CN114842977A - Medical decision-making system based on medical big data and artificial intelligence - Google Patents
Medical decision-making system based on medical big data and artificial intelligence Download PDFInfo
- Publication number
- CN114842977A CN114842977A CN202210756677.2A CN202210756677A CN114842977A CN 114842977 A CN114842977 A CN 114842977A CN 202210756677 A CN202210756677 A CN 202210756677A CN 114842977 A CN114842977 A CN 114842977A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- treatment
- keywords
- data
- information
- 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.)
- Granted
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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a medical decision-making system based on medical big data and artificial intelligence, which belongs to the technical field of medical data mining and specifically comprises the following steps: the system comprises a medical big data system, a data uploading module and an in-hospital system; the medical big data system is responsible for processing the uploaded data of the data uploading module, generating the pathology keywords of the patient to be diagnosed, matching the similarity with the pathology keywords of the historical clinical pathology, and obtaining a similar diagnosis and treatment case; extracting clinical diagnosis and treatment examination information data, matching the clinical diagnosis and treatment examination information data with the clinical diagnosis and treatment examination information data of similar diagnosis and treatment cases, and obtaining a diagnosis and treatment case; extracting clinical diagnosis and treatment image information of a patient to be diagnosed, matching the clinical diagnosis and treatment image information with clinical diagnosis and treatment image information according with diagnosis and treatment cases, and obtaining matched diagnosis and treatment cases; the data uploading module is responsible for uploading the uploaded data; the hospital system is responsible for generating uploaded data and pushing the matched diagnosis and treatment cases to a diagnostician, so that accurate and rapid medical record matching is realized.
Description
Technical Field
The invention belongs to the technical field of medical data mining, and particularly relates to a medical decision-making system based on medical big data and artificial intelligence.
Background
IBM corporation formally proposed the concept of "cloud computing" in 2007, and since then, information technologies such as cloud computing, artificial intelligence, internet + and the like are rapidly developed, and "Big Data" (Big Data) gradually appears in the daily life of the public, and is rapidly applied among various industries and becomes an indispensable part in the development process. The medical industry is one of data intensive industries and the earliest industry for realizing digital informatization, correctly and reasonably utilizes medical big data resources, and can enable medical institutions to make more reasonable and scientific decisions and plans. Meanwhile, common people can know and evaluate self health conditions more simply and conveniently, sanitary resources are utilized to the maximum extent, and the life of the people is healthier. Medical big data has close relation with daily life of each person, and has favorable influence on daily prevention and control, disease prediction, new medicine research and development, auxiliary accurate medical treatment and the like.
Chinese patent publication No. CN104915561B discloses an intelligent matching method for disease characteristics, which aims to solve the technical problem that doctors need to refer to similar cases during diagnosis, the search of the similar cases means that matched characteristic vectors are found from a huge case database, and obviously the traditional search mode based on keywords can not meet the requirement of quick matching of multidimensional characteristics, the invention adopts the steps of extracting corresponding values from the existing patient data in an electronic case database according to a disease sign set and a test inspection index set established in advance to form the characteristic vector of each patient, calculating the scores of each disease sign index and test inspection index of the patient to be matched by taking the similarity as a weight, selecting the disease sign index and/or the test inspection index with the score contribution degree of more than a certain percentage after sequencing as the main characteristics for judging the symptoms for auxiliary diagnosis, however, the above patent has a large amount of calculation work and a slow calculation speed, and for a doctor, the medical knowledge reserve and the accumulated diagnosis and treatment experience of the doctor greatly determine the judgment of the disease state of the patient, the selection of diagnosis and treatment advice and the subsequent treatment and rehabilitation degree of the patient, so that the subjective judgment of the doctor on the disease state of the patient is not accurate enough, the subsequent diagnosis and treatment of the patient have deviation, and the judgment error of the conclusion of the disease state health of the patient is increased.
The problems of the prior art are summarized: the case matching is large in calculation amount and slow in speed, and a system and a method for matching cases in steps are lacked.
Aiming at the technical problems, the invention provides a medical decision-making system based on medical big data and artificial intelligence.
Disclosure of Invention
In order to realize the purpose of the invention, the invention adopts the following technical scheme:
according to one aspect of the invention, a medical decision-making system based on medical big data and artificial intelligence is provided.
A medical decision-making system based on medical big data and artificial intelligence is characterized by comprising:
the system comprises a medical big data system, a data uploading module and an in-hospital system;
the medical big data system is responsible for processing the uploaded data of the data uploading module, generating a clinical pathology information report of the patient to be treated according to the clinical pathology description information of the patient to be treated, and extracting pathology keywords in the report; performing similarity matching according to the condition keywords and the condition keywords in the historical clinical condition information report of the diagnosis and treatment cases in the uploaded data, and taking the diagnosis and treatment cases with the similarity higher than a first threshold value as similar diagnosis and treatment cases; extracting clinical diagnosis and treatment examination information data of a patient to be diagnosed, matching the clinical diagnosis and treatment examination information data with the similar diagnosis and treatment cases, and taking the similar diagnosis and treatment cases with the conformity degree greater than a second threshold value as the diagnosis and treatment conforming cases; extracting clinical diagnosis and treatment image information of a patient to be diagnosed, matching the clinical diagnosis and treatment image information with the diagnosis and treatment case, and taking the diagnosis and treatment case with the matching degree larger than a third threshold value as a matched diagnosis and treatment case;
the data uploading module is responsible for uploading the uploaded data, the uploaded data comprises data of patients to be diagnosed and diagnosis and treatment cases, and the data comprises historical clinical pathology information reports, clinical diagnosis and treatment inspection information data and clinical diagnosis and treatment image information;
and the hospital system is responsible for generating the uploaded data and pushing the matched diagnosis and treatment cases obtained by the medical big data system to a diagnostician.
The hospital system generates upload data comprising data of a patient to be diagnosed and diagnosis and treatment cases, the data comprises a historical clinical pathology information report, clinical diagnosis and treatment inspection information data and clinical diagnosis and treatment image information, the upload data are uploaded to a medical big data system through a data upload module, the medical big data system firstly generates a clinical pathology information report of the patient to be diagnosed through describing information of the clinical pathology, and pathology keywords in the report are extracted; performing similarity matching according to the pathology keywords and the pathology keywords in the uploaded data to determine similar diagnosis and treatment cases; determining a corresponding diagnosis and treatment case in the similar diagnosis and treatment cases through clinical diagnosis and treatment inspection information data; the matched diagnosis and treatment cases in the matched diagnosis and treatment cases are determined through the clinical diagnosis and treatment image information, the matched diagnosis and treatment cases are pushed to doctors to assist diagnosis, and through three-step confirmation, the screened data dimensionality is gradually reduced, the screening efficiency is improved, and the screening difficulty is reduced.
The medical big data firstly generates a clinical pathology information report of a patient to be diagnosed through clinical pathology description information of the patient to be diagnosed, extracts pathology keywords in the report, determines a similar diagnosis and treatment case at the moment according to a similarity comparison result of the pathology keywords and the pathology keywords of the diagnosis and treatment case in the uploaded data, and can greatly screen out diagnosis and treatment cases similar to clinical pathology indexes because the clinical diagnosis and treatment inspection information and the clinical diagnosis and treatment image information of different diseases have certain repeatability, so that the efficiency is not high, and the diagnosis and treatment cases can be avoided because the clinical diagnosis and treatment inspection information and the clinical diagnosis and treatment image information are firstly adopted or the clinical diagnosis and treatment inspection information, the clinical diagnosis and treatment image information and the clinical pathology information report are simultaneously adopted, the problem of low efficiency is caused; after obtaining the similar diagnosis and treatment cases, the corresponding diagnosis and treatment cases are obtained by screening through the judgment of the clinical diagnosis and treatment inspection information, the clinical diagnosis and treatment inspection information is more visual and accurate compared with the clinical diagnosis and treatment image information, the corresponding diagnosis and treatment cases can be screened more quickly when being compared, so that the data volume of the finally performed clinical diagnosis and treatment image information is further reduced, the finally matched diagnosis and treatment cases can be obtained through the clinical medical influence information, the matched diagnosis and treatment cases can be pushed to doctors, the diagnosis reliability is improved, the clinical diagnosis and treatment image information with the lowest recognition efficiency is put to the last step through the judgment in steps, the clinical pathology information report with the strongest distinguishing capability is put to the first step, the recognition efficiency can be greatly improved, the speed is higher, the user experience degree is obviously improved, and therefore, the referring analysis of the doctor in the process of diagnosing and treating the patient can be combined with a plurality of diagnosis and treatment cases, the problem that medical knowledge storage and diagnosis and treatment experience accumulation of the doctor are insufficient is effectively solved, the accuracy of judgment of the doctor on the disease of the patient is improved, the error of judgment on the conclusion such as the disease health of the patient is reduced, and the doctor is assisted to make a diagnosis more quickly, accurately and reasonably.
The further technical scheme is that any one item or any two items of the disease state keyword matching, the clinical diagnosis and treatment inspection information data matching and the clinical diagnosis and treatment image information matching can be adopted for screening the cases.
According to different symptoms and types, clinical diagnosis and treatment tests or clinical diagnosis and treatment image tests or neither clinical diagnosis and treatment image tests are sometimes not needed, so that in actual operation, only one or two of three kinds of matching can be selected, and extraction of matched diagnosis and treatment cases can be realized.
The further technical scheme is that the sequence of the symptom keyword matching, the clinical diagnosis and treatment inspection information data matching and the clinical diagnosis and treatment image information matching can be adjusted according to different symptoms.
The medical decision-making system based on the medical big data and the artificial intelligence further comprises an out-of-hospital service module, provides auxiliary medical services, and aims at tracking diagnosis and treatment conditions and medicine taking conditions of a user in real time.
Through setting up out-of-hospital service module, solved original patient and see a doctor and treated the back, the problem that the doctor can not be tracked well to the recovery information after patient's treatment, because unable real-time tracking, lead to unable realization doctor and patient's real-time interaction during patient resumes, thereby make the doctor unable real-time master patient and resume the condition, can bring very big influence for subsequent treatment of patient and follow-up visit, through setting up out-of-employee service module, the doctor can realize the grasp to patient's recovery condition, thereby promote patient's gain and satisfaction, more be of value to patient's recovery.
The further technical solution is that the medical decision system based on medical big data and artificial intelligence further comprises: the system comprises a cloud server, a cloud computing processing platform, a data receiving module, a data processing control module, a basic system module and a user side.
The medical big data system, the cloud computing processing platform, the data uploading module, the data receiving module, the data processing control module, the basic system module, the user side, the in-hospital system and the out-of-hospital service module are all connected with the cloud server network; the medical big data system is connected with the data uploading module, and the data uploading module is in communication connection with the data receiving module and the data processing control module; the medical big data system processes the data uploaded by the data uploading module, compresses the data processed by the data processing control module, uploads the data to the medical big data system through the data uploading module, and finally simply processes the compressed data through the data processing control module and stores the data in the medical big data system; the cloud computing processing platform comprises a user authentication module, a service request management module and a large-scale data computing processing center module, wherein the large-scale data computing processing center module consists of a plurality of physical computing machines, and the computing resource allocation module is used for allocating work in computing resources; the basic system module is used for associating important medical data of patients to see a doctor and transmitting the important medical data to the cloud server; the hospital system provides medical service in the hospital, and is convenient for patients to see a doctor; the cloud server integrates the services of the basic system module, the in-hospital system and the out-of-hospital service module and provides an interface for the user side; the user side is in butt joint with the cloud server, so that medical service conditions can be known in real time, medical procedures can be followed, medical services can be optimally performed, and latest medical information can be fed back to the user in time.
The further technical scheme is that the method for extracting the symptom keywords comprises the following steps:
s11, performing word segmentation processing on the clinical pathology information report through a word segmentation tool to obtain words of the clinical pathology information report subjected to word segmentation processing;
s12, sending the words of the clinical pathology information report subjected to word segmentation processing into a trained classifier based on an LSTM algorithm for keyword extraction, and extracting the keywords through a TF-IDF algorithm;
s13, respectively assigning a first weight to the keywords extracted by the classifier based on the LSTM algorithm and assigning a second weight to the keywords extracted by the TF-IDF algorithm in a form of expert scoring, adding the weights of the same keywords extracted by the two algorithms, assigning weights corresponding to the extraction algorithms corresponding to different keywords, and taking the keywords with the weights larger than a fifth threshold value as the extracted keywords.
The method combines the modes of extracting keywords by two algorithms of supervised learning and unsupervised learning, gives a first weight to the keywords extracted by a classifier based on the LSTM algorithm in a form of expert scoring, gives a second weight to the keywords extracted by the TF-IDF algorithm, and selects the most appropriate keywords according to the weights, so that the extraction of the keywords can be more combined with a medical background, and the most important keywords for clinical information symptoms in a clinical symptom information report can be more extracted.
The further technical scheme is characterized in that the specific steps of matching the similarity of the pathology keywords are as follows:
s21, clustering the disease condition keywords through a clustering algorithm, wherein the disease condition keywords comprise a plurality of compound clustering nodes, and each compound clustering node corresponds to a plurality of keywords;
s22, the disease state key words are obtained, the disease state key words are matched with the compound clustering nodes, and finally matched compound clustering nodes are obtained, so that similarity matching of the key words is achieved.
Because different patients or different doctors have different expression modes and habits on the same symptoms, the matching accuracy and efficiency can be greatly improved in a compound clustering node mode, and the final similar diagnosis and treatment cases can be better screened.
The method is characterized in that the disease condition keywords comprise basic information keywords and disease information keywords, the similarity is the weighted sum of the similarity of the basic information keywords and the similarity of the disease information keywords, and the weight of the similarity of the basic information keywords and the similarity of the disease information keywords is determined by an expert algorithm.
The similarity of the two keywords is calculated by dividing the disease condition keywords into the basic information keywords and the disease information keywords, and the similarity of the basic information keywords and the similarity of the disease information keywords have different meanings when the disease similarity is finally determined, so that the weights of the similarities of the different keywords are determined through an expert algorithm, and the similarity of the final case can be reflected more accurately.
The further technical scheme is characterized in that the step of calculating the similarity of the basic information keywords and the similarity of the disease information keywords comprises the following steps:
s31, endowing different weights to the compound clustering nodes through an expert algorithm;
s32, matching the basic information keywords and the disease information keywords with the compound cluster nodes respectively, and calculating the similarity of the basic information keywords and the similarity of the disease information keywords according to the weight of the successfully matched compound cluster nodes and the number of the successfully matched compound cluster nodes.
Because different composite clustering nodes have different functions in the final disease judgment, the weights of the different composite clustering nodes are confirmed through an expert algorithm, and the final similarity is calculated according to the weights and the number of the composite clustering nodes successfully matched in a key mode, so that the similarity between two cases can be judged through the similarity, and a foundation is laid for finally confirming to obtain similar cases.
The technical scheme is characterized in that the specific steps of extracting the clinical diagnosis and treatment image information of the patient to be diagnosed and matching the clinical diagnosis and treatment image information according with the diagnosis and treatment case are as follows:
s41, classifying the clinical diagnosis and treatment images according to different acquisition modes and different body parts;
s42, clustering the classified clinical diagnosis and treatment images through a clustering algorithm to form different image clustering centers respectively, endowing the corresponding disease states with the images through an expert algorithm, and extracting the associated characteristic quantities of the different image clustering centers through an HOG algorithm.
S43, extracting the features of the image based on the HOG algorithm, and comparing the features with the associated feature quantity of the image clustering center to obtain the image clustering center associated with the features;
s44, according to the multiple cases obtained by the image clustering center and the image recognition method constructed based on the ResNet network, recognizing the clinical diagnosis and treatment images of the patient to be treated to obtain a disease state, further matching the multiple cases according to the disease state to obtain a matching degree, and determining the matched diagnosis and treatment case at the moment when the matching degree is greater than a third threshold value.
Because the standard and the definition of the images formed by different monitoring equipment for clinical diagnosis and treatment images are greatly different, and the images of different body parts also have no reference value, the number of image identification can be greatly reduced by classifying, and the identification speed is improved. By adopting a clustering algorithm, the images with the same disease judged from different angles at the same part can form clusters, so that the identification accuracy of the images is improved. The final judgment result is accurate and reliable by adopting a characteristic extraction mode firstly and then adopting image recognition of a neural network and two-step judgment.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.
Fig. 1 is a block diagram of a medical decision system based on medical big data and artificial intelligence according to embodiment 1.
Fig. 2 is a flowchart of the specific steps of the method for extracting a pathology keyword in embodiment 1.
Fig. 3 is a flowchart of the specific steps of matching the similarity to the pathology keywords in example 1.
Fig. 4 is a flowchart of the steps of calculating the similarity of the basic information keywords and the similarity of the disease information keywords in embodiment 1.
Fig. 5 is a flowchart illustrating the specific steps of extracting clinical image information of a patient to be diagnosed and matching the clinical image information according with a diagnosis case in embodiment 1.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their detailed description will be omitted.
The terms "a," "an," "the," "said" are used to indicate the presence of one or more elements/components/etc.; the terms "comprising" and "having" are intended to be inclusive and mean that there may be additional elements/components/etc. other than the listed elements/components/etc.
Example 1
According to one aspect of the present invention, there is provided a medical decision-making system based on medical big data and artificial intelligence, as shown in fig. 1.
A medical decision-making system based on medical big data and artificial intelligence is characterized by specifically comprising:
the system comprises a medical big data system, a data uploading module and an in-hospital system;
the medical big data system is responsible for processing the uploaded data of the data uploading module, generating a clinical pathology information report of the patient to be treated according to the clinical pathology description information of the patient to be treated, and extracting pathology keywords in the report; performing similarity matching according to the condition keywords and the condition keywords in the historical clinical condition information report of the diagnosis and treatment cases in the uploaded data, and taking the diagnosis and treatment cases with the similarity higher than a first threshold value as similar diagnosis and treatment cases; extracting clinical diagnosis and treatment examination information data of a patient to be diagnosed, matching the clinical diagnosis and treatment examination information data with the similar diagnosis and treatment cases, and taking the similar diagnosis and treatment cases with the conformity degree greater than a second threshold value as the diagnosis and treatment conforming cases; extracting clinical diagnosis and treatment image information of a patient to be diagnosed, matching the clinical diagnosis and treatment image information with the diagnosis and treatment case, and taking the diagnosis and treatment case with the matching degree larger than a third threshold value as a matched diagnosis and treatment case;
the data uploading module is responsible for uploading the uploaded data, the uploaded data comprises data of patients to be diagnosed and diagnosis and treatment cases, and the data comprises historical clinical pathology information reports, clinical diagnosis and treatment inspection information data and clinical diagnosis and treatment image information;
and the hospital system is responsible for generating the uploaded data and pushing the matched diagnosis and treatment cases obtained by the medical big data system to a diagnostician.
The hospital system generates upload data comprising data of a patient to be diagnosed and diagnosis and treatment cases, the data comprises a historical clinical pathology information report, clinical diagnosis and treatment inspection information data and clinical diagnosis and treatment image information, the upload data are uploaded to a medical big data system through a data upload module, the medical big data system firstly generates a clinical pathology information report of the patient to be diagnosed through describing information of the clinical pathology, and pathology keywords in the report are extracted; performing similarity matching according to the pathology keywords and the pathology keywords in the uploaded data to determine similar diagnosis and treatment cases; determining a corresponding diagnosis and treatment case in the similar diagnosis and treatment cases through clinical diagnosis and treatment inspection information data; the matched diagnosis and treatment cases in the matched diagnosis and treatment cases are determined through the clinical diagnosis and treatment image information, the matched diagnosis and treatment cases are pushed to doctors to assist diagnosis, and through three-step confirmation, the screened data dimensionality is gradually reduced, the screening efficiency is improved, and the screening difficulty is reduced.
The medical big data firstly generates a clinical pathology information report of a patient to be diagnosed through clinical pathology description information of the patient to be diagnosed, extracts pathology keywords in the report, determines a similar diagnosis and treatment case at the moment according to a similarity comparison result of the pathology keywords and the pathology keywords of the diagnosis and treatment case in the uploaded data, and can greatly screen out diagnosis and treatment cases similar to clinical pathology indexes because the clinical diagnosis and treatment inspection information and the clinical diagnosis and treatment image information of different diseases have certain repeatability, so that the efficiency is not high, and the diagnosis and treatment cases can be avoided because the clinical diagnosis and treatment inspection information and the clinical diagnosis and treatment image information are firstly adopted or the clinical diagnosis and treatment inspection information, the clinical diagnosis and treatment image information and the clinical pathology information report are simultaneously adopted, the problem of low efficiency is caused; after obtaining the similar diagnosis and treatment cases, the corresponding diagnosis and treatment cases are obtained by screening through the judgment of the clinical diagnosis and treatment inspection information, the clinical diagnosis and treatment inspection information is more visual and accurate compared with the clinical diagnosis and treatment image information, the corresponding diagnosis and treatment cases can be screened more quickly when being compared, so that the data volume of the finally performed clinical diagnosis and treatment image information is further reduced, the finally matched diagnosis and treatment cases can be obtained through the clinical medical influence information, the matched diagnosis and treatment cases can be pushed to doctors, the diagnosis reliability is improved, the clinical diagnosis and treatment image information with the lowest recognition efficiency is put to the last step through the judgment in steps, the clinical pathology information report with the strongest distinguishing capability is put to the first step, the recognition efficiency can be greatly improved, the speed is higher, the user experience degree is obviously improved, and therefore, the referring analysis of the doctor in the process of diagnosing and treating the patient can be combined with a plurality of diagnosis and treatment cases, the problem that medical knowledge storage and diagnosis and treatment experience accumulation of the doctor who sees a doctor are insufficient is effectively avoided, the accuracy of judging the disease of the patient by the doctor who sees a doctor is improved, the error of judging conclusions of the disease health of the patient and the like is reduced, and the doctor who sees a doctor is assisted to make a diagnosis more quickly, accurately and reasonably.
In another possible embodiment, the condition keyword matching, the clinical examination information data matching, and the clinical image information matching may be performed by using any one or two of them for screening of cases.
According to different symptoms and types, clinical diagnosis and treatment tests or clinical diagnosis and treatment image tests or neither clinical diagnosis and treatment image tests are sometimes not needed, so that in actual operation, only one or two of three kinds of matching can be selected, and extraction of matched diagnosis and treatment cases can be realized.
In another possible embodiment, the sequence of matching the disease condition keywords, matching the clinical examination information data, and matching the clinical examination image information may be adjusted according to different disease conditions.
In another possible embodiment, the medical decision system based on medical big data and artificial intelligence further includes an out-of-hospital service module, which provides an auxiliary medical service and aims at tracking diagnosis and treatment conditions and medicine taking conditions of the user in real time.
Through setting up out-of-hospital service module, solved original patient and see a doctor and treated the back, the problem that the doctor can not be tracked well to the recovery information after patient's treatment, because unable real-time tracking, lead to unable realization doctor and patient's real-time interaction during patient resumes, thereby make the doctor unable real-time master patient and resume the condition, can bring very big influence for subsequent treatment of patient and follow-up visit, through setting up out-of-employee service module, the doctor can realize the grasp to patient's recovery condition, thereby promote patient's gain and satisfaction, more be of value to patient's recovery.
In another possible embodiment, the medical decision system based on medical big data and artificial intelligence further includes: the system comprises a cloud server, a cloud computing processing platform, a data receiving module, a data processing control module, a basic system module and a user side.
