CN110739034A - method for DRGs grouping of case data - Google Patents
method for DRGs grouping of case data Download PDFInfo
- Publication number
- CN110739034A CN110739034A CN201910890362.5A CN201910890362A CN110739034A CN 110739034 A CN110739034 A CN 110739034A CN 201910890362 A CN201910890362 A CN 201910890362A CN 110739034 A CN110739034 A CN 110739034A
- Authority
- CN
- China
- Prior art keywords
- data
- group
- grouping
- adrgs
- mdca
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The invention provides methods for DRGs grouping of case data, which comprises the steps of judging whether codes of operation and treatment modes are matched with MDCA group information, entering an MDCA group if the codes are matched, entering the next step classification if the codes are not matched, judging age or discharge diagnosis, entering the next step classification if the ages are not more than 1, checking and correcting diagnosis if the ages are not matched, screening out data meeting MDCP disease coding information, grouping the data into the MDCP group, grouping the data of the MDCA group and the data of the MDCP group into the corresponding -grade ADRGs group according to the operation and operation codes, merging the obtained -grade ADRGs group according to clinical knowledge to obtain a second-grade ADRGs group.
Description
Technical Field
The invention relates to the field of medical system grouping methods, in particular to a method for performing DRGs grouping on medical record data.
Background
At present, the domestic DRGs grouping scheme is CN-DRG developed by the public health information center in Beijing, which takes ICD-10 clinical edition and ICD-9-CM3 clinical edition as standards, and the patients are classified into a plurality of diagnosis related groups according to the age, sex, hospitalization days, clinical diagnosis, disease symptoms, operation, disease severity, complications, other resource consumption and other factors of the patients. The quality of the data of the home page of the traditional Chinese medical record is not high; the grouping scheme has more errors, the formed grouping scheme does not meet the relevant requirements of the medical insurance bureau of the prefecture and is not suitable for the medical status of the prefecture.
The Chinese patent publication No. CN108376564A discloses disease diagnosis complication identification methods and systems based on a random forest algorithm, which includes the following steps S1 of classifying diseases according to human anatomy systems to form a plurality of disease diagnosis grouping anatomy categories, S2 of subdividing each disease diagnosis grouping anatomy category according to the diagnosis and operation of the diseases to form a plurality of disease diagnosis grouping operation categories, and S3 of subdividing complications in the disease diagnosis grouping operation categories by using the random forest algorithm to form a final disease diagnosis standard group.
Disclosure of Invention
The invention aims to provide methods for DRGs grouping of medical record data, and overcomes the defects of the existing medical record data grouping method by the DRGs grouping method of the medical record data.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides methods for DRGs grouping of medical record data, which comprises the following steps:
s1, judging whether the operation and treatment mode codes match with MDCA group information, if so, entering an MDCA group, and if not, entering the next step for classification;
s2, judging the age or the discharge diagnosis, if the age is less than or equal to 1, if so, entering the next step for classification, if not, checking the registration information again and correcting the diagnosis;
s3, screening out the data meeting the MDCP disease coding information, and classifying the data into an MDCP group;
s4, dividing the data of MDCA group and MDCP group into corresponding level ADRGs groups according to operation and operation codes;
the method comprises the steps of S5, combining -level ADRGs groups obtained according to clinical knowledge to obtain second-level ADRGs groups, classifying data processed according to MDCA group and MDCP disease coding information through operation and operation codes, combining -level ADRGs groups obtained to obtain second-level ADRGs groups, greatly improving accuracy of the processed data and facilitating reclassification through an algorithm, the grouping scheme is more flexible, fully considering the problem of quality of the data of the head page of the current Chinese medical records, the formed grouping scheme is more in line with relevant requirements of the municipal medical insurance bureau and is more suitable for the current medical situation of the city, the method is based on realization of DRGs grouping of an intelligent algorithm of the head page of the medical records, makes clear difference among different medical service technologies, objectively measures the joint resource consumption of the workload related to the medical services, meets comparability requirements, can help a health administration part , a medical institution, a medical insurance agency and the like to effectively control the increase of medical service cost, and promote the establishment of a hospital health administration system and promote the improvement of the medical information standardization and the improvement of the medical management system.
Optionally, before step S1, a new technical application grouping step is further performed, where the step is: and judging whether the grouped data conforms to the operation and operation coding information of the ICD-9-CM3, if so, classifying the grouped data into a Pre-New technology declaration group, and if not, entering the classification of the step S1. The invention is directed at the independent processing of the Pre-new technology declaration group, and the Pre-new technology declaration group can be expanded and managed according to the updating of actual data, so that the whole grouping algorithm is more flexible and can be more suitable for the current medical situation of the city.
Optionally, before the grouping step of the new technical application, a checking step is further provided, wherein the checking step is to check the data according to a medical record first page unit and remove the data which do not meet the grouping requirement.
Optionally, the data of the MDCA and MACP which are not grouped are delivered to the system to carry out main diagnosis verification of the case head page data and correct the main diagnosis, and other MDC groups except the MDCA group and the MDCP group are entered according to the main diagnosis, the invention further checks and corrects the main diagnosis in the case head page unit by the verification and correction, and corrects the residual data generated after the diagnosis to be grouped into other 24 MDC groups except the MDCA group and the MDCP group, and the accuracy of the data is further improved by the step of MDCP .
Optionally, the remaining data classified into other 24 MDC groups are sequentially subjected to the operations of step S4 and step S5.
Optionally, after step S5, an identification step is further provided, in which the obtained second-level ADRGs group is labeled with the identification of CC-associated complications and concomitant diseases/MCC-associated important complications and concomitant diseases. According to the invention, the accuracy of the subsequent algorithm is improved by marking the identification of CC with complications and the identification of the syndrome/MCC with important complications and the syndrome.
Based on professional clinical diagnosis and treatment data and the mining and analyzing capability of big data, the invention can automatically carry out penetrating mining analysis on the first page data of a large and complicated case, automatically correct the wrong data of diagnosis, main treatment mode and clinical actual consumption of a patient, combine individual characteristics such as age, complication and companion symptoms, subdivide similar cases into the same groups according to the complexity and cost of diseases, and finally, the grouping result of DRGs can be applied to hospital evaluation, medical quality management and medical payment management.
Optionally, the specific grouping operation of the decision tree algorithm grouping step is: calculating the coefficient of variation of the ADRGs; then directly distinguishing ADRGs, and if the variation coefficient of the ADRGs is less than 0.3 or the number of people is less than 30, directly making the ADRG become DRG;
if the coefficient of variation of ADRG is greater than or equal to 0.3 and the number of people is greater than or equal to 30, classifying and judging by using age, sex, hospitalization days, complications and complications until the coefficient of variation is less than 0.3 or the number of people is less than 30; if all the classification node variables are used up, the coefficient of variation is still equal to or more than 0.3, and the number of people is equal to or more than 30, the corresponding specialist clinician makes a judgment on whether to subdivide or not. Compared with the decision tree algorithm of BJ-DRG, the decision tree construction condition of the DRG grouping device is stricter; the accuracy of the processed data is greatly improved.
Compared with the prior art, the invention has the beneficial effects that:
the invention classifies the data processed according to MDCA group and MDCP disease coding information through operation and operation coding, then merges the obtained -level ADRGs groups to obtain the second-level ADRGs group class, greatly improves the accuracy of the processed data, is convenient for reclassification through an algorithm, has more flexible grouping scheme, fully considers the problem of the data quality of the first page of the current Chinese medical record, and forms the grouping scheme which more accords with the relevant requirements of the local medical insurance bureau and is more suitable for the current medical situation of the local city.
Drawings
FIG. 1 is a logic flow diagram of embodiment 1 of the present invention;
fig. 2 is an MDC classification table according to embodiment 1 of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and examples, but it should be understood that the specific examples described herein are only for the purpose of explaining the present invention and do not limit the scope of the present invention.
Thus, a definition of "", "second" may or may not include or more of that feature, and in the description of the invention, a "number" means two or more, unless specifically defined otherwise.
The Coefficient of Variation (Coefficient of Variation) of the present invention means that when the discrete degree of two sets of data need to be compared, if the difference between the measurement scales of the two sets of data is too large or the data dimensions are different, it is not appropriate to directly use the standard deviation to compare, and at this time, the influence of the measurement scales and dimensions should be eliminated, and the Coefficient of Variation can be at point , which is the ratio of the standard deviation of the original data to the average of the original data.
The medical record homepage unit is a database after registration of information such as the basic condition, hospitalization medical treatment and diagnosis condition, hospitalization medical expense condition and the like of all levels of hospitals required to record the basic condition, the hospitalization medical treatment and diagnosis condition and the hospitalization medical expense condition of patients in the homepage of the hospitalization medical record, is the main basis for the hospital to register, classify, examine and the like the hospitalization medical record, and is also the important basis for the medical insurance business handling related business.
As shown in fig. 2, the MDCA is collectively referred to as an advanced group disease and associated action group, and the clinical knowledge of the MDCA is embedded in the grouper, i.e., the MDCA table specifies what procedures and action codes can be grouped into the MDCA.
The MDCP disease code refers to the code of various diseases of newborn infants.
The decision tree model has the advantages of low computational complexity, convenient use and high efficiency, can process data with irrelevant characteristics, can easily construct rules which are easy to understand, and the rules are usually easy to explain and understand.
At present, the generation process of decision trees is mainly divided into the following 3 parts:
1) feature selection refers to selecting features from numerous features in training data as the splitting standard of the current node, and how to select the features has many different quantitative evaluation standard standards, thereby deriving different decision tree algorithms.
2) And (3) generating a decision tree: and generating child nodes from top to bottom recursively according to the selected characteristic evaluation standard, and stopping the growth of the decision tree until the data set is not separable. A recursive structure is the easiest way to understand in terms of a tree structure.
3) And (4) pruning, namely, decision trees are easy to over-fit, pruning is required as in , the scale of the tree structure is reduced, and over-fitting is relieved.
Three decision tree algorithms based on information theory are commonly used:
if training data have 20 features, which is selected as a basis for division.
The CART and C4.5 support the processing when the data characteristics are continuously distributed, and continuous variables are processed mainly by using binary segmentation, namely specific values are solved, namely a splitting value is solved, wherein when the characteristic value is larger than the splitting value, a left sub-tree is moved, or a right sub-tree is moved.
The ID3 algorithm was invented by Ross Quinlan and is based on the 'Oncard razor', the smaller the decision tree is, the better the larger the decision tree is (be simple theory), the ID3 algorithm evaluates and selects features based on information gain in information theory, and a decision module is made each time the feature with the largest information gain is selected.ID 3 algorithm can be used to divide a nominal data set, there is no pruning process, and in order to remove the problem of excessive data matching, it is possible to combine adjacent leaf nodes that cannot generate a large amount of information gain by clipping (e.g., set information gain thresholds). Using information gain actually has disadvantages, that is biased toward attributes with large values-that is, in a training set, the larger the number of different values taken by an attribute, the more likely it is to be taken as a split attribute, which is sometimes meaningless, and ID3 cannot handle continuously distributed data features, thus the CARC 4.5 algorithm also supports continuously distributed data features.
C4.5 is improved algorithms of ID3, inherit the advantages of the ID3 algorithm, the C4.5 algorithm selects attributes by using an information gain rate, overcomes the defect that attributes with a plurality of values are selected in a biased mode when the attributes are selected by using the information gain, prunes in the process of tree construction, can finish discretization processing of continuous attributes, and can process incomplete data, classification rules generated by the C4.5 algorithm are easy to understand and have high accuracy, but the efficiency is low, and because multiple times of sequential scanning and sequencing are needed to be carried out on a data set in the process of tree construction, the C4.5 algorithm is only suitable for the data set which can be resided in an internal memory because multiple times of data set scanning are needed.
The CART algorithm is called Classification And Regression Tree, Gini index (the characteristic s with the minimum Gini index) is used as a splitting standard, And post-pruning operation is also included. Although the ID3 algorithm and the C4.5 algorithm can mine as much information as possible in learning the training sample set, the generated decision tree has larger branches and larger scale. In order to simplify the scale of the decision tree and improve the efficiency of generating the decision tree, a decision tree algorithm CART for selecting test attributes according to the GINI coefficient appears.
In the invention, the system is automatically completed; wherein the CC/MCC rules are identified as follows:
1. the disease code (whether or not [ discharge diagnosis-main diagnosis ]) that has been confirmed as [ ADRG group-main diagnosis ] does not serve as a judgment of the comorbidity;
2. [ Condition 1 ]: filling in the field of discharge diagnosis-main diagnosis/other diagnosis-disease codes except for the ADRG group-main codes, and judging the corresponding value of the disease codes for the hospitalization illness state to be 2 when the field is provided with a consolidation symptom identifier (the consolidation symptom (CC) field in an ICD-10 disease code table, or 3, unknown conditions or 4, none, and extracting the value to be the consolidation symptom;
3. [ Condition 2 ]: when the condition 1 is not met, filling in the AdRG group-main codes, namely the discharge diagnosis-main diagnosis/other diagnoses-disease codes, extracting the disease codes which are not in the MDC group and have main diagnosis marks of T, and giving the marks of the syndrome CC;
4. extracting disease codes of the syndromes, and according to the identification in the field of the syndromes (CC):
[ CC ] with complications and concomitant diseases;
MCC with important comorbidities and concomitant diseases;
when no complications are extracted in the [ condition 1 ] or the [ condition 2 ], the identification is as follows: without complications and concomitant diseases.
Example 1
As shown in FIG. 1, the present invention discloses methods for DRGs grouping of medical record data, which comprises the following steps:
s1, verification step: and checking the data according to a first page unit of the medical record, and eliminating the data which does not meet the grouping requirement.
And S2, a new technology declaration grouping step, namely judging whether the grouped data conforms to ICD-9-CM3 operation and operation coding information, if so, grouping the grouped data into a Pre-new technology declaration group, and if not, entering the classification of the next step.
S3, judging whether the operation and treatment mode codes match with MDCA group information, if so, entering an MDCA group, and if not, entering the next step for classification;
s4, judging the age or the discharge diagnosis, if the age is less than or equal to 1, if so, entering the next step for classification, if not, checking the registration information again and correcting the diagnosis;
s5, screening out the data meeting the MDCP disease coding information, and classifying the data into an MDCP group;
s6, dividing the data of MDCA group and MDCP group into corresponding level ADRGs groups according to operation and operation codes;
and S7, combining the -level ADRGs groups according to clinical knowledge to obtain a second-level ADRGs group class.
S8, the data generated in the step S4 of the MDCA and MACP which are not grouped are delivered to the system to carry out the main diagnosis check of the first page data of the case and correct the main diagnosis, and the MDC groups except the MDCA group and the MDCP group are entered according to the main diagnosis.
S9: the remaining data divided into the other 24 MDC groups is sequentially subjected to the operations of step S5, step S6 and step S7.
S10, identification step, marking the obtained second grade ADRGs group with identification of CC complication and complication/MCC important complication and complication.
S11, grouping the decision tree algorithm: and grouping according to the individual factors and the CC/MCC identifications by a decision tree algorithm model to form a final DRGs grouping result.
In the embodiment, the CART algorithm is adopted, and in the grouping process from ADRG to DRG, cases are grouped according to age, number of hospitalizations, leaving pattern, degree of complication, and number of hospitalizations, respectively, according to the ADRG. It was determined from clinical knowledge whether certain ADRGs differed in age, day of stay and manner of leaving hospital, degree of complications and day of stay segmentation to determine whether to subdivide on this variable.
The decision tree algorithm runs:
firstly, calculating the variation coefficient of ADRGs; directly judging ADRGs, and if the variation coefficient of the ADRGs is less than 0.3 or the number of people is less than 30, directly making the ADRG become DRG; if the ADRG variation coefficient is greater than or equal to 0.3 and the number of people is greater than or equal to 30, the people are classified and judged by age, sex, hospitalization days, complications and complications until the variation coefficient is less than 0.3 or the number of people is less than 30. If all the classification node variables are used up, the coefficient of variation is still equal to or more than 0.3, and the number of people is equal to or more than 30, the corresponding specialist clinician makes a judgment on whether to subdivide or not. Compared with the decision tree algorithm of BJ-DRG, the decision tree construction condition of the DRG grouping device is stricter. The classification node in the present invention refers to age, sex, number of hospitalization days, complications, and the like.
The eye clinical experts classify diseases with similar clinical processes and similar resource consumption into ADRG (such as CAX007 eye extirpation) according to clinical experiences, the classified nodes are judged from ADRGs to DRG by using the variation coefficients, some ADRGs have small variation coefficients, such as CAX007 eye extirpation, and can be directly used as DRG, the requirement that the intra-group variation coefficient is less than 0.3 or less than 30 can be met by age subdivision methods, such as CCX007 cornea, iris and ciliary body diseases and less than 15 years old, some patients need to be subdivided by days of hospitalization, such as CAX004 + intraocular lens implantation, the age is more than 15 years old, the patients are hospitalized or transferred for less than 5 days, some patients need to be subdivided by age subdivision, complications and complications, such as CCX007 cornea, iris and ciliary body diseases, the eye diseases and lacrimal lens extraction experts, the eye diseases are more than years old, and the eye diseases are classified into the 24 major groups of ADRG (such as CAX007 eye diseases and cataract eye diseases), and the eye diseases are judged by the eye orbit degeneration factors after the eye disease is more than .
Example 2
S1, judging whether the operation and treatment mode codes match with MDCA group information, if so, entering an MDCA group, and if not, entering the next step for classification;
s2, judging the age or discharge diagnosis, if the age is less than or equal to 1, if so, entering the next step for classification, if not, checking and correcting the diagnosis;
s3, screening out the data meeting the MDCP disease coding information, and classifying the data into an MDCP group;
s4, dividing the data of MDCA group and MDCP group into corresponding level ADRGs groups according to operation and operation codes;
and S5, combining the -level ADRGs groups according to clinical knowledge to obtain a second-level ADRGs group class.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents or improvements made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1, method for DRGs grouping of medical record data, which is characterized by comprising the following steps:
s1, judging whether the operation and treatment mode codes match with MDCA group information, if so, entering an MDCA group, and if not, entering the next step for classification;
s2, judging the age or the discharge diagnosis, if the age is less than or equal to 1, if so, entering the next step for classification, if not, checking the registration information again and correcting the diagnosis;
s3, screening out the data meeting the MDCP disease coding information, and classifying the data into an MDCP group;
s4, dividing the data of MDCA group and MDCP group into corresponding level ADRGs groups according to operation and operation codes;
and S5, combining the -level ADRGs groups according to clinical knowledge to obtain a second-level ADRGs group class.
2. The method of claim 1, wherein before step S1, a new technology claim grouping step is further performed, the step being: and judging whether the grouped data conforms to the operation and operation coding information of the ICD-9-CM3, if so, classifying the grouped data into a Pre-New technology declaration group, and if not, entering the classification of the step S1.
3. The method as claimed in claim 2, wherein before the new technical application grouping step, a checking step is further provided, wherein the checking step is to check the data according to the first page unit of the medical record and remove the data which does not meet the grouping requirement.
4. The method of claim 1, wherein the data of the non-grouped MDCA and MACP is delivered to the system for performing a main diagnosis check of the case header page data and correcting the main diagnosis, and the other MDC groups except the MDCA group and the MDCP group are entered according to the main diagnosis.
5. The method of claim 3, wherein the remaining data divided into the other 24 MDC groups is sequentially subjected to the operations of step S4 and step S5.
6. The method of claim 1, 2, 3, 4 or 5, wherein step S5 is followed by a labeling step of labeling the secondary ADRGs group with CC and concomitant disease/MCC with significant complications and concomitant diseases.
7. The method of claim 6, wherein after the step of identifying, there is a step of decision tree algorithm grouping comprising: and grouping according to the individual factors and the CC/MCC identifications by a decision tree algorithm model to form a final DRGs grouping result.
8. The method of claim 7, wherein the specific grouping of the decision tree algorithm grouping step is: calculating the coefficient of variation of the ADRGs; then directly distinguishing ADRGs, and if the variation coefficient of the ADRGs is less than 0.3 or the number of people is less than 30, directly making the ADRG become DRG; if the coefficient of variation of ADRG is greater than or equal to 0.3 and the number of people is greater than or equal to 30, classifying and judging by using age, sex, hospitalization days, complications and complications until the coefficient of variation is less than 0.3 or the number of people is less than 30; if all the classification node variables are used up, the coefficient of variation is still equal to or more than 0.3, and the number of people is equal to or more than 30, the corresponding specialist clinician makes a judgment on whether to subdivide or not.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910890362.5A CN110739034A (en) | 2019-09-20 | 2019-09-20 | method for DRGs grouping of case data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910890362.5A CN110739034A (en) | 2019-09-20 | 2019-09-20 | method for DRGs grouping of case data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110739034A true CN110739034A (en) | 2020-01-31 |
Family
ID=69268325
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910890362.5A Pending CN110739034A (en) | 2019-09-20 | 2019-09-20 | method for DRGs grouping of case data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110739034A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111933301A (en) * | 2020-06-30 | 2020-11-13 | 望海康信(北京)科技股份公司 | DRG grouper forming system, method and corresponding equipment, storage medium |
CN111932142A (en) * | 2020-08-25 | 2020-11-13 | 望海康信(北京)科技股份公司 | Method, device, equipment and storage medium for scheme grouping and data grouping |
CN112035473A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Medical record data management method, device, equipment and storage medium |
CN112133395A (en) * | 2020-07-10 | 2020-12-25 | 青岛国新健康产业科技有限公司 | Case grouping method and device, electronic equipment and storage medium |
CN112466420A (en) * | 2020-11-26 | 2021-03-09 | 泰康保险集团股份有限公司 | Grouping method, grouping device, electronic equipment and storage medium |
CN112542220A (en) * | 2020-12-16 | 2021-03-23 | 四川省肿瘤医院 | Hospitalization case homepage-based tumor registration follow-up data processing method and system |
CN112560400A (en) * | 2020-12-30 | 2021-03-26 | 杭州依图医疗技术有限公司 | Medical data processing method and device and storage medium |
CN112632913A (en) * | 2020-12-21 | 2021-04-09 | 山东众阳健康科技集团有限公司 | Automatic grouping method and system for CHS-DRG (tunnel boring machine-dry data group) grouter |
CN113643168A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Method, device, computer equipment and storage medium for determining DRGs packets |
CN113779180A (en) * | 2021-09-29 | 2021-12-10 | 北京雅丁信息技术有限公司 | Regional DRG grouping simulation method |
CN114581075A (en) * | 2021-12-23 | 2022-06-03 | 武汉金豆医疗数据科技有限公司 | CHS-DRG ungrouped case payment settlement management system |
CN115576546A (en) * | 2022-10-08 | 2023-01-06 | 上海柯林布瑞信息技术有限公司 | Reusable DRG grouping method and device |
-
2019
- 2019-09-20 CN CN201910890362.5A patent/CN110739034A/en active Pending
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111933301A (en) * | 2020-06-30 | 2020-11-13 | 望海康信(北京)科技股份公司 | DRG grouper forming system, method and corresponding equipment, storage medium |
CN112331285B (en) * | 2020-07-10 | 2023-01-10 | 青岛国新健康产业科技有限公司 | Case grouping method, case grouping device, electronic equipment and storage medium |
CN112133395A (en) * | 2020-07-10 | 2020-12-25 | 青岛国新健康产业科技有限公司 | Case grouping method and device, electronic equipment and storage medium |
CN112331285A (en) * | 2020-07-10 | 2021-02-05 | 青岛国新健康产业科技有限公司 | Case grouping method, case grouping device, electronic equipment and storage medium |
CN111932142A (en) * | 2020-08-25 | 2020-11-13 | 望海康信(北京)科技股份公司 | Method, device, equipment and storage medium for scheme grouping and data grouping |
CN112035473A (en) * | 2020-08-28 | 2020-12-04 | 平安医疗健康管理股份有限公司 | Medical record data management method, device, equipment and storage medium |
CN112035473B (en) * | 2020-08-28 | 2023-11-21 | 平安医疗健康管理股份有限公司 | Medical record data management method, device, equipment and storage medium |
CN112466420A (en) * | 2020-11-26 | 2021-03-09 | 泰康保险集团股份有限公司 | Grouping method, grouping device, electronic equipment and storage medium |
CN112466420B (en) * | 2020-11-26 | 2023-06-02 | 泰康保险集团股份有限公司 | Grouping method, grouping device, electronic equipment and storage medium |
CN112542220A (en) * | 2020-12-16 | 2021-03-23 | 四川省肿瘤医院 | Hospitalization case homepage-based tumor registration follow-up data processing method and system |
CN112632913A (en) * | 2020-12-21 | 2021-04-09 | 山东众阳健康科技集团有限公司 | Automatic grouping method and system for CHS-DRG (tunnel boring machine-dry data group) grouter |
CN112560400A (en) * | 2020-12-30 | 2021-03-26 | 杭州依图医疗技术有限公司 | Medical data processing method and device and storage medium |
CN113643168A (en) * | 2021-08-30 | 2021-11-12 | 平安医疗健康管理股份有限公司 | Method, device, computer equipment and storage medium for determining DRGs packets |
CN113779180A (en) * | 2021-09-29 | 2021-12-10 | 北京雅丁信息技术有限公司 | Regional DRG grouping simulation method |
CN114581075A (en) * | 2021-12-23 | 2022-06-03 | 武汉金豆医疗数据科技有限公司 | CHS-DRG ungrouped case payment settlement management system |
CN115576546A (en) * | 2022-10-08 | 2023-01-06 | 上海柯林布瑞信息技术有限公司 | Reusable DRG grouping method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110739034A (en) | method for DRGs grouping of case data | |
CN107705839B (en) | Disease automatic coding method and system | |
CN107731269B (en) | Disease coding method and system based on original diagnosis data and medical record file data | |
US20220254493A1 (en) | Chronic disease prediction system based on multi-task learning model | |
WO2020181805A1 (en) | Diabetes prediction method and apparatus, storage medium, and computer device | |
Kitching | Cladistics: the theory and practice of parsimony analysis | |
CN112133441B (en) | Method and terminal for establishing MH postoperative crack state prediction model | |
CN108682457B (en) | Patient long-term prognosis quantitative prediction and intervention system and method | |
CN111967495A (en) | Classification recognition model construction method | |
CN116910172B (en) | Follow-up table generation method and system based on artificial intelligence | |
CN111243736A (en) | Survival risk assessment method and system | |
CN113889219A (en) | Drug recommendation method and system for chronic obstructive pulmonary disease | |
CN111370126B (en) | ICU mortality prediction method and system based on punishment integration model | |
CN111048190A (en) | DRG grouping method based on artificial intelligence | |
CN105718726B (en) | Lab test systematic knowledge based on rough set obtains and inference method | |
CN112837799A (en) | Remote internet big data intelligent medical system based on block chain | |
CN116259415A (en) | Patient medicine taking compliance prediction method based on machine learning | |
CN113674824B (en) | Disease coding method and system based on regional medical big data | |
CN109448856A (en) | Dicision of diagnosis and treatment system based on artificial intelligence | |
CN113539414A (en) | Method and system for predicting rationality of antibiotic medication | |
CN116092680B (en) | Abdominal aortic aneurysm early prediction method and system based on random forest algorithm | |
CN117195027A (en) | Cluster weighted clustering integration method based on member selection | |
US20230037183A1 (en) | Storage medium, adjustment method, and information processing apparatus | |
CN113470819A (en) | Early prediction method for adverse event of pressure sore of small unbalanced sample based on random forest | |
CN113257429A (en) | System, equipment and storage medium for recognizing fever diseases based on association rules |
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 |
Application publication date: 20200131 |
|
RJ01 | Rejection of invention patent application after publication |