CN116665904A - Cloud computing-based chronic disease patient health data tracking analysis system - Google Patents
Cloud computing-based chronic disease patient health data tracking analysis system Download PDFInfo
- Publication number
- CN116665904A CN116665904A CN202310944967.4A CN202310944967A CN116665904A CN 116665904 A CN116665904 A CN 116665904A CN 202310944967 A CN202310944967 A CN 202310944967A CN 116665904 A CN116665904 A CN 116665904A
- Authority
- CN
- China
- Prior art keywords
- target
- analysis
- patient
- diabetes
- analysis node
- 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
- 208000017667 Chronic Disease Diseases 0.000 title description 5
- 230000001684 chronic effect Effects 0.000 claims abstract description 15
- 206010012601 diabetes mellitus Diseases 0.000 claims description 321
- 238000012544 monitoring process Methods 0.000 claims description 138
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 104
- 235000005911 diet Nutrition 0.000 claims description 84
- 230000037213 diet Effects 0.000 claims description 81
- 201000010099 disease Diseases 0.000 claims description 76
- 239000008280 blood Substances 0.000 claims description 75
- 210000004369 blood Anatomy 0.000 claims description 75
- 230000033001 locomotion Effects 0.000 claims description 60
- 230000002354 daily effect Effects 0.000 claims description 46
- 238000012216 screening Methods 0.000 claims description 40
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 19
- 239000008103 glucose Substances 0.000 claims description 19
- 235000013305 food Nutrition 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 12
- 230000037406 food intake Effects 0.000 claims description 9
- 208000024891 symptom Diseases 0.000 claims description 9
- 235000012631 food intake Nutrition 0.000 claims description 7
- 230000003203 everyday effect Effects 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 10
- 235000021045 dietary change Nutrition 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000000378 dietary effect Effects 0.000 description 3
- 230000009693 chronic damage Effects 0.000 description 2
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 208000002249 Diabetes Complications Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000017442 Retinal disease Diseases 0.000 description 1
- 206010038923 Retinopathy Diseases 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 235000021152 breakfast Nutrition 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 229940109239 creatinine Drugs 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 210000001508 eye Anatomy 0.000 description 1
- 235000015219 food category Nutrition 0.000 description 1
- 210000002683 foot Anatomy 0.000 description 1
- 210000002216 heart Anatomy 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 208000017169 kidney disease Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000009182 swimming Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- 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 belongs to the technical field of health management of chronic patients, and particularly discloses a cloud computing-based chronic patient health data tracking analysis system.
Description
Technical Field
The invention belongs to the technical field of chronic patient health management, and particularly relates to a cloud computing-based chronic patient health data tracking analysis system.
Background
With the change of life style, the incidence rate of chronic diseases such as diabetes, hypertension, coronary heart disease and the like is increased year by year, particularly diabetes, the diabetes can cause chronic damage to various tissues of human bodies, particularly eyes, feet, kidneys, hearts, blood vessels, brains and nerves, serious consequences can be caused when the chronic damage is not treated in time, the diabetes is gradually younger due to the pursuit of high-sugar and high-calorie diet by young people and irregular work and rest, but the diabetes is lighter in symptoms and in the early stage of diabetes compared with the elderly diabetes, and the diabetes symptoms such as diet management and exercise management can be controlled by carrying out related management generally without medication for the diabetes patients.
However, for some young and middle-aged diabetics, only one management mode of diet and exercise can be selected to control blood sugar, and in order to ensure the blood sugar control effect of the diabetics, effective management means for treating diabetes need to be selected from diet management and exercise management.
It is known that when screening effective management means for treating diabetes, it is necessary to monitor the control effect of diabetes, however, in the prior art, the blood glucose monitoring result is generally used as a monitoring index of the control effect of diabetes, and neglecting diabetes complications also affects the control effect of diabetes.
In addition, in the existing effective management means corresponding to screening treatment of diabetes, in order to ensure the effectiveness of screening results, a large number of diabetes patients with middle-aged and young people are generally collected as analysis objects in order to avoid analysis errors caused by too few analysis objects, and the fact that the screening results are interfered in an intangible way due to the fact that the physical state and the disease state of each diabetes patient with middle-aged and young people have more or less individual differences is not considered, so that the analysis objects can not necessarily reduce the analysis errors for the screening results, and conversely, the effectiveness of the screening results is reduced to a great extent due to the interference of the individual differences, and ineffective screening is caused by serious people.
Disclosure of Invention
In view of this, in order to solve the problems presented in the above background art, a chronic disease patient health data tracking analysis system based on cloud computing is proposed for young and middle-aged diabetics.
The aim of the invention can be achieved by the following technical scheme: a cloud computing-based chronic patient health data tracking analysis system, comprising: and the diabetes patient information extraction module is used for extracting basic information and documenting disease information corresponding to each diabetes patient from the hospital patient library.
And the target diabetes patient screening module is used for screening out the target diabetes patients based on the basic information and the documented illness information corresponding to each diabetes patient.
And the daily management data uploading module is used for constructing a doctor-patient data transmission platform, and uploading daily management data to the platform every day by each target diabetes patient during treatment.
And the disease monitoring information extraction module is used for extracting disease monitoring information corresponding to each target diabetic patient during treatment from the patient archive, wherein the disease monitoring information comprises blood sugar monitoring information and complications monitoring information.
The analysis node dividing module is used for dividing the treatment period of each target diabetes patient into analysis nodes, dividing daily management data uploaded by each target diabetes patient into daily management data corresponding to each analysis node of each target diabetes patient based on the divided analysis nodes, and dividing the condition monitoring information corresponding to each target diabetes patient into condition monitoring information corresponding to each analysis node of each target diabetes patient.
And the analysis node illness management change analysis module is used for comparing daily management data corresponding to each analysis node with adjacent analysis nodes and analyzing change indexes corresponding to diet management and movement management of each target diabetic patient in each analysis node.
And the analysis node condition fluctuation analysis module is used for comparing condition monitoring information corresponding to each analysis node with adjacent analysis nodes and analyzing condition fluctuation indexes of each target diabetic patient at each analysis node.
The effective management means estimating module is used for estimating effective management means corresponding to diabetes treatment by taking the target diabetes patients as the diseased group.
In an alternative embodiment, the basic information includes age, gender, height, and weight, and the documented illness information includes documented illness time and documented blood glucose value.
In an alternative embodiment, the specific screening procedure for the subject diabetic patient is followed by the following steps: (1) Extracting age groups from the basic information, comparing the age groups corresponding to the diabetics, and screening the diabetics corresponding to the same age groups.
(2) Gender is extracted from the basic information, the gender corresponding to each diabetic in the diabetics corresponding to the same age range is compared, and the diabetics belonging to the same gender in the diabetics corresponding to the same age range are screened out from the basic information, so that the diabetes patients to be selected are formed.
(3) The height and the weight are extracted from the basic information, so that the body quality index corresponding to each diabetes in the diabetes group to be selected is calculated, and the diabetes corresponding to the same body quality index is selected from the body quality indexes to form the specific diabetes group.
(4) The method comprises the steps of extracting the documented illness time from the documented illness information, numbering the diabetics in the specific diabetes patient group, and further constructing a documented illness time interval corresponding to each diabetes patient in the specific diabetes patient group according to the documented illness time.
(5) According to the ordering of all diabetes patients in the specific diabetes patient group, all diabetes patients are sequentially taken as main diabetes patients, and the adjacent degree of the documenting disease duration corresponding to other diabetes patients is compared with the adjacent degree interval of the documenting disease duration corresponding to the main diabetes patients, so that a set of the documenting disease duration adjacent patients corresponding to all diabetes patients in the specific diabetes patient group is formed.
(6) And (3) extracting the documented blood sugar value from the documented illness information, and further forming a documented blood sugar similar patient set corresponding to each diabetes patient according to the same principle as the documented blood sugar value corresponding to each diabetes patient in the specific diabetes patient group according to the steps (4) and (5).
(7) Comparing the set of patients with similar documented disease time corresponding to each diabetic in the specific diabetic group with the set of patients with similar documented blood sugar, if the set of patients with similar documented disease time corresponding to a certain diabetic and the set of patients with similar documented blood sugar exist the same diabetic, extracting the same diabetic from the set of patients with similar documented disease time, and combining the same diabetic to serve as the target diabetic.
In an alternative embodiment, the daily management data includes diet data including food type ingested, food amount ingested, and diet interval duration, and exercise data including exercise pattern and exercise duration.
In an alternative embodiment, the analysis node partition is described in the following manner: and dividing analysis nodes of treatment time periods of all target diabetics based on blood glucose monitoring time corresponding to all target diabetics, wherein each blood glucose monitoring time corresponds to one analysis node.
In an alternative embodiment, the specific division manner of the daily management data corresponding to each analysis node for each target diabetes patient is as follows: and carrying out time calculation on each divided analysis node and the last analysis node to obtain the time period corresponding to each analysis node.
Daily management data in a period corresponding to each analysis node is extracted from daily management data uploaded by each target diabetic patient and is used as daily management data corresponding to each analysis node of each target diabetic patient.
The specific division mode of the disease monitoring information corresponding to each analysis node of each target diabetic patient is as follows: comparing the blood sugar monitoring time corresponding to each target diabetes patient with the complications associated index monitoring time, identifying appointed complications monitoring information corresponding to the blood sugar monitoring information, and accordingly extracting blood sugar monitoring values corresponding to each time of blood sugar monitoring and complications associated index monitoring values in the appointed complications monitoring information from the symptoms monitoring information corresponding to each target diabetes patient in the treatment period to serve as symptoms monitoring information corresponding to each analysis node of each target diabetes patient.
In an alternative embodiment, the change index corresponding to the diet management and the exercise management of each target diabetic patient in each analysis node is described in the following analysis process: extracting diet data from daily management data corresponding to each analysis node of each target diabetic, comparing the diet data of each analysis node of each target diabetic with the diet data of the last analysis node, and calculating change index corresponding to diet management of each diabetic in each analysis node The expression is calculated asWherein j represents the number of the target diabetic, </i >>T is denoted as the number of the analysis node, +.>Expressed as the degree of change in the type of food ingested by the j-th subject diabetic at the t-th analysis node corresponding to the t-1 th analysis node,、/>respectively are provided withExpressed as the change value of the intake food quantity, the change value of the diet interval duration and the +.>、/>Expressed as food intake and diet interval duration of the jth target diabetic at the t analysis node, respectively, and e is expressed as a natural constant.
Extracting motion data from daily management data corresponding to each analysis node of each target diabetic patient, comparing the motion data of each analysis node of each target diabetic patient with the motion data of the last analysis node, and calculating a change index corresponding to motion management of each diabetic patient in each analysis nodeThe expression is calculated as，/>The movement mode change degree of the j-th target diabetic patient corresponding to the t-1 th analysis node at the t-th analysis node is expressed,a motion duration change value which is expressed as the j-th target diabetic corresponding to the t-1 analysis node at the t-th analysis node, >Expressed as the length of movement of the jth target diabetic patient at the t analysis node.
In an alternative embodiment, the condition fluctuation index analysis formula of each target diabetic patient at each analysis node isIn the formula->、/>Respectively expressed as the variation corresponding to the blood sugar monitoring value and the complications sign monitoring value of the jth target diabetic at the t-th analysis node and the t-1 analysis node, and the +.>、/>Respectively expressed as a blood sugar monitoring value and a complication sign monitoring value of the jth target diabetic at the t analysis node.
In an alternative embodiment, the prediction of effective management means corresponding to diabetes treatment using the target diabetes patient as the diseased population is performed by the following prediction process: and constructing a two-dimensional coordinate system by taking the analysis nodes as the abscissa and the change indexes as the ordinate, and forming a diet management change curve and a movement management change curve corresponding to each target diabetes patient in the constructed two-dimensional coordinate system aiming at the change indexes corresponding to diet management and movement management of each target diabetes patient in each analysis node.
And constructing a two-dimensional coordinate system by taking the analysis nodes as abscissa and the condition fluctuation indexes as ordinate, and forming condition fluctuation change curves corresponding to the target diabetics in the constructed two-dimensional coordinate system aiming at the condition fluctuation indexes of the target diabetics at the analysis nodes.
And respectively acquiring the synchronicity of the diet management change curve, the movement management change curve and the disorder fluctuation change curve corresponding to each target diabetes patient, and selecting a management means corresponding to the maximum synchronicity from the synchronicity as a treatment tendency management means corresponding to each target diabetes patient.
The treatment tendency management means corresponding to each target diabetic patient are compared, so that the target diabetic patients corresponding to the same treatment tendency management means are classified, the occupation ratio corresponding to the diet management means and the exercise management is counted, meanwhile, the occupation ratio discrimination degree is calculated, and further, the effective management means corresponding to the treatment diabetes taking the target diabetic patients as the diseased group is obtained according to the occupation ratio discrimination degree.
Compared with the prior art, the invention has the following beneficial effects: (1) According to the invention, both the blood sugar monitoring result and the complications monitoring result are used as monitoring indexes of the diabetes control effect, so that the monitoring indexes of the diabetes control effect in the prior art are expanded, the scientific and reasonable monitoring of the diabetes control effect is realized, the monitoring one-sided performance can be avoided to a great extent, the accuracy of the monitoring result is improved, and objective and reliable screening basis is provided for screening effective management means corresponding to the treatment of diabetes.
(2) According to the invention, when the analysis object of the diabetes patient is determined, the collected diabetes patient is subjected to equivalent classification by acquiring the basic information and the profiling illness information of the diabetes patient, and then the target diabetes patient is selected from the classification result and used as the analysis object, so that the influence of individual differences of the diabetes patient on the screening result can be effectively avoided, the effectiveness of the screening result is improved to the maximum extent, and the occurrence rate of ineffective screening is greatly reduced.
(3) According to the invention, the treatment time period corresponding to each target diabetes patient is divided into analysis nodes, so that the diet data and the movement data of each target diabetes patient at the adjacent analysis nodes are subjected to change analysis, and meanwhile, the blood sugar monitoring result and the complications monitoring result of each target diabetes patient at the adjacent analysis nodes are subjected to disorder fluctuation analysis, so that the diet change and disorder fluctuation, the movement change and disorder fluctuation of the adjacent analysis nodes are synchronously analyzed, and the objective effective screening of effective management means for treating diabetes by the target diabetes patient is reflected by taking the screening basis, and the diet and disorder can be intuitively displayed due to the synchronism of the diet change and disorder fluctuation, the movement change and disorder fluctuation, so that the management means with larger correlation is selected as the effective management means more reasonably, thereby being beneficial to improving the reliability of the screening result.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the connection of the modules of the system of the present invention.
FIG. 2 is a graph showing the comparison of a diet management profile and a disorder fluctuation profile according to the present invention, wherein A represents the diet management profile and B represents the disorder fluctuation profile.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a cloud computing-based chronic disease patient health data tracking analysis system, which comprises a diabetes patient information extraction module, a target diabetes patient screening module, a daily management data uploading module, a disease monitoring information extraction module, an analysis node dividing module, an analysis node disease management change analysis module, an analysis node disease fluctuation analysis module and an effective management means prediction module, wherein the diabetes patient information extraction module is connected with the target diabetes patient screening module, the target diabetes patient screening module is respectively connected with the daily management data uploading module and the disease monitoring information extraction module, the daily management data uploading module and the disease monitoring information extraction module are respectively connected with the analysis node dividing module, the analysis node dividing module is respectively connected with the analysis node disease management change analysis module and the analysis node disease fluctuation analysis module, and the analysis node disease management change analysis module and the analysis node disease fluctuation analysis module are both connected with the effective management means prediction module.
The diabetes patient information extraction module is used for extracting basic information and documented disease information corresponding to each diabetes patient from a hospital patient library, wherein the basic information comprises age, gender, height and weight, and the documented disease information comprises documented disease duration and documented blood sugar value.
It should be noted that the diabetics extracted from the hospital patient library are all young and middle-aged patients with lighter symptoms.
It should be further explained that the documented disease information refers to disease information provided by a diabetic patient for pre-treatment condition documenting after confirming diabetes.
The target diabetes patient screening module is used for screening out target diabetes patients based on the basic information and the documented disease information corresponding to each diabetes patient, and the specific screening process is as follows: (1) Extracting age groups from the basic information, comparing the age groups corresponding to the diabetics, and screening the diabetics corresponding to the same age groups.
(2) Gender is extracted from the basic information, the gender corresponding to each diabetic in the diabetics corresponding to the same age range is compared, and the diabetics belonging to the same gender in the diabetics corresponding to the same age range are screened out from the basic information, so that the diabetes patients to be selected are formed.
(3) Extracting height and weight from the basic information, thereby calculating body mass index corresponding to each diabetes in the diabetes group to be selected, whereinAnd further selecting diabetics corresponding to the same body quality index from the diabetes patient group to be selected to form a specific diabetes patient group.
(4) The method comprises the steps of extracting the documented illness time from the documented illness information, numbering the diabetics in the specific diabetes patient group, and further constructing a documented illness time interval corresponding to each diabetes patient in the specific diabetes patient group according to the documented illness time.
In the specific embodiment of the above scheme, the process of constructing the proximity interval of the gear establishment disease duration corresponding to each diabetes in the specific diabetes group is as follows: comparing the disease time of the corresponding file of each diabetes in the group of diabetes to be selected with the reference disease time, and importing the formulaCalculating the similarity of the corresponding profiling illness time length of each diabetes patient in the diabetes patient group to be selected.
Combining the similarity of the documented disease duration corresponding to each diabetic in the specific diabetic group with the preset difference to obtain a documented disease duration similarity interval corresponding to each diabetic in the specific diabetic group Wherein->Expressed as the similarity of the corresponding documented disease duration of the ith diabetes in the specific diabetes group, i is expressed as the number of diabetes in the specific diabetes group,/day>，/>Expressed as a preset delta.
(5) According to the ordering of all diabetes in a specific diabetes group, all diabetes are sequentially taken as main diabetes, the adjacent degree of the documenting disease duration corresponding to other diabetes is compared with the adjacent degree of the documenting disease duration corresponding to the main diabetes, if the adjacent degree of the documenting disease duration corresponding to some other diabetes falls into the adjacent degree of the documenting disease duration corresponding to some main diabetes, the other diabetes is added into the adjacent patient set of the documenting disease duration corresponding to the main diabetes, thereby forming the adjacent patient set of the documenting disease duration corresponding to all diabetes.
(6) And (3) extracting the documented blood sugar value from the documented illness information, and further forming a documented blood sugar similar patient set corresponding to each diabetes in the specific diabetes group according to the same principle as the documented blood sugar value corresponding to each diabetes in the specific diabetes group according to the steps (4) and (5).
(7) Comparing a set of patients with similar documented disease time corresponding to each diabetic in a specific diabetic patient group with a set of patients with similar documented blood sugar, if the set of patients with similar documented disease time corresponding to a certain diabetic and the set of patients with similar documented blood sugar exist the same diabetic, the extracted same diabetic is similar to the diabetic in not only the documented disease time but also the documented blood sugar, and belongs to the same type of diabetic, at the moment, the same diabetic is extracted from the same diabetic, and the same diabetic is combined with the diabetic to serve as the target diabetic.
As an example of the above-mentioned scheme, the diabetes patients existing in the set of profiling patients with similar disease duration corresponding to a certain diabetes patient in the specific diabetes patient group are a, b, c, d, e, the diabetes patients existing in the set of profiling blood sugar similar patients corresponding to the diabetes patient are b, c, d, f, g, at this time, the set of profiling patients with similar disease duration corresponding to the diabetes patient and the set of profiling blood sugar similar patients exist the same diabetes patients, at this time, the same diabetes patients are extracted as b, c, d, which indicates that the extracted same diabetes patients are similar to the diabetes patients not only with similar disease duration of profiling, but also with similar blood sugar of profiling, and at this time, the extracted same diabetes patients and the diabetes patients form the target diabetes patient.
According to the invention, when the analysis object of the diabetes patient is determined, the collected diabetes patient is subjected to equivalent classification by acquiring the basic information and the profiling illness information of the diabetes patient, and then the target diabetes patient is selected from the classification result and used as the analysis object, so that the influence of individual differences of the diabetes patient on the screening result can be effectively avoided, the effectiveness of the screening result is improved to the maximum extent, and the occurrence rate of ineffective screening is greatly reduced.
The daily management data uploading module is used for constructing a doctor-patient data transmission platform, and each target diabetic patient uploads daily management data to the platform every day during treatment, wherein the daily management data comprise diet data and exercise data, the diet data comprise food intake types, food intake amounts and diet interval duration, and the exercise data comprise exercise modes and exercise duration.
It should be noted that the above method for obtaining the medium intake food amount is as follows: comparing the type of the ingested food with the preset blood sugar control association degree corresponding to various foods, matching the blood sugar control association degree corresponding to the type of the ingested food with the blood sugar control association degree as a weight factor corresponding to the type of the ingested food, carrying out weighted average calculation on the weight factor corresponding to the type of the ingested food and the ingestion amount corresponding to various ingested foods, and taking the calculation result as the ingestion amount.
It should be further appreciated that the diet interval period refers to an average diet interval period corresponding to an interval period of adjacent meals each day, and assuming that three meals each day are taken, the interval period between breakfast and lunch is T1, the interval period between lunch and dinner is T2, the diet interval period is。
As an example of the present invention, the exercise mode specifically refers to the exercise type, including, but not limited to, running, rope skipping, swimming.
The disease monitoring information extraction module is used for extracting disease monitoring information corresponding to each target diabetic patient in the treatment period from the patient archive, wherein the disease monitoring information comprises blood sugar monitoring information and complication monitoring information, the blood sugar monitoring information comprises blood sugar monitoring time and blood sugar monitoring values, and the complication monitoring information comprises complication associated index monitoring time and complication associated index monitoring values.
For example, the complications caused by diabetes include cardiovascular diseases, kidney diseases, retinopathy and the like, and the corresponding complication associated indexes can be blood pressure, blood fat, creatinine concentration, urine protein content and the like.
It should be noted that the blood glucose monitoring time and the complication associated index monitoring time are both presented in the form of date.
According to the invention, both the blood sugar monitoring result and the complications monitoring result are used as monitoring indexes of the diabetes control effect, so that the monitoring indexes of the diabetes control effect in the prior art are expanded, the scientific and reasonable monitoring of the diabetes control effect is realized, the monitoring one-sided performance can be avoided to a great extent, the accuracy of the monitoring result is improved, and objective and reliable screening basis is provided for screening effective management means corresponding to the treatment of diabetes.
The analysis node dividing module is used for dividing analysis nodes of treatment periods of all target diabetics, dividing daily management data uploaded by all target diabetics into daily management data corresponding to all analysis nodes of all target diabetics based on the divided analysis nodes, and dividing disease monitoring information corresponding to all target diabetics into disease monitoring information corresponding to all analysis nodes of all target diabetics.
Specifically, the above-mentioned analysis node is divided into: and dividing analysis nodes of treatment time periods of all target diabetics based on blood glucose monitoring time corresponding to all target diabetics, wherein each blood glucose monitoring time corresponds to one analysis node.
It is to be appreciated that diabetic patients need to monitor conditions periodically during treatment, each of which may reflect the control status of diabetes.
As an example of the above-mentioned scheme, if the blood glucose monitoring time of a certain target diabetic patient is 5 months 4 days, 6 months 4 days, 7 months 4 days, 8 months 4 days, and 9 months 4 days during the treatment, the analysis node corresponding to the target diabetic patient is 5 months 4 days, 6 months 4 days, 7 months 4 days, 8 months 4 days, and 9 months 4 days.
Preferably, the specific division mode of the daily management data corresponding to each analysis node of each target diabetes patient is as follows: and carrying out time calculation on each divided analysis node and the last analysis node to obtain the time period corresponding to each analysis node.
In particular, since the first analysis node has no previous analysis node corresponding thereto, this makes the first analysis node have no corresponding period.
Specifically, in combination with one example of the above scheme, the period corresponding to each analysis node of the target diabetic patient is 5 months 4 days, and since the previous analysis node does not exist, the period corresponding to the 5 months 4 days analysis node does not have a corresponding period, the period corresponding to the 6 months 4 days analysis node is 5 months 4 days-6 months 3 days, the period corresponding to the 7 months 4 days analysis node is 6 months 4 days-7 months 3 days, and the period corresponding to the 8 months 4 days analysis node is 7 months 4 days-8 months 3 days.
Daily management data in a period corresponding to each analysis node is extracted from daily management data uploaded by each target diabetic patient and is used as daily management data corresponding to each analysis node of each target diabetic patient.
It should be noted that, because the first analysis node does not have a corresponding period, the first analysis result does not have daily management data.
The specific division mode of the disease monitoring information corresponding to each analysis node of each target diabetic patient is as follows: comparing the blood sugar monitoring time corresponding to each target diabetes patient with the complications associated index monitoring time, identifying appointed complications monitoring information corresponding to the blood sugar monitoring information, and accordingly extracting blood sugar monitoring values corresponding to each time of blood sugar monitoring and complications associated index monitoring values in the appointed complications monitoring information from the symptoms monitoring information corresponding to each target diabetes patient in the treatment period to serve as symptoms monitoring information corresponding to each analysis node of each target diabetes patient.
In order to more comprehensively grasp the disease states of diabetics, the blood sugar monitoring is carried out in connection with the complication monitoring, and the monitoring time of the two is not long, in general, the blood sugar monitoring time and the monitoring time of the complication related index are in the same day, and the few cases are separated by one to two days, so when the blood sugar monitoring time corresponding to a certain target diabetics is 5 months 4 days, 6 months 4 days, 7 months 4 days, 8 months 4 days and 9 months 4 days, the monitoring time of the complication related index is 5 months 4 days, 6 months 5 days, 7 months 4 days, 8 months 4 days and 9 months 4 days, at this time, the specified complication monitoring information corresponding to the blood glucose monitoring information is 5 months 4 days blood glucose monitoring information, the specified complication monitoring information corresponding to the 6 months 4 days blood glucose monitoring information is 6 months 5 days complications monitoring information, the specified complication monitoring information corresponding to the 7 months 4 days blood glucose monitoring information is 7 months 4 days complications monitoring information, the specified complication monitoring information corresponding to the 8 months 4 days blood glucose monitoring information is 8 months 4 days complications monitoring information, and the specified complication monitoring information corresponding to the 9 months 4 days blood glucose monitoring information is 9 months 4 complications monitoring information.
The analysis node illness management change analysis module is used for comparing daily management data corresponding to each analysis node with adjacent analysis nodes and analyzing change indexes corresponding to diet management and movement management of each target diabetes patient in each analysis node, and the analysis process is specifically described in the following steps: extracting diet data from daily management data corresponding to each analysis node of each target diabetic, comparing the diet data of each analysis node of each target diabetic with the diet data of the last analysis node, and calculating change index corresponding to diet management of each diabetic in each analysis nodeThe calculation expression is +.>Wherein j represents the number of the target diabetic, </i >>，/>T is denoted as the number of the analysis node,expressed as j-th target diabetic at the t-th analysis node and t-1-th analysis nodePoint-corresponding degree of change in food category ingested, +.>、/>Respectively expressed as food intake quantity change value, diet interval duration change value and +.f of the j-th target diabetic corresponding to the t-1 th analysis node at the t-th analysis node>、/>Expressed as food intake and diet interval duration of the jth target diabetic at the t analysis node, respectively, and e is expressed as a natural constant.
The method for obtaining the variation of the type of the ingested food in the above formula is that when the type of the ingested food of a certain target diabetic patient is the same in the adjacent analysis nodes, the variation of the type of the ingested food of the adjacent analysis nodes is marked as 0, otherwise the variation of the type of the ingested food of the adjacent analysis nodes is marked as 1, and the variation corresponds to the expressionThe value of (2) is 0 or 1.
Extracting motion data from daily management data corresponding to each analysis node of each target diabetic patient, comparing the motion data of each analysis node of each target diabetic patient with the motion data of the last analysis node, and calculating a change index corresponding to motion management of each diabetic patient in each analysis nodeThe expression is calculated as，/>Represented as the j-th target diabetic patient at the t-th analysis node and t-1-th analysis node pairThe degree of change in the manner of movement to be accommodated,a motion duration change value which is expressed as the j-th target diabetic corresponding to the t-1 analysis node at the t-th analysis node,>expressed as the length of movement of the jth target diabetic patient at the t analysis node.
In the embodiment applied to the explanation, since the previous analysis node does not exist in the first analysis node and the daily management data does not exist in the first analysis result, that is, the daily management data of the 1 st analysis node and the daily management data of the 0 th analysis node do not exist, the daily management data of the 2 nd analysis node and the daily management data of the first analysis node are compared, so that the diet data and the exercise data of the 3 rd analysis node and the diet data and the exercise data of the 2 nd analysis node are directly compared in the variation index analysis process corresponding to diet management and exercise management, and the analysis result can be more reasonable and reliable.
The method for obtaining the motion mode variation degree in the above formula is that when the motion modes of a certain target diabetic patient at adjacent analysis nodes are the same, the motion mode variation degree of the adjacent analysis nodes is recorded as 0, otherwise, the motion mode variation degree of the adjacent analysis nodes is recorded as 1, and the motion mode variation degree of the adjacent analysis nodes corresponds to the expressionThe value of (2) is 0 or 1.
The invention is characterized in that the diet data and the exercise data of adjacent analysis nodes are uploaded every day when the diet data and the exercise data of the adjacent analysis nodes are compared, so that the diet data and the exercise data corresponding to each analysis node contain data of a plurality of days, and the analysis time periods corresponding to the analysis nodes are mostly the same.
The analysis node condition fluctuation analysis module is used for comparing condition monitoring information corresponding to each analysis node with adjacent analysis nodes and analyzing condition fluctuation indexes of each target diabetic patient at each analysis node, wherein a specific analysis formula is as follows In the formula->、Respectively expressed as the variation corresponding to the blood sugar monitoring value and the complications sign monitoring value of the jth target diabetic at the t-th analysis node and the t-1 analysis node, and the +.>、/>Respectively expressed as a blood sugar monitoring value and a complication sign monitoring value of the jth target diabetic at the t analysis node.
In order to facilitate the condition fluctuation analysis to be consistent with the diet management change and the movement management change analysis, the condition monitoring information of the 3 rd analysis node is directly compared with the condition monitoring information of the 2 nd analysis node when the condition fluctuation analysis is carried out.
The effective management means estimation module is used for estimating effective management means corresponding to diabetes treatment by taking a target diabetes patient as a diseased group, and the following estimation process is referred to: and constructing a two-dimensional coordinate system by taking the analysis nodes as the abscissa and the change indexes as the ordinate, and forming a diet management change curve and a movement management change curve corresponding to each target diabetes patient in the constructed two-dimensional coordinate system aiming at the change indexes corresponding to diet management and movement management of each target diabetes patient in each analysis node.
And constructing a two-dimensional coordinate system by taking the analysis nodes as abscissa and the condition fluctuation indexes as ordinate, and forming condition fluctuation change curves corresponding to the target diabetics in the constructed two-dimensional coordinate system aiming at the condition fluctuation indexes of the target diabetics at the analysis nodes.
In particular, a comparison of the diet management profile with the condition fluctuation profile is shown in figure 2.
The method comprises the steps of respectively acquiring the synchronicity of a diet management change curve and a movement management change curve corresponding to each target diabetic patient and a disease fluctuation change curve, selecting a management means corresponding to the maximum synchronicity from the synchronicity of the diet management change curve and the movement management change curve and the disease fluctuation change curve as treatment trend management means corresponding to each target diabetic patient, specifically, when the synchronicity of the diet management change curve and the disease fluctuation change curve is the maximum, the treatment trend management means is diet management, and when the synchronicity of the movement management change curve and the disease fluctuation change curve is the maximum, the treatment trend management means is movement management.
In a specific embodiment of the above solution, a specific method for obtaining the synchronization degree is as follows: the slope of the curve at each point is obtained from the diet management change curve and the movement management change curve corresponding to each target diabetes patient, and is marked as the slope of each point of diet management and the slope of each point of movement management, and the slope of the curve at each point is obtained from the disease fluctuation change curve corresponding to each target diabetes patient, and is marked as the slope of each point of disease fluctuation.
