CN112786214A - Detection method and detection system for restrictive medication violation - Google Patents
Detection method and detection system for restrictive medication violation Download PDFInfo
- Publication number
- CN112786214A CN112786214A CN202110132063.2A CN202110132063A CN112786214A CN 112786214 A CN112786214 A CN 112786214A CN 202110132063 A CN202110132063 A CN 202110132063A CN 112786214 A CN112786214 A CN 112786214A
- Authority
- CN
- China
- Prior art keywords
- restrictive
- medication
- drug
- diagnosis
- violation
- 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
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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Pharmacology & Pharmacy (AREA)
- Chemical & Material Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a detection method for restrictive medication violation, which comprises the following steps: rules are set relating to the restrictive drug. Setting a diagnosis discrimination model and a document discrimination model, and taking the admission diagnosis label and the diagnosis document of the case related to the restrictive drug as the input of the diagnosis discrimination model and the document discrimination model to respectively obtain the output results corresponding to the diagnosis discrimination model and the document discrimination model. And judging whether the restrictive medication has violation according to the output result and the rule. The method uses a machine to replace manpower, and solves the problems that the manual review efficiency of the restrictive medicine in the medical insurance review is low and the full review cannot be performed.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a detection method and a detection system for restrictive medication violation.
Background
In the process of examining and verifying medical records of a hospital by a medical insurance department, the medical records of the hospital often have some medication violation conditions, specifically, abuse of antibiotics, illegal use of proton pump inhibitors, excessive use of auxiliary drugs and the like, and currently, a professional doctor is often required to examine and verify the medical records. The whole medical record is examined manually, and a great deal of effort is consumed by doctors.
At present, medical insurance auditing adopts spot check, so that medical records cannot be checked in full quantity, and medical insurance funds are lost.
Disclosure of Invention
The invention provides a method for detecting restrictive medication violation, which replaces manpower with a machine and solves the problems that manual review of restrictive drugs in medical insurance review is low in efficiency and cannot be reviewed in full quantity.
In a first aspect of the invention, a method for limiting medication violation detection is disclosed, the method comprising: setting rules associated with the restrictive drug. And judging whether the expense list of the limiting medication violation object to be detected has limiting medication, and if the expense list of the limiting medication violation object to be detected does not have limiting medication, not detecting.
Judging whether the diagnosis disease mentioned in the medical insurance specification is contained or not according to the admission diagnosis label of the case related to the restrictive drug to obtain a first judgment result; and judging whether the condition required by the medical insurance specification is included according to the diagnostic document of the limited medication violation object to be detected to obtain a second judgment result.
And judging whether the restrictive medication has a violation according to the first judgment result, the second judgment result and the rule.
According to an embodiment of the present invention, the determining whether the diagnosis disease mentioned in the medical insurance specification is included according to the admission diagnosis label of the case related to the restrictive drug results in a first determination result, including: the setting diagnosis discrimination model takes the admission diagnosis label of the case related to the restrictive drug as input, and judges whether the admission diagnosis of the case related to the restrictive drug contains the diagnosis disease mentioned by the medical insurance standard.
According to an embodiment of the present invention, the determining whether the condition required by the medical insurance code is included according to the diagnosis paper of the case related to the restrictive drug to obtain the second determination result includes: the set text discrimination model determines whether the medical history of the case related to the restrictive drug includes a condition required by medical insurance standards.
According to an embodiment of the present invention, the determining whether the diagnostic disease mentioned in the medical insurance specification is included according to the admission diagnosis label of the case related to the restrictive drug results in a first determination result; before the step of judging whether conditions required by medical insurance specifications are included or not according to the diagnostic documents of the restricted medication violation objects to be detected to obtain second judgment results, checking a cost list of the restricted medication violation objects to be detected, judging whether restricted medication exists or not, if the cost list of the restricted medication violation objects to be detected does not have the restricted medication, not detecting, and if the cost list of the restricted medication violation objects to be detected has the restricted medication, continuing to detect.
In a second aspect, the invention discloses a detection system for limiting medication violations, the detection system comprising: a setting module for setting rules related to the restrictive medication.
And the diagnosis judging module is used for judging whether the hospitalization diagnosis of the case related to the restrictive drug contains the diagnosis diseases mentioned by the medical insurance standard.