The medical big data system, the cloud computing processing platform, the data uploading module, the data receiving module, the data processing control module, the basic system module, the user side, the in-hospital system and the out-of-hospital service module are all connected with the cloud server network; the medical big data system is connected with the data uploading module, and the data uploading module is in communication connection with the data receiving module and the data processing control module; the medical big data system processes the data uploaded by the data uploading module, compresses the data processed by the data processing control module, uploads the data to the medical big data system through the data uploading module, and finally simply processes the compressed data through the data processing control module and stores the data in the medical big data system; the cloud computing processing platform comprises a user authentication module, a service request management module and a large-scale data computing processing center module, wherein the large-scale data computing processing center module consists of a plurality of physical computing machines, and the computing resource allocation module is used for allocating work in computing resources; the basic system module is used for associating important medical data of patients to see a doctor and transmitting the important medical data to the cloud server; the system in the hospital provides medical service in the hospital, and is convenient for patients to see a doctor; the cloud server integrates the services of the basic system module, the in-hospital system and the out-of-hospital service module and provides an interface for the user side; the user side is in butt joint with the cloud server, so that medical service conditions can be known in real time, medical procedures can be followed, medical services can be optimally performed, and latest medical information can be fed back to the user in time.
In another possible embodiment, the method for extracting the disease condition keywords comprises:
s11, performing word segmentation processing on the clinical pathology information report through a word segmentation tool to obtain words of the clinical pathology information report subjected to word segmentation processing;
s12, sending the words of the clinical pathology information report subjected to word segmentation processing into a trained classifier based on an LSTM algorithm for keyword extraction, and extracting the keywords through a TF-IDF algorithm;
s13, respectively assigning a first weight to the keywords extracted by the classifier based on the LSTM algorithm and assigning a second weight to the keywords extracted by the TF-IDF algorithm in a form of expert scoring, adding the weights of the same keywords extracted by the two algorithms, assigning weights corresponding to the extraction algorithms corresponding to different keywords, and taking the keywords with the weights larger than a fifth threshold value as the extracted keywords.
The method combines the modes of extracting keywords by two algorithms of supervised learning and unsupervised learning, gives a first weight to the keywords extracted by a classifier based on the LSTM algorithm in a form of expert scoring, gives a second weight to the keywords extracted by the TF-IDF algorithm, and selects the most appropriate keywords according to the weights, so that the extraction of the keywords can be more combined with a medical background, and the most important keywords for clinical information symptoms in a clinical symptom information report can be more extracted.
In another possible embodiment, the specific steps of performing the similarity matching on the disease condition keywords are as follows:
s21, clustering the disease condition keywords through a clustering algorithm, wherein the disease condition keywords comprise a plurality of compound clustering nodes, and each compound clustering node corresponds to a plurality of keywords;
s22, the disease state key words are obtained, the disease state key words are matched with the compound clustering nodes, and finally matched compound clustering nodes are obtained, so that similarity matching of the key words is achieved.
Because different patients or different doctors have different expression modes and habits on the same symptoms, the matching accuracy and efficiency can be greatly improved in a compound clustering node mode, and the final similar diagnosis and treatment cases can be better screened.
In another possible embodiment, the disease condition keywords include basic information keywords and disease information keywords, the similarity is a weighted sum of similarity of the basic information keywords and similarity of the disease information keywords, and the similarity of the basic information keywords and the similarity of the disease information keywords are determined by an expert algorithm.
The similarity of the two keywords is calculated by dividing the disease condition keywords into the basic information keywords and the disease information keywords, and the similarity of the basic information keywords and the similarity of the disease information keywords have different meanings when the disease similarity is finally determined, so that the weights of the similarities of the different keywords are determined through an expert algorithm, and the similarity of the final case can be reflected more accurately.
In another possible embodiment, the step of calculating the similarity between the basic information keyword and the disease information keyword comprises:
s31, endowing different weights to the compound clustering nodes through an expert algorithm;
s32, matching the basic information keywords and the disease information keywords with the compound cluster nodes respectively, and calculating the similarity of the basic information keywords and the similarity of the disease information keywords according to the weight of the successfully matched compound cluster nodes and the number of the successfully matched compound cluster nodes.
Because different composite clustering nodes have different functions in the final disease judgment, the weights of the different composite clustering nodes are confirmed through an expert algorithm, and the final similarity is calculated according to the weights and the number of the composite clustering nodes successfully matched in a key mode, so that the similarity between two cases can be judged through the similarity, and a foundation is laid for finally confirming to obtain similar cases.
In another possible embodiment, the specific steps of extracting clinical medical image information of a patient to be treated and matching the clinical medical image information according with the medical case include:
s41, classifying the clinical diagnosis and treatment images according to different acquisition modes and different body parts;
s42, clustering the classified clinical diagnosis and treatment images through a clustering algorithm to form different image clustering centers respectively, endowing the corresponding disease states with the images through an expert algorithm, and extracting the associated characteristic quantities of the different image clustering centers through an HOG algorithm.
S43, extracting the features of the image based on the HOG algorithm, and comparing the features with the associated feature quantity of the image clustering center to obtain the image clustering center associated with the features;
s44, according to the multiple cases obtained by the image clustering center and the image recognition method constructed based on the ResNet network, recognizing the clinical diagnosis and treatment images of the patient to be treated to obtain a disease state, further matching the multiple cases according to the disease state to obtain a matching degree, and determining the matched diagnosis and treatment case at the moment when the matching degree is greater than a third threshold value.
In embodiments of the present invention, the term "plurality" means two or more unless explicitly defined otherwise. The terms "mounted," "connected," "secured," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, a removable connection, or an integral connection. Specific meanings of the above terms in the embodiments of the present invention can be understood by those of ordinary skill in the art according to specific situations.
In the description of the embodiments of the present invention, it should be understood that the terms "upper", "lower", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the embodiments of the present invention and simplifying the description, but do not indicate or imply that the referred devices or units must have a specific direction, be configured in a specific orientation, and operate, and thus, should not be construed as limiting the embodiments of the present invention.
In the description herein, the appearances of the phrase "one embodiment," "a preferred embodiment," or the like, are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the embodiments of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The present invention can be configured as follows:
1) the medical decision-making system based on medical big data and artificial intelligence specifically comprises:
the system comprises a medical big data system, a data uploading module and an in-hospital system;
the medical big data system is responsible for processing the uploaded data of the data uploading module, generating a clinical pathology information report of the patient to be treated according to the clinical pathology description information of the patient to be treated, and extracting pathology keywords in the report; performing similarity matching according to the pathology keywords and the pathology keywords in the historical clinical pathology information report of the diagnosis and treatment case in the uploaded data, and taking the diagnosis and treatment case with the similarity higher than a first threshold value as a similar diagnosis and treatment case; extracting clinical diagnosis and treatment examination information data of a patient to be diagnosed, matching the clinical diagnosis and treatment examination information data with the clinical diagnosis and treatment examination information data of similar diagnosis and treatment cases, and taking the similar diagnosis and treatment cases with the conformity degree greater than a second threshold value as the diagnosis and treatment conforming cases; extracting the clinical diagnosis and treatment image information of the patient to be diagnosed, matching the clinical diagnosis and treatment image information with the clinical diagnosis and treatment image information conforming to the diagnosis and treatment case, and taking the conforming diagnosis and treatment case with the matching degree larger than a third threshold value as a matched diagnosis and treatment case;
the data uploading module is responsible for uploading uploaded data, the uploaded data comprise data of patients to be diagnosed and diagnosis and treatment cases, and the data comprise historical clinical pathology information reports, clinical diagnosis and treatment inspection information data and clinical diagnosis and treatment image information;
and the hospital system is responsible for generating uploaded data and pushing the matched diagnosis and treatment cases obtained by the medical big data system to a diagnostician.
2) According to the medical decision-making system based on medical big data and artificial intelligence in the step 1), any one or two of the disease state keyword matching, the clinical diagnosis and treatment inspection information data matching and the clinical diagnosis and treatment image information matching can be adopted for screening the cases.
3) According to the medical decision-making system based on medical big data and artificial intelligence of 1) or 2), the sequence of condition keyword matching, clinical diagnosis and treatment inspection information data matching and clinical diagnosis and treatment image information matching can be adjusted according to different conditions.
4) The medical decision-making system based on the medical big data and the artificial intelligence according to any one of 1) to 3), further comprises an out-of-hospital service module, provides auxiliary medical services, and tracks diagnosis and treatment conditions and medicine taking conditions of a user in real time in a targeted manner.
5) The medical decision-making system based on medical big data and artificial intelligence according to any one of 1) to 4), further comprising: the system comprises a cloud server, a cloud computing processing platform, a data receiving module, a data processing control module, a basic system module and a user side.
6) The medical decision system based on medical big data and artificial intelligence according to any one of 1) to 5), wherein the extraction method of the disease state key words comprises the following steps:
s11, performing word segmentation processing on the clinical pathology information report through a word segmentation tool to obtain words of the clinical pathology information report subjected to word segmentation processing;
s12, sending the words of the clinical pathology information report subjected to word segmentation processing into a trained classifier based on an LSTM algorithm for keyword extraction, and extracting the keywords through a TF-IDF algorithm;
s13, respectively assigning a first weight to the keywords extracted by the classifier based on the LSTM algorithm and assigning a second weight to the keywords extracted by the TF-IDF algorithm in a form of expert scoring, adding the weights of the same keywords extracted by the two algorithms, assigning weights corresponding to the extraction algorithms corresponding to different keywords, and taking the keywords with the weights larger than a fifth threshold value as the extracted keywords.
7. According to the medical decision-making system based on medical big data and artificial intelligence in any one of 1) -6), the specific steps of matching the similarity of the keywords of the disease state are as follows:
s21 clustering the disease condition keywords through a clustering algorithm, wherein the disease condition keywords comprise a plurality of compound clustering nodes, and each compound clustering node corresponds to a plurality of keywords;
s22, obtaining the disease state key words, matching the disease state key words with the compound cluster nodes, and finally obtaining the matched compound cluster nodes, thereby realizing similarity matching of the key words.
8. According to the medical decision making system based on medical big data and artificial intelligence of 7), the disease state keywords comprise basic information keywords and disease information keywords, the similarity is the weighted sum of the similarity of the basic information keywords and the similarity of the disease information keywords, and the weight of the similarity of the basic information keywords and the similarity of the disease information keywords is determined by an expert algorithm.
9. According to 8) the medical decision system based on medical big data and artificial intelligence, the calculation steps of the similarity of the basic information keywords and the similarity of the disease information keywords are as follows:
s31, giving different weights to the compound clustering nodes through an expert algorithm;
s32, matching the basic information keywords and the disease information keywords with the compound cluster nodes respectively, and calculating the similarity of the basic information keywords and the similarity of the disease information keywords according to the weight of the successfully matched compound cluster nodes and the successfully matched number.
10. According to the medical decision-making system based on medical big data and artificial intelligence of 1) -9), the specific steps of extracting the clinical diagnosis and treatment image information of the patient to be diagnosed and matching the clinical diagnosis and treatment image information according with the diagnosis and treatment cases are as follows:
s41, classifying the clinical diagnosis and treatment images according to different acquisition modes and different body parts;
s42, clustering the classified clinical diagnosis and treatment images through a clustering algorithm to form different image clustering centers respectively, endowing the corresponding disease states with the images through an expert algorithm, and extracting the associated characteristic quantities of the different image clustering centers through an HOG algorithm.
S43, extracting features of the image based on the HOG algorithm, and comparing the features with the associated feature quantity of the image clustering center to obtain the image clustering center associated with the features;
s44, according to the multiple cases obtained by the image clustering center and the image recognition method constructed based on the ResNet network, recognizing the clinical diagnosis and treatment images of the patient to be diagnosed to obtain the disease state, further matching the multiple cases according to the disease state to obtain the matching degree, and determining the matched diagnosis and treatment case at the moment until the matching degree is greater than a third threshold value.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the present embodiment by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.
Claims (10)
1. A medical decision-making system based on medical big data and artificial intelligence is characterized by specifically comprising:
the system comprises a medical big data system, a data uploading module and an in-hospital system;
the medical big data system is responsible for processing the uploaded data of the data uploading module, generating a clinical pathology information report of the patient to be treated according to the clinical pathology description information of the patient to be treated, and extracting pathology keywords in the report; performing similarity matching according to the pathology keywords and pathology keywords in historical clinical pathology information reports of the diagnosis and treatment cases in the uploaded data, and taking the diagnosis and treatment cases with similarity higher than a first threshold value as similar diagnosis and treatment cases; extracting clinical diagnosis and treatment examination information data of a patient to be diagnosed, matching the clinical diagnosis and treatment examination information data with the similar diagnosis and treatment cases, and taking the similar diagnosis and treatment cases with the conformity degree greater than a second threshold value as the diagnosis and treatment conforming cases; extracting clinical diagnosis and treatment image information of a patient to be diagnosed, matching the clinical diagnosis and treatment image information with the diagnosis and treatment case, and taking the diagnosis and treatment case with the matching degree larger than a third threshold value as a matched diagnosis and treatment case;
the data uploading module is responsible for uploading the uploaded data, the uploaded data comprises data of patients to be diagnosed and diagnosis and treatment cases, and the data comprises historical clinical pathology information reports, clinical diagnosis and treatment inspection information data and clinical diagnosis and treatment image information;
and the hospital system is responsible for generating the uploaded data and pushing the matched diagnosis and treatment cases obtained by the medical big data system to a diagnostician.
2. The medical big data and artificial intelligence based medical decision making system according to claim 1, wherein the condition keyword matching, the clinical examination information data matching and the clinical image information matching can adopt any one or two of them for case screening.
3. The medical decision making system based on medical big data and artificial intelligence according to claim 1 or 2, wherein the sequence of matching of disease condition keywords, matching of clinical examination information data and matching of clinical examination image information can be adjusted according to different disease conditions.
4. The medical big data and artificial intelligence based medical decision making system as claimed in claim 1, further comprising an out-of-hospital service module providing auxiliary medical services for tracking diagnosis and treatment conditions and medication conditions of the user in real time.
5. The medical big data and artificial intelligence based medical decision making system according to claim 1, wherein the medical big data and artificial intelligence based medical decision making system further comprises: the system comprises a cloud server, a cloud computing processing platform, a data receiving module, a data processing control module, a basic system module and a user side.
6. The medical decision-making system based on medical big data and artificial intelligence according to claim 1, wherein the extraction method of the disease state keywords is as follows:
s11, performing word segmentation processing on the clinical pathology information report through a word segmentation tool to obtain words of the clinical pathology information report subjected to word segmentation processing;
s12, sending the words of the clinical pathology information report subjected to word segmentation processing into a trained classifier based on an LSTM algorithm for keyword extraction, and extracting the keywords through a TF-IDF algorithm;
s13, respectively assigning a first weight to the keywords extracted by the classifier based on the LSTM algorithm and assigning a second weight to the keywords extracted by the TF-IDF algorithm in a form of expert scoring, adding the weights of the same keywords extracted by the two algorithms, assigning weights corresponding to the extraction algorithms corresponding to different keywords, and taking the keywords with the weights larger than a fifth threshold value as the extracted keywords.
7. The medical decision-making system based on medical big data and artificial intelligence according to claim 1, wherein the similarity matching of the disease state keywords comprises the following specific steps:
s21, clustering the disease condition keywords through a clustering algorithm, wherein the disease condition keywords comprise a plurality of compound clustering nodes, and each compound clustering node corresponds to a plurality of keywords;
s22, the disease state key words are obtained, the disease state key words are matched with the compound clustering nodes, and finally matched compound clustering nodes are obtained, so that similarity matching of the key words is achieved.
8. The medical big data and artificial intelligence based medical decision making system according to claim 7, wherein the disease condition keywords comprise basic information keywords and disease information keywords, the similarity is a weighted sum of similarity of the basic information keywords and similarity of the disease information keywords, and the weight of similarity of the basic information keywords and the similarity of the disease information keywords is determined by an expert algorithm.
9. The medical decision-making system based on medical big data and artificial intelligence of claim 8, wherein the calculating step of the similarity of the basic information keywords and the similarity of the disease information keywords is as follows:
s31, endowing different weights to the compound clustering nodes through an expert algorithm;
s32, matching the basic information keywords and the disease information keywords with the compound cluster nodes respectively, and calculating the similarity of the basic information keywords and the similarity of the disease information keywords according to the weight of the successfully matched compound cluster nodes and the number of the successfully matched compound cluster nodes.
10. The medical decision making system based on medical big data and artificial intelligence as claimed in claim 1, wherein the specific steps of extracting clinical diagnosis image information of a patient to be treated and matching the clinical diagnosis image information according with a diagnosis case are as follows:
s41, classifying the clinical diagnosis and treatment images according to different acquisition modes and different body parts;
s42, clustering the classified clinical diagnosis and treatment images through a clustering algorithm to form different image clustering centers respectively, endowing the corresponding disease states with the images through an expert algorithm, and extracting the associated characteristic quantities of the different image clustering centers through an HOG algorithm;
s43, extracting the features of the image based on the HOG algorithm, and comparing the features with the associated feature quantity of the image clustering center to obtain the image clustering center associated with the features;
s44, according to the multiple cases obtained by the image clustering center and the image recognition method constructed based on the ResNet network, recognizing the clinical diagnosis and treatment images of the patient to be treated to obtain a disease state, further matching the multiple cases according to the disease state to obtain a matching degree, and determining the matched diagnosis and treatment case at the moment when the matching degree is greater than a third threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210756677.2A CN114842977B (en) | 2022-06-30 | 2022-06-30 | Medical decision-making system based on medical big data and artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210756677.2A CN114842977B (en) | 2022-06-30 | 2022-06-30 | Medical decision-making system based on medical big data and artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114842977A true CN114842977A (en) | 2022-08-02 |
| CN114842977B CN114842977B (en) | 2022-10-21 |
Family
ID=82573379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210756677.2A Active CN114842977B (en) | 2022-06-30 | 2022-06-30 | Medical decision-making system based on medical big data and artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114842977B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116013552A (en) * | 2023-03-27 | 2023-04-25 | 慧医谷中医药科技(天津)股份有限公司 | Remote consultation method and system based on blockchain |
| CN116246779A (en) * | 2023-05-10 | 2023-06-09 | 潍坊护理职业学院 | Dental diagnosis and treatment scheme generation method and system based on user image data |
| CN117174234A (en) * | 2023-11-03 | 2023-12-05 | 南京都昌信息科技有限公司 | Medical text data analysis method and system |
| CN117275752A (en) * | 2023-11-20 | 2023-12-22 | 中国人民解放军总医院 | Case clustering analysis method and system based on machine learning |
| CN117690581A (en) * | 2023-12-13 | 2024-03-12 | 江苏济远医疗科技有限公司 | Disease inquiry process auxiliary information generation method based on large language model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678504A (en) * | 2013-11-19 | 2014-03-26 | 西安华海盈泰医疗信息技术有限公司 | Similarity-based breast image matching image searching method and system |
| CN110277165A (en) * | 2019-06-27 | 2019-09-24 | 清华大学 | Aided diagnosis method, device, equipment and storage medium based on figure neural network |
| CN111310072A (en) * | 2020-01-17 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Keyword extraction method, keyword extraction device and computer-readable storage medium |
| US20210124967A1 (en) * | 2018-08-24 | 2021-04-29 | Advanced New Technologies Co., Ltd. | Method and apparatus for sample labeling, and method and apparatus for identifying damage classification |
| CN114220514A (en) * | 2022-02-22 | 2022-03-22 | 橙意家人科技（天津）有限公司 | Internet hospital patient diagnosis and treatment data analysis processing method, equipment and storage medium |
-
2022
- 2022-06-30 CN CN202210756677.2A patent/CN114842977B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678504A (en) * | 2013-11-19 | 2014-03-26 | 西安华海盈泰医疗信息技术有限公司 | Similarity-based breast image matching image searching method and system |
| US20210124967A1 (en) * | 2018-08-24 | 2021-04-29 | Advanced New Technologies Co., Ltd. | Method and apparatus for sample labeling, and method and apparatus for identifying damage classification |
| CN110277165A (en) * | 2019-06-27 | 2019-09-24 | 清华大学 | Aided diagnosis method, device, equipment and storage medium based on figure neural network |
| CN111310072A (en) * | 2020-01-17 | 2020-06-19 | 腾讯科技（深圳）有限公司 | Keyword extraction method, keyword extraction device and computer-readable storage medium |
| CN114220514A (en) * | 2022-02-22 | 2022-03-22 | 橙意家人科技（天津）有限公司 | Internet hospital patient diagnosis and treatment data analysis processing method, equipment and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116013552A (en) * | 2023-03-27 | 2023-04-25 | 慧医谷中医药科技(天津)股份有限公司 | Remote consultation method and system based on blockchain |
| CN116246779A (en) * | 2023-05-10 | 2023-06-09 | 潍坊护理职业学院 | Dental diagnosis and treatment scheme generation method and system based on user image data |
| CN117174234A (en) * | 2023-11-03 | 2023-12-05 | 南京都昌信息科技有限公司 | Medical text data analysis method and system |
| CN117174234B (en) * | 2023-11-03 | 2024-01-05 | 南京都昌信息科技有限公司 | Medical text data analysis method and system |
| CN117275752A (en) * | 2023-11-20 | 2023-12-22 | 中国人民解放军总医院 | Case clustering analysis method and system based on machine learning |
| CN117275752B (en) * | 2023-11-20 | 2024-03-22 | 中国人民解放军总医院 | Case clustering analysis method and system based on machine learning |
| CN117690581A (en) * | 2023-12-13 | 2024-03-12 | 江苏济远医疗科技有限公司 | Disease inquiry process auxiliary information generation method based on large language model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114842977B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114842977B (en) | Medical decision-making system based on medical big data and artificial intelligence | |
| Reddy et al. | Hybrid firefly-bat optimized fuzzy artificial neural network based classifier for diabetes diagnosis. | |
| Duggal et al. | Prediction of thyroid disorders using advanced machine learning techniques | |
| JP2021511584A (en) | Systems and methods for modeling probability distributions | |
| CN117457147B (en) | Personalized nursing planning method and system for rehabilitation patient | |
| CN112017789B (en) | Triage data processing method, triage data processing device, triage data processing equipment and triage data processing medium | |
| CN110111884A (en) | A kind of man-machine coordination intelligent medical treatment aid decision-making system based on CMKMC | |
| WO2022233121A1 (en) | Unsupervised medical behavior compliance assessment method based on electronic medical record | |
| KR20180002234A (en) | A smart examination apparatus for dementia early diagnosis and the method by using the same | |
| CN114639479A (en) | Intelligent diagnosis auxiliary system based on medical knowledge map | |
| CN115579104A (en) | Artificial intelligence-based liver cancer full-course digital management method and system | |
| Sindhiya et al. | A survey on genetic algorithm based feature selection for disease diagnosis system | |
| CN117542474A (en) | Remote nursing monitoring system and method based on big data | |
| Salih et al. | Benchmarking framework for COVID-19 classification machine learning method based on fuzzy decision by opinion score method | |
| CN109192312B (en) | Intelligent management system and method for adverse events of heart failure patients | |
| Cheng et al. | Combining knowledge extension with convolution neural network for diabetes prediction | |
| Koktas et al. | Ensemble classifiers for medical diagnosis of knee osteoarthritis using gait data | |
| Gothane | Data mining classification on hypo thyroids detection: Association women outnumber men | |
| Jiang et al. | A cloud-based training and evaluation system for facial paralysis rehabilitation | |
| CN112568911A (en) | Method and equipment for classifying electrocardiogram data and device with storage function | |
| Alagarsamy et al. | Smart System for Predicting the Diabetes using Machine Learning Techniques | |
| Hossain et al. | Comparative study of deep learning algorithms for the detection of facial paralysis | |
| CN117373658B (en) | Data processing-based auxiliary diagnosis and treatment system and method for depression | |
| AU2021102832A4 (en) | System & method for automatic health prediction using fuzzy based machine learning | |
| Jurisica et al. | Extending case-based reasoning by discovering and using image features in IVF |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |