CN116434965A - Diabetes eye disease risk assessment system and method based on blood sugar - Google Patents
Diabetes eye disease risk assessment system and method based on blood sugar Download PDFInfo
- Publication number
- CN116434965A CN116434965A CN202310279762.9A CN202310279762A CN116434965A CN 116434965 A CN116434965 A CN 116434965A CN 202310279762 A CN202310279762 A CN 202310279762A CN 116434965 A CN116434965 A CN 116434965A
- Authority
- CN
- China
- Prior art keywords
- data
- eye disease
- risk assessment
- blood glucose
- model
- 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.)
- Pending
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 61
- 239000008280 blood Substances 0.000 title claims abstract description 54
- 210000004369 blood Anatomy 0.000 title claims abstract description 54
- 206010012601 diabetes mellitus Diseases 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 25
- 208000030533 eye disease Diseases 0.000 title claims abstract description 15
- 208000010837 Diabetic eye disease Diseases 0.000 claims abstract description 61
- 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 abstract description 43
- 239000008103 glucose Substances 0.000 claims abstract description 43
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 201000010099 disease Diseases 0.000 claims abstract description 25
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 22
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000013480 data collection Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 238000011282 treatment Methods 0.000 claims description 8
- 208000017442 Retinal disease Diseases 0.000 claims description 6
- 206010038923 Retinopathy Diseases 0.000 claims description 6
- 238000013501 data transformation Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 206010023365 keratopathy Diseases 0.000 claims description 6
- 208000030159 metabolic disease Diseases 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013176 antiplatelet therapy Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 102000017011 Glycated Hemoglobin A Human genes 0.000 description 1
- 108010014663 Glycated Hemoglobin A Proteins 0.000 description 1
- 208000010038 Ischemic Optic Neuropathy Diseases 0.000 description 1
- 206010030924 Optic ischaemic neuropathy Diseases 0.000 description 1
- 208000007135 Retinal Neovascularization Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 201000007058 anterior ischemic optic neuropathy Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 208000016097 disease of metabolism Diseases 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003345 hyperglycaemic effect Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 208000013441 ocular lesion Diseases 0.000 description 1
- 208000001749 optic atrophy Diseases 0.000 description 1
- 208000020911 optic nerve disease Diseases 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000035488 systolic blood pressure Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Images
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
- G16H50/70—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- 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 discloses a diabetes eye disease risk assessment system and a diabetes eye disease risk assessment method based on blood sugar, wherein the system comprises the following steps: the data collection module is used for storing the original data acquired from outpatient service, inpatient service and questionnaire survey so as to establish a database; the data selection module is used for selecting the data in the database based on a preset selection factor so as to form a sample data set; the selection factors include blood glucose level, time of disease and diabetic eye disease; the model building module is used for training based on the sample data set so as to build a risk assessment model; the risk assessment module is used for loading the risk assessment model to carry out online assessment on patient data to be assessed and outputting assessment data; the effect is that: the method overcomes the defects that in the prior art, due to the clinical experience difference of different doctors, the evaluation results are various, misdiagnosis and missed diagnosis are easy to occur, and the obtained reference basis has lower accuracy.
Description
Technical Field
The invention relates to the technical field of medical data processing, in particular to a diabetes eye disease risk assessment system and method based on blood sugar.
Background
Diabetes is a rather common chronic metabolic disease in clinic, and is mainly manifested by a long-term hyperglycemic state, damaging systemic small blood vessels and micro blood vessels, and further affecting blood supply of in vivo tissues. Ocular lesions are one of the most common complications for diabetics.
In the prior art, the evaluation of the diabetic patients is mainly carried out by combining the clinical experience of the doctors with the examination results of the body and laboratory, and the factors considered during the evaluation are different due to the clinical experience difference of different doctors, so that the evaluation results are various, misdiagnosis and missed diagnosis are easy to occur, and the best opportunity for prevention and treatment is missed, so that the defect of lower accuracy of the obtained reference basis is caused.
Disclosure of Invention
In view of the above problems, a system and a method for evaluating the risk of diabetic eye disease based on blood sugar are provided to overcome the defect of low accuracy of the obtained reference basis due to the clinical experience difference of different doctors in the prior art.
First aspect: a blood glucose-based diabetes eye disease risk assessment system, the system comprising:
the data collection module is used for storing the original data acquired from outpatient service, inpatient service and questionnaire survey so as to establish a database;
the data selection module is used for selecting the data in the database based on a preset selection factor so as to form a sample data set; wherein the selection factors include blood glucose level, time of disease and diabetic eye disease; wherein the diabetic eye disease comprises retinopathy, keratopathy and crystallopathy;
the model building module is used for training based on the sample data set so as to build a risk assessment model;
the risk assessment module is used for loading the risk assessment model to carry out online assessment on patient data to be assessed and outputting assessment data; wherein the evaluation data includes data relating to the diabetic eye disease and at least one of blood glucose level and time of disease.
Preferably, the data collection module is further configured to perform data processing on the obtained raw data, where the data processing includes data specifications and data transformation.
Preferably, the data protocol specifically includes:
the data integration and the data types are unified; wherein, the data integration means that data with different attributes or different formats are integrated according to logic; the unification of the data types is that all the index value type data are unified into preset data types.
Preferably, the data transformation specifically includes:
noise filtering and data normalization; the noise filtering is to delete the data missing value and the data abnormal value; and normalizing the data into normalized data after filtering.
Preferably, the diabetes mellitus eye disease risk assessment system based on blood sugar further comprises a feature module, wherein before the risk assessment model is established, feature selection is performed based on the sample data set, so that feature variables which have significant influence on the diabetes mellitus eye disease are screened out, and the feature variables are used as input variables of the risk assessment model.
Preferably, the risk assessment model is trained by:
performing cross combination based on the characteristic variables and combining the sample data sets to form a plurality of characteristic data sets;
dividing the characteristic data set into a training set and a testing set, wherein the training set is used for model training, and the testing set is used for simulating the evaluation effect of a real data testing model; wherein the model adopts an XGBoost model;
debugging parameters of a model based on the evaluation effect;
and storing the trained model so as to facilitate subsequent model calling.
Preferably, the evaluation data includes data relating to at least one of blood glucose level and time of disease and the diabetic eye disease, specifically including:
a first assessment value between the blood glucose level and the diabetic eye disease;
a second evaluation value between the disease course time and the diabetic eye disease;
and a third evaluation value between the blood glucose level and the time of illness and the diabetic eye disease.
Preferably, the evaluation data further includes guidance data, the guidance data including: health education, control of metabolic disorders, antiplatelet therapy, medical treatment for diabetic eye disease, and ophthalmic treatment.
Second aspect: a blood glucose-based diabetic eye disease risk assessment method applied to the blood glucose-based diabetic eye disease risk assessment system of the first aspect, the method comprising:
storing raw data acquired from outpatients, hospitalizations and questionnaires, thereby establishing a database;
selecting data in the database based on a preset selection factor to form a sample data set; wherein the selection factors include blood glucose level, time of disease and diabetic eye disease; wherein the diabetic eye disease comprises retinopathy, keratopathy and crystallopathy;
training based on the sample dataset to establish a risk assessment model;
loading the risk assessment model to perform on-line assessment on patient data to be assessed, and outputting assessment data; wherein the evaluation data includes data relating to the diabetic eye disease and at least one of blood glucose level and time of disease.
Preferably, the method further comprises: and performing feature selection based on the sample data set to screen out feature variables which have significant influence on the diabetic eye disease, and taking the feature variables as input variables of the risk assessment model.
By adopting the technical scheme, the diabetes eye disease risk assessment system and the diabetes eye disease risk assessment method based on blood sugar, which are provided by the invention, select the data in the database by taking the blood sugar level, the disease course time and the diabetes eye disease as preset selection factors so as to form a sample data set; training according to the sample data set to establish a risk assessment model, so as to realize online assessment of patient data to be assessed; therefore, the defects that in the prior art, due to the clinical experience difference of different doctors, the evaluation results are various, misdiagnosis and missed diagnosis are easy to occur, and the obtained reference basis has lower accuracy are overcome.
Drawings
FIG. 1 is a block diagram of a blood glucose based diabetic eye risk assessment system according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for evaluating risk of diabetic eye disease based on blood sugar according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved by the present invention more apparent, the following detailed description will be given with reference to the accompanying drawings and specific embodiments, it being apparent that the described embodiments are some, but not all embodiments of the present invention. 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.
