching the mean portrait according to the physical parameters, and generating medication prompts according to the assignment of the mean portrait comprises:
when acquiring the acquisition right of the inquiry data granted to any patient, recording the physical index and the numerical value thereof in a time period;
Constructing a short-term representation of the patient based on a construction process of the patient representation;
traversing the existing average value portrait according to the short-time portrait to match the target portrait;
And extracting an assignment in the next time period from the target portrait, generating a medication prompt according to the assignment result, and sending the medication prompt to the patient.
7. A medication return visit task management system for a patient with chronic obstructive pulmonary disease, the system comprising:
The patient portrait construction module is used for acquiring time-containing body parameters of a patient according to rights granted by the patient and constructing a patient portrait according to the body parameters; the patient representation is a curve set;
The patient portrait assignment module is used for inquiring the medication information of each patient and assigning values to the patient portraits according to the medication information;
the mean value portrait extraction module is used for clustering the assigned patient portraits and synchronously extracting the mean value portraits of each type of patient portraits;
The information matching module is used for recording the physical parameters of any patient in real time according to the granted authority of the patient, matching the mean portrait according to the physical parameters and generating a medication prompt according to the assignment condition of the mean portrait.
8. The chronic obstructive pulmonary disease patient medication return visit task management system of claim 7, wherein the patient representation construction module comprises:
The right acquisition unit is used for receiving a return visit management request uploaded by a patient and applying inquiry data acquisition right to the patient;
the system comprises a value acquisition unit, a time stamp acquisition unit and a data processing unit, wherein the value acquisition unit is used for acquiring a physical index containing a time stamp of a patient and a value thereof when receiving inquiry data acquisition permission granted by the patient;
The forward unit is used for forward converting the numerical value based on the body index and inserting the forward numerical value into the same coordinate system; the horizontal axis of the coordinate system is time, the vertical axis is a numerical value, and each body index corresponds to a unique vertical axis section; the corresponding relation between the body index and the vertical axis section is preset by staff;
The numerical fitting unit is used for fitting the inserted numerical values in time sequence when each vertical axis section is used for generating a curve; when all values of the vertical axis segments are fit, the curve set is taken as a patient representation.
9. The chronic obstructive pulmonary disease patient medication return visit task management system of claim 7, wherein the patient representation assignment module comprises:
the medication information acquisition unit is used for acquiring medication information of a patient, wherein the medication information contains a time stamp;
A medication point marking unit for marking medication points in a horizontal axis of the patient representation based on the time stamps;
the assignment execution unit is used for determining the characteristic values of other moments based on the medication points and assigning the corresponding positions of all curves at the moments based on the characteristic values;
the determination process of the characteristic value is as follows:
; in the/> N is the number of the administration points and is the characteristic value at the time t/(The medicine taking value is the medicine taking value of the kth medicine taking point, the medicine taking value is determined by medicine taking information, and the corresponding relation between the medicine taking information and the medicine taking value is preset by staff; /(I)Is the time difference between the kth administration point and the time t.
10. The chronic obstructive pulmonary disease patient medication return visit task management system of claim 7, wherein the mean image extraction module comprises:
The format conversion unit is used for carrying out format conversion on the assigned patient portrait and converting the patient portrait into a picture;
the clustering unit is used for acquiring the histogram of the picture, comparing the histogram and clustering the picture according to the comparison result;
the average value calculation unit is used for calculating the numerical average value of each curve at each moment for each type of patient portrait, and calculating the assigned average value of each curve at each moment to obtain an average value curve;
The statistics unit is used for counting the mean curve to obtain a mean portrait;
The comparison process of the histograms is as follows:
And converting the histogram into an array, calculating the Euclidean distance of the array, and determining the similarity of the histogram based on the Euclidean distance according to the Euclidean distance, wherein the similarity is inversely proportional to the Euclidean distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410487374.4A CN118098492B (en) | 2024-04-23 | 2024-04-23 | Administration return visit task management method and system for chronic obstructive pulmonary disease patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410487374.4A CN118098492B (en) | 2024-04-23 | 2024-04-23 | Administration return visit task management method and system for chronic obstructive pulmonary disease patient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118098492A true CN118098492A (en) | 2024-05-28 |
| CN118098492B CN118098492B (en) | 2024-06-28 |
Family
ID=91157279
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410487374.4A Active CN118098492B (en) | 2024-04-23 | 2024-04-23 | Administration return visit task management method and system for chronic obstructive pulmonary disease patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118098492B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115116569A (en) * | 2022-04-28 | 2022-09-27 | 阿斯利康投资(中国)有限公司 | A digital system for providing cancer digital disease management |
| CN115602332A (en) * | 2022-09-14 | 2023-01-13 | 杭州逸曜信息技术有限公司（Cn） | User portrait label mining method and device based on medicine data and computer equipment |
| CN117894424A (en) * | 2024-03-14 | 2024-04-16 | 四川省医学科学院·四川省人民医院 | Recommendation system for constructing T2DM patient drug scheme based on deep learning and reinforcement learning |
-
2024
- 2024-04-23 CN CN202410487374.4A patent/CN118098492B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115116569A (en) * | 2022-04-28 | 2022-09-27 | 阿斯利康投资(中国)有限公司 | A digital system for providing cancer digital disease management |
| CN115602332A (en) * | 2022-09-14 | 2023-01-13 | 杭州逸曜信息技术有限公司（Cn） | User portrait label mining method and device based on medicine data and computer equipment |
| CN117894424A (en) * | 2024-03-14 | 2024-04-16 | 四川省医学科学院·四川省人民医院 | Recommendation system for constructing T2DM patient drug scheme based on deep learning and reinforcement learning |
Non-Patent Citations (2)
| Title |
|---|
| 刘莉;朱勋梅;李俊;陈先来;周宇葵;安莹;李忠民;: "健康画像在慢阻肺个性化健康管理系统中的应用研究", 中国医学物理学杂志, no. 07, 25 July 2020 (2020-07-25) * |
| 王煜: "面向医学文献的知识抽取关键技术研究", 《中国博士学位论文全文数据库 医药卫生科技辑》, 15 January 2023 (2023-01-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118098492B (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bakeman et al. | Observer agreement for timed-event sequential data: A comparison of time-based and event-based algorithms | |
| CN107133437B (en) | The method and device that monitoring drug uses | |
| CN108553081B (en) | Diagnosis system based on tongue fur image | |
| JPH07381A (en) | Modeling method for craniofacial structure using cephalometric lateral roentgenogram | |
| CN112231670A (en) | Identity recognition system based on data processing | |
| WO2021208091A1 (en) | Neural network-based virus screening and epidemic prevention system and method | |
| CN111688711A (en) | Alcohol detection management system and method based on cloud computing | |
| CN118098492B (en) | Administration return visit task management method and system for chronic obstructive pulmonary disease patient | |
| KR20170052974A (en) | Method for Translation Correction and Server for Providing Translation Correction Service | |
| CN109189961A (en) | A kind of calculation method and system of recognition of face confidence level | |
| CN109545319B (en) | Prescription alarm method based on knowledge relation analysis and terminal equipment | |
| CN110298241A (en) | Pain information processing method, device, equipment and storage medium | |
| CN116561601B (en) | Writing scoring method, device and storage medium | |
| WO2023246352A1 (en) | Health data management method and apparatus, and electronic device and readable storage medium | |
| CN116563038A (en) | Medical insurance fee control recommendation method, system and storage medium based on regional big data | |
| US20220138947A1 (en) | Method for assessing cardiothoracic ratio and cardiothoracic ratio assessment system | |
| CN108288491B (en) | Control method, control system and storage device for automatically processing medical record data | |
| WO2021217944A1 (en) | Method and apparatus for verifying electronic signature, and computer device and storage medium | |
| US20040199407A1 (en) | System for processing data related to a partial reimbursement claim | |
| CN111653367A (en) | Respiratory infectious disease monitoring system and method based on cough symptoms | |
| CN117373585B (en) | Construction method of hemodialysis model based on artificial intelligence | |
| CN115995282B (en) | Expiratory flow data processing system based on knowledge graph | |
| CN115188483B (en) | Automatic chest pain clinical path judgment recognition management system based on big data | |
| WO2019164103A1 (en) | Lifelog-based health-related insurance rate calculating system | |
| Marks et al. | Agreement between insurance claim and self-reported hospital and emergency room utilization data among persons with diabetes |
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 |