CN116501990B - Hospital specialty influence assessment method and device based on outpatient big data - Google Patents
Hospital specialty influence assessment method and device based on outpatient big data Download PDFInfo
- Publication number
- CN116501990B CN116501990B CN202310387600.7A CN202310387600A CN116501990B CN 116501990 B CN116501990 B CN 116501990B CN 202310387600 A CN202310387600 A CN 202310387600A CN 116501990 B CN116501990 B CN 116501990B
- Authority
- CN
- China
- Prior art keywords
- patient
- specialty
- target
- determining
- intervals
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 16
- 230000001186 cumulative effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 238000000638 solvent extraction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 239000008186 active pharmaceutical agent Substances 0.000 description 7
- 238000011161 development Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 210000004185 liver Anatomy 0.000 description 2
- 230000000399 orthopedic effect Effects 0.000 description 2
- 210000000496 pancreas Anatomy 0.000 description 2
- 241000195940 Bryophyta Species 0.000 description 1
- 208000025747 Rheumatic disease Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 235000011929 mousse Nutrition 0.000 description 1
- 238000009206 nuclear medicine Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 230000000552 rheumatic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/22—Social work or social welfare, e.g. community support activities or counselling services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Child & Adolescent Psychology (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of hospital specialty influence assessment, and discloses a hospital specialty influence assessment method and device based on outpatient service big data. The method comprises the following steps: determining the special department clinic quantity and the patient source information based on the clinic big data; constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set; dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals; determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set; determining a source index of a target specialty in the target hospital based on the weights of the sections and the specialty sample proportions of the sections; and evaluating the influence of the target specialty based on the specialty clinic volume and the source location index. The patient population can be selected based on the patient population, and the patient population can be evaluated for patient impact.
Description
Technical Field
The invention relates to the technical field of hospital specialty influence assessment, in particular to a hospital specialty influence assessment method and device based on outpatient service big data.
Background
The clinical specialty of the hospital reflects the level and development potential of medical institutions for providing specialty medical services, and the quantitative evaluation of the clinical specialty of the hospital has important values in the aspects of medical resource allocation, industry supervision, hospital management and the like. Over the last 20 years, some institutions have ranked or rated hospitals and specialty in China to help guide patients in selecting the appropriate hospital or medical center for treatment. However, the current hospital department influence evaluation system is complex in calculation, reflects the expert opinion and the scientific research capability of doctors, rarely truly focuses on the patient group, lacks relatively objective evaluation criteria, and therefore cannot provide good medical selection for patients.
Disclosure of Invention
The invention mainly aims to provide a hospital specialty influence assessment method and device based on outpatient big data, and aims to solve the technical problem that the prior art cannot provide good medical selection for patients because the existing hospital specialty influence assessment system is very little concerned with patient groups.
In order to achieve the above object, the present invention provides a hospital specialty influence assessment method based on outpatient big data, the method comprising the steps of:
acquiring outpatient big data of a target hospital;
determining specialty clinic volume and patient source location information based on the clinic big data;
constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set;
dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals;
determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set;
determining a source index of a target specialty in the target hospital based on the weights of the sections and the specialty sample proportions of the sections;
and evaluating the influence of the target specialty based on the specialty clinic volume and the source location index.
Optionally, the constructing a target data set according to the patient source information includes:
if the patient source information comprises a patient text address, converting the patient text address into longitude and latitude coordinates of a patient through an API service of geocoding;
if only the patient telephone information exists in the patient source information, the attribution of the patient telephone information is used as a patient text address, and then the patient text address is converted into longitude and latitude coordinates of the patient through a geocoding API service;
and determining patient distance information according to the longitude and latitude coordinates of the patient, and constructing a target data set based on the patient distance information.
Optionally, said fitting the statistical distribution of the target dataset comprises:
fitting a reference distance distribution based on the target dataset;
and determining parameter estimation of the reference distance distribution to obtain statistical distribution of the target data set, wherein the statistical distribution is obtained by fitting the target data set.
Optionally, the dividing the statistical distribution into intervals to obtain an interval range of each interval and an accumulated probability of each interval includes:
determining that k intervals exist in the fitting distribution;
and taking MSE as a loss function of the statistical distribution, and determining k representative points of the statistical distribution, a range of k intervals and the cumulative probability of the k intervals when the loss function is the minimum value.
Optionally, the determining the MSE as the loss function of the statistical distribution, when the loss function is the minimum value, the k representative points of the statistical distribution, the interval range of k intervals, and the cumulative probability of k intervals includes:
s4021, setting the initial value of the representative point of k sections as y= { y 1 ,y 2 ,…,y k And } wherein,
c≤y 1 ≤y 2 ≤…≤y k ≤d；
s4022, determining the end point of the interval as
S4023. Calculating conditional expectation of ith intervalObtaining the representative point updated values of k intervals
S4024, judging whether the absolute value of the difference between the initial value of the representative point and the updated value of the representative point is smaller than a preset value;
s4025, when it is determined that the absolute value of the difference between the representative point initial value and the representative point update value is not smaller than the preset value, repeating steps S4022-S4025 with the representative point update value as a new representative point initial value until the absolute value of the difference between the representative point initial value and the representative point update value is smaller than the preset value, thereby obtaining k representative points of the statistical distribution, a range of intervals of k intervals, and an accumulated probability of k intervals.