And the document judging module is used for judging whether the medical history of the case related to the restrictive drug contains the conditions required by the medical insurance standard.
And the output module is used for judging whether the case related to the restrictive drug has the restrictive drug violation or not according to the output result of the diagnosis judging module and the output result of the document judging module.
According to an embodiment of the invention, the detection system further comprises: and the judging module is used for judging whether the bill of the restricted medication violation object to be detected has the restricted medication.
A third aspect of the present invention discloses a storage medium, characterized by comprising: a readable storage medium and computer instructions stored in the readable storage medium; the computer instructions are for implementing the above-described method for limiting medication violation detection.
The technical scheme for solving the technical problems is as follows: the machine is used for replacing manpower, so that the problems that the manual review efficiency of the restrictive medicine in the medical insurance review is low and the full review cannot be realized are solved.At the same timeBy adopting a data marking mode, an artificial intelligence model is constructed, whether the limiting medication violation exists in the entire medical record can be automatically judged, and the cost of manual examination is greatly reduced.
Drawings
FIG. 1 is a flowchart of a method for limiting medication violation detection as disclosed in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a diagnostic decision model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a document discrimination model according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
According to the detection method for the restrictive medication violation, the artificial intelligent model is constructed in a data marking mode, whether the restrictive medication violation exists in the entire medical record can be automatically judged, and the cost of manual review is greatly reduced.
According to the regulations of medical insurance bureau, all the medicines with limited use have the corresponding use specifications. We break the specification down into individually subdivided rules that satisfy or equal different logical conditions between the rules.
As illustrated in fig. 1, S101: and judging whether the bill of the restricted medication violation object to be detected has restricted medication, and if the bill of the restricted medication violation object to be detected does not have restricted medication, not detecting to step 105. And if the expense list of the limiting medication violation object to be detected has limiting medication, continuing to detect and executing step 102.
S102: setting rules associated with the restrictive drug.
If the recombinant human interleukin-2 is required to be used in the medical insurance catalogue, the requirements of 'renal cell carcinoma, melanoma and cancerous hydrothorax and peritoneal cavity hydrops' are necessarily limited. We disassemble it into:
rule 1: renal cell carcinoma related diagnosis
Rule 2: has melanoma related diagnosis
Rule 3: the course of disease or the record of examination indicates cancer cells in the hydrothorax and ascites.
The logic conditions corresponding to the specification are as follows: ((rule or rule 2) and rule 3).
S103: setting a diagnosis discrimination model and a document discrimination model, wherein the admission diagnosis label of the case related to the restrictive drug and the diagnosis document are used as the input of the diagnosis discrimination model and the document discrimination model, and respectively obtaining the output results corresponding to the diagnosis discrimination model and the document discrimination model.
Taking recombinant human interleukin-2 as an example, the 1 st rule comprises rule 1, renal cell carcinoma related diagnosis; rule 2 there is a diagnosis related to melanoma.
For the judgment of class 1 rule, we extract admission diagnosis in case: 1. renal clear cell carcinoma renal cell carcinoma and 1. renal clear cell carcinoma are spliced into [ CLS ] renal cell carcinoma [ SEP ]1. renal clear cell carcinoma [ CLS ], wherein [ CLS ] represents the beginning and the end of an input, [ SEP ] represents the division of two clauses, the input is sent into a model 1 for judgment, the output of the model is 1, and the output of the model can meet the rule 1. Where [ CLS ] is the classification task for downstream. Including single text classification tasks and statement pair classification tasks, where statement pair classification tasks are employed.
Similarly, rule 2 is judged, and the model output is 0, which means that it cannot be satisfied.
Similarly, the same type 2 rules are applied to interpretation, except that the extracted documents are changed from admission diagnosis to disease course.
All rules are mainly classified into the following two categories:
1. whether to meet the requirements of the relevant diagnosis
2. The disease course, examination and examination, admission record and other documents meet certain specific conditions.
With respect to the type 1 rule, it is determined whether or not relevant diagnoses are included in the admission diagnoses of the medical records by using a diagnosis discrimination model. The model frame is shown in fig. 2:
the input of the model is admission diagnosis and diagnosis required in medical insurance regulations.
The output of the model is whether the hospitalization diagnosis contains the diagnosis required in the medical insurance code.
And aiming at the 2 nd rule, extracting all corresponding documents in the medical record by using a document discrimination model, and judging whether the documents meet specific conditions. The model frame is shown in fig. 3:
the input of the model is the specific conditions required by the corresponding document content and the medical insurance specification.
The output of the model is whether the corresponding document meets the specific conditions required in the medical insurance specification.
S104: and finally, comparing the result returned by the model with the condition corresponding to the specification to see whether the condition of the specification is met, if so, directly quitting, and if not, prompting the violation of the corresponding restrictive medication.
The invention achieves the technical effects that: the machine is used for replacing manpower, so that the problems that the manual review efficiency of the restrictive medicine in the medical insurance review is low and the full review cannot be realized are solved. Meanwhile, an artificial intelligence model is constructed in a data labeling mode, whether restrictive medication violation exists in the entire medical record or not can be automatically judged, and the cost of manual examination is greatly reduced.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A detection method for a restrictive medication violation, the detection method comprising:
setting rules associated with the restrictive drug;
judging whether the diagnosis disease mentioned in the medical insurance specification is contained or not according to the admission diagnosis label of the case related to the restrictive drug to obtain a first judgment result; judging whether conditions required by medical insurance specifications are included according to the diagnostic documents of the limited medication violation objects to be detected to obtain a second judgment result;
and judging whether the restrictive medication has a violation according to the first judgment result, the second judgment result and the rule.
2. The method for detecting according to claim 1, wherein the determining whether the patient includes the diagnosis disease mentioned in the medical insurance specification according to the admission diagnosis label of the case related to the restrictive drug is a first determination result, comprising: the setting diagnosis discrimination model takes the admission diagnosis label of the case related to the restrictive drug as input, and judges whether the admission diagnosis of the case related to the restrictive drug contains the diagnosis disease mentioned by the medical insurance standard.
3. The method of claim 1, wherein the determining whether the condition required by the medical insurance specification is included according to the diagnostic paper of the case related to the restrictive drug results in a second determination result, comprising: the set text discriminant model determines whether the medical history of the case related to the restrictive drug includes a condition required by medical insurance standards, based on the diagnostic paper of the case related to the restrictive drug.
4. The method according to claim 1, wherein the determination of whether to include the diagnosis disease mentioned in the medical insurance specification based on the admission diagnosis label of the case related to the restrictive drug is a first determination result; after the step of setting the rule related to the restrictive drug before the step of obtaining the second judgment result by judging whether the condition required by the medical insurance specification is included according to the diagnostic document of the subject to be detected with the restrictive drug violation, the method further comprises the following steps: and judging whether the expense list of the limiting medication violation object to be detected has limiting medication, if the expense list of the limiting medication violation object to be detected does not have limiting medication, the detection is not carried out, and if the expense list of the limiting medication violation object to be detected has limiting medication, the detection is carried out continuously.
5. A detection system for limiting medication violations, the detection system comprising:
a setting module for setting rules related to the restrictive drug;
the diagnosis judging module is used for judging whether the hospitalization diagnosis of the case related to the restrictive drug contains the diagnosis diseases mentioned by the medical insurance standard;
the document judging module is used for judging whether the medical history of the case related to the restrictive drug contains the conditions required by medical insurance standards;
and the output module is used for judging whether the case related to the restrictive drug has the restrictive drug violation or not according to the output result of the diagnosis judging module and the output result of the document judging module.
6. The detection system of claim 5, further comprising:
and the judging module is used for judging whether the bill of the restricted medication violation object to be detected has the restricted medication.
7. A storage medium, comprising: a readable storage medium and computer instructions stored in the readable storage medium; the computer instructions are for implementing the method for detection of a restrictive medication violation according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110132063.2A CN112786214A (en) | 2021-01-31 | 2021-01-31 | Detection method and detection system for restrictive medication violation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110132063.2A CN112786214A (en) | 2021-01-31 | 2021-01-31 | Detection method and detection system for restrictive medication violation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112786214A true CN112786214A (en) | 2021-05-11 |
Family
ID=75760114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110132063.2A Pending CN112786214A (en) | 2021-01-31 | 2021-01-31 | Detection method and detection system for restrictive medication violation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112786214A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451400A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical act monitoring method and system |
| CN107451401A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical insurance intelligent checks method and system |
| CN109256186A (en) * | 2018-10-30 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medication checking method, device, server and storage medium based on audit model |
| CN109636642A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, equipment and the readable storage medium storing program for executing of Misuse adjuvant |
| CN109670788A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Medical insurance checking method, device, equipment and storage medium based on data analysis |
| CN110391006A (en) * | 2019-07-23 | 2019-10-29 | 夹江县人民医院 | Drug for medical insurance clearing marks method certainly |
| CN111951924A (en) * | 2020-08-14 | 2020-11-17 | 江苏云脑数据科技有限公司 | Abnormal medication behavior detection method and system |
| CN111986037A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Method, device and equipment for monitoring medical insurance audit data and storage medium |
| CN111986035A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Medical insurance service auditing method, device, equipment and storage medium |
| CN111986770A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Prescription medication auditing method, device, equipment and storage medium |
-
2021
- 2021-01-31 CN CN202110132063.2A patent/CN112786214A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451400A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical act monitoring method and system |
| CN107451401A (en) * | 2017-07-11 | 2017-12-08 | 武汉金豆医疗数据科技有限公司 | A kind of medical insurance intelligent checks method and system |
| CN109256186A (en) * | 2018-10-30 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medication checking method, device, server and storage medium based on audit model |
| CN109636642A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Recognition methods, device, equipment and the readable storage medium storing program for executing of Misuse adjuvant |
| CN109670788A (en) * | 2018-12-13 | 2019-04-23 | 平安医疗健康管理股份有限公司 | Medical insurance checking method, device, equipment and storage medium based on data analysis |
| CN110391006A (en) * | 2019-07-23 | 2019-10-29 | 夹江县人民医院 | Drug for medical insurance clearing marks method certainly |
| CN111951924A (en) * | 2020-08-14 | 2020-11-17 | 江苏云脑数据科技有限公司 | Abnormal medication behavior detection method and system |
| CN111986037A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Method, device and equipment for monitoring medical insurance audit data and storage medium |
| CN111986035A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Medical insurance service auditing method, device, equipment and storage medium |
| CN111986770A (en) * | 2020-08-31 | 2020-11-24 | 平安医疗健康管理股份有限公司 | Prescription medication auditing method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 周彬，程超，童俊东，赵雪飞，周阿华: "基于智能审核的医保病种控费模型设计与探索", 中国医院管理. * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10796080B2 (en) | Artificial intelligence based document processor | |
| US11200969B2 (en) | Peer-review flagging system | |
| US20200357118A1 (en) | Medical scan viewing system with enhanced training and methods for use therewith | |
| US20230144137A1 (en) | Systems and methods for processing images to classify the processed images for digital pathology | |
| US20090192822A1 (en) | Methods and computer program products for natural language processing framework to assist in the evaluation of medical care | |
| US10061894B2 (en) | Systems and methods for medical referral analytics | |
| US8751252B2 (en) | Systems and methods for clinical data validation | |
| US20210366106A1 (en) | System with confidence-based retroactive discrepancy flagging and methods for use therewith | |
| US20220172809A9 (en) | Report generating system and methods for use therewith | |
| US20130262364A1 (en) | Clinical Documentation Debugging Decision Support | |
| CN113488180B (en) | Clinical guideline knowledge modeling method and system | |
| KR101954029B1 (en) | Method for supporting review of health insurance considering the condition of patient, and computer program recorded on record-medium for executing method therefor | |
| Mabotuwana et al. | Improving quality of follow-up imaging recommendations in radiology | |
| Li et al. | Automated measurement of pressure injury through image processing | |
| CN109559807A (en) | A kind of medical treatment detection method and device | |
| CN112786214A (en) | Detection method and detection system for restrictive medication violation | |
| US11669678B2 (en) | System with report analysis and methods for use therewith | |
| CN109545319B (en) | Prescription alarm method based on knowledge relation analysis and terminal equipment | |
| CN107066826A (en) | Medication information processing method based on test rating | |
| CN115841674A (en) | Automatic recording method and device for CRF, electronic equipment and storage medium | |
| CN109065118A (en) | A kind of medical data processing method, device, terminal and readable storage medium storing program for executing | |
| AU2019201632A1 (en) | Artificial intelligence based document processor | |
| US20130218587A1 (en) | Coverage Discovery | |
| Brown et al. | Making audit actionable: an example algorithm for blood pressure management in chronic kidney disease | |
| CN113160946B (en) | Method and system for sending medical DICOM images |
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 |