Comparing the absolute value of the slope of each point of diet management corresponding to each target diabetes patient with the slope of each point of disorder fluctuation corresponding to each target diabetes patient, and expressing by the expression And calculating the corresponding dietary change-disorder fluctuation synchronization degree of each target diabetic patient.
The diet management change curve, the movement management change curve and the disease fluctuation change curve are formed based on analysis nodes, so that each point on the change curve corresponds to one analysis node, and the number of the analysis nodes is the number of the points on the change curve.
Comparing the absolute value of the slope of each point of motion management corresponding to each target diabetes patient with the slope of each point of disorder fluctuation corresponding to each target diabetes patient, and expressing the absolute value by the expressionAnd calculating the corresponding motion change-disorder fluctuation synchronization degree of each target diabetic patient.
It should be noted that, the greater the absolute value of the slope of each point in the diet management change curve, the motion management change curve and the disorder fluctuation change curve corresponding to each target diabetes patient, the higher the change degree of the change curve at the corresponding point, and when the absolute value of the slope of each point in the diet management change curve corresponding to a certain target diabetes patient is closer to the absolute value of the slope of each point in the disorder fluctuation change curve, the more consistent the change degree of each point in the diet management change curve corresponding to the target diabetes patient and the change degree of each point in the disorder fluctuation change curve are, that is, the greater the probability of synchronous fluctuation of the disorder when the diet representing the target diabetes patient changes is, and similarly, the greater the probability of synchronous fluctuation of the disorder when the absolute value of the slope of each point in the motion management change curve corresponding to a certain target diabetes patient is closer to the absolute value of the slope of each point in the disorder fluctuation change curve is represented when the motion of the target diabetes patient changes.
According to the invention, by acquiring the dietary change-disorder fluctuation synchronization and the movement change-disorder fluctuation synchronization, the correlation state of the dietary change and the movement change with disorder fluctuation can be visually displayed, and the larger the synchronization is, the larger the correlation degree is, and the larger the representative correlation degree is.
Comparing the treatment trend management means corresponding to each target diabetes patient, classifying the target diabetes patients corresponding to the same treatment trend management means to obtain the number of target diabetes patients corresponding to diet management and the number of target diabetes patients corresponding to movement management, dividing the total number of target diabetes patients by the total number of target diabetes patients to obtain the occupation ratio corresponding to diet management means and movement management, and respectively marking asAnd->Simultaneously performing a ratio discrimination calculation, wherein the ratio discrimination calculation expression is +.>At this time, the ratio discrimination is compared with a set threshold, if the ratio discrimination is larger than the set threshold, the difference between the ratio corresponding to the diet management means and the ratio corresponding to the exercise management is larger, one of the ratios has a certain predominance, and then the ratio corresponding to the diet management means and the exercise management is compared, if the ratio discrimination is larger than the set threshold, the ratio corresponding to the exercise management means is larger than the ratio corresponding to the diet management means >>Dietary management is taken as an effective management means corresponding to diabetes treatment with the target diabetes patient as the diseased group, if-></>And taking the exercise management as an effective management means corresponding to the diabetes treatment by taking the target diabetes patient as a diseased group, and taking the diet management and the exercise management as the effective management means corresponding to the diabetes treatment by taking the target diabetes patient as the diseased group if the ratio difference degree is smaller than or equal to a set threshold value, which indicates that the difference between the ratio of the diet management means and the ratio of the exercise management is smaller, and one of the diet management means and the ratio of the exercise management means does not have a certain dominant ratio.
According to the invention, the treatment time period corresponding to each target diabetes patient is divided into analysis nodes, so that the diet data and the movement data of each target diabetes patient at the adjacent analysis nodes are subjected to change analysis, and meanwhile, the blood sugar monitoring result and the complications monitoring result of each target diabetes patient at the adjacent analysis nodes are subjected to disorder fluctuation analysis, so that the diet change and disorder fluctuation, the movement change and disorder fluctuation of the adjacent analysis nodes are synchronously analyzed, and the objective effective screening of effective management means for treating diabetes by the target diabetes patient is reflected by taking the screening basis, and the diet and disorder can be intuitively displayed due to the synchronism of the diet change and disorder fluctuation, the movement change and disorder fluctuation, so that the management means with larger correlation is selected as the effective management means more reasonably, thereby being beneficial to improving the reliability of the screening result.
The foregoing is merely illustrative and explanatory of the principles of this invention, as various modifications and additions may be made to the specific embodiments described, or similar arrangements may be substituted by those skilled in the art, without departing from the principles of this invention or beyond the scope of this invention as defined in the claims.
Claims (10)
1. A cloud computing-based chronic patient health data tracking analysis system, comprising:
the diabetes patient information extraction module is used for extracting basic information and documenting disease information corresponding to each diabetes patient from a hospital patient library;
the target diabetes mellitus patient screening module is used for screening out target diabetes mellitus patients based on the basic information and the documented illness information corresponding to each diabetes mellitus patient;
the daily management data uploading module is used for constructing a doctor-patient data transmission platform, and uploading daily management data to the platform every day by each target diabetes patient during treatment;
the system comprises a disease monitoring information extraction module, a disease analysis module and a disease analysis module, wherein the disease monitoring information extraction module is used for extracting disease monitoring information corresponding to each target diabetic during treatment from a patient archive, and the disease monitoring information comprises blood sugar monitoring information and complications monitoring information;
The analysis node dividing module is used for dividing analysis nodes of treatment time periods of all target diabetics, dividing daily management data uploaded by all target diabetics into daily management data corresponding to all analysis nodes of all target diabetics based on the divided analysis nodes, and dividing disease monitoring information corresponding to all target diabetics into disease monitoring information corresponding to all analysis nodes of all target diabetics;
the analysis node illness management change analysis module is used for comparing daily management data corresponding to each analysis node with adjacent analysis nodes and analyzing change indexes corresponding to diet management and movement management of each target diabetic patient in each analysis node;
the analysis node condition fluctuation analysis module is used for comparing condition monitoring information corresponding to each analysis node with adjacent analysis nodes and analyzing condition fluctuation indexes of each target diabetic patient at each analysis node;
the effective management means estimating module is used for estimating effective management means corresponding to diabetes treatment by taking the target diabetes patients as the diseased group.
2. The cloud computing-based chronic patient health data tracking analysis system of claim 1, wherein: the basic information comprises age, gender, height and weight, and the documented illness information comprises documented illness time and documented blood sugar value.
