CN116364273A - CDSS-based metformin recommendation method, CDSS-based metformin recommendation system, terminal and medium - Google Patents
CDSS-based metformin recommendation method, CDSS-based metformin recommendation system, terminal and medium Download PDFInfo
- Publication number
- CN116364273A CN116364273A CN202310206734.4A CN202310206734A CN116364273A CN 116364273 A CN116364273 A CN 116364273A CN 202310206734 A CN202310206734 A CN 202310206734A CN 116364273 A CN116364273 A CN 116364273A
- Authority
- CN
- China
- Prior art keywords
- metformin
- target patient
- cdss
- blood glucose
- data
- 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
- XZWYZXLIPXDOLR-UHFFFAOYSA-N metformin Chemical compound CN(C)C(=N)NC(N)=N XZWYZXLIPXDOLR-UHFFFAOYSA-N 0.000 title claims abstract description 134
- 229960003105 metformin Drugs 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000008280 blood Substances 0.000 claims abstract description 108
- 210000004369 blood Anatomy 0.000 claims abstract description 108
- 238000012549 training Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 12
- 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 64
- 239000008103 glucose Substances 0.000 claims description 64
- 238000012544 monitoring process Methods 0.000 claims description 16
- 230000000291 postprandial effect Effects 0.000 claims description 16
- 102000017011 Glycated Hemoglobin A Human genes 0.000 claims description 12
- 108010014663 Glycated Hemoglobin A Proteins 0.000 claims description 12
- 235000012054 meals Nutrition 0.000 claims description 12
- 206010012601 diabetes mellitus Diseases 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 235000005911 diet Nutrition 0.000 claims description 6
- 230000037213 diet Effects 0.000 claims description 6
- 230000002218 hypoglycaemic effect Effects 0.000 claims description 6
- 208000002249 Diabetes Complications Diseases 0.000 claims description 5
- 208000013016 Hypoglycemia Diseases 0.000 claims description 5
- 206010022489 Insulin Resistance Diseases 0.000 claims description 5
- 150000001720 carbohydrates Chemical class 0.000 claims description 5
- 235000014633 carbohydrates Nutrition 0.000 claims description 5
- 235000006694 eating habits Nutrition 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 208000001380 Diabetic Ketoacidosis Diseases 0.000 claims description 4
- 206010019280 Heart failures Diseases 0.000 claims description 4
- 206010067584 Type 1 diabetes mellitus Diseases 0.000 claims description 4
- 230000001154 acute effect Effects 0.000 claims description 4
- 230000037396 body weight Effects 0.000 claims description 4
- 208000015181 infectious disease Diseases 0.000 claims description 4
- 210000004185 liver Anatomy 0.000 claims description 4
- 208000035408 type 1 diabetes mellitus 1 Diseases 0.000 claims description 4
- 206010062237 Renal impairment Diseases 0.000 claims description 3
- 230000005977 kidney dysfunction Effects 0.000 claims description 3
- 208000019423 liver disease Diseases 0.000 claims description 3
- 230000005976 liver dysfunction Effects 0.000 claims description 3
- 208000004104 gestational diabetes Diseases 0.000 abstract description 28
- 230000035935 pregnancy Effects 0.000 abstract description 9
- 239000003814 drug Substances 0.000 description 23
- 229940079593 drug Drugs 0.000 description 13
- 230000002641 glycemic effect Effects 0.000 description 3
- 206010012655 Diabetic complications Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 201000001421 hyperglycemia Diseases 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 208000000857 Hepatic Insufficiency Diseases 0.000 description 1
- 208000001647 Renal Insufficiency Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000002552 dosage form Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012552 review Methods 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a CDSS-based (compact digital single-shot) metformin recommendation method, a CDSS-based metformin recommendation system, a CDSS-based metformin recommendation terminal and a CDSS-based metformin recommendation medium, relates to the technical field of physiological signal processing, and solves the problem that a real-time and accurate metformin use recommendation scheme aiming at gestational diabetes patients is not available. The technical key points are as follows: the prediction model of the recommended scheme of the metformin is obtained by carrying out statistics and training on clinical data of historical gestational diabetics. When the blood sugar control of the gestational diabetes mellitus patient is not ideal, inputting clinical index data of the gestational diabetes mellitus patient into a metformin use recommended scheme prediction model to obtain a metformin use recommended scheme of the gestational diabetes mellitus patient. So as to achieve the aims of timely and effectively recommending the recommended proposal for the use of the metformin to the diabetics in gestation period and improving the accuracy of the recommended proposal for the use of the metformin.
Description
Technical Field
The invention relates to the technical field of physiological signal processing, in particular to a CDSS-based metformin recommendation method, a CDSS-based metformin recommendation system, a CDSS-based metformin recommendation terminal and a CDSS-based metformin recommendation medium.
Background
Gestational diabetes mellitus (Gestational Diabetes Mellitus, GDM) refers to hyperglycemia that occurs in women during pregnancy, has become the most common complication in gestation, and the incidence rate of gestational diabetes mellitus in China is about 14.8%, so that the health of mother and infant is seriously endangered. The clinical auxiliary decision support system (Clinical Decision Support System, CDSS) fully utilizes available and proper computer technology, improves and improves the decision efficiency through a man-machine interaction mode, takes the computer technology and the mobile medical technology as implementation means, and provides decision advice for patients and medical staff. The metformin is taken as the only recommended oral hypoglycemic medicament for diagnosis and treatment guidelines of gestational hyperglycemia, not only can effectively control the blood sugar of gestational diabetes patients, but also can reduce the occurrence rate of bad pregnancy ending, and the effectiveness and short-term safety of the metformin are proved. In recent years, CDSS is increasingly applied to diabetes management, but the field of drug recommendation for gestational diabetes patients is not yet related, and a real-time and accurate drug use recommendation method for gestational diabetes patients is lacking.
Disclosure of Invention
The invention aims to provide a CDSS-based metformin use recommendation method, a CDSS-based metformin use recommendation system, a CDSS-based metformin use recommendation terminal and a CDSS-based metformin use recommendation medium, wherein a metformin use recommendation scheme prediction model is obtained by carrying out statistics and training on clinical data of historical gestational diabetes patients. When the blood sugar control of the gestational diabetes mellitus patient is not ideal, inputting clinical index data of the gestational diabetes mellitus patient into a metformin use recommended scheme prediction model to obtain a metformin use recommended scheme of the gestational diabetes mellitus patient. So as to achieve the aims of timely and effectively recommending the recommended proposal for the use of the metformin to the diabetics in gestation period and improving the accuracy of the recommended proposal for the use of the metformin.
The technical aim of the invention is realized by the following technical scheme:
a CDSS-based metformin recommendation method comprising the operations of: s1, acquiring clinical data of a historical patient in a database, wherein each clinical data comprises first index data of a clinical index and metformin usage data corresponding to the first index data; s2, training the first index data and the metformin usage data in the clinical data as training objects to obtain a metformin usage recommendation scheme prediction model; s3, identifying the user information of the target patient, and if the identification is successful, executing S4; s4, acquiring second index data of clinical indexes of the target patient; s5, inputting the second index data into a metformin use recommended scheme prediction model to obtain a metformin use recommended scheme of a target patient; s6, monitoring the blood glucose value of the target patient after the metformin is adopted to use the recommended scheme, and obtaining a monitoring result.
Further, the clinical indicators include age, body weight, body mass index, insulin sensitivity coefficient, carbohydrate coefficient, diabetes type, course of diabetes, blood routine examination data, eating habits, blood glucose, history of hypoglycemia, diabetic complications.
Further, in S3, the identifying process of the target patient user information includes: s31, acquiring a blood sugar control state of a target patient, and executing S32 if the blood sugar control state of the target patient is not ideal; s32, judging whether the target patient is a metformin usage contraindicated crowd, if not, executing S33; s33, acquiring a selection result of the target patient on the use of the metformin, and if the selection result is yes, successfully identifying the user information of the target patient.
Further, in S31, the process of obtaining the blood glucose control state of the target patient is: constructing a threshold value group for judging the blood sugar control state of the target patient, wherein the threshold value group is used for limiting the values of fasting blood sugar, pre-meal blood sugar, 1-hour postprandial blood sugar, 2-hour postprandial blood sugar and glycosylated hemoglobin of the target patient; collecting fasting blood glucose, pre-meal blood glucose, 1 hour post-meal blood glucose, 2 hours post-meal blood glucose and glycosylated hemoglobin values of a target patient after 1-2 weeks using a diet exercise instruction regimen; if the fasting blood glucose level, the pre-meal blood glucose level, the 1-hour postprandial blood glucose level, the 2-hour postprandial blood glucose level and the glycosylated hemoglobin level of the target patient do not meet the threshold set, the blood glucose control state of the target patient is ideal for blood glucose control; otherwise, the blood glucose control state of the target patient is not ideal.