Optionally, the determining the weight of each section according to the accumulated probability of each section includes:
determining initial weights of all the intervals according to the accumulated probabilities of all the intervals, wherein the initial weights are the inverse of the accumulated probabilities;
determining an initial weight sum according to the initial weights of the intervals;
and taking the ratio of the initial weight of each interval to the initial weight sum as the weight of each interval.
Optionally, the determining the proportion of the special sample in each section according to the target data set includes:
determining the number of patients in the target specialty based on the target data set, and determining the target number of patients in each section based on the target data set;
and determining the proportion of the special sample in each section based on the number of the patients in the target special department and the target number of the patients in each section.
In addition, in order to achieve the above object, the present invention also provides a hospital specific influence assessment device based on outpatient big data, the hospital specific influence assessment device based on outpatient big data comprising:
the acquisition module is used for acquiring the outpatient big data of the target hospital;
the determining module is used for determining the special department clinic quantity and the information of the source place of the patient based on the clinic big data;
the fitting module is used for constructing a target data set according to the information of the source of the patient and fitting the statistical distribution of the target data set;
the fitting module is further used for dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals;
the fitting module is further used for determining the weight of each section according to the accumulated probability of each section and determining the proportion of the special sample of each section according to the target data set;
the fitting module is further used for determining a source index of a target specialty in the target hospital based on the weight of each section and the specialty sample proportion of each section;
and the evaluation module is used for evaluating the influence of the target specialty based on the specialty clinic quantity and the source index.
In addition, in order to achieve the above object, the present invention also proposes a hospital specific influence assessment apparatus based on outpatient big data, the hospital specific influence assessment apparatus based on outpatient big data comprising: the system comprises a memory, a processor and an outpatient-data-based hospital specialty impact assessment program stored on the memory and executable on the processor, the outpatient-data-based hospital specialty impact assessment program configured to implement the steps of the outpatient-data-based hospital specialty impact assessment method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a hospital specific influence assessment program based on outpatient big data, which when executed by a processor, implements the steps of the hospital specific influence assessment method based on outpatient big data as described above.
The hospital department influence assessment method and device based on the outpatient big data provided by the invention are characterized in that the outpatient big data of a target hospital are obtained; determining specialty clinic volume and patient source location information based on the clinic big data; constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set; dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals; determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set; determining a source index of a target specialty in the target hospital based on the weights of the sections and the specialty sample proportions of the sections; and evaluating the influence of the target specialty based on the specialty clinic volume and the source location index. The method can take the source information of the patient as an influence factor when evaluating the influence of the special department of the hospital, does not need to acquire expert opinion or expert scientific research capability, can acquire the source index and the special department outpatient quantity for evaluating the influence of the special department of the hospital only by using big outpatient data, and can also reflect the development characteristics of different special departments of the hospital by combining the source index and the two dimensions of the outpatient quantity, thereby providing important reference value for a hospital leader when making special department development decisions.
Drawings
FIG. 1 is a schematic diagram of a hospital specific impact assessment device based on outpatient big data for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a hospital specialty impact assessment method based on outpatient big data according to the present invention;
FIG. 3 is a schematic diagram of distance intervals and weights in a first embodiment of a hospital specialty impact assessment method based on outpatient big data according to the present invention;
FIG. 4 is a schematic diagram of an influence assessment model of a target specialty in a first embodiment of a hospital specialty influence assessment method based on outpatient big data according to the present invention;
FIG. 5 is a two-dimensional joint evaluation chart of influence of a target specialty in a first embodiment of a hospital specialty influence evaluation method based on outpatient big data of the present invention;
FIG. 6 is a flow chart of a second embodiment of the hospital specialty impact assessment method based on outpatient big data of the present invention;
FIG. 7 is a histogram and probability density function chart of a reference distance distribution in a second embodiment of the hospital specialty impact assessment method based on outpatient big data of the present invention;
FIG. 8 is a diagram of a non-surgical department source index in a second embodiment of a hospital specialty impact assessment method based on outpatient big data according to the present invention;
FIG. 9 is a diagram of a laboratory source index in a second embodiment of the hospital specialty impact assessment method based on outpatient big data of the present invention;
fig. 10 is a block diagram showing the configuration of a first embodiment of the hospital specific influence assessment apparatus based on outpatient big data according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a hospital specific impact assessment device based on outpatient big data in a hardware operation environment according to an embodiment of the present invention.
As shown in fig. 1, the hospital specific influence assessment apparatus based on outpatient big data may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the hospital specific impact assessment device based on outpatient big data, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a hospital specific influence evaluation program based on outpatient big data may be included in the memory 1005 as one storage medium.
In the hospital specialist impact assessment apparatus based on outpatient big data shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the outpatient-big-data-based hospital specialty influence assessment device can be arranged in the outpatient-big-data-based hospital specialty influence assessment device, and the outpatient-big-data-based hospital specialty influence assessment device calls the outpatient-data-based hospital specialty influence assessment program stored in the memory 1005 through the processor 1001 and executes the outpatient-big-data-based hospital specialty influence assessment method provided by the embodiment of the invention.
Based on the hardware structure, the embodiment of the hospital specialty influence assessment method based on the outpatient big data is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a hospital specialty influence assessment method based on outpatient big data according to the present invention.
In this embodiment, the hospital specialty influence assessment method based on outpatient big data includes the following steps:
step S10: and acquiring outpatient big data of the target hospital.
It should be noted that, the execution body of the embodiment may be a computing service device with functions of data processing, network communication and program running, such as a mobile phone, a tablet computer, a personal computer, or an electronic device capable of implementing the above functions or a hospital department influence assessment device based on outpatient big data. The present embodiment and the following embodiments will be described below by taking the hospital specific influence assessment apparatus based on the outpatient big data as an example.
It should be noted that the outpatient big data of the target hospital includes outpatient data of all departments in the target hospital.
Step S20: and determining the special department clinic quantity and the information of the source place of the patient based on the clinic big data.
In particular implementations, the specialty clinic volume and patient source information may be determined by data cleansing out of clinic big data.
Step S30: and constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set.
It should be noted that the patient source of each patient may include a patient text address and patient telephone information, may include only a patient text address, may include only patient telephone information, and may include neither a patient text address nor patient telephone information.
In one embodiment, the constructing a target data set from the patient source information includes:
if the patient source information comprises a patient text address, converting the patient text address into longitude and latitude coordinates of a patient through an API service of geocoding;
if only the patient telephone information exists in the patient source information, the attribution of the patient telephone information is used as a patient text address, and then the patient text address is converted into longitude and latitude coordinates of the patient through a geocoding API service;
and determining patient distance information according to the longitude and latitude coordinates of the patient, and constructing a target data set based on the patient distance information.
It should be noted that, when the patient source information includes only the patient text address, there may be an address bar blank or the address information may not be recognized.
It should be noted that, the patient text address may be converted into latitude and longitude coordinates through the geocoding API service provided by the hundred degree map open platform, and the distance between the patient and the target hospital (i.e., the patient distance information) may also be calculated according to the latitude and longitude coordinates using the python's library geopy, wherein the default WGS-84 model is used in determining the patient distance information.
In a specific implementation, whether the patient distance information accords with the actual situation can be judged, specifically, a preset target value can be set in advance, and when the patient distance information is larger than the preset target value, it can be judged that the patient distance information does not accord with the actual situation and the patient distance information is removed.
In an embodiment, said fitting the statistical distribution of the target dataset comprises:
fitting a reference distance distribution based on the target dataset;
and determining parameter estimation of the reference distance distribution to obtain statistical distribution of the target data set, wherein the statistical distribution is obtained by fitting the target data set.
In a specific implementation, the parameter estimate of the reference distance distribution may be determined by a maximum likelihood estimate. In this embodiment, since most of the patients in the hospital come from the place and the surrounding area of the hospital, the probability of visiting the patient in the outside is relatively much smaller, and the distance distribution should be a right-biased distribution, so that the distance distribution from the source of the patient to the hospital can be better described by using the Gamma distribution.
Step S40: and dividing the statistical distribution into sections to obtain the section range of each section and the cumulative probability of each section.
It should be noted that the statistical distribution may be divided into intervals according to the statistical distribution representative point theory.
The MSE may be used to determine the representative point distribution of the statistical distribution and the section division, and then determine the section range of each section and the cumulative probability of each section.
In a specific implementation, k representative points of the statistical distribution, a range of intervals of k intervals in the statistical distribution, and an accumulated probability of k intervals are shown in the following table 1, where y represents a representative point, Ω represents a range of intervals, and P represents an accumulated probability:
TABLE 1
Step S50: and determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set.
In an embodiment, the determining the weight of each section according to the accumulated probability of each section includes:
determining initial weights of all the intervals according to the accumulated probabilities of all the intervals, wherein the initial weights are the inverse of the accumulated probabilities;
determining an initial weight sum according to the initial weights of the intervals;
and taking the ratio of the initial weight of each interval to the initial weight sum as the weight of each interval.
The cumulative probability of the ith interval is p i For example, then the initial weight of the ith interval is 1/p i The initial weight sum of all intervals isThe weight of the i-th interval can be obtained as:
wherein k represents the number of intervals in the statistical distribution, 1/p i Representing the initial weight of the i-th interval,representing the initial weight sum of k intervals.
It can be understood that, as shown in fig. 3, the distance interval and the weight are schematic, and it can be seen from the figure that the closer to the hospital, the lower the weight of the impact score is, and the higher the weight is in the scoring model as the distance is larger.
In an embodiment, the determining the proportion of the special sample in each section according to the target data set includes:
determining the number of patients in the target specialty based on the target data set, and determining the target number of patients in each section based on the target data set;
and determining the proportion of the special sample in each section based on the number of the patients in the target special department and the target number of the patients in each section.
Step S60: and determining the source index of the target specialty in the target hospital based on the weight of each section and the specialty sample proportion of each section.
In a specific implementation, the calculation formula of the source index of the target specialty is as follows:
where PRI represents the index of origin,the proportion of the special samples representing the ith interval, k representing the number of intervals of statistical distribution, w i The weight of the i-th interval is represented.
Step S70: and evaluating the influence of the target specialty based on the specialty clinic volume and the source location index.
It should be noted that, the calculation of the source index only needs the source information of the patient, which is completely driven by actual data, and the source information is clinic basic information of each hospital, and expert questionnaires are not needed to be made.
In a specific implementation, fig. 4 is an impact assessment model of a target specialty.
In a specific implementation, a two-dimensional joint evaluation chart of outpatient big data can be generated according to the outpatient quantity and the source index, and then the influence of the specialty of the hospital is evaluated according to the two-dimensional joint evaluation chart, as shown in fig. 5, the specialty of the target hospital can be roughly classified into 4 categories. The first category is an excellent specialty with large clinic volume and high social influence; the second category belongs to a special department with small clinic volume but various patient sources, which shows that the special departments still have higher social reputation, the special departments have strong professional ability, and a considerable part of outpatients come from remote mousse; the third type of special department has large clinic volume, and the main constitution of the patient is the resident nearby, and the special department has strong business capability; the fourth category is those specialized where the clinic volume is relatively small and the patient source is also relatively centralized.
In the embodiment, the outpatient big data of the target hospital are acquired; determining specialty clinic volume and patient source location information based on the clinic big data; constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set; dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals; determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set; determining a source index of a target specialty in the target hospital based on the weights of the sections and the specialty sample proportions of the sections; based on the specialty clinic volume and the source location index, the specialty impact of the target hospital is evaluated. The method can take the source information of the patient as an influence factor when evaluating the influence of the special department of the hospital, does not need to acquire expert opinion or expert scientific research capability, can acquire the source index and the special department outpatient quantity for evaluating the influence of the special department of the hospital only by using big outpatient data, and can also reflect the development characteristics of different special departments of the hospital by combining the source index and the two dimensions of the outpatient quantity, thereby providing important reference value for a hospital leader when making special department development decisions.
Referring to fig. 6, fig. 6 is a schematic flow chart of a second embodiment of a hospital specialty influence assessment method based on outpatient big data according to the present invention.
Based on the first embodiment, the step S40 of the hospital specialty impact assessment method based on outpatient big data in this embodiment includes:
step S401: determining that the fit distribution exists in k intervals.
Step S402: and taking MSE as a loss function of the statistical distribution, and determining k representative points of the statistical distribution, a range of k intervals and the cumulative probability of the k intervals when the loss function is the minimum value.
In an embodiment, the determining the MSE as the loss function of the statistical distribution, the k representative points of the statistical distribution, the interval range of k intervals, and the cumulative probability of k intervals when the loss function is at a minimum value includes:
s4021, setting the initial value of the representative point of k sections as y= { y 1 ,y 2 ,…,y k And } wherein,
c≤y 1 ≤y 2 ≤…≤y k ≤d；
s4022, determining the end point of the interval as
S4023 calculating the condition expectation of the ith sectionObtaining the representative point updated values of k intervals
S4024, judging whether the absolute value of the difference between the initial value of the representative point and the updated value of the representative point is smaller than a preset value;
s4025, when it is determined that the absolute value of the difference between the representative point initial value and the representative point update value is not smaller than the preset value, repeating steps S4022-S4025 with the representative point update value as a new representative point initial value until the absolute value of the difference between the representative point initial value and the representative point update value is smaller than the preset value, thereby obtaining k representative points of the statistical distribution, a range of intervals of k intervals, and an accumulated probability of k intervals.
After determining the number of sections, it is necessary to set an initial value of a representative point in each section, to determine an initial section end point based on the initial value of the representative point, to expect conditions of each section as a representative point update value of each section after determining the section end point of each section, to compare an absolute value of a difference between the initial value of the representative point and the representative point update value with a preset value to determine whether the section end point needs to be continuously updated, and to determine that the section end point does not need to be updated, then to use the current k representative points and the current section end point as the k representative points of the statistical distribution and the section range of the k sections.
In a specific implementation, the influence of the department of the three-phase hospital of the province A in 2014-2021 is evaluated, wherein the outpatient big data are data of all outpatients of 16 departments of the three-phase hospital of the province A in 2014-2021, including address and contact phone filled by the patients, and we use all departments of the institution as an illustration of a specific calculation process of the index of the origin of the patients:
(1) Patient source distance calculation:
we first convert all the information of the available sources in the database into latitude and longitude, and then calculate the distance from each source to the hospital.
The source information of the consultant is extracted mainly from address and telephone information filled in when the patient is in medical treatment. The hundred degree map open platform provides a geocoded API service that can translate text addresses into latitude and longitude coordinates. For invalid address information, such as address bar blank or address information which cannot be identified, a phone module of python is used for extracting the home location of the mobile phone number to approximately replace the address of the doctor, and then the address is converted into longitude and latitude coordinates through an API. Data having neither a valid address nor a valid handset number will be considered invalid data.
The library geopy using python can calculate its distance to the hospital site from the latitude and longitude coordinates of the visit (using the default WGS-84 model, all latitude and longitude coordinates retain four decimal places).
Fitting the reference distance distribution Ga (alpha, beta) with all the effective outpatient data of the hospital, obtaining parameter estimation according to maximum likelihood estimationFig. 7 is a histogram of the reference distance distribution and a probability density function of the gamma distribution Ga (0.1875,0.0014) obtained by fitting. The fitted gamma distribution can be seen to well describe the right bias characteristics of the distance distribution of the source of the consultant, i.e. most of the consultants come from areas closer to the hospital, and the number of the consultants is significantly reduced with the increase of the distance.
(3) Calculating the source index of each department:
according to experience, the gamma distribution obtained by fitting is divided into 6 grade sections, 6 representative points of Ga (0.1875,0.0014), section ranges of each section and cumulative probability of each section are obtained by using an Lloyd-Max method, and the weight of each section is determined according to the cumulative probability of each section. As shown in table 2 below, wherein Ω in table 2 represents a section range, y represents a representative point, p represents an accumulation probability, and W represents a weight:
TABLE 2
Next, the distance distribution (i.e., the ratio of the specialty samples) of 16 specialty departments of the hospital from 2014-2021 each year of the source of the consultant was calculated based on the division of the distance intervals in Table 2Weighting according to the weight of the intervalAnd (5) calculating average to obtain the influence evaluation indexes of the 16 special areas of the hospital. Since the hospital specific influence score obtained by directly weighting according to the proportion is smaller in value, the average value of the hospital in 2017 can be taken as a reference, the score is 100, and other departments can also be adjusted in proportion. Namely:
it should be noted that, fig. 8 shows the index of origin of 8 non-operative departments in 2014-2021, fig. 9 shows the index of origin of 8 operative departments in 2014-2021, and it can be seen from the figure that, as the hospitals develop, the sources of the patients in the specialized departments in the hospitals are more and more diversified, and the influence is gradually improved. Some of the specialized departments were greatly affected by 2017 medical changes, and the index of the patient origin fell back. It can be seen that the patient source index of some specialty has a significant fall back in 2020.
(4) Joint assessment of origin and clinic volume (dividing different specialty, importance (professional) -performance (clinic volume)):
similarly, the average clinic volume of each department in 2017 is taken as a reference, the score is 100, and the clinic volume of each department is adjusted to be:
it should be noted that we combine the index of patient origin with the clinic volume, as shown in fig. 5, to obtain distribution diagrams of two dimensions of clinic volume-origin of different specialized departments.
As can be seen from fig. 5, of the 8 disciplines that are non-surgical disciplines, the traditional Chinese medical and pediatric department belongs to a discipline with a large clinic volume, but with a relatively limited patient origin (PRI < 75). Nuclear medicine and rheumatics are smaller in outpatient setting (OA < 50) due to the nature of the specialty, but the patient source index is of intermediate level. The dermatological department has a large clinic volume (OA of 150 or more) and a high origin index (PRI of 150 or more) in 8 non-surgical specialized departments. The general surgical specialty patient sources are relatively wide, as compared to the non-surgical specialty, each of which can reach PRI >100 in certain years. Among them, gynaecology and obstetrics belongs to the special department that the clinic volume is very big, and patient's source is also very extensive. But orthopedics department, liver and gall pancreas department belongs to clinic quantity little, but patient source is a wider special department, which shows that the orthopedics department, liver and gall pancreas department has a certain influence.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a hospital specialty influence evaluation program based on the outpatient big data, and the hospital specialty influence evaluation program based on the outpatient big data realizes the steps of the hospital specialty influence evaluation method based on the outpatient big data when being executed by a processor.
Referring to fig. 10, fig. 10 is a block diagram showing the configuration of a first embodiment of the hospital specific influence assessment apparatus based on outpatient big data according to the present invention.
As shown in fig. 10, the hospital specialty influence assessment device based on outpatient big data according to the embodiment of the present invention includes:
and the acquisition module 10 is used for acquiring the outpatient big data of the target hospital.
A determining module 20 for determining the specialty clinic volume and the patient source information based on the clinic big data.
Fitting module 30 is configured to construct a target data set based on the patient source information and fit a statistical distribution of the target data set.
The obtaining module 10 is further configured to divide the statistical distribution into intervals, and obtain an interval range of each interval and an accumulated probability of each interval.
The determining module 20 is further configured to determine a weight of each section according to the cumulative probability of each section, and determine a proportion of the specialty sample of each section according to the target data set.
The determining module 20 is further configured to determine a source index of a target specialty in the target hospital based on the weights of the intervals and the specialty sample proportions of the intervals.
An evaluation module 40 for evaluating the influence of the target specialty based on the specialty clinic volume and the source location index.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
In the embodiment, the outpatient big data of the target hospital are acquired; determining specialty clinic volume and patient source location information based on the clinic big data; constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set; dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals; determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set; determining a source index of a target specialty in the target hospital based on the weights of the sections and the specialty sample proportions of the sections; based on the specialty clinic volume and the source location index, the specialty impact of the target hospital is evaluated. The method can take the source information of the patient as an influence factor when evaluating the influence of the special department of the hospital, does not need to acquire expert opinion or expert scientific research capability, can acquire the source index and the special department outpatient quantity for evaluating the influence of the special department of the hospital only by using big outpatient data, and can also reflect the development characteristics of different special departments of the hospital by combining the source index and the two dimensions of the outpatient quantity, thereby providing important reference value for a hospital lead when making special department development decisions.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details which are not described in detail in the present embodiment can be referred to the hospital specialist influence evaluation method based on the outpatient big data provided in any embodiment of the present invention, and are not described here again.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (6)
1. The hospital specialty influence assessment method based on the outpatient big data is characterized by comprising the following steps of:
acquiring outpatient big data of a target hospital;
determining specialty clinic volume and patient source location information based on the clinic big data;
constructing a target data set according to the information of the source of the patient, and fitting the statistical distribution of the target data set;
dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals;
determining the weight of each section according to the accumulated probability of each section, and determining the proportion of the special sample of each section according to the target data set;
determining a source index of a target specialty in the target hospital based on the weights of the sections and the specialty sample proportions of the sections, wherein the source index of the target specialty has the following calculation formula:
where PRI represents the index of origin,the proportion of the special samples representing the ith interval, k representing the number of intervals of statistical distribution, w i A weight representing the i-th interval;
evaluating the influence of the target specialty based on the specialty outpatient quantity and the origin index, wherein a two-dimensional joint evaluation chart of outpatient big data is generated according to the specialty outpatient quantity and the origin index, and then the specialty influence of the hospital is evaluated according to the two-dimensional joint evaluation chart;
the constructing a target data set according to the patient source information comprises:
if the patient source information comprises a patient text address, converting the patient text address into longitude and latitude coordinates of a patient through an API service of geocoding;
if only the patient telephone information exists in the patient source information, the attribution of the patient telephone information is used as a patient text address, and then the patient text address is converted into longitude and latitude coordinates of the patient through a geocoding API service;
determining patient distance information according to the longitude and latitude coordinates of the patient, and constructing a target data set based on the patient distance information;
said fitting of the statistical distribution of the target dataset comprises:
fitting a reference distance distribution based on the target dataset;
determining parameter estimation of the reference distance distribution to obtain statistical distribution of the target data set, wherein the statistical distribution is the statistical distribution obtained by fitting the target data set, wherein the parameter estimation of the reference distance distribution is determined through maximum likelihood estimation, the distance distribution is a right-biased distribution, and Gamma distribution is used for describing the distance distribution from a patient source to a hospital;
the determining the weight of each section according to the accumulated probability of each section comprises the following steps:
determining initial weights of all the intervals according to the accumulated probabilities of all the intervals, wherein the initial weights are the inverse of the accumulated probabilities;
determining an initial weight sum according to the initial weights of the intervals;
taking the ratio of the initial weight of each interval to the initial weight sum as the weight of each interval;
the determining the proportion of the special samples of each interval according to the target data set comprises the following steps:
determining the number of patients in the target specialty based on the target data set, and determining the target number of patients in each section based on the target data set;
and determining the proportion of the special sample in each section based on the number of the patients in the target special department and the target number of the patients in each section.
2. The method of claim 1, wherein the partitioning the statistical distribution into bins and accumulating probabilities for each bin comprises:
determining that the statistical distribution has k intervals;
and taking MSE as a loss function of the statistical distribution, and determining k representative points of the statistical distribution, a range of k intervals and the cumulative probability of the k intervals when the loss function is the minimum value.
3. The method of claim 2, wherein the determining the cumulative probability of k representative points, a range of k intervals, and k intervals of the statistical distribution with the loss function being a minimum using MSE as the loss function of the statistical distribution comprises:
s4021, setting the initial value of the representative point of k sections as y= { y 1 ,y 2 ,…,y k And c.ltoreq.y 1 ≤y 2 ≤…≤y k ≤d；
S4022, determining the end point of the interval as
S4023 calculating the condition expectation of the ith sectionGet the representative point update value of k intervals +.>
S4024, judging whether the absolute value of the difference between the initial value of the representative point and the updated value of the representative point is smaller than a preset value;
s4025, when it is determined that the absolute value of the difference between the representative point initial value and the representative point update value is not smaller than the preset value, repeating steps S4022-S4025 with the representative point update value as a new representative point initial value until the absolute value of the difference between the representative point initial value and the representative point update value is smaller than the preset value, thereby obtaining k representative points of the statistical distribution, a range of intervals of k intervals, and an accumulated probability of k intervals.
4. The utility model provides a hospital specialty influence evaluation device based on outpatient service big data which characterized in that, hospital specialty influence evaluation device based on outpatient service big data includes:
the acquisition module is used for acquiring the outpatient big data of the target hospital;
the determining module is used for determining the special department clinic quantity and the information of the source place of the patient based on the clinic big data;
the fitting module is used for constructing a target data set according to the information of the source of the patient and fitting the statistical distribution of the target data set;
the fitting module is further used for dividing the statistical distribution into intervals to obtain interval ranges of all the intervals and accumulated probability of all the intervals;
the fitting module is further used for determining the weight of each section according to the accumulated probability of each section and determining the proportion of the special sample of each section according to the target data set;
the fitting module is further configured to determine a source index of a target specialty in the target hospital based on the weights of the intervals and the specialty sample proportions of the intervals, where a calculation formula of the source index of the target specialty is as follows:
where PRI represents the index of origin,the proportion of the special samples representing the ith interval, k representing the number of intervals of statistical distribution, w i A weight representing the i-th interval;
the evaluation module is used for evaluating the influence of the target specialty based on the specialty outpatient quantity and the origin index, wherein a two-dimensional joint evaluation chart of outpatient big data is generated according to the specialty outpatient quantity and the origin index, and then the specialty influence of the hospital is evaluated according to the two-dimensional joint evaluation chart;
the fitting module is further configured to:
if the patient source information comprises a patient text address, converting the patient text address into longitude and latitude coordinates of a patient through an API service of geocoding;
if only the patient telephone information exists in the patient source information, the attribution of the patient telephone information is used as a patient text address, and then the patient text address is converted into longitude and latitude coordinates of the patient through a geocoding API service;
determining patient distance information according to the longitude and latitude coordinates of the patient, and constructing a target data set based on the patient distance information;
the fitting module is further configured to:
fitting a reference distance distribution based on the target dataset;
determining parameter estimation of the reference distance distribution to obtain statistical distribution of the target data set, wherein the statistical distribution is the statistical distribution obtained by fitting the target data set, wherein the parameter estimation of the reference distance distribution is determined through maximum likelihood estimation, the distance distribution is a right-biased distribution, and Gamma distribution is used for describing the distance distribution from a patient source to a hospital;
the fitting module is further configured to:
determining initial weights of all the intervals according to the accumulated probabilities of all the intervals, wherein the initial weights are the inverse of the accumulated probabilities;
determining an initial weight sum according to the initial weights of the intervals;
taking the ratio of the initial weight of each interval to the initial weight sum as the weight of each interval;
the fitting module is further configured to:
determining the number of patients in the target specialty based on the target data set, and determining the target number of patients in each section based on the target data set;
and determining the proportion of the special sample in each section based on the number of the patients in the target special department and the target number of the patients in each section.
5. A hospital specialty impact assessment device based on outpatient big data, the device comprising: a memory, a processor and an outpatient big data based hospital specialty impact assessment program stored on the memory and executable on the processor, the outpatient big data based hospital specialty impact assessment program being configured to implement the steps of the outpatient big data based hospital specialty impact assessment method of any of claims 1 to 3.
6. A storage medium, wherein a hospital specific influence assessment program based on outpatient big data is stored on the storage medium, which when executed by a processor, implements the steps of the hospital specific influence assessment method based on outpatient big data as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310387600.7A CN116501990B (en) | 2023-04-11 | 2023-04-11 | Hospital specialty influence assessment method and device based on outpatient big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310387600.7A CN116501990B (en) | 2023-04-11 | 2023-04-11 | Hospital specialty influence assessment method and device based on outpatient big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116501990A CN116501990A (en) | 2023-07-28 |
| CN116501990B true CN116501990B (en) | 2024-01-26 |
Family
ID=87323977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310387600.7A Active CN116501990B (en) | 2023-04-11 | 2023-04-11 | Hospital specialty influence assessment method and device based on outpatient big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116501990B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110415831A (en) * | 2019-07-18 | 2019-11-05 | 天宜(天津)信息科技有限公司 | A kind of medical treatment big data cloud service analysis platform |
| CN110533273A (en) * | 2019-05-28 | 2019-12-03 | 自然资源部四川基础地理信息中心 | Medical institutions' performance classification evaluation method based on the medical geographical big data of patient |
| CN112331322A (en) * | 2020-12-04 | 2021-02-05 | 上海蓬海涞讯数据技术有限公司 | Method, device, processor and storage medium for realizing quantitative evaluation processing aiming at special ability of hospital based on neural network |
| WO2021139146A1 (en) * | 2020-01-09 | 2021-07-15 | 平安国际智慧城市科技股份有限公司 | Information recommendation method, device, computer-readable storage medium, and apparatus |
| CN113344274A (en) * | 2021-06-11 | 2021-09-03 | 华南理工大学 | Hospital emergency spatial layout optimization method and device, computer equipment and storage medium |
| CN113742193A (en) * | 2021-09-13 | 2021-12-03 | 上海晓途网络科技有限公司 | Data analysis method and device, electronic equipment and storage medium |
| CN114155943A (en) * | 2021-11-19 | 2022-03-08 | 郑州大学第一附属医院 | Medical emergency information management system |
| CN114493954A (en) * | 2022-01-21 | 2022-05-13 | 中国科学院地理科学与资源研究所 | Analysis method for medical service utilization of remote patient seeking medical treatment |
| WO2022110053A1 (en) * | 2020-11-27 | 2022-06-02 | 西门子（中国）有限公司 | Intelligent guide method, device, and system for hospital outpatient clinics |
-
2023
- 2023-04-11 CN CN202310387600.7A patent/CN116501990B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533273A (en) * | 2019-05-28 | 2019-12-03 | 自然资源部四川基础地理信息中心 | Medical institutions' performance classification evaluation method based on the medical geographical big data of patient |
| CN110415831A (en) * | 2019-07-18 | 2019-11-05 | 天宜(天津)信息科技有限公司 | A kind of medical treatment big data cloud service analysis platform |
| WO2021139146A1 (en) * | 2020-01-09 | 2021-07-15 | 平安国际智慧城市科技股份有限公司 | Information recommendation method, device, computer-readable storage medium, and apparatus |
| WO2022110053A1 (en) * | 2020-11-27 | 2022-06-02 | 西门子（中国）有限公司 | Intelligent guide method, device, and system for hospital outpatient clinics |
| CN112331322A (en) * | 2020-12-04 | 2021-02-05 | 上海蓬海涞讯数据技术有限公司 | Method, device, processor and storage medium for realizing quantitative evaluation processing aiming at special ability of hospital based on neural network |
| CN113344274A (en) * | 2021-06-11 | 2021-09-03 | 华南理工大学 | Hospital emergency spatial layout optimization method and device, computer equipment and storage medium |
| CN113742193A (en) * | 2021-09-13 | 2021-12-03 | 上海晓途网络科技有限公司 | Data analysis method and device, electronic equipment and storage medium |
| CN114155943A (en) * | 2021-11-19 | 2022-03-08 | 郑州大学第一附属医院 | Medical emergency information management system |
| CN114493954A (en) * | 2022-01-21 | 2022-05-13 | 中国科学院地理科学与资源研究所 | Analysis method for medical service utilization of remote patient seeking medical treatment |
Non-Patent Citations (2)
| Title |
|---|
| 住院病人空间分布函数研究;侯磊;温伟军;金超;熊雪晨;周奕男;白鸽;罗力;;中国卫生政策研究(第09期);全文 * |
| 精神病专科医院病源分布与影响力的研究;温全球;郭建雄;徐昌武;刘海燕;吴东涛;;罕少疾病杂志(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116501990A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Comparing the performance of approaches for testing the homogeneity of variance assumption in one-factor ANOVA models | |
| Campbell et al. | Estimating sample sizes for binary, ordered categorical, and continuous outcomes in two group comparisons | |
| Sacco et al. | Comparison of alternative methods for assessing injury severity based on anatomic descriptors | |
| US8949079B2 (en) | Patient data mining | |
| Ahmed et al. | False discovery rate estimation for frequentist pharmacovigilance signal detection methods | |
| US8548137B2 (en) | Generic fraud detection model | |
| DiGaetano | Sample frame and related sample design issues for surveys of physicians and physician practices | |
| Gruber et al. | Inequality in health care utilization in Germany? Theoretical and empirical evidence for specialist consultation | |
| US10741272B2 (en) | Term classification based on combined crossmap | |
| CN111899821A (en) | Method for processing medical institution data, method and device for constructing database | |
| Berta et al. | % CEM: a SAS macro to perform coarsened exact matching | |
| CN111310009A (en) | User classification method and device, storage medium and computer equipment | |
| Mossman et al. | Using dual beta distributions to create “proper” ROC curves based on rating category data | |
| Nelson et al. | A measure of association for ordered categorical data in population-based studies | |
| CN116091113A (en) | Marketing model data processing method, system and computer readable storage medium | |
| CN111696656A (en) | Doctor evaluation method and device of Internet medical platform | |
| Robertson et al. | Using numerical methods to design simulations: revisiting the balancing intercept | |
| CN116501990B (en) | Hospital specialty influence assessment method and device based on outpatient big data | |
| JP6747438B2 (en) | Information processing apparatus, information processing method, and program | |
| Di Noia et al. | Goodness-of-fit test for count distributions with finite second moment | |
| CN111028931A (en) | Medical data processing method and device, electronic equipment and storage medium | |
| Leyk et al. | Modeling ambiguity in census microdata allocations to improve demographic small area estimates | |
| US20150339602A1 (en) | System and method for modeling health care costs | |
| WO2014150436A1 (en) | Interactive healthcare modeling with continuous convergence | |
| CN113436725A (en) | Data processing method, system, computer device and computer readable storage medium |
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 |