CN108091398A - Patient's group technology and device - Google Patents
Patient's group technology and device Download PDFInfo
- Publication number
- CN108091398A CN108091398A CN201611021603.5A CN201611021603A CN108091398A CN 108091398 A CN108091398 A CN 108091398A CN 201611021603 A CN201611021603 A CN 201611021603A CN 108091398 A CN108091398 A CN 108091398A
- Authority
- CN
- China
- Prior art keywords
- patient
- type
- diagnosis
- disease
- transaction
- 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.)
- Granted
Links
- 201000010099 disease Diseases 0.000 claims abstract description 92
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 92
- 238000003745 diagnosis Methods 0.000 claims abstract description 54
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000010606 normalization Methods 0.000 claims abstract description 15
- 208000001072 type 2 diabetes mellitus Diseases 0.000 claims description 23
- 238000005065 mining Methods 0.000 claims description 14
- 206010067584 Type 1 diabetes mellitus Diseases 0.000 claims description 10
- 208000004104 gestational diabetes Diseases 0.000 claims description 10
- 206010020772 Hypertension Diseases 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 208000004930 Fatty Liver Diseases 0.000 description 8
- 206010019708 Hepatic steatosis Diseases 0.000 description 8
- 208000010706 fatty liver disease Diseases 0.000 description 8
- 231100000240 steatosis hepatitis Toxicity 0.000 description 8
- 208000007530 Essential hypertension Diseases 0.000 description 7
- 206010012601 diabetes mellitus Diseases 0.000 description 6
- 206010028980 Neoplasm Diseases 0.000 description 3
- 238000013517 stratification Methods 0.000 description 3
- 239000003814 drug Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 201000009906 Meningitis Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 206010039083 rhinitis Diseases 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The disclosure is directed to a kind of patient's group technology and devices.This method includes：The transaction set for including the sick type is excavated from medical data according to the sick type of patient, wherein, each affairs in transaction set include one or more diagnosis；It counts sick type in each affairs and associates property coefficient with the first of diagnosis, and frequent item set is generated according to the first association property coefficient and first threshold；Each diagnosis in frequent item set is normalized in the Classification of Diseases coding of diagnosis in frequent item set；And the sick type calculated after normalization associates property coefficient with the second of diagnosis, and determine that the patient of disease type is grouped based on the described second association property coefficient and second threshold.The disclosure can efficiently and accurately automatically patient is grouped, it is possible to reduce cost of labor is conducive to further carry out personal management and service to patient.
Description
Technical Field
The disclosure relates to the field of medical big data, in particular to a patient grouping method and a patient grouping device.
Background
With the advancement of medical informatization, medical information systems such as HIS (hospital information system) and EMR (electronic medical record) have been developed in various hospitals, which greatly improves the efficiency of hospital management and patient care.
In terms of patient management, different patient groupings will correspond to different management schemes. The patients are managed after being grouped, so that diagnosis and treatment nursing means can be standardized, and the patients can be optimally treated and nursed; the working efficiency is improved, and unnecessary resource waste is reduced; effectively manage the use of resources and limit the increase of medical expenses. Due to the above-mentioned advantages of patient grouping, there is an increasing interest in how to scientifically group patients. However, at present, patient grouping in medical institutions is manually performed according to disease classification standard regulations.
Manual grouping is not only inefficient, but it is difficult to accurately group patients because of differences in their true condition and disease classification criteria.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
An object of the present disclosure is to provide a patient grouping method and a patient grouping apparatus, which overcome, at least to some extent, one or more of the problems due to the limitations and disadvantages of the related art.
According to an aspect of the present disclosure, there is provided a patient grouping method including:
mining a set of transactions containing a patient's type of illness from medical data according to the patient's type of illness, wherein each transaction in the set of transactions includes one or more diagnoses;
counting a first correlation coefficient of the disease type and the diagnosis in each transaction, and generating a frequent item set according to the first correlation coefficient and a first threshold value;
normalizing each of the diagnoses in the frequent item set according to the disease classification criteria code for the diagnosis in the frequent item set; and
calculating a second correlation coefficient of the disease type and the diagnosis after normalization, and determining a patient group of the disease type based on the second correlation coefficient and a second threshold.
In an exemplary embodiment of the disclosure, the patient's type of disease includes one or more of diabetes type 1, diabetes type 2, and gestational diabetes.
In an exemplary embodiment of the disclosure, the one or more diagnostics include one or more of 1 diagnostics, 2 diagnostics, or 3 diagnostics.
In an exemplary embodiment of the present disclosure, the first relevance coefficient and the second relevance coefficient are both a support degree and/or a confidence degree.
In an exemplary embodiment of the disclosure, the disease classification criteria code comprises an ICD-10 code.
According to another aspect of the present disclosure, there is also provided a patient grouping apparatus comprising:
a transaction set mining unit, which is used for mining a transaction set containing the disease type from medical data according to the disease type of a patient, wherein each transaction in the transaction set comprises one or more diagnoses;
a frequent item set generating unit, configured to count a first correlation coefficient between the disease type and the diagnosis in each transaction, and generate a frequent item set according to the first correlation coefficient and a first threshold;
a normalization unit, configured to normalize each diagnosis in the frequent item set according to a disease classification standard code of the diagnosis in the frequent item set; and
a patient group determination unit for calculating a second correlation coefficient of the disease type after normalization and the diagnosis, and determining a patient group of the disease type based on the second correlation coefficient and a second threshold.
In an exemplary embodiment of the disclosure, the patient's type of disease includes one or more of diabetes type 1, diabetes type 2, and gestational diabetes.
In an exemplary embodiment of the disclosure, the one or more diagnostics include one or more of 1 diagnostics, 2 diagnostics, or 3 diagnostics.
In an exemplary embodiment of the disclosure, it is characterized in that the first relevance coefficient and the second relevance coefficient are both support degree and/or confidence degree.
In an exemplary embodiment of the disclosure, the disease classification criteria code comprises an ICD-10 code.
The patient grouping method and the patient grouping device in an exemplary embodiment of the disclosure count a first correlation coefficient of disease types and diagnoses in each transaction mined from medical data, and generate a frequent item set according to the first correlation coefficient and a first threshold; and normalizing each diagnosis in the frequent item set according to the disease classification standard codes, calculating a second correlation coefficient of the disease type and the diagnosis after normalization, and determining the patient grouping of the disease type based on the second correlation coefficient and a second threshold value. On one hand, by appropriately setting the first relevance coefficient and the first threshold, a set of items with small relevance can be excluded, so that the total amount of calculation can be reduced; on the other hand, the diagnosis in the frequent item set is normalized through the disease classification standard codes, the item sets with consistent codes are unified together, and then the patient grouping is evaluated by combining a preset second threshold value, so that the accuracy of the patient grouping can be improved; on the other hand, the patients can be efficiently, accurately and automatically grouped, so that the labor cost can be reduced, and the personalized management and service for the patients can be further facilitated.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The above and other features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
Fig. 1 shows a flow chart of a first patient grouping method according to an exemplary embodiment of the present disclosure;
FIGS. 2 a-2 c show schematic diagrams of frequent 2-item sets for three types of diabetes, according to an exemplary embodiment of the present disclosure;
FIG. 3 shows a schematic diagram of a frequent 3 item set for type 2 diabetes, according to an example embodiment of the present disclosure;
FIG. 4 shows a schematic diagram of a frequent 4-item set for type 2 diabetes, according to an example embodiment of the present disclosure;
FIG. 5 shows a schematic diagram of normalizing diagnosis in a frequent item set using ICD-10 encoding according to an example embodiment of the present disclosure;
fig. 6 shows a flowchart of a second patient grouping method according to another exemplary embodiment of the present disclosure; and
fig. 7 shows a block diagram of a patient grouping apparatus according to an exemplary embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the embodiments of the disclosure can be practiced without one or more of the specific details, or with other methods, components, materials, devices, steps, and so forth. In other instances, well-known structures, methods, devices, implementations, materials, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in the form of software, or in one or more software-hardened modules, or in different networks and/or processor devices and/or microcontroller devices.
In the present exemplary embodiment, a patient grouping method is first provided. Referring to fig. 1, the patient grouping method includes the steps of:
s110: mining a set of transactions containing a patient's type of illness from medical data according to the patient's type of illness, wherein each transaction in the set of transactions includes one or more diagnoses;
s120: counting a first correlation coefficient of the disease type and the diagnosis in each transaction, and generating a frequent item set according to the first correlation coefficient and a first threshold value;
s130: normalizing each of the diagnoses in the frequent item set according to the disease classification criteria code for the diagnosis in the frequent item set; and
s140: calculating a second correlation coefficient of the disease type and the diagnosis after normalization, and determining a patient group of the disease type based on the second correlation coefficient and a second threshold.
According to the patient grouping method in the present exemplary embodiment, on the one hand, by appropriately setting the first relevance coefficient and the first threshold, a set of items with little relevance can be excluded, so that the total amount of calculation can be reduced; on the other hand, the diagnosis in the frequent item set is normalized through the disease classification standard codes, the item sets with consistent codes are unified together, and then the patient grouping is evaluated by combining a preset second threshold value, so that the accuracy of the patient grouping can be improved; on the other hand, the patients can be efficiently, accurately and automatically grouped, so that the labor cost can be reduced, and the personalized management and service for the patients can be further facilitated.
Next, a patient grouping method in the present exemplary embodiment will be further explained.
In step S110, a set of transactions including a patient type is mined from medical data according to the patient type, wherein each transaction in the set of transactions includes one or more diagnoses.
First, terms commonly used in association analysis are introduced. Let I ═ I1，i2，…，imItem (in this disclosure, an item is a medical data item such as a type of illness and diagnosis in medical data). Let task-related transaction set T ═ T1，t2，…，tNIs the set of all transactions, each transaction t contains a set of items that are a subset of I. In relevance analysis, a collection of items is referred to as a set of items. If a set of items contains k items, it is called a set of k items. For example, { type 2 diabetes, fatty liver, essential hypertension } is a 3-item set.
Further, in the present exemplary embodiment, each transaction T in the transaction set T is a non-empty set including a disease type and one or more diagnoses related to the disease type. For example, in an exemplary embodiment of the present disclosure, where the patient's type of disease is type 2 diabetes, each transaction T in the set of transactions T may include type 2 diabetes and one or more diagnoses related to type 2 diabetes, wherein the one or more diagnoses related to type 2 diabetes may include fatty liver, coronary heart disease, essential hypertension, sinus rhythm, and the like.
In the present exemplary embodiment, the disease type may include diabetes type 1, diabetes type 2, or gestational diabetes, but the disease type in the exemplary embodiments of the present disclosure is not limited thereto, and for example, the disease type may also include a disease type related to meningitis, a disease type related to rhinitis, a disease type related to tumor, and the like.
Further, in the present exemplary embodiment, the one or more diagnoses may include one or more of 1 diagnosis, 2 diagnoses, or 3 diagnoses, but the one or more diagnoses in the exemplary embodiments of the present disclosure may also include other integers within a certain range, for example, the one or more diagnoses may include 4 diagnoses, 5 diagnoses, and 7 diagnoses, etc., which also fall within the scope of the present disclosure.
Next, in step S120, a first correlation coefficient between the disease type and the diagnosis in each transaction is counted, and a frequent item set is generated according to the first correlation coefficient and a first threshold.
Mining of frequent item sets is an important content in relevance analysis. In an exemplary embodiment of the present disclosure, all the item sets whose first relevance coefficients satisfy the first threshold are referred to as frequent item sets, and mining the frequent item sets is to find all the item sets whose first relevance coefficients satisfy the first threshold. The first threshold value is a value set according to the number of transactions T in the transaction set T, the number of items in the transactions T, the computational performance of the computer, and the like. When the number of transactions T in the transaction set is large and the number of entries in the transactions T is large, the first threshold may be set to a large value, for example, the first threshold when three diagnoses are included in the transactions T may be set to a larger value than the first threshold when 1 diagnosis is included in the transactions T.
In an exemplary embodiment of the present disclosure, setting an appropriate first threshold value may exclude a set of items that are less relevant, reducing the number of frequent sets of items generated, and thus reducing the total amount of computation.
Next, the mining process of a frequent item set within 4 items is exemplarily described. Excavating a frequent item set through the following steps: (a) counting first correlation coefficients of the disease type in the transaction and the occurrence of each 1 diagnosis independently; (b) counting a first correlation coefficient of the disease type in the transaction and each 2 diagnoses; (c) counting a first correlation coefficient of the disease type in the transaction and each 3 diagnoses; (d) and combining the first relevance coefficient in the steps a, b and c and the first threshold value to generate a frequent 2 item set, a frequent 3 item set and a frequent 4 item set. 2 a-2 c, 3, and 4, FIGS. 2 a-2 c show schematic diagrams of frequent 2-item sets for three types of diabetes, according to an exemplary embodiment of the present disclosure; FIG. 3 shows a schematic diagram of a frequent 3 item set for type 2 diabetes, according to an example embodiment of the present disclosure; fig. 4 shows a schematic diagram of a frequent 4-item set for type 2 diabetes, according to an example embodiment of the present disclosure.
Further, in the present exemplary embodiment, the first relevance coefficient may be a support degree and/or a confidence degree, but the first relevance coefficient in the exemplary embodiment of the present disclosure is not limited thereto, for example, the first relevance coefficient may also be a simple frequency, and may also be a function constructed based on the support degree and/or the confidence degree, which is also within the protection scope of the present disclosure. The first correlation coefficient will be further described below in connection with fig. 2 a-2 c.
As shown in fig. 2a to 2c, in an exemplary embodiment of the present disclosure, when the first correlation coefficient is a support degree, the support degree represents a probability that the type of disease and the diagnosis related to the type of disease simultaneously occur in the transaction set T, which may be represented as P (a UB), for example, the probability that type 1 diabetes and fatty liver simultaneously occur in the transaction set T may be 0.10, the probability that type 2 diabetes and fatty liver simultaneously occur in the transaction set T may be 0.54, and the probability that gestational diabetes and fatty liver simultaneously occur in the transaction set may be 0.12. In the case where the first correlation coefficient is a confidence coefficient, the confidence coefficient indicates a probability that a diagnosis related to a disease type occurs while the disease type occurs in the transaction set T, and may be represented as P (a | B), for example, the probability that fatty liver occurs while type 1 diabetes occurs in the transaction set T may be 0.10, the probability that fatty liver occurs while type 2 diabetes occurs in the transaction set T may be 0.54, and the probability that fatty liver occurs while gestational diabetes occurs in the transaction set T may be 0.12.
Further, in an exemplary embodiment of the disclosure, the first relevance coefficient may also be a customized function, for example, a function constructed based on the support degree and/or the confidence degree, a series of functions set in proportion, and the like, which also belong to the protection scope of the disclosure.
Next, in step S130, each of the diagnoses in the frequent item set is normalized according to the disease classification criteria code of the diagnosis in the frequent item set.
In the present exemplary embodiment, the disease classification standard code may include an ICD-10 code, but the disease classification standard code in the exemplary embodiments of the present disclosure is not limited thereto, and for example, the disease classification standard code may also include a chinese medicine disease code, a tumor morphology code, and the like.
Furthermore, since the granularity of diagnosis is generally fine in medical data, the granularity of diagnosis in the mined frequent item set is fine, for example, the frequent 2 items of type 2 diabetes occur (type 2 diabetes, essential hypertension), (type 2 diabetes, hypertension (III), high risk), (type 2 diabetes, hypertension class 2 (high risk)). However, in a scenario where patients are grouped (e.g., a scenario of scientific research or patient management), the granularity of diagnosis is relatively coarse to apply, and therefore, the diagnosis in the mined frequent item set is normalized.
Because the first 4 codes of the ICD-10 codes of three diagnoses of essential hypertension, hypertension (III grade, extremely high risk) and hypertension 2 grade (extremely high risk) are I10x, the first 4 codes of the ICD-10 codes can be used for normalizing the diagnosis in the mined frequent item set. The process of normalizing diagnosis in a frequent item set using ICD-10 encoding according to an exemplary embodiment of the present disclosure is described below with reference to fig. 5.
In the present exemplary embodiment, the process of normalizing the diagnosis in the frequent item set using ICD-10 encoding may include: three diagnoses of essential hypertension, hypertension (III grade, extremely high risk) and hypertension 2 grade (extremely high risk) with the ICD-10 code of which the first 4 bits are I10x are associated together. However, the normalization process in the exemplary embodiment of the disclosure is not limited thereto, and for example, the diagnosis in the frequent item set may be normalized using the chinese medical science disease code, which also belongs to the scope of the disclosure.
Next, in step S140, a second correlation coefficient of the disease type after normalization and the diagnosis is calculated, and a patient group of the disease type is determined based on the second correlation coefficient and a second threshold value.
In the present exemplary embodiment, calculating the second correlation coefficient of the disease type after normalization and the diagnosis may include: the first correlation coefficients of each of the three diagnoses of essential hypertension, hypertension (class III, high risk) and hypertension 2 (high risk) with all the first 4 bits of ICD-10 encoding I10x are added, but the calculation of the second correlation coefficient of the exemplary embodiment of the present disclosure is not limited thereto, for example, the first correlation coefficients of each of the three diagnoses of essential hypertension, hypertension (class III, high risk) and hypertension 2 (high risk) with all the first 4 bits of ICD-10 encoding I10x may be weighted and then added, which also falls into the protection scope of the present disclosure.
In the present exemplary embodiment, the second threshold value may be a value set based on the distribution of values of the second correlation coefficient. By appropriately setting the second threshold, the patient group of the disease type can be accurately determined.
Further, in another exemplary embodiment of the present disclosure, the patient grouping method may further include: typing the disease type of the patient, wherein when the disease type of the patient is diabetes, the disease type of the diabetic patient is classified into diabetes type 1, diabetes type 2 and gestational diabetes. The patient grouping method of this exemplary embodiment is described below in conjunction with fig. 6.
Fig. 6 shows a flowchart of a second patient grouping method according to another exemplary embodiment of the present disclosure. As shown in fig. 6, the second patient stratification method is different from the first patient stratification method in that the second patient stratification method may further include: the disease types of patients are classified, wherein the disease types of diabetes patients are classified into diabetes type 1, diabetes type 2 and gestational diabetes. The other steps of the second patient grouping method are the same as those of the first patient grouping method, and will not be described herein again. Typing the patient's disease type can reduce the amount of data that needs to be mined, thereby reducing the amount of computation, on the one hand, and can more accurately determine the patient's grouping of disease types, on the other hand.
It should be noted that although the various steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that these steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
In an exemplary embodiment of the present disclosure, a patient grouping apparatus is also provided. Referring to fig. 7, the patient grouping apparatus 700 includes: a transaction set mining unit 710, a frequent item set generation unit 720, a normalization unit 730, and a patient grouping determination unit 740. Wherein,
the transaction set mining unit 710 is used for mining a transaction set containing a disease type from medical data according to the disease type of a patient, wherein each transaction in the transaction set comprises one or more diagnoses;
the frequent item set generating unit 720 is configured to count a first correlation coefficient between the disease type and the diagnosis in each transaction, and generate a frequent item set according to the first correlation coefficient and a first threshold;
the normalization unit 730 is configured to normalize each diagnosis in the frequent item set according to the disease classification criteria code of the diagnosis in the frequent item set; and
the patient group determination unit 740 is configured to calculate a second correlation coefficient between the disease type and the diagnosis after normalization, and determine a patient group of the disease type based on the second correlation coefficient and a second threshold.
In another exemplary embodiment according to the present disclosure, the patient grouping apparatus 700 may further include: a disease typing unit for typing a disease type of a patient, wherein the disease typing unit classifies the disease type of the diabetic patient into diabetes type 1, diabetes type 2, and gestational diabetes. Typing the patient's disease type can reduce the amount of data that needs to be mined, thereby reducing the amount of computation, on the one hand, and can more accurately determine the patient's grouping of disease types, on the other hand.
In the present exemplary embodiment, the first relevance coefficient and the second relevance coefficient may both be a support degree and/or a confidence degree, but the first relevance coefficient and the second relevance coefficient in the exemplary embodiment of the present disclosure are not limited thereto, and for example, the first relevance coefficient and the second relevance coefficient may also be functions constructed based on the support degree and/or the confidence degree, which is also within the scope of the present disclosure.
Further, in the present exemplary embodiment, the first threshold value is a value set according to the number of transactions T in the transaction set T, the number of items in the transactions T, the computational performance of the computer, and the like. Setting the appropriate first threshold value can eliminate item sets with small relevance, reduce the number of generated frequent item sets and further reduce the total calculation amount.
Further, in the present exemplary embodiment, the disease classification standard code may include the ICD-10 code, but the disease classification standard code in the exemplary embodiments of the present disclosure is not limited thereto, and for example, the disease classification standard code may also include a chinese medicine disease code, a tumor morphology code, and the like.
Since the functional modules of the patient grouping apparatus 700 of the exemplary embodiment of the present disclosure correspond to the steps of the exemplary embodiment of the patient grouping method described above, they are not described herein again.
It should be noted that although several modules or units of the patient grouping apparatus 700 are mentioned in the above detailed description, such division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit, according to embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A patient grouping method, comprising:
mining a set of transactions containing a patient's type of illness from medical data according to the patient's type of illness, wherein each transaction in the set of transactions includes one or more diagnoses;
counting a first correlation coefficient of the disease type and the diagnosis in each transaction, and generating a frequent item set according to the first correlation coefficient and a first threshold value;
normalizing each of the diagnoses in the frequent item set according to the disease classification criteria code for the diagnosis in the frequent item set; and
calculating a second correlation coefficient of the disease type and the diagnosis after normalization, and determining a patient group of the disease type based on the second correlation coefficient and a second threshold.
2. The patient grouping method of claim 1, wherein the patient's type of disease comprises one or more of diabetes type 1, diabetes type 2, and gestational diabetes.
3. The patient grouping method according to claim 1 or 2, wherein the one or more diagnoses comprise one or more of 1 diagnosis, 2 diagnoses, or 3 diagnoses.
4. The patient grouping method according to claim 1 or 2, wherein the first correlation coefficient and the second correlation coefficient are both a support degree and/or a confidence degree.
5. The patient grouping method according to claim 1 or 2, wherein the disease classification criteria code comprises an ICD-10 code.
6. A patient grouping apparatus, comprising:
the system comprises a transaction set mining unit, a diagnosis processing unit and a diagnosis processing unit, wherein the transaction set mining unit is used for mining a transaction set containing a disease type from medical data according to the disease type of a patient, and each transaction in the transaction set comprises one or more diagnoses;
a frequent item set generating unit, configured to count a first correlation coefficient between the disease type and the diagnosis in each transaction, and generate a frequent item set according to the first correlation coefficient and a first threshold;
a normalization unit, configured to normalize each diagnosis in the frequent item set according to a disease classification standard code of the diagnosis in the frequent item set; and
a patient group determination unit for calculating a second correlation coefficient of the disease type after normalization and the diagnosis, and determining a patient group of the disease type based on the second correlation coefficient and a second threshold.
7. The patient grouping device of claim 6, wherein the patient's type of disease comprises one or more of diabetes type 1, diabetes type 2, and gestational diabetes.
8. The patient grouping device of claim 6 or 7, wherein said one or more diagnoses comprise one or more of 1 diagnosis, 2 diagnoses, or 3 diagnoses.
9. The patient grouping device according to claim 6 or 7, wherein the first and second correlation coefficients are both a support degree and/or a confidence degree.
10. The patient grouping device according to claim 6 or 7, wherein the disease classification criteria code comprises an ICD-10 code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611021603.5A CN108091398B (en) | 2016-11-21 | 2016-11-21 | Patient grouping method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611021603.5A CN108091398B (en) | 2016-11-21 | 2016-11-21 | Patient grouping method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108091398A true CN108091398A (en) | 2018-05-29 |
| CN108091398B CN108091398B (en) | 2022-03-04 |
Family
ID=62168293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611021603.5A Active CN108091398B (en) | 2016-11-21 | 2016-11-21 | Patient grouping method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108091398B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115305A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视数字技术股份有限公司 | Group identification method and device and computer readable storage medium |
| CN114023456A (en) * | 2021-11-03 | 2022-02-08 | 泰康保险集团股份有限公司 | Outpatient grouping method, outpatient grouping device, electronic device, and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1582443A (en) * | 2001-11-02 | 2005-02-16 | 西门子共同研究公司 | Patient data mining |
| US20150073824A1 (en) * | 2013-09-10 | 2015-03-12 | MD Insider, Inc. | Systems and Methods for Evaluating Health Care Provider Referrals |
| CN104854247A (en) * | 2012-10-12 | 2015-08-19 | 新加坡科技研究局 | Method of prognosis and stratification of ovarian cancer |
| CN105512477A (en) * | 2015-12-03 | 2016-04-20 | 万达信息股份有限公司 | Unplanned readmission risk assessment prediction model based on dimension reduction combination classification algorithm |
| US20160111020A1 (en) * | 2014-10-21 | 2016-04-21 | i-Human Patients, Inc. | Healthcare Education Content Authoring Assistant with Interactive Suggestion Interface Based on Patient and Clinical research Data |
| CN105975608A (en) * | 2016-05-17 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Data mining method and device |
-
2016
- 2016-11-21 CN CN201611021603.5A patent/CN108091398B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1582443A (en) * | 2001-11-02 | 2005-02-16 | 西门子共同研究公司 | Patient data mining |
| CN104854247A (en) * | 2012-10-12 | 2015-08-19 | 新加坡科技研究局 | Method of prognosis and stratification of ovarian cancer |
| US20150073824A1 (en) * | 2013-09-10 | 2015-03-12 | MD Insider, Inc. | Systems and Methods for Evaluating Health Care Provider Referrals |
| US20160111020A1 (en) * | 2014-10-21 | 2016-04-21 | i-Human Patients, Inc. | Healthcare Education Content Authoring Assistant with Interactive Suggestion Interface Based on Patient and Clinical research Data |
| CN105512477A (en) * | 2015-12-03 | 2016-04-20 | 万达信息股份有限公司 | Unplanned readmission risk assessment prediction model based on dimension reduction combination classification algorithm |
| CN105975608A (en) * | 2016-05-17 | 2016-09-28 | 北京京东尚科信息技术有限公司 | Data mining method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115305A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视数字技术股份有限公司 | Group identification method and device and computer readable storage medium |
| CN112115305B (en) * | 2019-06-21 | 2024-04-09 | 杭州海康威视数字技术股份有限公司 | Group identification method apparatus and computer-readable storage medium |
| CN114023456A (en) * | 2021-11-03 | 2022-02-08 | 泰康保险集团股份有限公司 | Outpatient grouping method, outpatient grouping device, electronic device, and medium |
| CN114023456B (en) * | 2021-11-03 | 2024-10-11 | 泰康保险集团股份有限公司 | Outpatient grouping method, outpatient grouping device, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108091398B (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107799160B (en) | Medication aid decision-making method and device, storage medium and electronic equipment | |
| Zech et al. | Natural language–based machine learning models for the annotation of clinical radiology reports | |
| US10692594B2 (en) | Methods for improving natural language processing with enhanced automated screening for automated generation of a clinical summarization report and devices thereof | |
| CN113707297B (en) | Medical data processing method, device, equipment and storage medium | |
| US9165116B2 (en) | Patient data mining | |
| Dickinson et al. | Pragmatic cluster randomized trials using covariate constrained randomization: a method for practice-based research networks (PBRNs) | |
| CN109524070B (en) | Data processing method and device, electronic equipment and storage medium | |
| Najjar et al. | A two-step approach for mining patient treatment pathways in administrative healthcare databases | |
| CN108573758A (en) | A kind of intelligent medical big data service system and application process | |
| WO2017017554A1 (en) | Reliability measurement in data analysis of altered data sets | |
| Enriko et al. | Heart disease diagnosis system with k-nearest neighbors method using real clinical medical records | |
| Thakkar et al. | Health care decision support system for swine flu prediction using naïve bayes classifier | |
| US10741272B2 (en) | Term classification based on combined crossmap | |
| US20150025908A1 (en) | Clustering and analysis of electronic medical records | |
| CN108091398B (en) | Patient grouping method and device | |
| CN111061835B (en) | Query method and device, electronic equipment and computer readable storage medium | |
| Xing et al. | Non-imaging medical data synthesis for trustworthy AI: A comprehensive survey | |
| Choi et al. | Survey of Medical Applications of Federated Learning | |
| CN109597989B (en) | Diagnostic word normalization method and device, storage medium and electronic equipment | |
| Chen et al. | Effects of comorbidity and clustering upon referrals in primary care | |
| Tsumoto et al. | Mining clinical process from hospital information system: A granular computing approach | |
| KR102505749B1 (en) | Method and apparatus for providing an optimal threshold value for optimal triage of infectious disease patients under limited clinical data and healthcare resources | |
| CN110364265B (en) | Data value generation and implementation method based on health data bank | |
| WO2018029028A1 (en) | Electronic clinical decision support device based on hospital demographics | |
| US20220067926A1 (en) | Treatment planning based on multimodal case similarity |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |