CN114862597A - Health insurance claim settlement risk prediction method and system based on medical big data - Google Patents
Health insurance claim settlement risk prediction method and system based on medical big data Download PDFInfo
- Publication number
- CN114862597A CN114862597A CN202210511690.1A CN202210511690A CN114862597A CN 114862597 A CN114862597 A CN 114862597A CN 202210511690 A CN202210511690 A CN 202210511690A CN 114862597 A CN114862597 A CN 114862597A
- Authority
- CN
- China
- Prior art keywords
- medical
- model
- patient
- risk
- age
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to a health insurance claim risk prediction method and system based on medical big data, wherein the method comprises the following steps: performing multi-dimensional feature extraction on the medical big data to obtain first feature information, second feature information and third feature information; constructing a feature distribution model based on the first feature information, the second feature information and the third feature information; constructing a medical behavior time sequence model based on the first characteristic information; and acquiring medical file data of the patient, inputting the medical file data into the characteristic distribution model and the time sequence model, and carrying out risk prompt according to results output by the characteristic distribution model and the time sequence model. The invention can more comprehensively and accurately identify potential health insurance claim settlement fraud based on the information provided by the actual medical record.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to a health insurance claim settlement risk prediction method and system based on medical big data.
Background
With the development of internet finance and electronic commerce, people utilize networks to conduct transactions, payments and loans, and generally, in the process of the loans and the payments, risk control assessment is very critical. Taking the health insurance claim in the insurance field as an example, there may be a false report case of the claim user for cheating insurance.
Because an insurance company needs a quick and accurate method for identifying or evaluating a large number of possible fraud risks of insurance claims when processing health insurance claims, the conventional risk prediction models and performs prediction evaluation on future claim cases by collecting data of historical claim cases, but the model cannot provide a sufficiently accurate and effective prediction evaluation due to too few samples of the claim cases.
Disclosure of Invention
The invention aims to provide a health insurance claim risk prediction method and system based on medical big data, which can more comprehensively and accurately identify potential health insurance claim fraud based on information provided by actual medical records.
The technical scheme adopted by the invention for solving the technical problems is as follows: the health insurance claim risk prediction method based on medical big data comprises the following steps:
(1) performing multi-dimensional feature extraction on the medical big data to obtain first feature information, second feature information and third feature information;
(2) constructing a feature distribution model based on the first feature information, the second feature information and the third feature information;
(3) constructing a medical behavior time sequence model based on the first characteristic information;
(4) and acquiring medical file data of the patient, inputting the medical file data into the characteristic distribution model and the time sequence model, and carrying out risk prompt according to results output by the characteristic distribution model and the time sequence model.
The first characteristic information in the step (1) comprises: history of gender, age, disease diagnosis, and medical behavior; the second feature information includes: examination items and test items related to the medical action; the third characteristic information is a medical institution grade and a medical expense for performing the medical action.
The step (2) is specifically as follows: and taking the grade, the sex, the age and the disease diagnosis of the medical institution executing the medical behavior as independent variables, taking the medical cost for executing the medical behavior, examination items and test items related to the medical behavior as dependent variables to construct a regression model, and obtaining the characteristic distribution model after machine learning.
The step (3) is specifically as follows: and taking the sex, the age and the disease diagnosis as independent variables, taking the historical records of the medical behaviors as dependent variables to construct a regression model, and obtaining the medical behavior time sequence model after machine learning.
The step (4) is specifically as follows:
acquiring medical record data of a patient, wherein the medical record data comprises sex, age, disease diagnosis, historical records of medical behaviors, examination items and test items related to the medical behaviors, and medical institution grades and medical expenses for executing the medical behaviors of the patient;
inputting the sex, age, disease diagnosis, medical behavior history of the patient and the grade of a medical institution executing the medical behavior into the characteristic distribution model to obtain a first prediction result;
comparing the first prediction result with medical expenses of the patient for executing the medical action, examination items and test items related to the medical action, and performing risk prompt if a first threshold value is exceeded;
inputting the sex, age and disease diagnosis of the patient into the medical behavior time sequence model to obtain a second prediction result;
and carrying out similarity evaluation on the second prediction result and the historical record of the medical behavior of the patient, and carrying out risk prompt if the similarity is lower than a second threshold value.
The technical scheme adopted by the invention for solving the technical problems is as follows: the health insurance claim risk prediction system based on medical big data comprises:
the characteristic extraction module is used for carrying out multi-dimensional characteristic extraction on the medical big data to obtain first characteristic information, second characteristic information and third characteristic information;
the first model building module is used for building a feature distribution model based on the first feature information, the second feature information and the third feature information;
the second model building module is used for building a medical behavior time sequence model based on the first characteristic information;
and the risk prompting module is used for acquiring medical archive data of a patient, inputting the medical archive data into the characteristic distribution model and the time sequence model, and performing risk prompting according to results output by the characteristic distribution model and the time sequence model.
The first feature information includes: history of gender, age, disease diagnosis, and medical behavior; the second feature information includes: examination items and test items related to the medical action; the third characteristic information is a medical institution grade and a medical expense for performing the medical action.
The first model building module takes the grade, sex, age and disease diagnosis of the medical institution executing the medical action as independent variables, takes the medical cost of executing the medical action, examination items and test items related to the medical action as dependent variables to build a regression model, and obtains the feature distribution model after machine learning.
And the second model building module takes the sex, the age and the disease diagnosis as independent variables, takes the historical records of the medical behaviors as dependent variables to build a regression model, and obtains the medical behavior time sequence model after machine learning.
The risk prompt module comprises:
an acquisition unit for acquiring medical record data of a patient, the medical record data including sex, age, disease diagnosis, history of medical actions, examination items and test items related to the medical actions, and medical institution level and medical expenses for performing the medical actions of the patient;
a first prediction unit, configured to input the sex, age, disease diagnosis, history of medical behaviors, and medical institution level for executing the medical behaviors of the patient into the feature distribution model, so as to obtain a first prediction result;
the first comparison unit is used for comparing the first prediction result with the medical cost of the patient for executing the medical action, the examination items and the test items related to the medical action, and performing risk prompt if the first prediction result exceeds a first threshold;
the second prediction unit is used for inputting the sex, the age and the disease diagnosis of the patient into the medical behavior time sequence model to obtain a second prediction result;
and the second comparison unit is used for evaluating the similarity between the second prediction result and the medical behavior historical record of the patient, and performing risk prompt if the similarity is lower than a second threshold.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects: according to the invention, through machine learning of medical big data, a feature distribution model of medical expense, examination and test projects is constructed based on the medical institution grade, disease diagnosis, sex and age range dimensions; the invention forms a medical behavior time sequence model for specific disease diagnosis, gender and age group dimensions based on the history of medical behaviors recorded in a medical archive by machine learning of medical big data. When prediction is carried out, the risk of potential overdischarge or overdetection of the claim case can be evaluated through the feature distribution model, the actual medical expense occurrence situation can be well met, the risk of potential overdose or unreasonable diagnosis of the claim case is evaluated through the medical behavior time sequence model, and therefore potential health insurance claim fraud can be accurately identified based on information provided by actual medical records more comprehensively.
Drawings
Fig. 1 is a flowchart of a first embodiment of the present invention.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. It should be understood that these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.
The first embodiment of the invention relates to a health insurance claim risk prediction method based on medical big data, as shown in fig. 1, comprising the following steps:
step 1, performing multi-dimensional data feature extraction on medical big data. The method specifically comprises the following steps: step 1a, extracting characteristic information directly related to medical behaviors, such as sex, age, disease diagnosis, history of medical behaviors and the like of a patient, wherein the history of the medical behaviors comprises: the type of medication, dosage, treatment mode and time of visit; step 1b, extracting characteristic information indirectly related to medical behaviors, such as examination items and test items related to the medical behaviors; and (4) extracting relevant characteristic information such as the grade of the medical institution and the medical expense relevant in the step 1a and the step 1 b.
And 2, carrying out distribution modeling on the medical expense and the characteristic information of related examination items and test items through the same medical institution grade, disease diagnosis, sex and age range dimensions to obtain a characteristic distribution model. Specifically, a regression model is constructed using the medical institution level, sex, age, and disease diagnosis for executing the medical action as independent variables, and using the medical cost for executing the medical action, examination items and test items related to the medical action as dependent variables, and the feature distribution model is obtained by machine learning.
And 3, performing time sequence modeling on the history records of the medical behaviors through the dimensions of disease diagnosis, gender and age groups to obtain a medical behavior time sequence model. Specifically, the gender, age, and disease diagnosis are used as independent variables, the history of the medical behavior is used as a dependent variable to construct a regression model, and the time-series model of the medical behavior is obtained through machine learning.
And 4, when the health insurance claim settlement case risk assessment is carried out, matching the medical archive data of the patient with the characteristic distribution model and the medical behavior time sequence model to generate a risk assessment result. The method specifically comprises the following steps: step 4a, matching medical expenses and related examination and test items into a feature distribution model according to the medical institution grade, disease diagnosis, sex and age group dimensions of a claim case, namely inputting the sex, age, disease diagnosis and medical behavior history of the patient and the medical institution grade for executing the medical behavior into the feature distribution model to obtain a first prediction result; and comparing the first prediction result with the medical cost of the patient for executing the medical action, the examination items and the test items related to the medical action, and performing risk prompt if the first prediction result exceeds a first threshold value. In this step, the closer the claim settlement cases are to the prediction results of the feature distribution model, the smaller the risk is, otherwise, the larger the risk is prompted. In the present embodiment, risk presentation is performed by using three times the standard deviation of the feature distribution model as the first threshold. And 4b, extracting a history record of the medical behavior according to the medical file of the claim case and matching the history record with the medical time sequence model, namely inputting the sex, the age and the disease diagnosis of the patient into the medical behavior time sequence model to obtain a second prediction result, performing similarity evaluation on the second prediction result and the history record of the medical behavior of the patient, and performing risk prompt if the similarity is lower than a second threshold value. In the embodiment, a simple string similarity evaluation algorithm or a more complex semantic similarity evaluation algorithm can be used to obtain the evaluation of the matching degree, and when the matching degree is higher, the risk of the claim case is less, otherwise, the possibility of over-treatment or other risks of the claim case is indicated.
The invention can easily find that the invention constructs a feature distribution model of medical expense, examination and test projects based on the medical institution grade, disease diagnosis, sex and age group dimensionality by machine learning of medical big data; the invention forms a medical behavior time sequence model for specific disease diagnosis, gender and age group dimensions based on the history of medical behaviors recorded in a medical archive by machine learning of medical big data. When prediction is carried out, the risk of potential overdischarge or overdetection of the claim case can be evaluated through the feature distribution model, the actual medical expense occurrence situation can be well met, the risk of potential overdose or unreasonable diagnosis of the claim case is evaluated through the medical behavior time sequence model, and therefore potential health insurance claim fraud can be accurately identified based on information provided by actual medical records more comprehensively.
A second embodiment of the present invention relates to a health insurance claim risk prediction system based on medical big data, including: the characteristic extraction module is used for carrying out multi-dimensional characteristic extraction on the medical big data to obtain first characteristic information, second characteristic information and third characteristic information; the first model building module is used for building a feature distribution model based on the first feature information, the second feature information and the third feature information; the second model building module is used for building a medical behavior time sequence model based on the first characteristic information; and the risk prompting module is used for acquiring medical archive data of a patient, inputting the medical archive data into the characteristic distribution model and the time sequence model, and performing risk prompting according to results output by the characteristic distribution model and the time sequence model.
The first feature information includes: history of gender, age, disease diagnosis, and medical behavior; the second feature information includes: examination items and test items related to the medical action; the third characteristic information is a medical institution level and a medical expense for performing the medical action.
The first model building module takes the grade, sex, age and disease diagnosis of the medical institution executing the medical action as independent variables, takes the medical cost of executing the medical action, examination items and test items related to the medical action as dependent variables to build a regression model, and obtains the feature distribution model after machine learning.
And the second model building module takes the sex, the age and the disease diagnosis as independent variables, takes the historical records of the medical behaviors as dependent variables to build a regression model, and obtains the medical behavior time sequence model after machine learning.
The risk prompt module comprises: an acquisition unit for acquiring medical record data of a patient, the medical record data including sex, age, disease diagnosis, history of medical actions, examination items and test items related to the medical actions, and medical institution level and medical expenses for performing the medical actions of the patient; a first prediction unit, configured to input the sex, age, disease diagnosis, history of medical behaviors, and medical institution level for executing the medical behaviors of the patient into the feature distribution model, so as to obtain a first prediction result; the first comparison unit is used for comparing the first prediction result with the medical cost of the patient for executing the medical action, the examination items and the test items related to the medical action, and performing risk prompt if the first prediction result exceeds a first threshold; the second prediction unit is used for inputting the sex, the age and the disease diagnosis of the patient into the medical behavior time sequence model to obtain a second prediction result; and the second comparison unit is used for evaluating the similarity between the second prediction result and the medical behavior historical record of the patient, and performing risk prompt if the similarity is lower than a second threshold.
Claims (10)
1. A health insurance claim settlement risk prediction method based on medical big data is characterized by comprising the following steps:
(1) performing multi-dimensional feature extraction on the medical big data to obtain first feature information, second feature information and third feature information;
(2) constructing a feature distribution model based on the first feature information, the second feature information and the third feature information;
(3) constructing a medical behavior time sequence model based on the first characteristic information;
(4) and acquiring medical file data of the patient, inputting the medical file data into the characteristic distribution model and the time sequence model, and carrying out risk prompt according to results output by the characteristic distribution model and the time sequence model.
2. The health insurance claim risk prediction method based on medical big data according to claim 1, wherein the first characteristic information in the step (1) comprises: history of gender, age, disease diagnosis, and medical behavior; the second feature information includes: examination items and test items related to the medical action; the third characteristic information is a medical institution grade and a medical expense for performing the medical action.
3. The method for predicting the risk of health insurance claim based on medical big data as claimed in claim 2, wherein the step (2) is specifically as follows: and taking the grade, the sex, the age and the disease diagnosis of the medical institution executing the medical behavior as independent variables, taking the medical cost for executing the medical behavior, examination items and test items related to the medical behavior as dependent variables to construct a regression model, and obtaining the characteristic distribution model after machine learning.
4. The health insurance claim risk prediction method based on medical big data as claimed in claim 2, wherein the step (3) is specifically as follows: and taking the sex, the age and the disease diagnosis as independent variables, taking the historical records of the medical behaviors as dependent variables to construct a regression model, and obtaining the medical behavior time sequence model after machine learning.
5. The health insurance claim risk prediction method based on medical big data as claimed in claim 1, wherein the step (4) is specifically as follows:
acquiring medical record data of a patient, wherein the medical record data comprises sex, age, disease diagnosis, historical records of medical behaviors, examination items and test items related to the medical behaviors, and medical institution grades and medical expenses for executing the medical behaviors of the patient;
inputting the sex, age, disease diagnosis, history of medical behaviors of the patient and the grade of a medical institution executing the medical behaviors into the characteristic distribution model to obtain a first prediction result;
comparing the first prediction result with medical expenses of the patient for executing the medical action, examination items and test items related to the medical action, and performing risk prompt if a first threshold value is exceeded;
inputting the sex, age and disease diagnosis of the patient into the medical behavior time sequence model to obtain a second prediction result;
and carrying out similarity evaluation on the second prediction result and the historical record of the medical behavior of the patient, and carrying out risk prompt if the similarity is lower than a second threshold value.
6. A health insurance claim risk prediction system based on medical big data, comprising:
the characteristic extraction module is used for carrying out multi-dimensional characteristic extraction on the medical big data to obtain first characteristic information, second characteristic information and third characteristic information;
the first model building module is used for building a feature distribution model based on the first feature information, the second feature information and the third feature information;
the second model building module is used for building a medical behavior time sequence model based on the first characteristic information;
and the risk prompting module is used for acquiring medical archive data of a patient, inputting the medical archive data into the characteristic distribution model and the time sequence model, and performing risk prompting according to results output by the characteristic distribution model and the time sequence model.
7. The health insurance claim risk prediction system based on medical big data according to claim 6, wherein the first feature information includes: history of gender, age, disease diagnosis, and medical behavior; the second feature information includes: examination items and test items related to the medical action; the third characteristic information is a medical institution grade and a medical expense for performing the medical action.
8. The health insurance claim risk prediction system based on medical big data according to claim 7, wherein the first model building module builds a regression model by using the medical institution level, sex, age and disease diagnosis for executing the medical action as independent variables, and using the medical cost for executing the medical action, examination items and laboratory test items related to the medical action as dependent variables, and obtains the feature distribution model by machine learning.
9. The health insurance claim risk prediction system based on medical big data as claimed in claim 7, wherein the second model construction module takes the sex, age and disease diagnosis as independent variables, takes the history of the medical action as dependent variables to construct a regression model, and obtains the medical action time series model after machine learning.
10. The health insurance claim risk prediction system based on medical big data according to claim 6, wherein the risk prompt module comprises:
an acquisition unit for acquiring medical record data of a patient, the medical record data including sex, age, disease diagnosis, history of medical actions, examination items and test items related to the medical actions, and medical institution level and medical expenses for performing the medical actions of the patient;
a first prediction unit, configured to input the sex, age, disease diagnosis, history of medical behaviors, and medical institution level for executing the medical behaviors of the patient into the feature distribution model, so as to obtain a first prediction result;
the first comparison unit is used for comparing the first prediction result with the medical cost of the patient for executing the medical action, the examination items and the test items related to the medical action, and performing risk prompt if the first prediction result exceeds a first threshold;
the second prediction unit is used for inputting the sex, the age and the disease diagnosis of the patient into the medical behavior time sequence model to obtain a second prediction result;
and the second comparison unit is used for evaluating the similarity between the second prediction result and the medical behavior historical record of the patient, and performing risk prompt if the similarity is lower than a second threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210511690.1A CN114862597A (en) | 2022-05-11 | 2022-05-11 | Health insurance claim settlement risk prediction method and system based on medical big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210511690.1A CN114862597A (en) | 2022-05-11 | 2022-05-11 | Health insurance claim settlement risk prediction method and system based on medical big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114862597A true CN114862597A (en) | 2022-08-05 |
Family
ID=82638186
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210511690.1A Pending CN114862597A (en) | 2022-05-11 | 2022-05-11 | Health insurance claim settlement risk prediction method and system based on medical big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114862597A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116342300A (en) * | 2023-05-26 | 2023-06-27 | 凯泰铭科技(北京)有限公司 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
-
2022
- 2022-05-11 CN CN202210511690.1A patent/CN114862597A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116342300A (en) * | 2023-05-26 | 2023-06-27 | 凯泰铭科技(北京)有限公司 | Method, device and equipment for analyzing characteristics of insurance claim settlement personnel |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Milovic et al. | Prediction and decision making in health care using data mining | |
US11610152B2 (en) | Machine learning model development and optimization process that ensures performance validation and data sufficiency for regulatory approval | |
JP5586373B2 (en) | Computer-readable storage medium storing a program for causing a computer system to realize the function of a component that processes a payment request, and a method of operating a computer system that causes a computer system to process a payment request | |
CN111861768B (en) | Service processing method and device based on artificial intelligence, computer equipment and medium | |
Sadikin et al. | Comparative study of classification method on customer candidate data to predict its potential risk | |
CN111145910A (en) | Abnormal case identification method and device based on artificial intelligence and computer equipment | |
US20240013919A1 (en) | Supervised machine learning-based modeling of sensitivities to potential disruptions | |
CN113657548A (en) | Medical insurance abnormity detection method and device, computer equipment and storage medium | |
CN114862597A (en) | Health insurance claim settlement risk prediction method and system based on medical big data | |
CN111709845A (en) | Medical insurance fraud behavior identification method and device, electronic equipment and storage medium | |
Sunarya et al. | Deciphering digital social dynamics: A comparative study of logistic regression and random forest in predicting e-commerce customer behavior | |
Ling et al. | An error detecting and tagging framework for reducing data entry errors in electronic medical records (EMR) system | |
Monahan et al. | Models predicting hospital admission of adult patients utilizing prehospital data: systematic review using PROBAST and CHARMS | |
Dubey et al. | Smart Underwriting System: An Intelligent Decision Support System for Insurance Approval & Risk Assessment | |
Xia et al. | Process monitoring based on improved recursive PCA methods by adaptive extracting principal components | |
CN113436027B (en) | Medical insurance reimbursement abnormal data detection method and system | |
CN115358878A (en) | Financing user risk preference level analysis method and device | |
Johnson et al. | Healthcare provider summary data for fraud classification | |
Garcia et al. | From data to knowledge mining | |
Pal et al. | Application of data mining techniques in health fraud detection | |
US11989112B2 (en) | Model validation based on sub-model performance | |
CN113706258B (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
Gomes et al. | A Survey of Explainable AI and Proposal for a Discipline of Explanation Engineering | |
Madhavi et al. | Early Discovery of Chronic Kidney Disease by Attributing Missing Values | |
Goldmann | Enhancing Credit Risk Prediction in Retail Banking: Integrating Time Series and Classical ML Algorithms |
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 |