3. A cloud computing based chronic patient health data tracking analysis system as defined in claim 2, wherein: the specific screening process of the target diabetics is as follows:
(1) Extracting age groups from the basic information, comparing the age groups corresponding to the diabetics, and screening the diabetics corresponding to the same age groups;
(2) Extracting gender from the basic information, comparing the gender corresponding to each diabetic in the diabetics corresponding to the same age range, and screening the diabetics belonging to the same gender in the diabetics corresponding to the same age range to form a diabetes patient group to be selected;
(3) Extracting the height and the weight from the basic information, thereby calculating the body quality index corresponding to each diabetes in the diabetes group to be selected, and further selecting the diabetes corresponding to the same body quality index from the diabetes group to be selected to form a specific diabetes group;
(4) Extracting the disease time of the profiling from the disease information of the profiling, and further forming a patient set with similar disease time of the profiling corresponding to each diabetic patient;
(5) Extracting the documented blood sugar value from the documented illness information, and further forming a documented blood sugar similar patient set corresponding to each diabetes patient in the specific diabetes patient group;
(6) Comparing the patient set with similar documented disease duration corresponding to each diabetes in the specific diabetes group with the patient set with similar documented blood sugar, and screening out the target diabetes.
4. The cloud computing-based chronic patient health data tracking analysis system of claim 1, wherein: the daily management data includes diet data including a type of food ingested, an amount of food ingested, and a duration of a diet interval, and exercise data including a mode of exercise and a duration of exercise.
5. The cloud computing-based chronic patient health data tracking analysis system of claim 1, wherein: the blood glucose monitoring information comprises blood glucose monitoring time and blood glucose monitoring value, and the complications monitoring information comprises complications associated index monitoring time and complications associated index monitoring value.
6. The cloud computing-based chronic patient health data tracking analysis system of claim 5, wherein: the analysis node partition is described in the following way: and dividing analysis nodes of treatment time periods of all target diabetics based on blood glucose monitoring time corresponding to all target diabetics, wherein each blood glucose monitoring time corresponds to one analysis node.
7. The cloud computing-based chronic patient health data tracking analysis system of claim 6, wherein: the specific division mode of the daily management data corresponding to each analysis node of each target diabetes patient is as follows:
performing time calculation on each divided analysis node and the last analysis node to obtain a time period corresponding to each analysis node;
extracting daily management data in a period corresponding to each analysis node from daily management data uploaded by each target diabetic patient, and taking the daily management data as daily management data corresponding to each analysis node of each target diabetic patient;
the specific division mode of the disease monitoring information corresponding to each analysis node of each target diabetic patient is as follows:
comparing the blood sugar monitoring time corresponding to each target diabetes patient with the complications associated index monitoring time, identifying appointed complications monitoring information corresponding to the blood sugar monitoring information, and accordingly extracting blood sugar monitoring values corresponding to each time of blood sugar monitoring and complications associated index monitoring values in the appointed complications monitoring information from the symptoms monitoring information corresponding to each target diabetes patient in the treatment period to serve as symptoms monitoring information corresponding to each analysis node of each target diabetes patient.
8. The cloud computing-based chronic patient health data tracking analysis system of claim 4, wherein: the change indexes corresponding to diet management and exercise management of each target diabetic patient in each analysis node are shown in the following analysis process:
extracting diet data from daily management data corresponding to each analysis node of each target diabetic, comparing the diet data of each analysis node of each target diabetic with the diet data of the last analysis node, and calculating change index corresponding to diet management of each diabetic in each analysis nodeThe expression is calculated asWherein j represents the number of the target diabetic, </i >>T is denoted as the number of the analysis node, +.>Expressed as the degree of change in the type of food ingested by the j-th subject diabetic at the t-th analysis node corresponding to the t-1 th analysis node,、/>respectively expressed as food intake quantity change value, diet interval duration change value and +.f of the j-th target diabetic corresponding to the t-1 th analysis node at the t-th analysis node>、/>Respectively representing the food intake and the diet interval duration of a jth target diabetic at a t analysis node, wherein e represents a natural constant;
Extracting motion data from daily management data corresponding to each analysis node of each target diabetic patient, comparing the motion data of each analysis node of each target diabetic patient with the motion data of the last analysis node, and calculating a change index corresponding to motion management of each diabetic patient in each analysis nodeThe expression is calculated as，/>The movement mode change degree of the j-th target diabetic patient corresponding to the t-1 th analysis node at the t-th analysis node is expressed,a motion duration change value which is expressed as the j-th target diabetic corresponding to the t-1 analysis node at the t-th analysis node,>expressed as the length of movement of the jth target diabetic patient at the t analysis node.
9. The cloud computing based chronic patient health data tracking analysis system of claim 7, wherein: the disease fluctuation index analysis formula of each target diabetic patient at each analysis node is as followsIn the formula->、Respectively expressed as the variation corresponding to the blood sugar monitoring value and the complications sign monitoring value of the jth target diabetic at the t-th analysis node and the t-1 analysis node, and the +.>、/>Respectively expressed as a blood sugar monitoring value and a complication sign monitoring value of the jth target diabetic at the t analysis node.
10. The cloud computing-based chronic patient health data tracking analysis system of claim 1, wherein: the effective management means corresponding to the diabetes treatment of the target diabetes patients serving as the disease group is estimated by the following estimation process:
constructing a two-dimensional coordinate system by taking analysis nodes as abscissa and taking a change index as ordinate, and forming a diet management change curve and a motion management change curve corresponding to each target diabetes patient in the constructed two-dimensional coordinate system aiming at the change indexes corresponding to diet management and motion management of each target diabetes patient in each analysis node;
constructing a two-dimensional coordinate system by taking the analysis nodes as abscissa and the condition fluctuation indexes as ordinate, and forming condition fluctuation change curves corresponding to all target diabetics in the constructed two-dimensional coordinate system aiming at the condition fluctuation indexes of all target diabetics at all analysis nodes;
respectively acquiring the synchronicity of a diet management change curve and a movement management change curve corresponding to each target diabetes patient and a disease fluctuation change curve, and selecting a management means corresponding to the maximum synchronicity from the synchronicity as a treatment tendency management means corresponding to each target diabetes patient;
The treatment tendency management means corresponding to each target diabetic patient are compared, so that the target diabetic patients corresponding to the same treatment tendency management means are classified, the occupation ratio corresponding to the diet management means and the exercise management is counted, meanwhile, the occupation ratio discrimination degree is calculated, and further, the effective management means corresponding to the treatment diabetes taking the target diabetic patients as the diseased group is obtained according to the occupation ratio discrimination degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310944967.4A CN116665904B (en) | 2023-07-31 | 2023-07-31 | Cloud computing-based chronic disease patient health data tracking analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310944967.4A CN116665904B (en) | 2023-07-31 | 2023-07-31 | Cloud computing-based chronic disease patient health data tracking analysis system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116665904A true CN116665904A (en) | 2023-08-29 |
| CN116665904B CN116665904B (en) | 2023-10-20 |
Family
ID=87712207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310944967.4A Active CN116665904B (en) | 2023-07-31 | 2023-07-31 | Cloud computing-based chronic disease patient health data tracking analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665904B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117009831B (en) * | 2023-10-07 | 2023-12-08 | 山东世纪阳光科技有限公司 | Fine chemical accident risk prediction assessment method |
| CN117373677A (en) * | 2023-12-07 | 2024-01-09 | 深圳问止中医健康科技有限公司 | Intelligent health monitoring system based on digital medical archive management |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030032867A1 (en) * | 2001-06-21 | 2003-02-13 | Animas Corporation. | System and method for managing diabetes |
| JP2012088947A (en) * | 2010-10-20 | 2012-05-10 | Seiko Epson Corp | Method and system for blood glucose value estimation |
| CN103500285A (en) * | 2013-10-14 | 2014-01-08 | 宋涛 | Glycemic control map |
| CN105160199A (en) * | 2015-09-30 | 2015-12-16 | 刘毅 | Continuous blood sugar monitoring based method for processing and displaying diabetes management information with intervention information |
| WO2017035024A1 (en) * | 2015-08-21 | 2017-03-02 | Medtronic Minimed, Inc. | Data analytics and insight delivery for the management and control of diabetes |
| CN108511070A (en) * | 2018-04-18 | 2018-09-07 | 郑州大学第附属医院 | A kind of diabetic assessment and management system |
| CN110718302A (en) * | 2019-10-22 | 2020-01-21 | 江苏健康无忧网络科技有限公司 | Diabetes management path system based on big data |
| CN110767278A (en) * | 2019-10-21 | 2020-02-07 | 北京盛世东康科技发展有限公司 | Chronic disease management method and system |
| KR20210008267A (en) * | 2019-07-12 | 2021-01-21 | 동국대학교 산학협력단 | System for monitoring health condition of user and analysis method thereof |
-
2023
- 2023-07-31 CN CN202310944967.4A patent/CN116665904B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030032867A1 (en) * | 2001-06-21 | 2003-02-13 | Animas Corporation. | System and method for managing diabetes |
| JP2012088947A (en) * | 2010-10-20 | 2012-05-10 | Seiko Epson Corp | Method and system for blood glucose value estimation |
| CN103500285A (en) * | 2013-10-14 | 2014-01-08 | 宋涛 | Glycemic control map |
| WO2017035024A1 (en) * | 2015-08-21 | 2017-03-02 | Medtronic Minimed, Inc. | Data analytics and insight delivery for the management and control of diabetes |
| CN105160199A (en) * | 2015-09-30 | 2015-12-16 | 刘毅 | Continuous blood sugar monitoring based method for processing and displaying diabetes management information with intervention information |
| CN108511070A (en) * | 2018-04-18 | 2018-09-07 | 郑州大学第附属医院 | A kind of diabetic assessment and management system |
| KR20210008267A (en) * | 2019-07-12 | 2021-01-21 | 동국대학교 산학협력단 | System for monitoring health condition of user and analysis method thereof |
| CN110767278A (en) * | 2019-10-21 | 2020-02-07 | 北京盛世东康科技发展有限公司 | Chronic disease management method and system |
| CN110718302A (en) * | 2019-10-22 | 2020-01-21 | 江苏健康无忧网络科技有限公司 | Diabetes management path system based on big data |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117009831B (en) * | 2023-10-07 | 2023-12-08 | 山东世纪阳光科技有限公司 | Fine chemical accident risk prediction assessment method |
| CN117373677A (en) * | 2023-12-07 | 2024-01-09 | 深圳问止中医健康科技有限公司 | Intelligent health monitoring system based on digital medical archive management |
| CN117373677B (en) * | 2023-12-07 | 2024-03-08 | 深圳问止中医健康科技有限公司 | Intelligent health monitoring system based on digital medical archive management |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116665904B (en) | 2023-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116665904B (en) | Cloud computing-based chronic disease patient health data tracking analysis system | |
| Woldaregay et al. | Data-driven modeling and prediction of blood glucose dynamics: Machine learning applications in type 1 diabetes | |
| CN111292853B (en) | Multi-parameter-based cardiovascular disease risk prediction network model and construction method thereof | |
| Chakradar et al. | A non-invasive approach to identify insulin resistance with triglycerides and HDL-c ratio using machine learning | |
| CN114830132A (en) | System and method for processing human-related data including physiological signals to make context-aware decisions using distributed machine learning of edges and clouds | |
| CN107194138B (en) | Fasting blood glucose prediction method based on physical examination data modeling | |
| Shahid et al. | A novel approach for coronary artery disease diagnosis using hybrid particle swarm optimization based emotional neural network | |
| CN110299205A (en) | Biomedicine signals characteristic processing and evaluating method, device and application based on artificial intelligence | |
| Olaniyi et al. | Neural network diagnosis of heart disease | |
| Fialho et al. | Disease-based modeling to predict fluid response in intensive care units | |
| Barhate et al. | Analysis of classifiers for prediction of type ii diabetes mellitus | |
| US20210338171A1 (en) | Tensor amplification-based data processing | |
| Mansouri et al. | Predicting hospital length of stay of neonates admitted to the NICU using data mining techniques | |
| Huo et al. | Predicting the meal macronutrient composition from continuous glucose monitors | |
| Derevitskii et al. | Analysis course of the disease of type 2 diabetes patients using Markov chains and clustering methods. | |
| Gecili et al. | Functional data analysis and prediction tools for continuous glucose-monitoring studies | |
| Suneetha et al. | Fine tuning bert based approach for cardiovascular disease diagnosis | |
| US20200352481A1 (en) | Predicting food macronutrients from blood biomarkers | |
| Golovco et al. | Acute kidney injury prediction with gradient boosting decision trees enriched with temporal features | |
| Pappy et al. | Predicting High-Flow Nasal Cannula Failure in an ICU Using a Recurrent Neural Network with Transfer Learning and Input Data Perseveration: A Retrospective Analysis | |
| Ahmed et al. | Recent trends and techniques of blood glucose level prediction for diabetes control | |
| Aamir et al. | Pre-diabetic diagnosis from habitual and medical features using ensemble classification | |
| Aline et al. | Data fusion for predicting ARDS using the MIMIC II physiological database | |
| Machado et al. | Impact of the glycaemic sampling method in diabetes data mining | |
| CN111048199B (en) | Method for exploring importance degree of multiple physiological variables on diseases |
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 |