The technical terms of the present embodiment are the common meanings understood in the computer field unless otherwise specified.
As shown in fig. 1, the system for evaluating the risk of diabetic eye disease based on blood sugar according to the embodiment of the present invention includes:
and the data collection module is used for storing the raw data acquired from the outpatient service, the inpatient service and the questionnaire survey so as to establish a database.
Specifically, collecting data in a grabbing manner to obtain a large number of public and shared disease data sets or sharing and purchasing desensitized scientific research data from a hospital and physical examination institution protocol, and then processing the data;
the clinic data and the hospitalization similarity are high, and mainly comprise basic information, past medical history, various examinations, therapeutic treatments and the like of patients;
the questionnaire data prepares a questionnaire for a user to investigate some characteristics which are easier to induce the diabetic eye disease according to the medical experience and the form of medical expert judgment, and the related problems specifically comprise:
1) Lifestyle may lead to diseases with a strong correlation;
2) The suffering from or about to suffer from the disease may produce a daily experience as described by the questionnaire;
3) A prolonged blood glucose level;
4) The time of the course of diabetes;
5) Which diabetic eye diseases exist.
In implementation, to improve data quality, the data collection module is further configured to perform data processing on the obtained raw data, where the data processing includes data specification and data transformation.
Specifically, the data protocol specifically includes:
the data integration and the data types are unified; wherein, the data integration means that data with different attributes or different formats are integrated according to logic; the unification of the data types is that all index value type data are unified into preset data types; the floating point numbers may be unified in this embodiment.
The data transformation specifically comprises:
noise filtering and data normalization; the noise filtering is to delete the data missing value and the data abnormal value; and normalizing the data into normalized data after filtering.
The data selection module is used for selecting the data in the database based on a preset selection factor so as to form a sample data set; wherein the selection factors include blood glucose level, time of disease and diabetic eye disease; wherein the retinopathy, keratopathy and crystallopathy; it should be noted that the inclusion of the selection factors is merely illustrative and not limiting.
In particular, the selection factor may elicit relevant data for the diabetic eye disease; this example illustrates the blood glucose levels and time of disease associated with diabetes; thereby correlating the data relating to blood glucose level and time of disease with diabetic eye disease, thereby selecting data with a high degree of correlation;
classifying according to different detection result attributes; the detection results of each index are classified into a description type result, a numerical type result and a null value.
Further, the diabetic eye disease also comprises optic nerve diseases, mainly comprising non-arteritic anterior segment ischemic optic neuropathy, diabetic optic papillary lesions, diabetic optic disc neovascularization and diabetic optic atrophy; among these, age, diabetes course, glycosylated hemoglobin and systolic blood pressure are factors that have significant effects, and increase in risk of occurrence with the prolongation of diabetes course or increase in HbA1c level.
And the model construction module is used for training based on the sample data set so as to establish a risk assessment model.
In application, in order to improve the prediction effect of the risk assessment model, the diabetes eye disease risk assessment system based on blood sugar further comprises a feature module, wherein the feature module is used for performing feature selection based on the sample data set before the risk assessment model is established so as to screen out feature variables which have significant influence on the diabetes eye disease and take the feature variables as input variables of the risk assessment model.
During implementation, the feature selection plays a key role in later model prediction, and the accuracy and stability of the whole model can be improved by the correct feature selection; in the embodiment, when the feature is selected, the IV value analysis can be adopted to select the feature, which measures the influence degree of a certain feature on a target, and the basic idea is to compare and calculate the association degree according to the ratio of the hit black-white sample of the feature to the ratio of the total black-white sample, so as to effectively remove redundant features, determine the final optimal feature subset and train a model; IV, english name (Information value), which is the information value as the name implies, is used to evaluate the predictive power of variables.
Correspondingly, the risk assessment model is trained by the following steps:
performing cross combination based on the characteristic variables and combining the sample data sets to form a plurality of characteristic data sets; the clustering algorithm can be used in the step, so that a small data set which is clustered according to a certain characteristic is divided into a plurality of small data sets to serve as a plurality of characteristic data sets, and the model is more accurate.
Dividing the characteristic data set into a training set and a testing set, wherein the training set is used for model training, and the testing set is used for simulating the evaluation effect of a real data testing model; wherein the model adopts an XGBoost model;
XGBoost is an improved GBDT algorithm, and can automatically learn out the processing strategy of the missing item, so that the running speed and the prediction accuracy are improved, and meanwhile, the overfitting phenomenon is effectively inhibited; GBDT is a Boosting algorithm proposed by Friedman et al in 2001, and is an iterative decision tree algorithm which consists of a plurality of decision trees, and the conclusions of all the trees are added up to serve as final answers;
specifically, 70% may be used as training samples, and 30% may be used as test samples; because the classification threshold has great influence on the accuracy of the model, the application adopts the interval accuracy of the sample to determine the final threshold; for example, the method is divided into a plurality of sections, and the section with the highest accuracy is taken as the final threshold value corresponding to the end point value.
Debugging parameters of a model based on the evaluation effect;
and storing the trained model so as to facilitate subsequent model calling.
In the evaluation, the accuracy, the precision and the recall are used for evaluation; accuracy refers to the ratio of the number of correctly classified samples to the total number of samples; the accuracy rate indicates the proportion of samples predicted to be positive and actually positive; the recall represents the proportion of samples that are predicted to be positive in the actual positive samples.
The risk assessment module is used for loading the risk assessment model to carry out online assessment on patient data to be assessed and outputting assessment data; wherein the evaluation data includes data relating to the diabetic eye disease and at least one of blood glucose level and time of disease.
The method specifically comprises the following steps:
a first assessment value between the blood glucose level and the diabetic eye disease;
a second evaluation value between the disease course time and the diabetic eye disease;
and a third evaluation value between the blood glucose level and the time of illness and the diabetic eye disease.
When the method is applied, the image-text report is adopted to display the risk probability that a certain or compound factor possibly causes the diabetic eye disease to a doctor, and the risk probability is described in detail for the doctor to refer to; the report is provided to the physician in the form of PDF, WORD, H pages, etc.
Meanwhile, the evaluation data further includes guidance data including: health education, control of metabolic disorders, antiplatelet therapy, medical treatment for diabetic eye disease, and ophthalmic treatment.
According to the scheme, the data in the database are selected to form a sample data set by taking blood glucose level, disease course time and diabetic eye disease as preset selection factors; training according to the sample data set to establish a risk assessment model, so as to realize online assessment of patient data to be assessed; therefore, the defects that in the prior art, due to the clinical experience difference of different doctors, the evaluation results are various, misdiagnosis and missed diagnosis are easy to occur, and the obtained reference basis has lower accuracy are overcome.
Based on the same inventive concept, referring to fig. 2, an embodiment of the present invention further provides a blood glucose-based diabetic eye disease risk assessment method, which is applied to the blood glucose-based diabetic eye disease risk assessment system described above, and the method includes:
s101, storing raw data acquired from outpatient service, hospitalization and questionnaire survey, so as to establish a database;
s102, selecting data in the database based on a preset selection factor to form a sample data set; wherein the selection factors include blood glucose level, time of disease and diabetic eye disease; wherein the diabetic eye disease comprises retinopathy, keratopathy and crystallopathy;
s103, training based on the sample data set to establish a risk assessment model;
s104, loading the risk assessment model to perform on-line assessment on patient data to be assessed, and outputting assessment data; wherein the evaluation data includes data relating to the diabetic eye disease and at least one of blood glucose level and time of disease.
Further, to promote the prediction effect of the risk assessment model, the method further includes: and performing feature selection based on the sample data set to screen out feature variables which have significant influence on the diabetic eye disease, and taking the feature variables as input variables of the risk assessment model.
In practice, the risk assessment model is trained by:
performing cross combination based on the characteristic variables and combining the sample data sets to form a plurality of characteristic data sets;
dividing the characteristic data set into a training set and a testing set, wherein the training set is used for model training, and the testing set is used for simulating the evaluation effect of a real data testing model; wherein the model adopts an XGBoost model;
debugging parameters of a model based on the evaluation effect;
and storing the trained model so as to facilitate subsequent model calling.
It should be noted that, for a brief description of the method embodiments provided in the embodiments of the present invention, the details and details of the description of the embodiments are not mentioned in the description of the embodiments, and reference may be made to the related text in the foregoing system embodiments.
By the scheme, the defect that the risk assessment of the existing diabetes eye disease is based on personal experience and physical examination data of doctors can be overcome, the subjectivity is high, and misdiagnosis and missed diagnosis are easy to occur; according to the method, the diabetes mellitus, the diabetic eye disease and the machine learning are combined, a machine learning algorithm is adopted to assist a doctor, a reference is provided for the doctor, diagnosis and scientificity can be improved to a great extent, and the problem of subjectivity of the doctor in empirical diagnosis is effectively solved.
Alternatively, as another preferred embodiment of the present invention, the above-mentioned diabetic eye disease risk assessment system based on blood glucose may include: one or more processors and memory interconnected by a bus, the memory for storing a computer program comprising program instructions configured to invoke the program instructions to perform the method of the above-described embodiment of a blood glucose-based diabetic eye risk assessment method.
It should be appreciated that in embodiments of the present invention, the processor may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include read only memory and random access memory and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory.
In several embodiments provided herein, it should be understood that the disclosed modules and methods may be implemented in other manners. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A blood glucose-based diabetes mellitus eye disease risk assessment system, the system comprising:
the data collection module is used for storing the original data acquired from outpatient service, inpatient service and questionnaire survey so as to establish a database;
the data selection module is used for selecting the data in the database based on a preset selection factor so as to form a sample data set; wherein the selection factors include blood glucose level, time of disease and diabetic eye disease; wherein the diabetic eye disease comprises retinopathy, keratopathy and crystallopathy;
the model building module is used for training based on the sample data set so as to build a risk assessment model;
the risk assessment module is used for loading the risk assessment model to carry out online assessment on patient data to be assessed and outputting assessment data; wherein the evaluation data includes data relating to the diabetic eye disease and at least one of blood glucose level and time of disease.
2. The blood glucose-based diabetic eye disease risk assessment system of claim 1, wherein the data collection module is further configured to perform data processing on the raw data obtained, the data processing including data specifications and data transformations.
3. The blood glucose-based diabetic eye disease risk assessment system of claim 2, wherein the data protocol specifically comprises:
the data integration and the data types are unified; wherein, the data integration means that data with different attributes or different formats are integrated according to logic; the unification of the data types is that all the index value type data are unified into preset data types.
4. The blood glucose-based diabetic eye disease risk assessment system of claim 2, wherein the data transformation specifically comprises:
noise filtering and data normalization; the noise filtering is to delete the data missing value and the data abnormal value; and normalizing the data into normalized data after filtering.
5. The blood glucose-based diabetic eye disease risk assessment system of claim 2, further comprising a feature module for performing feature selection based on the sample dataset to screen out feature variables having a significant impact on the diabetic eye disease and using them as input variables to the risk assessment model prior to establishing the risk assessment model.
6. The blood glucose-based diabetic eye disease risk assessment system according to claim 5, wherein the risk assessment model is trained by:
performing cross combination based on the characteristic variables and combining the sample data sets to form a plurality of characteristic data sets;
dividing the characteristic data set into a training set and a testing set, wherein the training set is used for model training, and the testing set is used for simulating the evaluation effect of a real data testing model; wherein the model adopts an XGBoost model;
debugging parameters of a model based on the evaluation effect;
and storing the trained model so as to facilitate subsequent model calling.
7. The blood glucose-based diabetic eye disease risk assessment system of claim 6, wherein the assessment data comprises data relating to the diabetic eye disease and at least one of blood glucose level and time of disease, specifically comprising:
a first assessment value between the blood glucose level and the diabetic eye disease;
a second evaluation value between the disease course time and the diabetic eye disease;
and a third evaluation value between the blood glucose level and the time of illness and the diabetic eye disease.
8. The blood glucose-based diabetic eye disease risk assessment system of claim 7, wherein the assessment data further comprises instructional data comprising: health education, control of metabolic disorders, antiplatelet therapy, medical treatment for diabetic eye disease, and ophthalmic treatment.
9. A method for assessing risk of diabetic eye disease based on blood glucose, applied to the system for assessing risk of diabetic eye disease based on blood glucose of claim 1, the method comprising:
storing raw data acquired from outpatients, hospitalizations and questionnaires, thereby establishing a database;
selecting data in the database based on a preset selection factor to form a sample data set; wherein the selection factors include blood glucose level, time of disease and diabetic eye disease; wherein the diabetic eye disease comprises retinopathy, keratopathy and crystallopathy;
training based on the sample dataset to establish a risk assessment model;
loading the risk assessment model to perform on-line assessment on patient data to be assessed, and outputting assessment data; wherein the evaluation data includes data relating to the diabetic eye disease and at least one of blood glucose level and time of disease.
10. The method of claim 9, further comprising: and performing feature selection based on the sample data set to screen out feature variables which have significant influence on the diabetic eye disease, and taking the feature variables as input variables of the risk assessment model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310279762.9A CN116434965A (en) | 2023-03-21 | 2023-03-21 | Diabetes eye disease risk assessment system and method based on blood sugar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310279762.9A CN116434965A (en) | 2023-03-21 | 2023-03-21 | Diabetes eye disease risk assessment system and method based on blood sugar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116434965A true CN116434965A (en) | 2023-07-14 |
Family
ID=87091771
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310279762.9A Pending CN116434965A (en) | 2023-03-21 | 2023-03-21 | Diabetes eye disease risk assessment system and method based on blood sugar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116434965A (en) |
-
2023
- 2023-03-21 CN CN202310279762.9A patent/CN116434965A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cheung et al. | A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre | |
| Knottnerus et al. | The evidence base of clinical diagnosis: theory and methods of diagnostic research | |
| Rahmani et al. | The effect of the teach-back method on knowledge, performance, readmission, and quality of life in heart failure patients | |
| WO2006084195A2 (en) | Personal assessment including familial risk analysis for personalized disease prevention plan | |
| Chatziefstratiou et al. | Scales for assessing medication adherence in patients with hypertension | |
| Lee et al. | Psychometric evaluation of the diabetes self-management instrument short form (DSMI-20) | |
| Li et al. | Diabetes literacy and knowledge among patients with type 2 diabetes mellitus attending a primary care clinic in Seremban, Malaysia. | |
| CN114023440A (en) | Model and device capable of explaining layered old people MODS early death risk assessment and establishing method thereof | |
| Mohamed et al. | Maternal juvenile rheumatoid arthritis may be associated with preterm birth but not poor fetal growth | |
| Polak et al. | Artificial intelligence technology as a tool for initial GDM screening | |
| Jorge et al. | Abnormal responses in cognitive impulsivity circuits are associated with glycosylated hemoglobin trajectories in type 1 diabetes mellitus and impaired metabolic control | |
| WO2023173538A1 (en) | Alzheimer disease evaluation method and system, and device and storage medium | |
| CN116434965A (en) | Diabetes eye disease risk assessment system and method based on blood sugar | |
| CN112132782B (en) | Method and terminal for processing DME (DME) typing based on deep neural network | |
| Wooliscroft et al. | Predictors of early onset glaucoma | |
| Abou El Enein et al. | An audit of diabetes care at 3 centres in Alexandria | |
| Herrin et al. | Cost and effects of performance feedback and nurse case management for medicare beneficiaries with diabetes: a randomized controlled trial | |
| Chauhan | A mobile platform for non-invasive diabetes screening | |
| LU504548B1 (en) | Intelligent early screening model and construction method thereof for alzheimer's disease | |
| Mamtora et al. | Assessing the clinical utility of point of care HbA1c in the ophthalmology outpatient setting | |
| US20240136071A1 (en) | Intelligent early screening model and construction method thereof for alzheimer’s disease | |
| Stein et al. | Patient‐Reported Outcomes in Cancer: Application and Utility in Clinical Practice and Research | |
| RU2696684C1 (en) | Method for determining types of cognitive disorders in patients with cerebral microangiopathy | |
| Hsu | Glucose Control and Behavior Psychology of a T2D Patient using GH-Method: Mentality-Personality Modeling via Math-Physical Medicine (No. 306) | |
| Horinouchi et al. | Polypharmacy in Japanese primary care and association with length of hospital stay: a prospective cohort study |
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 |