CN114550930A - Disease prediction method, device, equipment and storage medium - Google Patents
Disease prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114550930A CN114550930A CN202210152089.8A CN202210152089A CN114550930A CN 114550930 A CN114550930 A CN 114550930A CN 202210152089 A CN202210152089 A CN 202210152089A CN 114550930 A CN114550930 A CN 114550930A
- Authority
- CN
- China
- Prior art keywords
- data
- disease
- user
- target user
- repaired
- 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
- 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
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies
-
- 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
Abstract
The invention relates to the technical field of artificial intelligence and discloses a disease prediction method, a disease prediction device, disease prediction equipment and a storage medium. The method comprises the following steps: performing quality detection on the acquired user disease course data, and determining data to be corrected when a data abnormal signal is identified; repairing the user repair demand data based on the received data repair request to obtain target user disease data; carrying out feature extraction on the disease data of the target user to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease related data of the user, and further disease correlation analysis is carried out on the user, so that the technical problem of low accuracy of a disease prediction result is solved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a disease prediction method, a disease prediction device, disease prediction equipment and a storage medium.
Background
In the previous research on disease influence factors, a long period is needed to track a complete diagnosis and treatment course of a patient, and during the period, researchers need to continuously go to telephone follow-up and questionnaire survey, so that a large amount of manpower, material resources and financial resources are needed in the process to record the complete course of the disease of a plurality of patients. However, the process may involve some risks of privacy disclosure of the patient, that the patient is not willing to fill in with a questionnaire, or that the patient fills in problems at will, which may result in cases where the collected patient disease-related data is far from the actual one.
Meanwhile, with the improvement of the attention degree to medical treatment, the disease data are more generally analyzed, and in the existing disease data analysis and prediction scheme, the disease data are not analyzed and predicted in multiple directions, and the analyzed disease data are not comprehensive and real enough, so that the disease data cannot be accurately analyzed, the accuracy of disease early warning is low, and the loss of patients is serious.
Disclosure of Invention
The invention mainly aims to perform data modeling on disease-related data of a user through big data analysis, further perform disease-related analysis on the user and solve the technical problem of low disease prediction accuracy.
In a first aspect, the present invention provides a method for disease prediction, comprising: acquiring user disease course data of a target user, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal; receiving a data repairing request, and repairing the data to be repaired based on the data repairing request to obtain target user disease data; performing feature extraction on the target user disease data, and performing vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
Optionally, in a first implementation manner of the first aspect of the present invention, after the performing quality detection on the user disease process data and determining data to be corrected in the user disease process data when the quality of the user disease process data is detected to be abnormal, the method further includes: and identifying data to be repaired corresponding to the user repair demand data, and matching target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired.
Optionally, in a second implementation manner of the first aspect of the present invention, the identifying data to be repaired corresponding to the user repair demand data, and matching, from a preset database, target repair data corresponding to the data to be repaired based on the data to be repaired includes: identifying the data to be repaired, and determining the characteristic data of the data to be repaired; and matching target repair data corresponding to the data to be repaired based on the feature data.
Optionally, in a third implementation manner of the first aspect of the present invention, the receiving a data repair request, and repairing the data to be repaired based on the data repair request to obtain target user disease data includes: receiving a data repair request, and identifying the data repair request to obtain scheme data carried in the data repair request; auditing the scheme data to obtain an auditing result; and when the auditing result passes, repairing the data to be repaired based on the data repairing request to obtain target user disease data.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the performing feature extraction on the target user disease data, and performing vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data includes: cleaning the disease data of the target user to obtain cleaning data; extracting pathological indexes of preset diseases from the cleaning data; vectorizing the pathological indexes to obtain the characteristic vectors of the preset diseases.
Optionally, in a fifth implementation manner of the first aspect of the present invention, before the inputting the feature vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user, the method further includes: acquiring patient disease data of a preset type of diseases from a preset database, and performing feature extraction on the patient disease data to obtain a feature vector of the patient disease data, wherein the patient disease data comprises medical examination data and electronic medical record data of a patient; building a neural network model, and training the neural network model through the characteristic vector to obtain an initial disease prediction model; and calculating a loss function of the initial disease prediction model, and updating parameters of the initial disease prediction model based on the loss function until the initial disease prediction model converges to obtain a target disease prediction model.
A second aspect of the present invention provides a disease prediction apparatus comprising: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring user disease course data of a target user, and the user disease course data comprises medical examination data and electronic medical record data of the target user; the determining module is used for detecting the quality of the user disease course data, and determining data to be corrected in the user disease course data when the user disease course data is detected to be abnormal in quality; the restoration module is used for receiving a data restoration request, restoring the data to be restored based on the data restoration request and obtaining disease data of a target user; the first feature extraction module is used for performing feature extraction on the target user disease data and performing vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data; and the analysis module is used for inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
Optionally, in a first implementation manner of the second aspect of the present invention, the disease prediction apparatus further includes: and the matching module is used for identifying data to be repaired corresponding to the user repair demand data and matching target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired.
Optionally, in a second implementation manner of the second aspect of the present invention, the matching module is specifically configured to: identifying the data to be repaired, and determining the characteristic data of the data to be repaired; and matching target repair data corresponding to the data to be repaired based on the feature data.
Optionally, in a third implementation manner of the second aspect of the present invention, the repair module is specifically configured to: receiving a data repair request, and identifying the data repair request to obtain scheme data carried in the data repair request; auditing the scheme data to obtain an auditing result; and when the auditing result passes, repairing the data to be repaired based on the data repairing request to obtain target user disease data.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the first feature extraction module includes: the data cleaning unit is used for cleaning the disease data of the target user to obtain cleaning data; the characteristic extraction unit is used for extracting pathological indexes of preset types of diseases from the cleaning data; and the vectorization unit is used for vectorizing the pathological indexes to obtain the characteristic vectors of the preset diseases.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the disease prediction apparatus further includes:
the second feature extraction module is used for acquiring patient disease data of preset diseases from a preset database and performing feature extraction on the patient disease data to obtain a feature vector of the patient disease data, wherein the patient disease data comprises medical examination data and electronic medical record data of a patient; the building module is used for building a neural network model, and training the neural network model through the characteristic vector to obtain an initial disease prediction model; and the updating module is used for calculating a loss function of the initial disease prediction model, and updating the parameters of the initial disease prediction model based on the loss function until the initial disease prediction model converges to obtain a target disease prediction model.
A third aspect of the present invention provides a disease prediction apparatus comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the disease prediction device to perform the steps of the disease prediction method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the above-mentioned disease prediction method.
According to the technical scheme provided by the invention, the user disease course data of the target user are acquired, wherein the user disease course data comprise medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Drawings
FIG. 1 is a schematic diagram of a first embodiment of a disease prediction method provided by the present invention;
FIG. 2 is a schematic diagram of a second embodiment of a disease prediction method provided by the present invention;
FIG. 3 is a schematic diagram of a third embodiment of the disease prediction method provided by the present invention;
FIG. 4 is a diagram of a fourth embodiment of the disease prediction method provided by the present invention;
FIG. 5 is a schematic diagram of a fifth embodiment of the disease prediction method provided by the present invention;
FIG. 6 is a schematic diagram of a first embodiment of a disease prediction apparatus provided in the present invention;
FIG. 7 is a schematic view of a second embodiment of the disease prediction apparatus provided in the present invention;
fig. 8 is a schematic diagram of an embodiment of a disease prediction apparatus provided in the present invention.
Detailed Description
According to the disease prediction method, the device, the equipment and the storage medium provided by the embodiment of the invention, the user disease course data of a target user are obtained, wherein the user disease course data comprise medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Moreover, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For understanding, the following describes a specific process of an embodiment of the present invention, and with reference to fig. 1, a first embodiment of a disease prediction method according to an embodiment of the present invention includes:
101. acquiring user disease course data of a target user, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user;
in this embodiment, medical examination data and electronic medical record data of a user visiting a hospital are acquired from the HIS, RIS, and LIS.
The HIS refers to a Hospital Information System (HIS), and provides capabilities of collecting, storing, processing, extracting and exchanging data of diagnosis and treatment Information and administrative management Information of patients for all departments to which the Hospital belongs by using an electronic computer and communication equipment, and meets the functional requirements of all authorized users. The LIS refers to a Laboratory Information Management System (LIS), which is a set of Information Management System specially designed for hospital clinical Laboratory, and can form a network with Laboratory instruments and computers, so that complicated operation processes such as patient sample login, experimental data access, report review, printing distribution, experimental data statistical analysis and the like are realized, and intelligent, automatic and standardized Management is realized. The system is beneficial to improving the overall management level of a laboratory, reducing loopholes and improving the inspection quality. The RIS is a radiology information management system (RIS), which is a software system for optimizing the workflow management of the radiology department of the hospital, and a typical flow includes links such as registration appointment, diagnosis, image generation, film production, report, audit, film distribution and the like.
Further, the electronic medical record data comprises: the name, identification number, telephone number, address, medical history, disease condition, etc. of the patient, and the medical examination data includes image pictures or diagnosis data obtained through various medical examination instruments such as a CT, an X-ray machine, etc.
102. Performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal;
in this embodiment, the quality detection result includes abnormal information of abnormal data to be repaired in the user disease course data, and the result table includes user disease course data identification information of the user disease course data.
In some embodiments, the quality detection mode may be implemented by technical means in the related art, and the quality detection method adopted by the disease course data of each user may be the same or different without limitation. One database may include one or more user disease course data, and the quality detection may be performed on all user disease course data in the database, or may be performed on a part of user disease course data. The quality detection of the disease course data of each user in each database may be performed simultaneously or sequentially, and is not limited herein.
103. Receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user;
in this embodiment, a data repair request is received, and the data to be repaired is repaired based on the data repair request, so as to obtain target user disease data.
Specifically, the detection type of abnormal data to be repaired is obtained; and determining a preset repair rule according to the detection type, and repairing abnormal data to be repaired according to the preset repair rule.
For different detection types, the detected abnormal data to be repaired have different abnormal problems, so that different preset repair rules need to be set correspondingly so as to repair the detected abnormal data to be repaired when the abnormal data to be repaired is detected. For example, when the detection type is a null value type, the repair rule is preset to be automatically filled with a fixed value or a random value. When a repairing instruction is received, automatic filling data is set according to a preset repairing rule, and then the abnormal data to be repaired can be repaired. The preset repair rule can be set by those skilled in the art as needed.
Optionally, when the detection type includes a uniqueness problem, the preset repair rule includes a screening operation performed on abnormal data to be repaired which has repetition, and only one abnormal data to be repaired is reserved. When the detection type includes a value range problem, the preset repair rule includes modifying the abnormal data to be repaired, which is higher than the value range, to the maximum value of the value range, and modifying the abnormal data to be repaired, which is lower than the value range, to the minimum value of the value range, for example, the value range is [ 0,100 ], the abnormal data to be repaired is-1, 800, and 106, and then-1 is repaired to 0,800 and 106 is repaired to 100.
Optionally, the abnormal data to be repaired may be automatically repaired according to the preset repair rule, where the preset repair rule further includes a budget value and/or a budget algorithm, and when the automatic repair instruction is received, the abnormal data to be repaired is subjected to data repair according to the preset repair rule. .
104. Carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user;
in this embodiment, feature extraction: the feature extraction will get a new feature space through data transformation or data mapping, although the new feature space is derived based on the original features, the association between the new data set and the original data set may not be seen by human eye observation.
In this embodiment, the feature may be extracted from the image after it is detected. This process may require many image processing computers. The result is called a feature description or feature vector. Feature extraction and feature selection are both to find the most efficient features from the original features.
105. And inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
In this embodiment, when the probability that the target user suffers from the preset type of disease is calculated to be less than 70% by using the disease prediction model, it is determined that the disease is not pancreatitis and may be other diseases related to pancreas; and when the probability of the target user suffering from the preset type of diseases is calculated by using the standard disease prediction model to be larger than a preset threshold value, such as 70%, judging that the disease is pancreatitis as the analysis result.
In detail, in this embodiment, the calculating, by using the standard disease prediction model, the probability of the target user suffering from the predetermined kind of disease includes: the medical examination data and electronic medical record data of the target user are input into the standard disease prediction model for analysis, and the result normalization is performed through a normalization function, such as a Softmax function.
Specifically, the output result of the disease prediction model is (— infinity, + ∞), and the normalization process is a process of converting the data result of the disease prediction model into a value between 0 and 1.
The Softmax function, y ═ exp (x), can transform the output of the disease prediction model onto an exponential function, guaranteeing the nonnegativity of the probability. For example, the present embodiment may obtain a pancreatic index of the patient, input the pancreatic index into the standard disease prediction model, and obtain the prevalence probability of pancreatitis suffered by the user; and when the disease probability of the target person exceeds a first preset value, judging that the target person possibly suffers from pancreatitis, and outputting a pre-constructed past diagnosis and treatment scheme close to the condition of the target person.
For example, the first preset value is generally 70%, when the probability of suffering from pancreatitis is greater than 70%, it is determined that the target person may suffer from pancreatitis, and the previous diagnosis and treatment scheme may be obtained from a pre-constructed hospital medical database.
In the embodiment of the invention, the user disease course data of the target user is acquired, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Referring to fig. 2, a second embodiment of the disease prediction method according to the embodiment of the present invention includes:
201. acquiring user disease course data of a target user;
202. performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal;
203. identifying data to be repaired corresponding to the user repair demand data, and matching target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired;
in this embodiment, data to be repaired corresponding to the user repair demand data is identified, and feature data of the data to be repaired is determined; and matching target repair data corresponding to the data to be repaired from a preset database based on the characteristic data.
Specifically, based on the preset scene data and the feature data, matching target repair data in the preset scene, that is, matching a repair scheme template in the preset scene; the restoration scheme template matched in the preset scene can be directly obtained by comparing the characteristic data with preset scene data in the preset scene database; the preset scene can be obtained by comparing the characteristic data with preset scene data in the preset scene database, and the characteristic data is identified by combining the preset scene data to obtain the repairing scheme template; the preset scene can be obtained by comparing the characteristic data with preset scene data in the preset scene database, and the restoration scheme template is obtained by combining restoration scheme template selection data input by a user. Matching the target repair data corresponding to the abnormal data, and matching the target repair data corresponding to the abnormal data based on the scene data and the feature data after matching the scene data; and matching the target repair data corresponding to the abnormal data based on scene demand data input by a user after matching the scene data.
204. Identifying data to be repaired, and determining characteristic data of the data to be repaired;
in this embodiment, the selected abnormal data is identified, and the feature data in the abnormal data is identified, where the feature data may be field value data in abnormal data, and matching of scene data may be implemented based on the field value data.
205. Matching target repair data corresponding to the data to be repaired based on the characteristic data;
in this embodiment, based on the feature data, matching preset scene data corresponding to the feature data in a preset scene database; comparing the feature data with preset scene data in the preset scene database, acquiring preset scene data corresponding to the feature data based on the comparison result,
in another embodiment, preset scene data corresponding to the abnormal data is matched based on the feature data and in combination with a preset machine learning model. And identifying the preset scene data and the characteristic data, and matching the target repair data corresponding to the abnormal data. The preset scene data comprises a plurality of data restoration scheme templates, and the restoration scheme templates mainly comprise: the scheme template number is the only number of the scheme template, the scheme template name, the name of the scheme template which can be identified by business personnel, and the repair steps can correspond to a plurality of repair step templates with sequences, and the auditor executes manual audit when the manual audit is needed.
206. Receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user;
207. carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user;
208. and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
The steps 201-.
In the embodiment of the invention, the user disease course data of the target user is acquired, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the disease course data of the user, and determining data to be repaired in the disease course data of the user when the quality of the disease course data of the user is detected to be abnormal, wherein the data required for repairing the user is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Referring to fig. 3, a third embodiment of the disease prediction method according to the embodiment of the present invention includes:
301. acquiring user disease course data of a target user;
302. performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal;
303. receiving a data repair request, and identifying the data repair request to obtain scheme data carried in the data repair request;
in this embodiment, the data repair request includes a repair scheme and repair logic data for repairing the abnormal data, which are generated based on the repair scenario data.
304. Auditing the scheme data to obtain an auditing result;
in this embodiment, a corresponding repair scheme in the data repair request is identified, the repair scheme for the abnormal data is checked, whether the repair scheme can perform repair of the abnormal data is checked, and the accuracy of the repair scheme for the abnormal data is improved, so that the efficiency and the accuracy of repairing the abnormal data are improved.
305. When the auditing result passes, repairing the data to be repaired based on the data repairing request to obtain target user disease data;
in this embodiment, when the audit result passes, the data to be repaired is repaired based on the data repair request, and the logical data corresponding to the execution of the repair step is identified, for example, if the step template of the repair scheme is to perform call interface repair on the abnormal data, the repair logical data between the steps of executing data repair in a call interface manner is obtained, so as to execute data repair based on the repair logical data.
The repairing step in the repairing scheme comprises the following steps: the method comprises the steps of calling interface repair, offline manual repair, sending work order repair, autonomous repair and the like, wherein in the process of executing the repair scheme to repair, various repair steps can exist in a compatible mode in the repair process, for example, taking calling interface repair as an example, reading difference data, generating repair request data, and then directly calling a repair interface to repair. If the current step is successful, the current step is executed successfully, meanwhile, a work order interface is called to examine and approve the repair node, then the work order can flow to the next repair node, the process is repeated until the last node is repaired, the whole work order is finished, the corresponding difference data is repaired, and if the data repair is finished, the repair result data is output.
306. Carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user;
307. and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
The steps 301-.
In the embodiment of the invention, the user disease course data of the target user is acquired, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Referring to fig. 4, a fourth embodiment of the disease prediction method according to the embodiment of the present invention includes:
401. acquiring user disease course data of a target user;
402. performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal;
403. receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user;
404. cleaning disease data of a target user to obtain cleaning data;
in this embodiment, the cleaning is data cleaning, and includes processes of data screening, duplicate removal and classification, and the embodiment of the present invention removes privacy information in a case, such as sensitive information or redundant data, such as an identity card number, a mobile phone number, a face picture, and the like, through the data screening, and supplements missing values in the medical examination data and the electronic medical record data.
In this embodiment, the medical examination data and the electronic medical record data are imported into a pre-constructed cleaning processing database; utilizing the cleaning process database; calculating the missing value proportion of each field in the medical examination data and the electronic medical record data; according to the missing value ratio and the importance of the field. And selecting a corresponding filling strategy according to a preset strategy table, and filling the medical examination data and the electronic medical record data according to the filling strategy to obtain the cleaning data.
405. Extracting pathological indexes of preset diseases from the cleaning data;
in this embodiment, for example, the stomach disease may be extracted, and the stomach indexes include: the medical electronic medical record data (medical history, symptoms, physical sign data and the like) and the medical examination data (ultrasonic examination data, fine needle puncture examination data and the like).
406. Vectorizing the pathological indexes to obtain characteristic vectors of preset diseases;
in this embodiment, preset statistical processing is performed on the recorded values of the pathological index at a plurality of time points to obtain multidimensional measurement; and vectorizing the multi-dimensional statistics to obtain the characteristic vector of the preset type of diseases.
The pathological index comprises recorded values of various physiological information such as the electronic medical record data of the patient and the medical examination data in each time period, the recorded values are recorded at different times, for example, the physiological information of the blood pressure of the corresponding patient comprises 24 blood pressure values recorded every other hour within 24 hours a day.
The hospital carries out preset statistical treatment on the pathological indexes, wherein the preset statistical treatment can be a preset treatment mode, for example, an average value of a plurality of recorded values of each pathological index is calculated to be used as a statistic of the pathological index, and the statistic of a plurality of pathological indexes forms multidimensional statistic.
407. And inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
The steps 401, 403, 407 in this embodiment are similar to the steps 101, 103, 106 in the first embodiment, and are not described herein again.
In the embodiment of the invention, the user disease course data of the target user is acquired, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Referring to fig. 5, a fifth embodiment of the disease prediction method according to the present invention includes:
501. acquiring user disease course data of a target user;
502. performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal;
503. receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user;
504. carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user;
505. acquiring patient disease data of a preset type of diseases from a preset database, and performing feature extraction on the patient disease data to obtain feature vectors of the patient disease data;
in this embodiment, patient disease data including a preset type of disease is acquired, and the patient disease data of the preset type of disease is used as training sample data, where the training data set includes, but is not limited to: information related to physical conditions (e.g., sex, age, allergy history, etc.), name of disease, type of disease, symptoms of disease, medication for disease. The training data may be obtained from a database used by each hospital to store patient data.
506. Building a neural network model, and training the neural network model through the characteristic vectors to obtain an initial disease prediction model;
in this embodiment, the neural network model is stored in the server, and the server may send the neural network model of the disease prediction model to be trained to the client according to a request of the client, so that the client performs local modeling by using the neural network model.
507. Calculating a loss function of the initial disease prediction model, and updating parameters of the initial disease prediction model based on the loss function until the initial disease prediction model converges to obtain a target disease prediction model;
in this embodiment, a loss function of the initial disease prediction model is calculated, and parameters of the initial disease prediction model are updated based on the loss function until the initial disease prediction model converges.
Specifically, performing loss function calculation on the initial disease prediction model, and comparing a currently calculated loss function with a historical loss function stored in a preset database; when the difference value between the current calculated loss function and the historical loss function is smaller than or equal to a preset value, judging that the combined initial disease prediction model is in a convergence state; and when the difference value between the current calculated loss function and the historical loss function is larger than the preset value, judging that the combined initial disease prediction model is not in a convergence state, and updating the historical loss function stored in the preset database by using the current calculated loss function.
And when the initial disease prediction model is not converged, sending the combined initial disease prediction model to a client, and further training the combined initial disease prediction model through the characteristic vector in the client to obtain a better initial disease prediction model.
And successfully converging, updating the model loss function of the disease prediction model to be trained of the local hospital by using the converged loss function, and locally completing the construction of the disease prediction model to be trained by using the updated model loss function to obtain the target disease prediction model.
508. And inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
Steps 501-504 and 508 in the present embodiment are similar to steps 101-104 and 105 in the first embodiment, and are not described herein again.
In the embodiment of the invention, the user disease course data of the target user is acquired, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
With reference to fig. 6, the disease prediction method in the embodiment of the present invention is described above, and the disease prediction apparatus in the embodiment of the present invention is described below, where the first embodiment of the disease prediction apparatus in the embodiment of the present invention includes:
an obtaining module 601, configured to obtain user medical procedure data of a target user, where the user medical procedure data includes medical examination data and electronic medical record data of the target user;
a determining module 602, configured to perform quality detection on the user disease course data, and determine data to be repaired in the user disease course data when it is detected that the quality of the user disease course data is abnormal;
a repairing module 603, configured to receive a data repairing request, and repair the data to be repaired based on the data repairing request to obtain target user disease data;
a first feature extraction module 604, configured to perform feature extraction on the target user disease data, and perform vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data;
and the analysis module 605 is configured to input the feature vector of the disease data of the target user into a preset disease prediction model, and perform disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
In the embodiment of the invention, the disease course data of a target user are acquired, wherein the disease course data of the user comprise medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Referring to fig. 7, a disease prediction apparatus according to a second embodiment of the present invention specifically includes:
an obtaining module 601, configured to obtain user medical procedure data of a target user, where the user medical procedure data includes medical examination data and electronic medical record data of the target user;
a determining module 602, configured to perform quality detection on the user disease course data, and determine data to be repaired in the user disease course data when it is detected that the quality of the user disease course data is abnormal;
a repairing module 603, configured to receive a data repairing request, and repair the data to be repaired based on the data repairing request to obtain target user disease data;
a first feature extraction module 604, configured to perform feature extraction on the target user disease data, and perform vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data;
and the analysis module 605 is configured to input the feature vector of the disease data of the target user into a preset disease prediction model, and perform disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
In this embodiment, the disease prediction apparatus further includes:
a matching module 606, configured to identify data to be repaired corresponding to the user repair demand data, and match target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired.
In this embodiment, the matching module 606 is specifically configured to:
identifying the data to be repaired, and determining the characteristic data of the data to be repaired;
and matching target repair data corresponding to the data to be repaired based on the feature data.
In this embodiment, the repairing module 603 is specifically configured to:
receiving a data repair request, and identifying the data repair request to obtain scheme data carried in the data repair request;
auditing the scheme data to obtain an auditing result;
and when the auditing result passes, repairing the data to be repaired based on the data repairing request to obtain target user disease data.
In this embodiment, the first feature extraction module 604 includes:
a data cleaning unit 6041, configured to clean the target user disease data to obtain cleaning data;
a feature extraction unit 6042 configured to extract a pathological index of a preset type of disease from the cleaning data;
a vectorization unit 6043, configured to perform vectorization on the pathological indicators to obtain feature vectors of the preset types of diseases.
In this embodiment, the disease prediction apparatus further includes:
a second feature extraction module 607, configured to obtain patient disease data of a preset type of disease from a preset database, and perform feature extraction on the patient disease data to obtain a feature vector of the patient disease data, where the patient disease data includes medical examination data and electronic medical record data of a patient;
a building module 608, configured to build a neural network model, and train the neural network model through the feature vector to obtain an initial disease prediction model;
and the updating module 609 is used for calculating a loss function of the initial disease prediction model, and updating the parameters of the initial disease prediction model based on the loss function until the initial disease prediction model converges to obtain a target disease prediction model.
In the embodiment of the invention, the user disease course data of the target user is acquired, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user; performing quality detection on the user disease course data, and determining data to be repaired in the user disease course data when the quality of the user disease course data is detected to be abnormal, wherein the user repair demand data is the data to be repaired; receiving a data repair request, and repairing data to be repaired based on the data repair request to obtain disease data of a target user; carrying out feature extraction on the disease data of the target user, and carrying out vectorization processing on the extracted feature data to obtain a feature vector of the disease data of the target user; and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user. According to the invention, through big data analysis, data modeling is carried out on the disease-related data of the user, and further, the disease-related analysis is carried out on the user, so that the technical problem of low disease prediction accuracy is solved.
Fig. 6 and 7 describe the disease prediction apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the disease prediction apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 8 is a schematic structural diagram of a disease prediction apparatus provided in an embodiment of the present invention, where the disease prediction apparatus 800 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) storing an application 833 or data 832. Memory 820 and storage medium 830 may be, among other things, transient or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instructions operating on the disease prediction apparatus 800. Further, the processor 810 may be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the disease prediction apparatus 800 to implement the steps of the disease prediction method provided by the above-described method embodiments.
The disease prediction device 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input-output interfaces 860, and/or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the disease prediction device configuration shown in fig. 8 does not constitute a limitation of the disease prediction device provided herein, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the above-mentioned disease prediction method.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method of disease prediction, comprising:
acquiring user disease course data of a target user, wherein the user disease course data comprises medical examination data and electronic medical record data of the target user;
performing quality detection on the user disease course data, and determining data to be corrected in the user disease course data when the quality of the user disease course data is detected to be abnormal;
receiving a data repairing request, and repairing the data to be repaired based on the data repairing request to obtain target user disease data;
performing feature extraction on the target user disease data, and performing vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data;
and inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
2. The method for predicting diseases according to claim 1, wherein after the performing quality detection on the disease process data of the user and determining data to be repaired in the disease process data when the quality of the disease process data of the user is detected to be abnormal, the method further comprises:
and identifying data to be repaired corresponding to the user repair demand data, and matching target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired.
3. The disease prediction method according to claim 2, wherein the identifying data to be repaired corresponding to the user repair demand data, and the matching of the target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired comprises:
identifying the data to be repaired, and determining the characteristic data of the data to be repaired;
and matching target repair data corresponding to the data to be repaired based on the characteristic data.
4. The disease prediction method according to claim 1, wherein the receiving a data repair request, and repairing the data to be repaired based on the data repair request to obtain the target user disease data comprises:
receiving a data repair request, and identifying the data repair request to obtain scheme data carried in the data repair request;
auditing the scheme data to obtain an auditing result;
and when the auditing result passes, repairing the data to be repaired based on the data repairing request to obtain target user disease data.
5. The disease prediction method of claim 1, wherein the extracting the features of the disease data of the target user and vectorizing the extracted features to obtain the feature vector of the disease data of the target user comprises:
cleaning the disease data of the target user to obtain cleaning data;
extracting pathological indexes of preset diseases from the cleaning data;
vectorizing the pathological indexes to obtain the characteristic vectors of the preset diseases.
6. The disease prediction method of claim 1, wherein before the step of inputting the feature vector of the disease data of the target user into a preset disease prediction model and performing a disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user, the method further comprises:
acquiring patient disease data of a preset type of diseases from a preset database, and performing feature extraction on the patient disease data to obtain a feature vector of the patient disease data, wherein the patient disease data comprises medical examination data and electronic medical record data of a patient;
building a neural network model, and training the neural network model through the characteristic vector to obtain an initial disease prediction model;
and calculating a loss function of the initial disease prediction model, and updating parameters of the initial disease prediction model based on the loss function until the initial disease prediction model converges to obtain a target disease prediction model.
7. A disease prediction apparatus, characterized in that the disease prediction apparatus comprises:
the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring user disease process data of a target user, and the user disease process data comprises medical examination data and electronic medical record data of the target user;
the determining module is used for performing quality detection on the user disease process data and determining to-be-repaired data in the user disease process data when the user disease process data is detected to have abnormal quality;
the restoration module is used for receiving a data restoration request, restoring the data to be restored based on the data restoration request and obtaining disease data of a target user;
the first feature extraction module is used for performing feature extraction on the target user disease data and performing vectorization processing on the extracted feature data to obtain a feature vector of the target user disease data;
and the analysis module is used for inputting the characteristic vector of the disease data of the target user into a preset disease prediction model, and performing disease correlation analysis on the target user through the disease prediction model to obtain a disease prediction result of the disease course data of the user.
8. The disease prediction device of claim 7, further comprising:
and the matching module is used for identifying data to be repaired corresponding to the user repair demand data and matching target repair data corresponding to the data to be repaired from a preset database based on the data to be repaired.
9. A disease prediction apparatus characterized by comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;
the at least one processor invokes the instructions in the memory to cause the disease prediction device to perform the steps of the disease prediction method of any one of claims 1-6.
10. A computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when being executed by a processor, is adapted to carry out the steps of the method for disease prediction according to any of the claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210152089.8A CN114550930A (en) | 2022-02-18 | 2022-02-18 | Disease prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210152089.8A CN114550930A (en) | 2022-02-18 | 2022-02-18 | Disease prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114550930A true CN114550930A (en) | 2022-05-27 |
Family
ID=81674951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210152089.8A Pending CN114550930A (en) | 2022-02-18 | 2022-02-18 | Disease prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114550930A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240854A (en) * | 2022-07-29 | 2022-10-25 | 中国医学科学院北京协和医院 | Method and system for processing pancreatitis prognosis data |
-
2022
- 2022-02-18 CN CN202210152089.8A patent/CN114550930A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240854A (en) * | 2022-07-29 | 2022-10-25 | 中国医学科学院北京协和医院 | Method and system for processing pancreatitis prognosis data |
| CN115240854B (en) * | 2022-07-29 | 2023-10-03 | 中国医学科学院北京协和医院 | Pancreatitis prognosis data processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10937164B2 (en) | Medical evaluation machine learning workflows and processes | |
| KR101873926B1 (en) | Method for providing medical counseling service between insurance organization and specialist based on bigdata | |
| US20220156934A1 (en) | Ai-based heat map generating system and methods for use therewith | |
| Hoffman et al. | Big bad data: law, public health, and biomedical databases | |
| RU2533500C2 (en) | System and method for combining clinical signs and image signs for computer-aided diagnostics | |
| JP5952835B2 (en) | Imaging protocol updates and / or recommenders | |
| US11488299B2 (en) | Method and system for computer-aided triage | |
| US20030149597A1 (en) | System for supporting clinical decision-making | |
| US20220172809A9 (en) | Report generating system and methods for use therewith | |
| CN113808738B (en) | Disease identification system based on self-identification image | |
| US20210398650A1 (en) | Medical imaging characteristic detection, workflows, and ai model management | |
| WO2020236847A1 (en) | Method and system for analysis of spine anatomy and spine disease | |
| CN103370629B (en) | Clinical quality analytics system | |
| US20220037019A1 (en) | Medical scan artifact detection system and methods for use therewith | |
| US20220005565A1 (en) | System with retroactive discrepancy flagging and methods for use therewith | |
| CN114550930A (en) | Disease prediction method, device, equipment and storage medium | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| US20230022030A1 (en) | Systems and methods for processing images for image matching | |
| CN114926396B (en) | Mental disorder magnetic resonance image preliminary screening model construction method | |
| KR20180002229A (en) | An agent apparatus for constructing database for dementia information and the operating method by using the same | |
| Lohitha et al. | Detecting Renal Disease using Meta-Classifiers | |
| CN117012379A (en) | Health management system, method, device, medium and program product for target object | |
| CN117409960A (en) | Intelligent hospital high-quality operation management method and system based on big data | |
| WO2023095042A1 (en) | A system and method for medical queries | |
| WO2022036351A1 (en) | Automatic medical scan triaging system and methods for use therewith |
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 |