CN119480074A - A inspection item decision system and method based on data processing - Google Patents
A inspection item decision system and method based on data processing Download PDFInfo
- Publication number
- CN119480074A CN119480074A CN202411558057.3A CN202411558057A CN119480074A CN 119480074 A CN119480074 A CN 119480074A CN 202411558057 A CN202411558057 A CN 202411558057A CN 119480074 A CN119480074 A CN 119480074A
- Authority
- CN
- China
- Prior art keywords
- data
- item
- health
- model
- data processing
- 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
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
- 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
- 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
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- 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
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention belongs to the field of medical information systems, and provides a data processing-based examination item decision system and a data processing-based examination item decision method, wherein the examination item decision system comprises a data acquisition and preprocessing module, a data processing module and a data processing module, wherein the data acquisition and preprocessing module is used for collecting and preprocessing health data of a patient to obtain first health data; the system comprises a first health data acquisition module, a first examination item decision module, a data generation module and a second examination item interpretation module, wherein the first health data acquisition module is used for acquiring a first examination item by inputting the first health data into a first model, the data generation module is used for sequentially removing one item of the first health data and inputting the first model to acquire a second examination item interpretation module, and the second examination item interpretation module is used for calculating the contribution value of health characteristics to the examination item according to the first health data, the first examination item and the second examination item and interpreting the first examination item according to the contribution value.
Description
Technical Field
The invention belongs to the field of medical information systems, and particularly relates to an inspection project decision system and method based on data processing.
Background
In existing examination item decision systems, although data driven models have been widely used in medical diagnostics, the problem of their lack of interpretation remains significant. Especially when complex machine learning models (such as neural networks, random forests, etc.) are applied, while these models are effective in generating recommendations for examination items from a large number of patient's health data, their black box nature makes it difficult for doctors and patients to understand the logic and basis behind the decision.
In particular, prior art inspection item decision models often output only predicted results or inspection item recommendation lists, lacking a quantitative interpretation of the specific contribution of each health feature in the decision process. For example, models may recommend blood glucose tests and electrocardiographic tests, but the specific reasons for recommending these items cannot be specified, whether the patient's blood glucose level is abnormal or whether other factors (such as family history or age) have an impact on model predictions. The problem of insufficient interpretation not only affects the clinical judgment of doctors, but also reduces the trust degree of patients on the recommended results of the system.
Furthermore, due to the complexity and multi-source heterogeneity of medical data, existing examination item decision models typically rely on analysis of large amounts of feature data, while the contributions of different features to the examination item tend to be different. However, existing systems fail to adequately reveal the impact of each feature on the final recommendation. This not only limits the transparency of the physician in the decision, but may also lead to unnecessary examination items being recommended, increasing the burden on the patient and waste of medical resources.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a checking project decision system based on data processing, which comprises the following modules:
The data acquisition and preprocessing module is used for collecting and preprocessing health data of a patient to obtain first health data;
The examination item decision module inputs the first health data into a first model to obtain a first examination item;
The data generation module is used for sequentially removing one item of the first health data and inputting the first model to obtain a second examination item
And the interpretation module is used for calculating the contribution value of the health characteristic to the examination item according to the first health data, the first examination item and the second examination item and interpreting the first examination item according to the contribution value.
The invention also provides a method for deciding the inspection items based on data processing, which uses the system to decide the inspection items.
By means of the interpretation module, the system is able to provide specific contribution values of each feature to the recommended examination item based on the patient's health data. The doctor and the patient can intuitively understand the effect of each feature in recommending the examination item, the interpretability of the system is enhanced, and the defect of opaque decision caused by the problem of 'black box' in the prior art is effectively overcome.
The system can rapidly process a large amount of health data through an automatic inspection project decision module to generate accurate inspection suggestions. The doctor no longer has to rely on manual analysis of the impact of each health feature, saving a lot of time. Meanwhile, the interpretation of the detailed contribution value provided by the interpretation module also helps doctors to make more accurate decisions in the process of checking and recommending, and the risks of misdiagnosis and missed diagnosis are reduced.
Through the interpretation module, the system can explain why the specific examination item is recommended to the patient in detail, and solves the problems of doubt and distrust of the patient on the recommendation of the examination item in the prior art. The patient can clearly know how each health characteristic (such as blood sugar level, blood pressure, family history and the like) affects the recommended result, so that the trust feeling of the patient on the medical diagnosis system is enhanced, and the efficiency of doctor-patient communication is improved.
In summary, the invention, by combining the data processing technology, the machine learning model and the explanatory analysis module, significantly improves the transparency, individuation and efficiency of the inspection item decision, solves the key problems in the prior art, is beneficial to optimizing the medical resource configuration, improving the patient experience and improving the overall quality of medical diagnosis.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a system block diagram of the method of the present invention.
Detailed Description
The invention will be described with reference to the drawings and detailed description.
The present embodiment solves the above problem by:
in one embodiment, referring to FIG. 1, the present invention provides a data processing based inspection item decision system.
In particular to the technical field of automatically generating an examination item recommendation scheme for an individual patient through acquisition, analysis and processing of medical data. The system mainly comprises a data acquisition module, a data processing module, a decision module and an interpretation module.
The method is characterized in that a computer system is used for collecting, cleaning, formatting and standardizing multi-source heterogeneous data such as electronic health records, laboratory detection data, imaging data, medical history records and the like of a patient, so that the integrity, consistency and usability of the data are ensured, and the subsequent analysis and decision are facilitated.
In the course of medical diagnosis or health examination, the system recommends specific diagnosis or examination items including, but not limited to, blood examination, image examination (e.g., CT, MRI), electrocardiographic examination, genetic examination, etc., based on clinical symptoms, past medical history, and other relevant factors of the patient.
By establishing a data analysis model, based on the individuation information of the patient, the computer system automatically analyzes and generates a recommended examination item list, corresponding explanation is given to the patient, and misunderstanding of the patient is reduced.
Each module will be further explained below.
The data acquisition and preprocessing module is used for collecting and preprocessing health data of a patient to obtain first health building data.
The data acquisition and preprocessing module is used for automatically or semi-automatically collecting health related information of patients from a plurality of data sources and preprocessing the collected data. The module includes, but is not limited to, a data input unit, a data cleansing unit, a data format conversion unit, and a data normalization unit.
The data acquisition can be used for acquiring the health related information such as physiological parameters, laboratory detection results, image data, medical history records, medicine use conditions and the like of patients from various medical equipment, hospital information systems (H I S), electronic Health Record (EHR) systems, laboratory Information Management Systems (LIMS) and other data sources. Data collection may be performed in a variety of ways, including real-time collection, batch upload, or API-based data synchronization.
And cleaning, denoising, supplementing missing values, eliminating redundancy, data standardization, format conversion and other processing operations are performed on the acquired health data, so that the integrity, consistency and accuracy of the data are ensured. The data cleaning includes deleting abnormal values or invalid data, and the format conversion includes converting the data in different systems into unified standard format, and the standardization is to perform unit conversion or scale normalization on the numerical data for subsequent data analysis and processing.
The various data related to the health condition of the patient include, but are not limited to, physiological parameters (such as body temperature, blood pressure, heart rate), laboratory test data (such as blood routine, urine routine), image data (such as X-ray film, CT image), medical history information (such as past disease, allergy history), genetic information, and other data information obtained by clinical examination.
The data acquisition and preprocessing module can effectively collect and process various health data from different sources, provide high-quality and structured input data for a subsequent decision module, and ensure the data processing capability and decision accuracy of the system in complex medical scenes.
The examination item decision module inputs the first rehabilitation data into a first model to obtain a first examination item;
The examination item decision module is used for automatically deciding and generating a personalized examination item recommendation list for a patient based on the first model and the preprocessed health data. The module comprises a model loading unit, a data input unit, a model reasoning unit and a result output unit, and can dynamically select the optimal examination item according to the health data of the patient.
And the model loading unit is used for loading and initializing the first model. The unit can dynamically load different types of machine learning models according to requirements, and the first model can be adjusted according to the health data change of a patient, so that the applicability and the accuracy of the model are ensured.
And the data input unit is used for receiving and inputting the preprocessed patient health data, wherein the data comprises, but is not limited to, age, sex, body mass index, medical history record, laboratory detection result, image data and the like of the patient. The data input unit can be connected with the data acquisition and preprocessing module in a butt joint mode, and automatic data input is achieved.
And the model reasoning unit is used for analyzing and reasoning the input patient health data based on the first model, automatically identifying the health condition and potential health risk of the patient, and generating a personalized examination item recommendation list according to the analysis result. The inference process may include the use of a variety of algorithmic models, such as classification, regression, clustering, and the like.
And a result output unit for outputting the inspection item recommendation list generated by the model inference unit. The result output unit provides the reasoning results in a structured form to the physician or patient, and the recommended examination items can be used directly for clinical decision making and support further examination adjustments or optimizations.
Preferably, the first model is a machine learning model. Specifically, the machine learning model may be a supervised learning model, an unsupervised learning model, or a semi-supervised learning model, which is suitable for different types of health data analysis scenarios. Preferably, the first model is one or more of a random forest model, a logistic regression model, a support vector machine model and a neural network model. The machine learning model can be used for training historical data of a patient, has prediction and reasoning capabilities for new input data, and ensures that the generated examination item recommendation result can be accurately matched with the actual requirement of the patient.
Further preferably, the machine learning model is capable of dynamically adjusting weights and parameters according to health data of different patients, ensuring personalization of examination item recommendations. By weight distribution of different feature data, the system can focus on key health indexes of the patient, so that more accurate examination suggestions are generated. The model reasoning unit can generate different examination item recommendations according to individual characteristics of different patients so as to realize personalized medical service in a real sense.
Illustratively, the random forest model is trained using historical data, the input data including age, gender, blood pressure, body Mass Index (BMI),
Blood glucose level, heart rate, family history, serum cholesterol, past illness, etc., and output data as examination items such as blood glucose test, electrocardiogram (ECG) examination, blood lipid analysis, etc.
It should be noted that, when all the outputs of the machine learning model are probabilistic, the probability that the probability exceeds 50% (or is set higher) is considered to be required for the examination, such as blood glucose detection, electrocardiogram (ECG) examination, and blood fat analysis {0.92,0.82,0.52}, the predicted probability of each item should be included in the first examination item of the output.
And the data generation module is used for sequentially removing one item of the first rehabilitation data and inputting the first model to obtain a second examination item.
In order to quantify the contribution of each feature in the recommended exam, the necessary data preparation for the calculation of the subsequent model is provided by sequentially removing one feature from the health data and inputting it into the first model (i.e., the exam decision model) and then observing the changes in the model output. Specifically, the subsequent model calculates the marginal contribution of each feature by comparing the effect of the model output (inspection item recommendation) when that feature is present and absent.
Specifically:
first, health data of a patient is acquired as input to a model. The health dataset may include a number of features such as age, gender, body mass index (BM I), blood pressure, blood glucose levels, medical history, and the like. Assume that the raw health data is:
x= { X 1,x2,x3,…,xn }, where
X 1 (age): 55 years old
X 2 (sex) male
X 3 (blood pressure) 150/90mmHg
X 4 (blood glucose level): 8.5mmol/L
X 5 (body Mass index): 28
X 6 (family history) there is a family history of diabetes
Raw health data X is input into the first model, which outputs recommended examination items based on these features. For example, the model may output a recommendation of Y= { Y 1,y2 }
Y 1 blood glucose test
Y 2 Electrocardiographic (ECG) examination
Next, each feature in the health data needs to be removed in turn, and then the remaining features are re-input into the first model, generating new inspection item recommendation results.
For example, feature X 1 (age) is first removed, resulting in a new health dataset, X new＝{x2,x3,x4,x5,x6 }
The new dataset X new is entered into the model, generating new inspection item recommendations. Assuming that the model output became Y new＝{y1 after age removal, this result indicates that after age removal the model only recommended blood glucose tests and no electrocardiographic examination.
Then, the other features are removed in turn, each feature is removed (e.g., blood glucose level, body mass index, family history is removed), and the change in model output is observed, recording a second inspection item of each removal of a certain feature output.
And the interpretation module is used for calculating the contribution value of the health characteristic to the examination item according to the first health data, the first examination item and the second examination item and interpreting the first examination item according to the contribution value.
The interpretation module aims to provide detailed interpretation by transparently processing the decision process behind the examination item recommendation to enhance the interpretability of the system and help doctors and patients understand the recommendation results. The module analyzes the recommended course of the inspection items using the second model and generates an interpretation report for each inspection item.
Specifically, the interpretation module includes:
For each feature's marginal contribution to the model output, its importance is quantified by comparing the difference in model output with and without the feature, the contribution value being calculated by the following formula:
φi=|f(X/{i})-f(X)|
Where phi i represents the contribution value of the feature i, the larger the value, the greater the influence of the feature on the predicted result. In predicting a test item, phi i is used to explain the specific contribution of a certain health characteristic of the patient (e.g., blood glucose level, blood pressure, etc.) when recommending the test item.
X/{ i } represents the set after the feature X i was removed from the input feature set X, as in the previous example, feature X 1 (age) was removed, resulting in a new health dataset: { X 2,x3,x4,x5,x6 }.
F (X) represents a probability value vector predicted using the input feature set X, and if the probability of blood glucose detection is predicted to be 0.86 and the probability of Electrocardiogram (ECG) examination to be performed is predicted to be 0.53, f (X) = {0.86,0.53}
F (X/{ i }) represents a probability value vector predicted by subtracting the feature X i from the input feature set X, and f (X/{ i }) = {0.80,0.41}, if the probability of predicting blood glucose detection after subtracting a certain feature is 0.80 and the probability of performing an Electrocardiogram (ECG) examination is 0.41 (usually less than 0.5 but not examined), the probability of performing an Electrocardiogram (ECG) examination is equal to or greater than 0.41
The expression of f (X/{ i }) -f (X) | is represented by subtracting f (X/{ i }) and f (X) by terms to obtain absolute values, and the above example is given below
I f (X/{ i }) -f (X) |= {0.06,0.12}, the removed item contributes 0.06 to blood glucose detection and 0.12 to Electrocardiogram (ECG) examination.
The contribution value assigns a specific contribution score to each feature for explaining why the feature affects the model recommendation exam.
And taking the relevant characteristics of the preset value quantity before the ranking of the contribution values for each inspection item, and explaining the inspection items according to the relevant characteristics.
For this patient's blood glucose test recommendation, the interpretation report may be as follows:
Blood glucose level x 3 (contribution value: 0.7: patient blood glucose level is high (8.5 mmol/L), which is the most important reason for recommending blood glucose tests.
Family history x 5 (contribution: 0.2) patient had a family history of diabetes, further increasing the recommended weight of blood glucose testing.
Age x 1 (contribution: 0.1) patient age is older and also has a certain influence on blood glucose test recommendations.
Through the contribution value calculation, the interpretation module can quantify the specific contribution of each health feature to the test item recommendation. The second model not only explains how the complex model makes decisions, but also ensures that each feature is fair and meaningful to the importance of the recommendation. In this way, doctors and patients can intuitively understand why the system recommends a particular examination item, as well as the specific role of health features in the decision making process.
On the other hand, the invention also discloses a method for deciding the inspection items based on data processing, which uses the system to make the decision of the inspection items.
The present invention is not limited to the specific partial module structure described in the prior art. The prior art to which this invention refers in the preceding background section as well as in the detailed description section can be used as part of the invention for understanding the meaning of some technical features or parameters. The protection scope of the present invention is subject to what is actually described in the claims.
Claims (9)
1. A data processing based inspection item decision system, the system comprising the following modules:
The data acquisition and preprocessing module is used for collecting and preprocessing health data of a patient to obtain first health data;
The data generation module is used for sequentially removing one item of the first health data and inputting the first model to obtain a second examination item
And the interpretation module is used for calculating the contribution value of the health characteristic to the examination item according to the first health data, the first examination item and the second examination item and interpreting the first examination item according to the contribution value.
2. The data processing-based inspection item decision system of claim 1, wherein the data acquisition and preprocessing module obtains patient physiological parameters, laboratory test results, image data, medical history records, and medication usage related information from medical devices, hospital information systems, electronic health record systems, and laboratory information management systems.
3. The data processing based inspection item decision system of claim 1 wherein the preprocessing includes cleaning, denoising, complement missing values, redundancy elimination, data normalization, format conversion.
4. The data processing based inspection item decision system of claim 1, wherein the health data includes physiological parameters, laboratory test data, imaging data, medical history information, genetic information, and clinical inspection data.
5. The data processing based inspection item decision system of claim 1 wherein the first model is a machine learning model.
6. The data processing based inspection item decision system of claim 5 wherein the first model is a random forest model.
7. The data processing based inspection item decision system of claim 1, wherein the first model is a machine learning model, the first inspection item including a predictive probability for each item.
8. The data processing based inspection item decision system of claim 1 wherein said interpreting the first inspection item in accordance with the contribution value comprises, for each inspection item, taking a pre-set number of related features of the contribution value rank, and interpreting the inspection item in accordance with the related features.
9. A method of decision making of inspection items based on data processing, characterized in that the system according to any of claims 1-8 is used for decision making of inspection items.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411558057.3A CN119480074A (en) | 2024-11-01 | 2024-11-01 | A inspection item decision system and method based on data processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411558057.3A CN119480074A (en) | 2024-11-01 | 2024-11-01 | A inspection item decision system and method based on data processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119480074A true CN119480074A (en) | 2025-02-18 |
Family
ID=94567260
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411558057.3A Pending CN119480074A (en) | 2024-11-01 | 2024-11-01 | A inspection item decision system and method based on data processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119480074A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860577A (en) * | 2020-06-08 | 2020-10-30 | 华南师范大学 | An Ethical Approach to Artificial Intelligence and Robots for Identifying Humans That Do Not Harm Humans |
| CN115587399A (en) * | 2022-05-31 | 2023-01-10 | 江西科晨洪兴信息技术有限公司 | Project progress management system and application based on BIM |
| CN116936056A (en) * | 2023-08-04 | 2023-10-24 | 陕西君凯医疗科技有限公司 | Physical examination scheme dynamic planning system based on patient analysis |
| CN117747113A (en) * | 2023-12-29 | 2024-03-22 | 铅山县人民医院 | Gastroenterology electronic data analysis method and system |
| CN117954032A (en) * | 2024-01-17 | 2024-04-30 | 海南大学 | Medical decision interpretation method and system |
| US11983777B1 (en) * | 2021-07-28 | 2024-05-14 | Massachusetts Mutual Life Insurance Company | Systems and methods for risk factor predictive modeling with model explanations |
-
2024
- 2024-11-01 CN CN202411558057.3A patent/CN119480074A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860577A (en) * | 2020-06-08 | 2020-10-30 | 华南师范大学 | An Ethical Approach to Artificial Intelligence and Robots for Identifying Humans That Do Not Harm Humans |
| US11983777B1 (en) * | 2021-07-28 | 2024-05-14 | Massachusetts Mutual Life Insurance Company | Systems and methods for risk factor predictive modeling with model explanations |
| CN115587399A (en) * | 2022-05-31 | 2023-01-10 | 江西科晨洪兴信息技术有限公司 | Project progress management system and application based on BIM |
| CN116936056A (en) * | 2023-08-04 | 2023-10-24 | 陕西君凯医疗科技有限公司 | Physical examination scheme dynamic planning system based on patient analysis |
| CN117747113A (en) * | 2023-12-29 | 2024-03-22 | 铅山县人民医院 | Gastroenterology electronic data analysis method and system |
| CN117954032A (en) * | 2024-01-17 | 2024-04-30 | 海南大学 | Medical decision interpretation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8554580B2 (en) | Automated management of medical data using expert knowledge and applied complexity science for risk assessment and diagnoses | |
| US20180107798A1 (en) | Method for aiding a diagnosis, program and apparatus | |
| US20090093686A1 (en) | Multi Automated Severity Scoring | |
| CN118173253B (en) | System and method for analyzing and managing based on patient data | |
| CN114023441A (en) | Severe AKI early risk assessment model and device based on interpretable machine learning model and development method thereof | |
| US20100217094A1 (en) | Point-of-care enactive medical system and method | |
| CN119227784B (en) | A decision tree generation method based on large language model and related equipment | |
| CN113838577A (en) | Convenient layered old people MODS early death risk assessment model, device and establishment method | |
| Panigrahy et al. | Predictive modelling of diabetes complications: insights from binary classifier on chronic diabetic mellitus | |
| CN114613487A (en) | Pregnancy decision support system and method | |
| Cox et al. | The definition of predictor and outcome variables in mortality prediction models: a scoping review and quality of reporting study | |
| JP7393518B2 (en) | Teacher data collection device, teacher data collection method and recording medium | |
| CN117612731A (en) | Method for constructing chronic disease risk model | |
| GB2555381A (en) | Method for aiding a diagnosis, program and apparatus | |
| CN119905265A (en) | A health examination data management method and system | |
| CN120072257A (en) | Clinical examination result analysis method based on medical knowledge graph | |
| CN119580981A (en) | Personalized medical path planning method and platform based on integrated data analysis | |
| CN118762826A (en) | Method for predicting coronary artery stenosis and FFR based on big data of coronary artery diagnosis and treatment | |
| CN119480074A (en) | A inspection item decision system and method based on data processing | |
| CN117116472B (en) | Medical diagnostic apparatus, electronic device, and storage medium | |
| AU2021102832A4 (en) | System & method for automatic health prediction using fuzzy based machine learning | |
| CN120376068A (en) | Traditional Chinese medicine artificial intelligence auxiliary diagnosis and treatment system and construction method | |
| Merphin et al. | Prediction of Metabolic Syndrome using Machine Learning Algorithms | |
| CN119517438A (en) | A method for analyzing radiology image data | |
| Wagachchi | Machine learning-based system to predicting the diagnosis of coronary artery disease |
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 |