CN112102956A - Method and system for improving compliance of diabetic patient - Google Patents
Method and system for improving compliance of diabetic patient Download PDFInfo
- Publication number
- CN112102956A CN112102956A CN202011088912.0A CN202011088912A CN112102956A CN 112102956 A CN112102956 A CN 112102956A CN 202011088912 A CN202011088912 A CN 202011088912A CN 112102956 A CN112102956 A CN 112102956A
- Authority
- CN
- China
- Prior art keywords
- compliance
- data
- patient
- model
- score
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 206010012601 diabetes mellitus Diseases 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 50
- 238000002372 labelling Methods 0.000 claims abstract description 17
- 230000006399 behavior Effects 0.000 claims description 39
- 239000003814 drug Substances 0.000 claims description 28
- 201000010099 disease Diseases 0.000 claims description 26
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 26
- 238000004140 cleaning Methods 0.000 claims description 19
- 230000036541 health Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 19
- 235000005911 diet Nutrition 0.000 claims description 17
- 230000037213 diet Effects 0.000 claims description 17
- 230000001737 promoting effect Effects 0.000 claims description 16
- 229940079593 drug Drugs 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 11
- 230000000694 effects Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 8
- 230000008094 contradictory effect Effects 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims description 5
- 230000005585 lifestyle behavior Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000005406 washing Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 description 26
- 230000008569 process Effects 0.000 description 11
- 208000017667 Chronic Disease Diseases 0.000 description 9
- 239000008280 blood Substances 0.000 description 8
- 210000004369 blood Anatomy 0.000 description 8
- 210000004556 brain Anatomy 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 230000002829 reductive effect Effects 0.000 description 6
- 230000000474 nursing effect Effects 0.000 description 5
- 206010061623 Adverse drug reaction Diseases 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 3
- 230000036772 blood pressure Effects 0.000 description 3
- 230000006866 deterioration Effects 0.000 description 3
- 206010061819 Disease recurrence Diseases 0.000 description 2
- 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 description 2
- 206010020751 Hypersensitivity Diseases 0.000 description 2
- 208000026935 allergic disease Diseases 0.000 description 2
- 230000007815 allergy Effects 0.000 description 2
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000002980 postoperative effect Effects 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 108091005515 EGF module-containing mucin-like hormone receptors Proteins 0.000 description 1
- 206010048038 Wound infection Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000013502 data validation Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001647 drug administration Methods 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 238000002079 electron magnetic resonance spectroscopy Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000009207 exercise therapy Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 230000006651 lactation Effects 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 230000008774 maternal effect Effects 0.000 description 1
- 230000002906 microbiologic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000021049 nutrient content Nutrition 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000000399 orthopedic effect Effects 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000144 pharmacologic effect Effects 0.000 description 1
- 230000035935 pregnancy Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 208000001072 type 2 diabetes mellitus Diseases 0.000 description 1
- 238000010200 validation analysis 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
- G16H50/70—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a system and a method for improving compliance of a diabetic patient, wherein the system comprises the following steps: the compliance service platform comprises a data acquisition module, a tag model, a compliance calculation engine and a compliance model, wherein the tag model is respectively connected with the acquisition module and the compliance calculation engine, and the compliance calculation engine is respectively connected with the compliance model and the client; the method comprises the following steps: s1, collecting medical data and follow-up visit management data of the patient; s2, labeling the basic attribute data and behavior data of the patient in the collected data; s3, transmitting the tagged data to a compliance calculation engine; s4, the compliance calculation engine calculates the compliance score of the patient through the compliance rule model, and obtains the compliance grade and the compliance promotion scheme through the compliance score; and S5, pushing the calculation result of the compliance to the client.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a method and a system for improving compliance of a diabetic patient.
Background
Compliance by diabetic patients refers to the extent to which the patient has performed physician orders and follow-up content, which underlies the effectiveness of medication. Among the factors that affect the therapeutic effect of drugs, the independence of patients is increasingly attracting the attention of medical workers
The diabetes patients in China are gradually developing towards the trend of youth and upgrowth, and the diabetes is different from the common diseases in that the diabetes generally needs to be observed and treated for a long time. Diabetes is mainly treated by outpatient follow-up or after-hospital follow-up, and the professional guidance of doctors can slow down the natural course of diseases, reverse the deterioration, reduce complications and improve the quality of life. However, due to the limitation of manpower and financial resources and insufficient attention, the follow-up visit of chronic diseases is always a vacuum zone for clinical research and clinical practice in the medical field. Doctors cannot accurately tell the number, kind and characteristics of the managed chronic diseases, and the patient's data is also spread among different departments and doctors.
In the prior art, most follow-up notes filled by doctors are adopted for management or follow-up visits are carried out through telephones, but the system collection and the structured management of data of patients cannot be realized, the management compliance of the patients cannot be effectively promoted, reasonable intervention suggestions cannot be given, and the treatment effect of the patients cannot be improved.
Therefore, necessary management, slowing down and even restraining the increase of the morbidity rate are not easy. The management compliance efficiency of chronic patients is effectively improved, the disease deterioration can be effectively reduced, the patient happiness is enhanced, but the existing products on the market are relatively deficient in cognition and research aiming at the management of the patient compliance.