Further, in S32, the metformin usage contraindicated population includes insulin dependent diabetes mellitus, liver and kidney insufficiency, heart failure, diabetic ketoacidosis and acute infections.
Further, clinical data of the historical patient in the database is obtained by using a named entity recognition algorithm.
A CDSS-based metformin recommendation system comprising: a database in which clinical data of historical patients are stored, wherein each clinical data comprises first index data of clinical indexes and metformin usage data corresponding to the first index data; the first acquisition module is used for acquiring clinical data of historical patients in the database; the training module is used for training the first index data and the metformin use data in the clinical data to obtain a metformin use recommended scheme prediction model; the identification module is used for identifying the user information of the target patient; the second acquisition module is used for acquiring second index data of the clinical index of the target patient after the user information of the target patient is successfully identified; the input module is used for inputting the second index data into a metformin use recommended scheme prediction model so as to obtain a metformin use recommended scheme of a target patient; and the monitoring module is used for monitoring the blood glucose value of the target patient after adopting the metformin use recommended scheme to obtain a monitoring result.
Further, the identification module comprises a first acquisition unit, a processing unit and a second acquisition unit; the first acquisition unit is used for acquiring the blood sugar control state of the target patient; the processing unit is used for judging the blood sugar control state of the target patient, and judging whether the target patient is a metformin use contraindication crowd when the blood sugar control state of the target patient is not ideal; the second obtaining unit is used for obtaining a selection result of the target patient on the use of the metformin when the target patient is a non-metformin use contraindicated crowd; the processing unit is further used for judging a selection result of the target patient, and if the selection result is yes, the user information of the target patient is successfully identified.
An electronic terminal, comprising: a memory for storing a computer program; and the processor is used for executing the computer program stored in the memory so as to enable the electronic terminal to execute the CDSS-based metformin recommendation method.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the CDSS-based metformin recommendation method.
Compared with the prior art, the invention has the following beneficial effects:
the prediction model of the recommended scheme of the metformin is obtained by carrying out statistics and training on clinical data of historical gestational diabetics. When the blood sugar control of the gestational diabetes mellitus patient is not ideal, inputting clinical index data of the gestational diabetes mellitus patient into a metformin use recommended scheme prediction model to obtain a metformin use recommended scheme of the gestational diabetes mellitus patient. So as to achieve the aims of timely and effectively recommending the recommended proposal for the use of the metformin to the diabetics in gestation period and improving the accuracy of the recommended proposal for the use of the metformin.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:
FIG. 1 is a schematic flow chart of a method for recommending metformin based on CDSS in an embodiment;
fig. 2 is a schematic structural diagram of a CDSS-based metformin recommendation system in an embodiment.
In the drawings, the reference numerals and corresponding part names:
1-a database; 2-a first acquisition module; 3-a training module;
4-an identification module; 41-a first acquisition unit; 42-a processing unit; 43-a second acquisition unit;
5-a second acquisition module; 6-an input module; 7-a monitoring module.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
The CDSS-based metformin recommendation method provided in this embodiment includes the following operations:
step1, acquiring clinical data of historical patients in a database, wherein each clinical data comprises first index data of a clinical index and metformin usage data corresponding to the first index data;
specifically, a blood sugar information database of gestational diabetes patients is constructed through Python language, django framework and MySQL database, and clinical indexes such as age, body weight, body mass index, insulin sensitivity coefficient, carbohydrate coefficient, diabetes typing, diabetes course, blood routine examination data, eating habits, blood sugar, hypoglycemia history, diabetes complication condition and the like are set in the database. The database stores a plurality of first index data of historical gestational diabetes patients, wherein the first index data corresponds to clinical indexes, and comprises clinical index values of age, weight, body mass index, insulin sensitivity coefficient, carbohydrate coefficient, diabetes type, diabetes course, blood routine examination data, eating habits, blood sugar, hypoglycemia history, diabetes complication condition and the like of the historical gestational diabetes patients. At the same time, the database also contains the historical usage data of the gestational diabetes patients on the metformin and other medicines.
Clinical data of historical patients in the database is obtained by using a named entity recognition algorithm.
Specifically, the word "metformin" is used for searching from a database to obtain clinical data of historical gestational diabetes patients, wherein the clinical data comprises first index data of the historical gestational diabetes patients and metformin usage data, and the metformin usage data mainly comprises the medication indication, medication contraindication, medication name and type, medication time, medication method, medication dosage and medication dosage form of the metformin.
Step2, training the first index data and the metformin usage data in the clinical data as training subjects to obtain a metformin usage recommendation scheme prediction model;
in this embodiment, the first index data and the metformin usage data in the clinical data are trained by using a deep learning model, wherein the deep learning model includes a convolutional neural network composed of an input layer, an output layer, and a hidden layer disposed between the input layer and the output layer.
Specifically, the input layer acquires first index data and metformin usage data of a historical gestational diabetes patient, and constructs a training sample containing the first index data and the metformin usage data. And labeling a blood glucose value in the first data of each historical gestational diabetes patient as a label of a training sample, the blood glucose value comprising: fasting blood glucose level, pre-meal blood glucose level, 1 hour post-meal blood glucose level, 2 hours post-meal blood glucose level, and glycosylated hemoglobin level. The hidden layer trains the metformin usage data in the training samples based on the training samples marked with the labels so as to learn the metformin usage data of diabetics in different historic gestational periods and obtain a metformin usage recommendation scheme prediction model. And outputting the metformin usage recommendation prediction model through an output layer.
Step3, identifying user information of the target patient, and if the identification is successful, executing Step4;
in this embodiment, in Step3, the identification process of the target patient user information includes:
step31, obtaining the blood sugar control state of the target patient, and if the blood sugar control state of the target patient is not ideal, executing Step32;
in Step31, the blood glucose control state of the target patient is obtained by the following steps: constructing a threshold value group for judging the blood sugar control state of the target patient, wherein the threshold value group is used for limiting the values of fasting blood sugar, pre-meal blood sugar, 1-hour postprandial blood sugar, 2-hour postprandial blood sugar and glycosylated hemoglobin of the target patient; collecting fasting blood glucose, pre-meal blood glucose, 1 hour post-meal blood glucose, 2 hours post-meal blood glucose and glycosylated hemoglobin values of a target patient after 1-2 weeks using a diet exercise instruction regimen; if the fasting blood glucose level, the pre-meal blood glucose level, the 1-hour postprandial blood glucose level, the 2-hour postprandial blood glucose level and the glycosylated hemoglobin level of the target patient do not meet the threshold set, the blood glucose control state of the target patient is ideal for blood glucose control; otherwise, the blood glucose control state of the target patient is not ideal.
Specifically, a threshold set for determining a target patient glycemic control state: fasting blood glucose and preprandial blood glucose are greater than 5.3mmol/L, postprandial 1h is greater than 7.8mmol/L, postprandial 2h blood glucose is greater than 6.7mmol/L, and glycosylated hemoglobin (HbA 1 c) is greater than 5.5%, wherein the target patient is a gestational diabetes patient serving as a detection subject.
The method comprises the steps of collecting fasting blood glucose values, pre-meal blood glucose values, postprandial 1-hour blood glucose values, postprandial 2-hour blood glucose values and glycosylated hemoglobin values of a target patient after 1-2 weeks using a diet exercise guidance scheme, comparing the collected values with a threshold group, and if the collected values do not meet the threshold group, considering that diet and exercise treatment are ideal in blood glucose control, and suggesting that the target patient continues to use the diet exercise guidance scheme. Otherwise, the "blood glucose control state of the target patient is considered to be the non-ideal blood glucose control", and Step32 is performed. Wherein fasting blood glucose refers to blood glucose levels at which no heat is taken for at least 8 hours. Pre-meal blood glucose refers to the blood glucose level before three meals.
Step32, judging whether the target patient is a metformin usage contraindicated population, if not, executing Step33;
in Step32, the population of metformin use contraindications includes insulin dependent diabetes mellitus, liver and kidney dysfunction, heart failure, diabetic ketoacidosis and acute infections.
The target patient may be treated with metformin if the target patient is free of contraindications in insulin-dependent diabetes mellitus, liver and kidney dysfunction, heart failure, diabetic ketoacidosis and acute infections.
Step33, obtaining a selection result of the target patient on the use of the metformin, and if the selection result is yes, successfully identifying the user information of the target patient.
Specifically, when the target patient is a non-metformin contraindicated population, and can be treated with metformin, the selection result is made after obtaining the benefit and risk of the target patient for fully understanding the use of metformin during pregnancy, and Step4 is executed if the selection result of the target patient is consent to the use of metformin.
Step4, obtaining second index data of clinical indexes of the target patient;
specifically, the second index data includes clinical index values of age, body weight, body mass index, insulin sensitivity coefficient, carbohydrate coefficient, diabetes type, diabetes course, blood routine examination data, eating habits, blood sugar, history of hypoglycemia, diabetic complications, and the like of the target patient.
Step5, inputting the second index data into a metformin use recommended plan prediction model to obtain a metformin use recommended plan of the target patient;
specifically, after the second index data is input into the metformin use recommended plan prediction model, an initial plan of the metformin use recommended plan is obtained, and after the initial plan of the metformin use recommended plan is audited by a main doctor, an expert and the like of the target patient, the metformin use recommended plan of the target patient is obtained. The recommended regimen for use of metformin in the subject patient includes the time of administration of metformin, the method of administration, the type, the amount of the administered agent and expert reviews.
Step6. Monitoring the blood glucose level of the target patient after the recommended regimen of metformin use to obtain a monitoring result.
Specifically, after the target patient adopts the metformin use recommended scheme, the blood sugar value of the target patient is monitored so as to achieve the purposes of conveniently finding the blood sugar state of the target patient in time and adaptively adjusting the metformin use recommended scheme of the target patient according to the blood sugar state of the target patient.
Example 2
A CDSS-based metformin recommendation system comprising: a database 1, wherein clinical data of a historical patient are stored in the database 1, and each clinical data comprises first index data of a clinical index and metformin usage data corresponding to the first index data; a first acquisition module 2 for acquiring clinical data of a historic patient in the database 1; the training module 3 is used for training the first index data and the metformin usage data in the clinical data to obtain a metformin usage recommendation scheme prediction model; the identification module 4 is used for identifying the user information of the target patient; the second obtaining module 5 is used for obtaining second index data of the clinical index of the target patient after the user information of the target patient is successfully identified; an input module 6 for inputting the second index data into a metformin usage recommendation prediction model to obtain a metformin usage recommendation of the target patient; and the monitoring module 7 is used for monitoring the blood glucose value of the target patient after adopting the metformin use recommended scheme to obtain a monitoring result.
In this embodiment, the identification module 4 includes a first acquisition unit 41, a processing unit 42, and a second acquisition unit 43; the first obtaining unit 41 is configured to obtain a blood glucose control state of a target patient; the processing unit 42 is configured to determine a glycemic control state of the target patient, and determine whether the target patient is a population of metformin usage contraindications when the glycemic control state of the target patient is not ideal; the second obtaining unit 43 is configured to obtain a result of selecting the target patient to use metformin when the target patient is a non-metformin usage contraindicated population; the processing unit 42 is further configured to determine a selection result of the target patient, and if the selection result is yes, the user information of the target patient is successfully identified.
The embodiment also provides an electronic terminal, including: a memory for storing a computer program; and the processor is used for executing the computer program stored in the memory so as to enable the electronic terminal to execute the CDSS-based metformin recommendation method.
The present embodiment also provides a computer-readable storage medium having a computer program stored thereon, which when executed by a processor, implements the CDSS-based metformin recommendation method.
Term interpretation:
gestational diabetes is a common complication of gestation, and refers to abnormal sugar metabolism which occurs for the first time in gestation.
The clinical decision support system (Clinical Decision Support System, CDSS) is a computer application system for assisting clinical staff in decision making through data, models and the like by man-machine interaction, and is the application of artificial intelligence in medicine.
History patient: refers to a patient who has the same disease in the past.
Named entity recognition refers to the recognition of entities with specific meanings in texts, and mainly comprises drug names, proper nouns and the like. Among other things, the named entity identification may be used to obtain the patient's metformin medication information, such as the medical record number: 1122334 since the case number is the unique identification code of the patient, the case number of the patient is used to represent the patient, and the medicine code is obtained by inputting the identified medicine name into the medicine knowledge base according to the mapping relation between the medicine recorded in the medicine knowledge base and the code. For example, patient X case number: 1122334, the medicine (medicine Y:111; medicine Z:222; etc.) is identified, and then the information is integrated to obtain the medication information of the patient X {1122334, Y111, Z222}.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A CDSS-based metformin recommendation method comprising the operations of:
s1, acquiring clinical data of a historical patient in a database, wherein each clinical data comprises first index data of a clinical index and metformin usage data corresponding to the first index data;
s2, training the first index data and the metformin usage data in the clinical data as training objects to obtain a metformin usage recommendation scheme prediction model;
s3, identifying the user information of the target patient, and if the identification is successful, executing S4;
s4, acquiring second index data of clinical indexes of the target patient;
s5, inputting the second index data into a metformin use recommended scheme prediction model to obtain a metformin use recommended scheme of a target patient;
s6, monitoring the blood glucose value of the target patient after the metformin is adopted to use the recommended scheme, and obtaining a monitoring result.
2. The CDSS-based metformin recommendation method as claimed in claim 1, wherein:
the clinical index comprises age, body weight, body mass index, insulin sensitivity coefficient, carbohydrate coefficient, diabetes type, diabetes course, blood routine examination data, eating habit, blood sugar, hypoglycemia history, and diabetes complication.
3. The CDSS-based metformin recommendation method according to claim 1, wherein in S3, the identifying process of the target patient user information comprises:
s31, acquiring a blood sugar control state of a target patient, and executing S32 if the blood sugar control state of the target patient is not ideal;
s32, judging whether the target patient is a metformin usage contraindicated crowd, if not, executing S33;
s33, acquiring a selection result of the target patient on the use of the metformin, and if the selection result is yes, successfully identifying the user information of the target patient.
4. The CDSS-based metformin recommendation method according to claim 3, wherein in S31, the acquisition process of the blood glucose control state of the target patient is:
constructing a threshold value group for judging the blood sugar control state of the target patient, wherein the threshold value group is used for limiting the values of fasting blood sugar, pre-meal blood sugar, 1-hour postprandial blood sugar, 2-hour postprandial blood sugar and glycosylated hemoglobin of the target patient;
collecting fasting blood glucose, pre-meal blood glucose, 1 hour post-meal blood glucose, 2 hours post-meal blood glucose and glycosylated hemoglobin values of a target patient after 1-2 weeks using a diet exercise instruction regimen;
if the fasting blood glucose level, the pre-meal blood glucose level, the 1-hour postprandial blood glucose level, the 2-hour postprandial blood glucose level and the glycosylated hemoglobin level of the target patient do not meet the threshold set, the blood glucose control state of the target patient is ideal for blood glucose control; otherwise, the blood glucose control state of the target patient is not ideal.
5. A CDSS-based metformin recommendation method according to claim 3, wherein:
in S32, the population of metformin use contraindications includes insulin dependent diabetes mellitus, liver and kidney dysfunction, heart failure, diabetic ketoacidosis and acute infections.
6. The CDSS-based metformin recommendation method as claimed in claim 1, wherein:
clinical data of historical patients in the database is obtained by using a named entity recognition algorithm.
7. A CDSS-based metformin recommendation system comprising:
a database (1), wherein clinical data of a historical patient are stored in the database (1), and each clinical data comprises first index data of a clinical index and metformin usage data corresponding to the first index data;
a first acquisition module (2) for acquiring clinical data of a historic patient in a database (1);
the training module (3) is used for training the first index data and the metformin use data in the clinical data to obtain a metformin use recommended scheme prediction model;
an identification module (4) for identifying user information of a target patient;
the second acquisition module (5) is used for acquiring second index data of the clinical index of the target patient after the user information of the target patient is successfully identified;
an input module (6) for inputting the second index data into a metformin use recommended plan prediction model to obtain a metformin use recommended plan of the target patient;
and the monitoring module (7) is used for monitoring the blood glucose value of the target patient after the metformin use recommended scheme is adopted, so as to obtain a monitoring result.
8. The CDSS-based metformin recommendation system as in claim 7 wherein:
the identification module (4) comprises a first acquisition unit (41), a processing unit (42) and a second acquisition unit (43);
the first acquisition unit (41) is used for acquiring the blood sugar control state of a target patient;
the processing unit (42) is used for judging the blood sugar control state of the target patient, and judging whether the target patient is a metformin use contraindication crowd when the blood sugar control state of the target patient is not ideal;
the second obtaining unit (43) is used for obtaining a selection result of the target patient on the use of the metformin when the target patient is a non-metformin use contraindicated population;
the processing unit (42) is further configured to determine a selection result of the target patient, and if the selection result is yes, the user information of the target patient is successfully identified.
9. An electronic terminal, comprising:
a memory for storing a computer program;
a processor for executing the computer program stored in the memory to cause an electronic terminal to perform the CDSS-based metformin recommendation method in accordance with any one of claims 1 to 6.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: the program when executed by a processor implements the CDSS-based metformin recommendation method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310206734.4A CN116364273A (en) | 2023-03-06 | 2023-03-06 | CDSS-based metformin recommendation method, CDSS-based metformin recommendation system, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310206734.4A CN116364273A (en) | 2023-03-06 | 2023-03-06 | CDSS-based metformin recommendation method, CDSS-based metformin recommendation system, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116364273A true CN116364273A (en) | 2023-06-30 |
Family
ID=86911564
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310206734.4A Pending CN116364273A (en) | 2023-03-06 | 2023-03-06 | CDSS-based metformin recommendation method, CDSS-based metformin recommendation system, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116364273A (en) |
-
2023
- 2023-03-06 CN CN202310206734.4A patent/CN116364273A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Beck et al. | Effect of continuous glucose monitoring on glycemic control in adults with type 1 diabetes using insulin injections: the DIAMOND randomized clinical trial | |
| O’Halloran et al. | Characterizing the patients, hospitals, and data quality of the eICU collaborative research database | |
| EP2710502A1 (en) | Dynamic data collection | |
| Afsaneh et al. | Recent applications of machine learning and deep learning models in the prediction, diagnosis, and management of diabetes: a comprehensive review | |
| US20210311070A1 (en) | Healthcare management method | |
| JPWO2020013230A5 (en) | ||
| WO2021073255A1 (en) | Time series clustering-based medication reminder method and related device | |
| Tamin et al. | Implementation of C4. 5 algorithm to determine hospital readmission rate of diabetes patient | |
| Carpentier et al. | The relationship of illness uncertainty and attributional style to long-term psychological distress in parents of children with type 1 diabetes mellitus | |
| CN116246768B (en) | MRI image inspection intelligent analysis management system based on artificial intelligence | |
| JP2023524473A (en) | Adaptive decision support system | |
| CN110534167B (en) | Diabetic patient medical care system based on personalized diary | |
| JP2003302406A (en) | Self blood sugar measurement system and self-blood sugar measurement unit | |
| CN113571180A (en) | C-peptide layering and organ function-based type 2 diabetes artificial intelligent diagnosis and treatment management system | |
| CN116364273A (en) | CDSS-based metformin recommendation method, CDSS-based metformin recommendation system, terminal and medium | |
| US11990238B2 (en) | Decision support and treatment administration systems | |
| CN111261257A (en) | Diabetes recommended medication method, storage medium and system based on big data | |
| KR20200029747A (en) | Semantically intelligent clinical decision support system for diabetes mellitus treatment | |
| Jemima Jebaseeli et al. | Machine learning and Internet of Things techniques to assist the type I diabetic patients to predict the regular optimal insulin dosage | |
| CN116453681A (en) | Intelligent insulin recommendation method and system and electronic equipment | |
| DeJoseph et al. | Death investigation of diabetes mellitus: Scene investigation and interrogation of technology | |
| US20220230751A1 (en) | Decision support system, and method in relation thereto | |
| Zhu et al. | Risk feature assessment of readmission for diabetes | |
| Hatlen et al. | Severe ketoacidosis in a patient taking an SGLT2 inhibitor for diabetes | |
| Colloff | The promise of technology in the management of the patient with diabetes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |