CN111640490A - Hospital outpatient self-service recommendation method based on big data - Google Patents
Hospital outpatient self-service recommendation method based on big data Download PDFInfo
- Publication number
- CN111640490A CN111640490A CN202010365815.5A CN202010365815A CN111640490A CN 111640490 A CN111640490 A CN 111640490A CN 202010365815 A CN202010365815 A CN 202010365815A CN 111640490 A CN111640490 A CN 111640490A
- Authority
- CN
- China
- Prior art keywords
- health
- data
- information
- analysis
- sub
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a hospital outpatient service self-service recommendation method based on big data, which is timely in guidance, high in efficiency and good in reliability. The hospital outpatient service self-service recommendation method based on the big data comprises the following steps: (10) data acquisition: carrying out health questionnaire survey on sub-health people and patients, and collecting user information in a classified manner; (20) identifying health status and evaluating risk: setting weight analysis aiming at the personal health information, and carrying out quantitative evaluation and risk evaluation on the health condition of the individual or the group; (30) data statistics and analysis: combining with a Bayesian algorithm, respectively carrying out classified statistics on personal health information data and case data, and simultaneously carrying out cluster analysis on case big data; (40) health consultation: providing corresponding health indexes and health reports, recommending big data specimens of cases, and continuing; (50) health intervention: the data statistics and analysis are carried out on partial information in the personal health information converted from sub-healthy people to diagnosed patients.
Description
Technical Field
The invention belongs to the technical field of big data application, and particularly relates to a hospital outpatient service self-service recommendation method based on big data.
Background
The hospital outpatient service self-help recommendation can fully utilize the existing resources of the hospital, effectively relieve the phenomena of ' queuing for 2 hours and seeing a doctor ' for 1 minute ' when the outpatient service visits the doctor, and enable the existing resources of the hospital to be effectively configured in a larger range.
In the prior art, different optimization schemes exist for hospital outpatients. For example, the appointment registration platform system can optimize the outpatient process and effectively reduce the waiting time of the patient in the medical institution.
Appointment registration is an important means for effectively relieving the difficulty in seeing a doctor. Due to the fact that the reservation requirements of different groups need to be met, the reservation means has the characteristic of diversity. The existing appointment registration steps are as follows:
(1) integrating reservation information collected from various different channels into a hospital information system;
(2) an information exchange platform is set up to integrate and integrate various reservation modes, and information integration service of seamless connection between various reservation registration modes and a hospital information system is realized;
(3) on the basis of finishing the real-time exchange of the appointment registration information, the real-time subscription of the hospital information by the hospital information publishing and each appointment registration system is gradually established, so that various medical services taking patients as the center are improved.
The appointment registration platform system is an all-directional system and comprises a plurality of modes such as doctor site appointment among the consulting rooms, network system appointment, self-service registration machine appointment, community referral appointment and the like, the most important function is to realize the shunting function on outpatients, realize the medical treatment equalization in the morning and afternoon, achieve the function of filling and completing, meanwhile, the appointment rate is continuously improved, and the planning performance and the configuration capacity of medical resources of hospitals can be improved.
The combination of the appointment registration platform system and the outpatient service one-stop self-service (such as self-service machine, etc.) can greatly improve many problems faced by patients during treatment, but is still not friendly enough, and still has many fundamental problems, such as:
(1) it is limited to provide optimization on the flow and guidance for the case from the source cannot be provided. Often, a patient needs to be informed when a department visits a doctor after making an appointment and registering on a platform with great effort, cannot make a diagnosis, and is recommended to go to another special hospital, and the condition is 'queue for 2 hours and see a doctor for 1 minute', which is not helpful for the patient to select a diagnosis and treatment institution and the department at an early stage;
(2) there is still too much reliance on physicians to provide outpatient opinions. For patients, whether the patients are ill or ill, the patients are in the same flow, the most convenient service cannot be obtained, and the patients are always in the registration flow in the platform. For the collected case information, the most direct treatment scheme cannot be provided, the outpatient opinions of experts are excessively relied on, and the compatibility and similarity of communication among cases are ignored, so that the number of outpatients cannot be effectively reduced all the time, and the pressure of outpatients doctors cannot be fundamentally reduced.
(3) The patient information collected on the platform is limited to registration and no valuable output is made. If the patient is cured by what diagnosis and treatment means due to what diseases are induced by the patient, the key information can not be transmitted to the sub-health population through the hospital all the time, so that the risk of the sub-health population avoiding the diseases can not be reduced all the time; meanwhile, the information release of the hospital stays at the level of protecting the privacy of patients, and case data are always undisclosed, so that sample data cannot be provided for sub-health people as reference during questionnaire survey; secondly, the analysis value of the behavior data of the patient is also ignored, some contents browsed on the hospital platform by sub-health people are often related to the hidden danger of the sub-health people, and then the user behavior data is not regarded by the hospital.
Disclosure of Invention
The invention aims to provide a hospital outpatient service self-service recommendation method based on big data, which is timely in guidance, high in efficiency and good in reliability.
The technical solution for realizing the purpose of the invention is as follows:
a hospital outpatient self-service recommendation method based on big data comprises the following steps:
(10) data acquisition: performing health questionnaire survey on sub-health population and patients, wherein the classified collection of user information comprises the collection of personal health information aiming at the sub-health population; for the patients with confirmed diagnosis, the personal health information is converted into case big data;
(20) identifying health status and evaluating risk: setting weight analysis aiming at the continuously collected personal health information, comparing and analyzing the weight analysis with the diagnosed case big data, and carrying out quantitative evaluation and risk evaluation on the health condition of the individual or the group;
(30) data statistics and analysis: the method is characterized in that a Bayesian algorithm is combined, personal health information data and case data are classified and counted respectively, meanwhile, large case data are subjected to clustering analysis, similar case information with reference value is extracted as a sample for sub-health crowds to browse and access, and meanwhile, a corresponding diagnosis and treatment scheme can be formulated by a clinician for a certain specific crowd;
(40) health consultation: after personal health information of sub-health people is collected, corresponding health indexes and health reports can be obtained, and meanwhile, after data statistics and analysis, big case data samples recommended by a hospital platform can be obtained, so that health consultation can be conducted directionally and specifically by combining the health reports of the sub-health people, and more authoritative diagnosis and treatment institutions can be selected;
(50) health intervention: in the personal health information of patients who are diagnosed from sub-health people, data statistics and analysis are carried out on partial information, for example, the relationship between the health index and the life eating habit is obtained by integrating previous cases, so that the evaluation object is helped to know the real health condition of the evaluation object and change or correct unhealthy behaviors of the evaluation object.
Compared with the prior art, the invention has the following remarkable advantages:
1. is no longer limited to providing optimizations across processes. For sub-health people who fill in questionnaires or have browsing records in the platform, guidance opinions can be provided at an early stage by constructing an evaluation matrix of a user-case, and direct help is provided for patients to select more authoritative diagnosis and treatment institutions and departments;
2. no more than much reliance is made on physicians to provide outpatient opinions. The most direct and convenient diagnosis scheme and suggestion can be given according to the collected case information and the compatibility and similarity of the communication among cases by combining the weight set by the questionnaire, the number of outpatients in a hospital can be reduced by about 20%, and the pressure of the outpatient team is greatly reduced;
3. and a concept of fuzzy set is added on the recommendation algorithm, so that a better clustering result can be obtained. The information of the platform can be output in a valuable mode, valuable cases are not hidden in the system like privacy, but can be used as samples to be referred to sub-health crowds, possible causes of diseases concerned by the cases can be effectively known by combining the cases, and cases of successful diagnosis before others are avoided, and well-defined class cases obtained by using a traditional clustering algorithm are avoided.
The invention is described in further detail below with reference to the figures and the detailed description.
Drawings
Fig. 1 is a main flow chart of a hospital outpatient self-service recommendation method based on big data.
Fig. 2 is a process of constructing a user-case neighbor set after the present invention collects case data.
FIG. 3 is a flow of designing fuzzy clustering after constructing neighbor sets according to the present invention.
FIG. 4 is a flow chart of the present invention for continuously iterating to generate the most appropriate recommendation.
Detailed Description
As shown in fig. 1, the hospital outpatient service self-service recommendation method based on big data of the present invention includes the following steps:
(10) data acquisition: performing health questionnaire survey on sub-health population and patients, wherein the classified collection of user information comprises the collection of personal health information aiming at the sub-health population; for the patients with confirmed diagnosis, the personal health information is converted into case big data;
the (10) data acquisition step comprises:
(11) constructing a hospital portal website, wherein different departments have questionnaires of corresponding departments and historical cases of the department at the same time, and encrypting according to actual conditions;
(12) the user can submit a corresponding questionnaire under a department concerned by the user according to needs, and the personal health information data is recorded after the questionnaire is filled in; or counting the past cases that the user visits and cares about in the portal website.
(13) Different departments set different weights according to different questions in the questionnaire, and health indexes and health reports with different tendencies are generated after weight analysis.
(20) Identifying health status and evaluating risk: setting weight analysis aiming at the continuously collected personal health information, comparing and analyzing the weight analysis with the diagnosed case big data, and carrying out quantitative evaluation and risk evaluation on the health condition of the individual or the group;
(30) data statistics and analysis: the method is characterized in that a Bayesian algorithm is combined, personal health information data and case data are classified and counted respectively, meanwhile, large case data are subjected to clustering analysis, similar case information with reference value is extracted as a sample for sub-health crowds to browse and access, and meanwhile, a corresponding diagnosis and treatment scheme can be formulated by a clinician for a certain specific crowd;
(40) health consultation: after personal health information of sub-health people is collected, corresponding health indexes and health reports can be obtained, and meanwhile, after data statistics and analysis, big case data samples recommended by a hospital platform can be obtained, so that health consultation can be conducted directionally and specifically by combining the health reports of the sub-health people, and more authoritative diagnosis and treatment institutions can be selected;
(50) health intervention: in the personal health information of patients who are diagnosed from sub-health people, data statistics and analysis are carried out on partial information, for example, the relationship between the health index and the life eating habit is obtained by integrating previous cases, so that the evaluation object is helped to know the real health condition of the evaluation object and change or correct unhealthy behaviors of the evaluation object.
As shown in FIG. 2, according to questionnaire data collected in data acquisition, a hospital data storage form based on a big data background is designed so as to carry out innovation mode research of hospital outpatient self-service recommendation. All data are classified and analyzed without using a shortcut such as a stochastic analysis method (sample survey). But the classification statistics is carried out by combining a Bayes algorithm (the Bayes classification algorithm is a classification method of statistics and is a classification algorithm which utilizes probability statistics knowledge to carry out classification). Bayesian algorithm basic formula:
wherein: p (B) is the prior probability or marginal probability of B, regardless of any factor in A; p (B | a) is the conditional probability of B after a is known to occur, and is also referred to as the a posteriori probability of B due to the value derived from a; p (a) is the conditional probability of a after B is known to occur, also called a posterior probability of a due to the value derived from B; p (a) is the prior probability or conditional probability of a, also called the normalization constant.
With reference to fig. 3, after the above-mentioned basic statistical classification is performed on the case big data, the following steps are performed:
(1) and calculating the similarity of the user and the case by using an attribute classification-based method to obtain a nearest neighbor set of the target user, wherein the nearest neighbor set is not set as U.
(2) And searching an item set E browsed by a target user, and if the number of items browsed by the user is small, using each item set browsed by the user in the U as the E.
(3) And searching a set T formed by all the elements in the cluster to which each element belongs.
(4) Based on the browsing matrix of the current user u, the browsing of the t-th item in the cluster by the user is calculated from the perspective of the user and the case, and the relation between two objects in the same cluster is expressed by using fuzzy set membership. The formula is as follows: wherein r isiIs the average of the associations of all users in U to item j, rjIs the average of the associations of user i to all items in T, and u is the membership of the element.
The method predicts the association of the target user to the case from the perspective of both the user and the case.
(5) And weighting and combining the two associations obtained in the last step to obtain the predicted association of the target user to the project.
rij=ωrij 1+(1-ω)rij 2
(6) Then, a weighting index is introduced (a hospital can set different weight values on different problems in a questionnaire filled by a patient), and the membership degree is attached to the weight m, so that the effectiveness of expanding a hard clustering algorithm function to a fuzzy clustering target function is ensured, and the general form { J } of the target function of the clustering algorithm appearsm(U,V),m[1,+∞]J, minimization by iterationmTo obtain the best clustering result U, V]The value range of Uij in the algorithm is [0, 1 ]]。
The mathematical language is used to describe the algorithm as follows
Where m represents a weighting coefficient, also referred to as a smoothing parameter (m > 1).
With reference to fig. 4, finding fuzzy clusters within an acceptable error range in successive loop iterations can be generally accomplished by the following steps.
Firstly, initializing basic parameters of a system, wherein the basic parameters comprise: the final number of the categories of the clusters is c, 2 is more than or equal to c and less than or equal to n, n is the number of sample data, and the weighting index m (1)<m<Infinity), threshold for iteration stop (n ∞>0) And a cluster center matrix VoAnd the counter b of the iteration is 0. .
Step dual-purpose formula pair membership degree matrix UbPerforming computation updates
Whereindij bThe distance between the ith element and the jth cluster center after b iterations is represented.
Step three, updating cluster central matrix V(b+1)The formula is as follows
Wherein U isij bRepresenting the elements in the attribute degree U after b iterations.
Step four if Vb-V(b+1)||<And stopping the algorithm and returning to the membership degree matrix U and the clustering center matrix V, otherwise, turning to the step two for iterative calculation, wherein b is b + 1. Where | | represents some suitable matrix norm.
After the continuous iteration process, the clustering is finished. And sorting all the items in a descending order according to the calculated browsing scores, taking the first N items as final recommendation results, and displaying the final recommendation results to the user.
Claims (2)
1. A hospital outpatient self-service recommendation method based on big data is characterized by comprising the following steps:
(10) data acquisition: performing health questionnaire survey on sub-health population and patients, wherein the classified collection of user information comprises the collection of personal health information aiming at the sub-health population; for the patients with confirmed diagnosis, the personal health information is converted into case big data;
(20) identifying health status and evaluating risk: setting weight analysis aiming at the continuously collected personal health information, comparing and analyzing the weight analysis with the diagnosed case big data, and carrying out quantitative evaluation and risk evaluation on the health condition of the individual or the group;
(30) data statistics and analysis: the method is characterized in that a Bayesian algorithm is combined, personal health information data and case data are classified and counted respectively, meanwhile, large case data are subjected to clustering analysis, similar case information with reference value is extracted as a sample for sub-health crowds to browse and access, and meanwhile, a corresponding diagnosis and treatment scheme can be formulated by a clinician for a certain specific crowd;
(40) health consultation: after personal health information of sub-health people is collected, corresponding health indexes and health reports can be obtained, and meanwhile, after data statistics and analysis, big case data samples recommended by a hospital platform can be obtained, so that health consultation can be conducted directionally and specifically by combining the health reports of the sub-health people, and more authoritative diagnosis and treatment institutions can be selected;
(50) health intervention: in the personal health information of patients who are diagnosed from sub-health people, data statistics and analysis are carried out on partial information, for example, the relationship between the health index and the life eating habit is obtained by integrating previous cases, so that the evaluation object is helped to know the real health condition of the evaluation object and change or correct unhealthy behaviors of the evaluation object.
2. The hospital clinic self-help recommendation method according to claim 1, wherein the (10) data collection step comprises:
(11) constructing a hospital portal website, wherein different departments have questionnaires of corresponding departments and historical cases of the department at the same time, and encrypting according to actual conditions;
(12) the user can submit a corresponding questionnaire under a department concerned by the user according to needs, and the personal health information data is recorded after the questionnaire is filled in; or counting the past cases that the user visits and cares about in the portal website.
(13) Different departments set different weights according to different questions in the questionnaire, and health indexes and health reports with different tendencies are generated after weight analysis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010365815.5A CN111640490A (en) | 2020-04-30 | 2020-04-30 | Hospital outpatient self-service recommendation method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010365815.5A CN111640490A (en) | 2020-04-30 | 2020-04-30 | Hospital outpatient self-service recommendation method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111640490A true CN111640490A (en) | 2020-09-08 |
Family
ID=72331899
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010365815.5A Withdrawn CN111640490A (en) | 2020-04-30 | 2020-04-30 | Hospital outpatient self-service recommendation method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111640490A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113593690A (en) * | 2021-09-29 | 2021-11-02 | 山东欣悦健康科技有限公司 | Medical health data acquisition and analysis system based on big data |
-
2020
- 2020-04-30 CN CN202010365815.5A patent/CN111640490A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113593690A (en) * | 2021-09-29 | 2021-11-02 | 山东欣悦健康科技有限公司 | Medical health data acquisition and analysis system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8504343B2 (en) | Disease diagnoses-bases disease prediction | |
CN109411082B (en) | Medical quality evaluation and treatment recommendation method | |
Fu et al. | Data-driven multiple criteria decision making for diagnosis of thyroid cancer | |
Li et al. | A survey on statistical methods for health care fraud detection | |
US8145582B2 (en) | Synthetic events for real time patient analysis | |
CN109830303A (en) | Clinical data mining analysis and aid decision-making method based on internet integration medical platform | |
US20090287503A1 (en) | Analysis of individual and group healthcare data in order to provide real time healthcare recommendations | |
CN116364299B (en) | Disease diagnosis and treatment path clustering method and system based on heterogeneous information network | |
Barnato et al. | Value and role of intensive care unit outcome prediction models in end-of-life decision making | |
Khan et al. | Towards development of national health data warehouse for knowledge discovery | |
Abdelfattah | Neutrosophic data envelopment analysis: An application to regional hospitals in Tunisia | |
CN111640490A (en) | Hospital outpatient self-service recommendation method based on big data | |
US20130253892A1 (en) | Creating synthetic events using genetic surprisal data representing a genetic sequence of an organism with an addition of context | |
Khademolqorani et al. | Development of a decision support system for handling health insurance deduction | |
Canino et al. | Feature selection model for diagnosis, electronic medical records and geographical data correlation | |
Theodoraki et al. | Innovative data mining approaches for outcome prediction of trauma patients | |
Khaleghi et al. | A tree based approach for multi-class classification of surgical procedures using structured and unstructured data | |
Demigha | Data mining for breast cancer screening | |
Shetaban et al. | Operations research and health systems: a literature review | |
Comito et al. | Improving influenza forecasting with web-based social data | |
Al-Dallal et al. | Prediction of non-communicable diseases using class comparison data mining | |
TW201426624A (en) | Personal medical expense prediction system | |
Baralis et al. | Digging deep into weighted patient data through multiple-level patterns | |
Demigha | Mining knowledge of the patient record: the Bayesian classification to predict and detect anomalies in breast cancer | |
CN116596161B (en) | Target prediction model construction method and prediction method under multi-center small sample scene |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200908 |
|
WW01 | Invention patent application withdrawn after publication |