Traditional medical institution management patient mode is mainly based on face-to-face communication, and is hindered by factors such as space, time and the like. The products for improving the patient compliance on the market are all based on patient information records, regularly remind medical staff to track the compliance of patients, medical staff such as doctors, nurses and the like are mainly called by telephone return visits, the patient compliance is mainly judged by the subjective judgment of the medical staff, oral propaganda and education are mainly carried out, the medical staff does not summarize the return visits in the system, summarize, effectively associate the patient conditions and do not take active measures, meanwhile, the chronic disease patients have great differences and defects in medical management, including insufficient capacity of chronic disease management staff, backward education modes of medical management and the like. Resulting in poor patient compliance. The compliance of the medical management of patients is poor, which not only affects the self health and treatment effect, but also affects the clinical judgment of medical staff, and even increases the social and economic burden.
Disclosure of Invention
In order to solve the defects of the prior art and achieve the purpose of improving the compliance of the medical management of patients, the invention adopts the following technical scheme:
a method of increasing compliance in a diabetic patient comprising the steps of:
s1, collecting medical data and follow-up visit management data of the patient;
s2, labeling the basic attribute data and behavior data of the patient in the collected data;
s3, transmitting the tagged data to a compliance calculation engine;
s4, the compliance calculation engine calculates the compliance score of the patient through the compliance rule model, and obtains the compliance grade and the compliance promotion scheme through the compliance score, the patient and the corresponding label data enter the compliance rule model, the compliance score of the matched patient is calculated according to the preset conditions in the compliance rule model, the compliance grade is divided according to the division rule of the score and the grade, the matching is carried out according to the score and the score interval corresponding to the promotion mode in the compliance rule model, and the matched promotion modes are combined to generate the compliance promotion task;
and S5, pushing the calculation result of the compliance to the client.
In the step S2, before tagging, data cleaning is performed on the collected data to clean basic attribute data and behavior data of the patient, where the behavior data includes medical behavior data, reading behavior data, health assessment behavior data, questionnaire survey behavior data, lifestyle behavior data, health monitoring behavior data, and communication activity behavior data, the data cleaning screens out basic attribute and behavior data related to the diabetic patient, eliminates other erroneous and invalid data, combines word-polysemy repeated data, and the data cleaning is also a classification process, so that the efficiency of tagging the cleaned data in the later period is improved, and the final tagging of data is facilitated.
The data cleaning comprises the following steps:
s21, preprocessing, loading the extracted source data in batches into a cleaning pool for processing, verifying the source data, including field interpretation, data source, code table of the source data and judging whether the information described by the data is complete, extracting the data difficult to identify, and manually checking the data which is difficult to identify and understand because of the medical data, wherein the data is intuitively understood by manual checking, and some problems are preliminarily found to prepare for later improvement, identification or other processing;
s22, cleaning missing values, determining the missing value range, filling missing contents, calculating the missing value proportion of each field, and formulating an information completion strategy according to the importance and the missing proportion of the data, wherein the completion mode comprises the following steps:
(1) filling missing values by business knowledge or experience speculation;
(2) filling missing values with the calculation results (mean, median, mode, etc.) of the same index;
(3) filling missing values according to the calculation results of different indexes;
then removing unnecessary fields, and for data with high importance and high loss rate, re-stocking the data, and sending a notice to a service handler by automatically identifying the fields with high importance and high loss rate;
and S23, format content cleaning, wherein when the source data is formatted data, only the following parts need to be cleaned:
(1) the display formats of time, date, numerical value, full half angle and the like are inconsistent;
(2) there are characters in the content that should not be present;
(3) the content should not be consistent with the field;
usually, the formatted data is a system log and the like, the format and the content of the formatted data are consistent with the data after cleaning, and only part of the format needs to be modified, so that the intensity of data processing is reduced, and the efficiency of data processing is improved;
and S24, performing logical error cleaning, including removing duplication, removing unreasonable values and correcting contradictory contents, wherein the unreasonable values are data which do not conform to natural rules, the correcting contradictory contents are data which are compared and contain the same patient attributes or behaviors, but key fields of the data are different, and the contradictory fields are corrected according to the importance of the data.
Establishing a unique index number of the patient, wherein the rule sequence is as follows:
(1) when the serial number is not empty, generating a unique index number of the patient by the serial number, the service data source, the name and the hospital code;
(2) when the identity card is not empty, the unique index number of the patient is generated by the identity card, the name and the hospital code;
(3) when the outpatient service number is not empty, generating a unique index number of the patient by the outpatient service number, the service data source, the name and the hospital code;
(4) when the business data index is not empty, generating a unique index number of the patient by the business data index number + name + hospital code;
(5) when the mobile phone number is not empty, the mobile phone number + name + hospital code generates a patient unique index number.
Through the above sequence, the uniqueness between the patient and the index number is ensured as much as possible in the face of numerous data which may have errors.
The labeling in step S2 is to match the specific content of the basic attribute data and behavior data of the patient with the content of the label and the range defined by the label, and when the specific content matches the content of the label or falls within the range defined by the label, attach a corresponding label to the specific content, where the labeling process is a content matching process and a range matching process, and not only marks the corresponding label to the specific content, but also performs a clustering process for scattered data in the same label range, thereby playing a role of data funnel.
In step S3, the compliance calculation engine receives the labeled data of the patient, selects different compliance promotion models according to the patient 'S scheduled tasks, and verifies the labeled data with the input data required by the models, where the patient' S scheduled tasks are the tasks required to be completed for the patient generated after discharge from the hospital.
The client feeds back the implementation result of the patient compliance promotion scheme, and the preset conditions are adjusted according to the implementation result, so that the compliance rule model is complied with.
A system for improving compliance of a diabetic patient comprises a compliance service platform and a client, wherein the compliance service platform comprises a data acquisition module, a label model, a compliance calculation engine and a compliance model, the label model is respectively connected with the acquisition module and the compliance calculation engine, the compliance calculation engine is respectively connected with the compliance model and the client, the acquisition module acquires patient data, the compliance model is labeled, the compliance score is calculated through the compliance calculation engine through the compliance model, a compliance grade and a compliance promotion task are obtained through the compliance score and are issued to the client, the client displays the compliance score, and the compliance promotion task is processed.
The label model comprises a patient basic information model, a patient disease model and a patient adverse drug reaction and medication contraindication model, the three models are respectively labeled according to specific contents of patient basic attribute data and behavior data, the labeling process is a content matching process and a range matching process, not only is a corresponding label marked for the specific contents, but also a clustering process is carried out on scattered data in the same label range, and the function of a data funnel is achieved.
The compliance calculation engine is connected with a knowledge base, the knowledge base comprises a basic attribute index base, a medical action index base, a reading and evaluation index base, a diet exercise index base and a physical sign monitoring index base, different indexes provide promotion modes for actions causing poor compliance, provide targeted promotion modes for a large amount of patient data input by the system, and simultaneously construct a knowledge graph for combing, extracting, fusing and reasoning knowledge after diagnosis and quality evaluation to form services of information retrieval, knowledge question answering, risk identification, follow-up access path analysis and the like.
The invention has the advantages and beneficial effects that:
the medical behavior data of the collected patient, the basic attribute data and the management tracking data are labeled to form a complete health portrait of the patient, the labeled data are transmitted to a compliance calculation engine, the compliance calculation engine is responsible for allocating and calculating compliance values, grading is carried out according to the compliance values, poor compliance is achieved, unreasonable items are used for generating compliance promotion tasks, the compliance promotion tasks are sent to a client through a message queue, the whole process is automatically completed by a system, correct promotion modes are timely adopted when the compliance is automatically found out to be insufficient, the management cost is greatly reduced, the efficiency is improved, the compliance of the patient can be effectively improved to slow down or even inhibit the state of the patient, and the deterioration of the state of the patient is reduced.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of the system of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
As shown in fig. 1, a method for improving compliance of a diabetic patient, comprising the steps of:
firstly, medical data and follow-up visit management data of a patient are collected.
The medical data is mainly acquired by patient data generated by systems such as HIS, LIS, PACS, follow-up visit and the like of a hospital, and the mainly acquired data comprises:
patient basic information, visit information (outpatient, emergency), prescription information, prescription details information, examination reports, examination results, microbiological examination results, outpatient costs, admission records, hospitalization costs, hospitalization advice, surgical records, examination application sheets, outpatient costs details, hospitalization costs details, outpatient costs settlement information, hospitalization costs settlement information, examination samples, follow-up information.
The follow-up management data includes: the living habits, eating habits, exercise habits, reading types, information exchange and the like of the patients.
And secondly, labeling the basic attributes and behaviors of the patient in the acquired data through a label model to form a patient health portrait.
And (3) carrying out data cleaning and labeling on the acquired data, wherein labeling refers to abstracting a labeled user image from information such as basic attributes, living habits, medical behaviors and the like of a patient through a label model. The patient representation is constructed using a "tagging scheme" that is a highly refined signature from analysis of user information. Through drawing pictures, the patient can be known more intuitively and accurately, the compliance of the patient can be predicted, and a compliance promotion scheme more suitable for the patient is recommended.
According to the collected data, basic attribute data, medical behavior data, reading behavior data, health assessment behavior data, questionnaire survey behavior data, life habit behavior data, health monitoring behavior data and communication activity behavior data of the patient are cleaned, and the method specifically comprises the following steps:
patient basic attribute data: age, occupation, gender, family history;
medical behavior data: the compound is used for the treatment of the disease;
reading behavior data: health promotion and education, and the like;
health assessment behavioral data: sleep assessment, disease risk assessment, etc.;
questionnaire behavioral data: medication situation survey, diet exercise survey, medical service survey, and the like;
lifestyle behavior data: exercise index, diet index, etc.;
health monitoring behavioral data: body weight, blood glucose, blood pressure, etc.;
and (3) communication activity data: telephone communications, etc.
The data cleaning comprises the following steps:
1. and preprocessing, namely loading the extracted source data into a cleaning pool in batches for processing, verifying the source data, including field interpretation, data source, code table and the like of the source data, and describing whether the information of the data is complete, extracting a part of data, visually knowing the data by using a manual viewing mode, preliminarily finding some problems and preparing for subsequent processing.
2. And cleaning missing values, determining missing content filled in a missing value range, calculating the missing value proportion of each field, and then formulating an information completion strategy according to the missing proportion and the field importance and the importance of data and the missing rate. The completion mode is as follows:
(1) filling missing values by business knowledge or experience speculation;
(2) filling missing values with the calculation results (mean, median, mode, etc.) of the same index;
(3) and filling the missing values with the calculation results of different indexes.
The unneeded fields are then removed, i.e. information that is not valuable for the dependency calculation is removed. If some indexes are very important and have high loss rate, the data needs to be fetched again, the fields with high loss rate are automatically identified, the indexes have high importance, meanwhile, the fields with high loss rate are met, a notice is sent to a service processing personnel, the service processing personnel judges whether other channels can fetch related data, and if so, the related data is added again.
3. Format content cleaning, when the source data is formatted data, only the following parts need to be cleaned:
(1) the display formats of time, date, numerical value, full half angle and the like are inconsistent;
(2) there are characters in the content that should not be present;
(3) the content should not be consistent with the field;
usually, the formatted data is a system log and the like, the format and the content of the formatted data are consistent with the data after cleaning, and only part of the format needs to be modified, so that the intensity of data processing is reduced, and the efficiency of data processing is improved.
4. Logical error clean-up, including deduplication, removes unreasonable values, such as patient age data of 200 years, corrects contradictory content, and can be verified against each other by fields, such as where the identification number is 1101031980XXXXXXXX, but the age is 18 years.
5. A patient unique index number is established since the patient data is derived from many sources such as: the data between all systems are required to be identified to be originated from the same patient, the patient unique index number is established for the patient, and the rule sequence for establishing the patient unique index number is as follows:
(1) when the serial number is not empty, generating a unique index number of the patient by the serial number, the service data source, the name and the hospital code;
(2) when the identity card is not empty, the unique index number of the patient is generated by the identity card, the name and the hospital code;
(3) when the outpatient service number is not empty, generating a unique index number of the patient by the outpatient service number, the service data source, the name and the hospital code;
(4) when the business data index is not empty, generating a unique index number of the patient by the business data index number + name + hospital code;
(5) when the mobile phone number is not empty, the mobile phone number + name + hospital code generates a patient unique index number.
The label model is constructed, most of collected data are unordered and incomplete, basic attribute data and behavior data of a patient are cleaned out and are input into the corresponding label model, the label model can be used for marking the label for the patient, for example, the label for the patient 1 comprises middle-aged, male and type II diabetes and medical history for 3 years, and for example, the label model can be divided into 1-3 years old according to age groups and is a baby and 60-70 old people, after the age of the patient is input, the age model can output the age group to which the patient belongs, the label model is a labeling process for the patient, and meanwhile, the label model is also used for data clustering and plays a role of a data funnel. The model comprises the following:
(1) constructing a basic information model of the patient: through data such as population information, physical examination reports, electronic health records and the like, model labels including patient gender, age, blood type, occupation (special occupation), allergy history, planned immunity, maternal and child health and the like are extracted.
(2) Constructing a patient disease model: and obtaining model labels of the past disease history, chronic diseases, disease conditions, concomitant diseases and the like of the patient through data such as electronic medical records, electronic health files, examination and inspection and the like.
(3) Constructing adverse drug reaction and medication contraindication models of patients: the adverse drug reaction and contraindication model label is constructed according to the information of allergy history, adverse drug reaction history, diseases (particularly liver and kidney), pregnancy and lactation conditions, special occupation (high-altitude operation athletes), drug administration within two weeks and the like of a patient.
And thirdly, transmitting the patient tagged data to a compliance calculation engine.
The compliance calculation engine receives the labeled data of the patient, selects diabetes compliance promotion models with different paths according to the planned tasks of the patient and verifies the labeled data and the data required by the models; the planning task of the patient is that the follow-up system of the hospital generates a plan for completing the task for the patient every month after the diabetic patient is discharged from the hospital, such as: a re-diagnosis plan, a medicine taking plan, a propaganda and education, a questionnaire, a telephone follow-up plan and the like.
Data validation is performed by matching the data content required in the model with the input patient label data, and data validity validation is completed, for example, blood glucose monitoring data required in the model is marked if not, and is input into the calculation compliance rule, and data with the data age range of 30-65 years beyond the range required in the model is classified as invalid.
The compliance calculation engine is also connected with a knowledge base, the knowledge base comprises a basic attribute index base, a medical action index base, a reading and evaluation index base, a diet movement index base and a physical sign monitoring index base, different indexes provide promotion modes for actions causing poor compliance, provide targeted promotion modes for a large amount of patient data input by the system, and simultaneously construct a knowledge graph for combing, extracting, fusing and reasoning knowledge after diagnosis and quality evaluation to form services of information retrieval, knowledge question answering, risk identification, follow-up access path analysis and the like. The node of the map comprises diseases, medicines, symptoms, auxiliary inspection, departments, operations, parts, exercises, diets, follow-up visits, propaganda and the like, and the node association relationship of the map comprises categories, clinical manifestations, related etiologies, pathogenesis, prevention, intervention, pharmacokinetics, pharmacological effects, identification, related diagnosis, related diet recommendation, contraindications and the like. Sources of construction of the knowledge-graph include clinical treatment guidelines, other published medical literature, extraction of disease medical fact knowledge from EMRs by knowledge extraction techniques, and supplemental knowledge organized by clinical experts.
And fourthly, the compliance calculation engine calculates the patient compliance score through the compliance rule model and obtains the compliance grade and a compliance promotion processing mode.
And sending the patient label data to a compliance rule model, calculating a matched patient compliance score according to preset conditions in the compliance rule model, dividing the compliance grade according to the compliance grade and a dividing rule, and generating a compliance promotion task according to a preset promotion mode in the compliance rule model.
For example: transmitting the basic attribute data of the patient to a compliance calculation engine, calling a compliance model to calculate by the compliance calculation engine, and analyzing to obtain a compliance score related to the basic attribute;
the patient re-diagnosis and re-examination data are transmitted to a compliance calculation engine, the compliance calculation engine calls a compliance model to calculate, and the compliance model is analyzed to obtain the re-diagnosis and re-examination compliance value and generate a compliance promotion scheme;
the method comprises the following steps of transmitting medication data, reading propaganda and education data, evaluation questionnaire content data, exercise data, diet data, blood sugar, blood pressure, weight and communication condition data of a patient to a compliance calculation engine, wherein the compliance calculation engine calls a compliance model to calculate, and analyzes and obtains medication compliance scores, such as medication, reading propaganda and education, evaluation, exercise, diet, blood sugar, blood pressure, weight and communication compliance scores, and a medication related compliance promotion scheme can be generated when the medication compliance scores are lower than rule preset values;
summarizing all the scores to obtain a total score, and calculating a corresponding compliance grade according to the total score, wherein the compliance grade division rule is as follows:
a, 0-150 points, the compliance is poor;
b, 150 and 250 points, the compliance is general;
c, 250-350, good;
d, 350 and 450, preferably;
e, 450-;
f, 550-;
g, 750-.
The compliance promoting scheme realizes the personalized promoting scheme according to the compliance score evaluation result and the illness state/treatment progress of the patient, improves the perception of the patient, and establishes an independent promoting task according to the characteristics of different disease types, different illness states and different body qualities of each patient by a key index warning and fragmentization propaganda and instruction practical heart sticking system, thereby achieving the compliance promoting target. For example, a patient has multiple labels, the labels are scored for compliance, if the score of a certain label or the accumulated score of a plurality of labels is lower than a preset value, compliance promotion schemes corresponding to the labels are generated, and different compliance promotion schemes are determined by different scores and different combinations of the labels.
The compliance promoting scheme comprises an exercise prescription, a diet prescription, health education and the like, the specific content of the compliance promoting scheme is sent to the client through the worming brain, and the patient is supervised, so that the compliance promoting scheme is realized, for example:
1. the medication compliance promotion scheme comprises the following steps:
firstly, the brain of the economic life can take the advice of medicine according to patient's hospital discharge, and the patient is reminded of using medicine every day, secondly, in the follow-up visit in-process, can discern whether the patient has followed the advice of medicine and use medicine, if it is discerned that the patient does not take medicine according to the advice of medicine, can in time push away the notice of reminding of using medicine to the patient, also can push away the message and give supervisor or administrator, improve patient's compliance of using medicine, promote patient's recovered effect, reduce the disease recurrence rate.
2. Exercise compliance promoting regimen:
like some orthopedic postoperative patients, the patient still needs to do rehabilitation exercise for a period of time after being discharged, and postoperative rehabilitation can be promoted. The Jieshen brain can send the recovered video of motion for the patient according to the rule instruction, and the patient only needs to do the recovered motion according to the video, and the Jieshen brain can monitor whether the patient does or not do relevant recovered motion, if monitor that the patient does not do, can in time push the warning notice to the patient, also can push the message for person in charge doctor or supervisor, improves patient's motion compliance, promotes patient's recovered effect, reduces the disease recurrence rate.
3. Care compliance promoting regimen:
if the patient needs to continue to do some continuation nursing after being discharged from hospital, such as indwelling needle nursing, the jieshen brain can send nursing processing videos to the patient according to rules, the patient only needs to do relevant processing according to the videos, the jieshen brain can monitor whether the patient does or does not do processing and whether the processing effect is normal, if the patient is monitored to be not done or abnormal after being processed, the patient can be timely pushed to remind the patient to be informed, messages can also be pushed to a doctor in charge or a manager, the nursing compliance of the patient is improved, the recovery effect of the patient is improved, and the occurrence of wound infection conditions is reduced.
In order to cooperate with the implementation of the compliance promoting scheme, the brain-saving module sends the specific content of the compliance promoting scheme to the client in a targeted manner, monitors the patient behavior of the client, and assists the compliance scheme to realize the compliance management function:
and (3) motion management: exercise therapy is one of the two major cornerstones of the treatment of chronic diseases. According to the disease type of the patient and the actual physical condition of the patient, a proper motion management scheme proposal is given, can be edited and modified, and is combined with a motion instrument to directly transmit motion data to a system server in real time in a wireless mode. Does not need complex computer operation, and reduces the operation difficulty of patients. According to real-time motion data, the motion scheme is adjusted regularly, so that the motion of a patient is more scientific and reasonable, excessive and insufficient motion is prevented, and powerful help is provided for treating chronic diseases.
Diet management: according to the disease types and grades and the actual conditions of patients with chronic diseases, reasonable diet schemes are made for the patients. The system automatically calculates the nutrient content and calorie of the food ingested by the patient according to a food nutrient model and a calorie model, can be compared with a formulated scheme, and starts to execute after being determined by an administrator. The system may automatically adjust the regimen after the patient's condition has changed. For example, a diabetic makes a certain amount of protein and cholesterol required to be taken every day according to the disease condition degree, under the condition of continuous blood sugar monitoring, unstable blood sugar control and slight rise are found, and a background can automatically adjust a diet scheme according to the condition, so that the automatic management of diseases is realized, and the diet of a chronic patient is scientifically and reasonably controlled.
Administration management: the patient can record the daily medicine taking condition and the illness state of the patient in the system, the medicine taking reminding rule can be set according to the specific condition of the patient, and the system automatically reminds the patient to take medicine according to the rule. When the patient's condition changes, the patient can also be guided to take medicine and doctor.
Health promotion and education: different education contents are sent according to different types of diseases of patients, and the education contents comprise good risk factors of the diseases, types of the diseases, evolution and outcome of the diseases, treatment of critical conditions of the diseases, disease psychological guidance and the like. The user can download from the system knowledge base template and can also edit the propaganda and education content in a self-defined way.
And (4) other management: the health care product can also manage the aspects of living habits, stress, emotions and the like of the patients, guide the patients to develop a reasonable living style, relieve worry about diseases, relieve the psychological pressure of the patients, enable the patients to keep an active and optimistic living attitude, and contribute to the treatment and management of chronic diseases.
Fifthly, pushing the compliance calculation result to the client through the message queue device
The compliance calculation results include: patient compliance scores, patient compliance management ratings, patient compliance facilitation tasks, etc.; the message queue is a technical implementation device for batch sending of data channels from a server side in a centralized mode.
As shown in fig. 2, a system for improving compliance of a diabetic patient includes a client and a compliance service platform, wherein the client includes: the system comprises a flow browsing module, a WeChat (public number, small program), an APP (application), a voice telephone, a compliance service platform, a data labeling module, a compliance calculation engine, a compliance rule model, a calculation index knowledge base and a message queue.
The client is used for receiving the compliance service platform message, processing the compliance promotion task, receiving the processing information of the server and displaying the information on a corresponding interface in a picture, character and video mode.
Voice calls are used to perform task reminders, special announcements, questionnaires, etc. for the patient.
The compliance service platform is used for collecting patient data, the patient data comprises blood sugar monitoring data, diet data, exercise data, propaganda feedback data, questionnaire feedback data and the like, and the collected data are subjected to labeling processing to form a patient health portrait; transmitting the tagged data to a compliance computation engine; calculating, by a compliance calculation engine, a patient compliance score and a compliance promotion task; the score of patient compliance and the compliance facilitation task are pushed to the client by the message queue device.
The data acquisition module is used for acquiring data from an HIS system, an LIS system, a PACS system and a follow-up system of a hospital in real time; the data labeling module is used for receiving the collected patient data and labeling the patient data according to the labeling model; the compliance calculation engine is used for receiving the tagged data of the patient, calculating a patient compliance score and generating a compliance promotion task; the knowledge base is used for calculating the compliance score and generating an index base of the compliance promotion task and a content base of propaganda and instruction and questionnaire survey, and mainly comprises the following components: a basic attribute index library, a medical behavior index library, a reading and evaluation index library, a diet exercise index library, a physical sign monitoring index library and the like; the compliance rule model is used for defining a compliance score index, each score is divided into three grades of top, middle and bottom, and different compliance promotion modes are adopted for different grades; the message queue is used for pushing the operation result of the compliance service platform on the compliance to the client in a centralized and batch manner; the pushed message includes: the medicine taking reminding review reminding propaganda and education questionnaire surveys the exercise promoting task, the diet promoting task, the medicine taking promoting task, the nursing promoting task and the like.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for increasing compliance of a diabetic patient, comprising the steps of:
s1, collecting medical data and follow-up visit management data of the patient;
s2, labeling the basic attribute data and behavior data of the patient in the collected data;
s3, transmitting the tagged data to a compliance calculation engine;
s4, the compliance calculation engine calculates the compliance score of the patient through the compliance rule model, and obtains the compliance grade and the compliance promotion scheme through the compliance score, the patient and the corresponding label data enter the compliance rule model, the compliance score of the matched patient is calculated according to the preset conditions in the compliance rule model, the compliance grade is divided according to the division rule of the score and the grade, the matching is carried out according to the score and the score interval corresponding to the promotion mode in the compliance rule model, and the matched promotion modes are combined to generate the compliance promotion task;
and S5, pushing the calculation result of the compliance to the client.
2. The method of claim 1, wherein in step S2, before labeling, the collected data is subjected to data washing to obtain basic attribute data and behavior data of the patient, wherein the behavior data includes medical behavior data, reading behavior data, health assessment behavior data, questionnaire behavior data, lifestyle behavior data, health monitoring behavior data, and communication activity behavior data.
3. The method of claim 2, wherein said data cleansing comprises the steps of:
s21, preprocessing, namely loading the extracted source data into a cleaning pool in batches for processing, verifying the source data, including field interpretation, data source and code table of the source data and judging whether the information described by the data is complete or not, extracting data which are difficult to identify, and checking the data manually;
s22, cleaning missing values, determining the missing value range, filling missing contents, calculating the missing value proportion of each field, and formulating an information completion strategy according to the importance and the missing proportion of the data, wherein the completion mode comprises the following steps:
(1) filling missing values by business knowledge or experience speculation;
(2) filling missing values with the calculation results (mean, median, mode, etc.) of the same index;
(3) filling missing values according to the calculation results of different indexes;
then removing unnecessary fields, and for data with high importance and high loss rate, re-stocking the data, and sending a notice to a service handler by automatically identifying the fields with high importance and high loss rate;
and S23, format content cleaning, wherein when the source data is formatted data, only the following parts need to be cleaned:
(1) the display formats of time, date, numerical value, full half angle and the like are inconsistent;
(2) there are characters in the content that should not be present;
(3) the content should not be consistent with the field;
and S24, performing logical error cleaning, including removing duplication, removing unreasonable values and correcting contradictory contents, wherein the unreasonable values are data which do not conform to natural rules, the correcting contradictory contents are data which are compared and contain the same patient attributes or behaviors, but key fields of the data are different, and the contradictory fields are corrected according to the importance of the data.
4. The method of claim 1, wherein the patient unique index number is established in the following order:
(1) when the serial number is not empty, generating a unique index number of the patient by the serial number, the service data source, the name and the hospital code;
(2) when the identity card is not empty, the unique index number of the patient is generated by the identity card, the name and the hospital code;
(3) when the outpatient service number is not empty, generating a unique index number of the patient by the outpatient service number, the service data source, the name and the hospital code;
(4) when the business data index is not empty, generating a unique index number of the patient by the business data index number + name + hospital code;
(5) when the mobile phone number is not empty, the mobile phone number + name + hospital code generates a patient unique index number.
5. The method of claim 1, wherein the labeling of step S2 is to match the specific content of the basic attribute data and behavior data of the patient with the content of the label and the range defined by the label, and to attach the corresponding label to the specific content when the specific content is matched with the content of the label or falls within the range defined by the label.
6. The method of claim 1, wherein in step S3, the compliance calculation engine receives labeled data of the patient, selects different compliance promotion models based on the patient ' S scheduled tasks, and verifies the labeled data with the input data required by the models, wherein the patient ' S scheduled tasks are the patient ' S need to complete scheduled tasks generated for the patient after discharge.
7. The method of claim 1, wherein the client end feeds back the result of the execution of the compliance promotion program, and the preset conditions are adjusted according to the result of the execution, thereby complying with the compliance rule model.
8. A system for improving compliance of a diabetic patient comprises a compliance service platform and a client, and is characterized in that the compliance service platform comprises a data acquisition module, a label model, a compliance calculation engine and a compliance model, wherein the label model is respectively connected with the acquisition module and the compliance calculation engine, the compliance calculation engine is respectively connected with the compliance model and the client, the acquisition module acquires patient data, the compliance model is labeled, the compliance score is calculated through the compliance calculation engine through the compliance model, the compliance grade and a compliance promotion task are obtained through the compliance score and are issued to the client, the client displays the compliance score, and the compliance promotion task is processed.
9. The system of claim 8, wherein the label models comprise a patient basic information model, a patient disease model, and a patient adverse drug reactions and medication contraindications model.
10. The system of claim 8, wherein the compliance calculation engine is coupled to a knowledge base, the knowledge base comprising a base attribute index database, a medical action index database, a reading and assessment index database, a diet exercise index database, and a physical signs monitoring index database, wherein different indices provide a promoting means for actions that result in poor compliance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011088912.0A CN112102956A (en) | 2020-10-13 | 2020-10-13 | Method and system for improving compliance of diabetic patient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011088912.0A CN112102956A (en) | 2020-10-13 | 2020-10-13 | Method and system for improving compliance of diabetic patient |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112102956A true CN112102956A (en) | 2020-12-18 |
Family
ID=73783240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011088912.0A Pending CN112102956A (en) | 2020-10-13 | 2020-10-13 | Method and system for improving compliance of diabetic patient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102956A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927812A (en) * | 2021-03-30 | 2021-06-08 | 平安科技（深圳）有限公司 | Dynamic intervention method and device of treatment strategy, electronic equipment and storage medium |
| CN113744819A (en) * | 2021-09-09 | 2021-12-03 | 北京嘉和美康信息技术有限公司 | Follow-up state management method and device |
| CN114969557A (en) * | 2022-07-29 | 2022-08-30 | 之江实验室 | Propaganda and education pushing method and system based on multi-source information fusion |
| CN117894424A (en) * | 2024-03-14 | 2024-04-16 | 四川省医学科学院·四川省人民医院 | Recommendation system for constructing T2DM patient drug scheme based on deep learning and reinforcement learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391941A (en) * | 2017-07-26 | 2017-11-24 | 上海科瓴医疗科技有限公司 | A kind of method and system for improving compliance |
| CN109063964A (en) * | 2018-07-02 | 2018-12-21 | 浙江百先得服饰有限公司 | A kind of platform data processing system |
| CN109739922A (en) * | 2019-01-10 | 2019-05-10 | 江苏徐工信息技术股份有限公司 | A kind of industrial data intelligent analysis system |
| CN110334274A (en) * | 2019-05-30 | 2019-10-15 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
-
2020
- 2020-10-13 CN CN202011088912.0A patent/CN112102956A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391941A (en) * | 2017-07-26 | 2017-11-24 | 上海科瓴医疗科技有限公司 | A kind of method and system for improving compliance |
| CN109063964A (en) * | 2018-07-02 | 2018-12-21 | 浙江百先得服饰有限公司 | A kind of platform data processing system |
| CN109739922A (en) * | 2019-01-10 | 2019-05-10 | 江苏徐工信息技术股份有限公司 | A kind of industrial data intelligent analysis system |
| CN110334274A (en) * | 2019-05-30 | 2019-10-15 | 平安科技（深圳）有限公司 | Information-pushing method, device, computer equipment and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927812A (en) * | 2021-03-30 | 2021-06-08 | 平安科技（深圳）有限公司 | Dynamic intervention method and device of treatment strategy, electronic equipment and storage medium |
| WO2022205601A1 (en) * | 2021-03-30 | 2022-10-06 | 平安科技（深圳）有限公司 | Dynamic intervention method and apparatus for treatment strategy, electronic device and storage medium |
| CN112927812B (en) * | 2021-03-30 | 2024-03-19 | 平安科技（深圳）有限公司 | Dynamic intervention method and device for treatment strategy, electronic equipment and storage medium |
| CN113744819A (en) * | 2021-09-09 | 2021-12-03 | 北京嘉和美康信息技术有限公司 | Follow-up state management method and device |
| CN113744819B (en) * | 2021-09-09 | 2024-04-12 | 北京嘉和美康信息技术有限公司 | Follow-up state management method and device |
| CN114969557A (en) * | 2022-07-29 | 2022-08-30 | 之江实验室 | Propaganda and education pushing method and system based on multi-source information fusion |
| CN117894424A (en) * | 2024-03-14 | 2024-04-16 | 四川省医学科学院·四川省人民医院 | Recommendation system for constructing T2DM patient drug scheme based on deep learning and reinforcement learning |
| CN117894424B (en) * | 2024-03-14 | 2024-05-14 | 四川省医学科学院·四川省人民医院 | Recommendation system for constructing T2DM patient drug scheme based on deep learning and reinforcement learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8670997B2 (en) | Quality metric extraction and editing for medical data | |
| CN112102956A (en) | Method and system for improving compliance of diabetic patient | |
| CA2861824C (en) | System and method for patient care plan management | |
| TWI444921B (en) | Online system, method, and computer readable medium to facilitate providing health and wellness assistance | |
| US20170316530A1 (en) | Method and System for Providing Reports and Segmentation of Physician Activities | |
| TWI557679B (en) | System and method for generating real-time health care alerts | |
| US20160342753A1 (en) | Method and apparatus for healthcare predictive decision technology platform | |
| US20190122770A1 (en) | Lightweight Clinical Pregnancy Preterm Birth Predictive System and Method | |
| Kortüm et al. | Using electronic health records to build an ophthalmologic data warehouse and visualize patients' data | |
| US20170109479A1 (en) | System and method for delivering digital coaching content | |
| Samal et al. | Health information technology to improve care for people with multiple chronic conditions | |
| CN102227730A (en) | Systems and methods for clinical element extraction, holding, and transmission in widget-based application | |
| CN112735610A (en) | Post-hospital follow-up system and follow-up method | |
| US7640175B1 (en) | Method for high-risk member identification | |
| CN114067940A (en) | Health management method and storage medium | |
| CN114496247A (en) | Community health management system | |
| CN114974530A (en) | Post-diagnosis follow-up method, system and storage medium | |
| RU2657856C2 (en) | Method for stepwise review of patient care | |
| US20210375429A1 (en) | Automation of medical nutrition therapy | |
| CN112466423A (en) | Intelligent chronic disease health management method and system | |
| US20110153365A1 (en) | System and method of managing and documenting lactation data | |
| CN113724895A (en) | Day operation postoperative health monitoring system and method and health management platform | |
| CN112053749A (en) | BPD follow-up information system based on multi-source data acquisition and integration | |
| CN116312926A (en) | Health path recommending method and related device, electronic equipment and storage medium | |
| Rasubala et al. | Digital twin roles in public healthcare |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201218 |