CN113838573A - Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium - Google Patents
Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113838573A CN113838573A CN202111084156.9A CN202111084156A CN113838573A CN 113838573 A CN113838573 A CN 113838573A CN 202111084156 A CN202111084156 A CN 202111084156A CN 113838573 A CN113838573 A CN 113838573A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- medical record
- ranking
- information
- candidate
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The application discloses a clinical auxiliary decision-making diagnosis self-learning method, device, equipment and medium, and relates to the technical field of clinical decision-making in the self-learning field and AI medical field. The specific implementation scheme is as follows: structuring the medical record information to be processed to obtain the entity information of the disease state of the medical record information to be processed; acquiring at least one candidate diagnosis and the recall probability of each candidate diagnosis according to the text information and the physical information of the medical record information to be processed; acquiring the region ordering characteristics of a current region where a clinical assistant decision-making diagnosis recommendation system is deployed; and ranking at least one candidate diagnosis based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis, and performing diagnosis self-learning according to the ranking result. According to the method and the device, the diagnosis recommendation result is more consistent with the diagnosis characteristics of the current region, the problem of region differentiation of diagnosis recommendation is solved to a certain extent, and the accuracy of clinical assistant decision diagnosis is improved.
Description
Technical Field
The present application relates to the field of clinical decision making technology in the field of self-learning and AI medical treatment, and more particularly, to a method, apparatus, device and storage medium for clinical assisted decision making, diagnosis and self-learning.
Background
With the continuous fusion of big data and medical treatment, a Clinical Decision Support System (CDSS) is becoming an important means for improving medical quality. The CDSS is based on the electronic medical record contents of patients, such as admission records, clinic records, disease course records, examination and inspection results, medical advice, operation records, nursing records and the like, advanced artificial intelligence technology is utilized to learn high-quality medical records with medical expert labels, and the algorithm can automatically recommend diseases which the patients possibly suffer from, so that doctors are assisted in making clinical diagnosis decisions, and the misdiagnosis missing probability of the doctors is reduced.
Disclosure of Invention
The application provides a clinical assistant decision-making diagnosis self-learning method, a device, equipment and a storage medium.
According to a first aspect of the application, there is provided a clinical assistant decision making, diagnosis and self-learning method comprising:
structuring medical record information to be processed to obtain entity information of the medical conditions of the medical record information to be processed;
acquiring at least one candidate diagnosis and the recall probability of each candidate diagnosis according to the text information of the medical record information to be processed and the entity information of the disease state;
acquiring the region ordering characteristics of a current region where a clinical assistant decision-making diagnosis recommendation system is deployed;
and ranking the at least one candidate diagnosis based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis, and performing diagnosis self-learning according to the ranking result.
According to a second aspect of the present application, there is provided a clinical assistant decision making diagnosis self-learning apparatus comprising:
the structured processing module is used for carrying out structured processing on medical record information to be processed to obtain entity information of the medical conditions of the medical record information to be processed;
the recall module is used for acquiring at least one candidate diagnosis and the recall probability of each candidate diagnosis according to the text information of the medical record information to be processed and the entity information of the disease state;
the acquisition module is used for acquiring the region ordering characteristics of the current region where the clinical assistant decision-making diagnosis recommendation system is deployed;
and the self-learning module is used for sequencing the at least one candidate diagnosis based on the region sequencing characteristics of the current region and the recall probability of each candidate diagnosis and performing diagnosis self-learning according to the sequencing result.
According to a third aspect of the present application, there is provided an electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of clinical assisted decision diagnostic self-learning of the first aspect.
According to a fourth aspect of the present application, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of clinical assisted decision making, diagnostic, self-learning of the aforementioned first aspect.
According to a fifth aspect of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the clinical assistant decision making, diagnostic, self-learning method according to the aforementioned first aspect.
According to the technical scheme of the application, the medical record information to be processed, which embodies the diagnosis characteristics of the current region, is subjected to structured processing to obtain the physical information of the medical record information to be processed, deep learning modeling is carried out on the basis of the text information and the physical information of the medical record information to be processed, and at least one candidate diagnosis and the recall probability of each candidate diagnosis are obtained; and sequencing at least one candidate diagnosis based on the region sequencing characteristics of the current region and the recall probability of each candidate diagnosis to obtain a sequencing result suitable for the candidate diagnosis of the current region, and performing diagnosis self-learning according to the sequencing result, so that the diagnosis recommendation result is more in line with the diagnosis characteristics of the current region, the problem of region differentiation of diagnosis recommendation is solved to a certain extent, and the accuracy of clinical auxiliary decision diagnosis is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present application, nor do they limit the scope of the present application. Other features of the present application will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
FIG. 1 is a flow chart of a method for clinical assisted decision-making, diagnostic, self-learning, provided in accordance with an implementation of the present application;
FIG. 2 is a flow chart for obtaining a region ranking characteristic of a current region for deploying a clinical assistant decision diagnostic recommendation system in accordance with an implementation of the present application;
FIG. 3 is a flow chart for deriving the probability of co-occurrence of disease incidence, condition and diagnosis in medical records, according to an embodiment of the present application;
FIG. 4 is a flow chart of ranking at least one candidate diagnosis and performing diagnostic self-learning based on the ranking results provided in accordance with an implementation of the present application;
FIG. 5 is a flow chart of another method of clinical assisted decision making, diagnostic, self-learning provided in accordance with an implementation of the present application;
FIG. 6 is a block diagram of a clinical assistant decision making, diagnosis and self-learning device provided in accordance with an implementation of the present application;
FIG. 7 is a block diagram of another clinical assistant decision making, diagnosis and self-learning device provided in accordance with an implementation of the present application;
FIG. 8 is a block diagram of an electronic device provided in accordance with implementations of the present application to implement a clinical assisted decision making, diagnostic, and self-learning method.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
With the continuous fusion of big data and medical treatment, a Clinical Decision Support System (CDSS) is becoming an important means for improving medical quality. At present, most clinical assistant decision support systems construct a general clinical assistant diagnosis recommendation system, however, due to regional differences of disease incidence, differences of doctor diagnosis habits in different regions, and the like, recommended diagnosis results given by expected algorithms of the same medical record in different regions may be different. Therefore, when the actual region falls to the ground, the system needs to establish the region self-learning capability of recommending diagnosis, so that diagnosis recommended by the algorithm can accord with the diagnosis characteristics of the current region.
In the prior art, the technical scheme of self-learning of the diagnosis recommendation area mainly comprises two types: using traditional machine learning models and using complex machine learning models. For a clinical assistant decision support system using a traditional machine learning model, a self-learning strategy directly updates a model recommendation result by counting medical record feature distribution of a current region; for a clinical assistant decision support system using a complex machine learning model (such as a convolutional neural network), most of electronic medical record data of a corresponding region needs to be re-analyzed, such as chief complaints, current medical history, assistant examination, physical examination, past history and the like, the medical record data are manually labeled, and then the model is retrained based on the labeled data to achieve the purpose of self-learning of a diagnosis region.
However, for a clinical assistant decision support system using a traditional machine learning model, such as a decision tree, fast regional self-learning can be achieved ideally, but the traditional model has poor actual floor diagnosis effect due to model complexity and the like. Secondly, for a clinical assistant decision support system using a complex machine learning model (such as a convolutional neural network), the model needs to be trained and updated after data is re-labeled, so that the cost is high, the period is long, and the flexibility is insufficient.
To this end, the present application provides a clinical assistant decision making diagnostic self-learning method, system, device and storage medium. In particular, the clinical assistant decision making diagnosis self-learning method, system, device and storage medium of the embodiments of the present application are described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for clinical assistant decision making, diagnosis and self-learning according to an embodiment of the application. It should be noted that the clinical assistant decision making diagnosis self-learning method of the embodiment of the present application can be applied to the clinical assistant decision making diagnosis self-learning device of the embodiment of the present application, and the clinical assistant decision making diagnosis self-learning device can be configured on an electronic device.
As shown in FIG. 1, the clinical assistant decision making diagnosis self-learning method may include the following steps:
It should be noted that the information to be processed may include the content of a chief complaint, a current medical history, an auxiliary examination, a physical examination, a past history, and the like. Because the medical record information to be processed is basically in a pure text form, in order to better analyze and understand the medical record information to be processed, entity analysis and extraction can be performed on the pure text in the medical record information to be processed based on a natural language processing technology, so as to obtain the entity information of the medical conditions of the medical record information to be processed. The entity information of the disease state can include information such as disease name, symptom, sign, inspection result, operation, medication, examination result, etc.
And step 102, acquiring at least one candidate diagnosis and the recall probability of each candidate diagnosis according to the text information and the physical information of the state of illness of the medical record information to be processed.
Optionally, in some embodiments of the present application, the candidate diagnoses and the recall probability of each candidate diagnosis may be obtained through deep learning modeling according to text information and condition entity information of medical record information to be processed. As an example, deep learning modeling can be carried out based on text information and physical information of the state of illness of medical record information to be processed, and diagnosis derivation is carried out after modeling features are fused, so that diseases possibly suffered by a patient can be returned to the greatest extent. For modeling of text information of medical record information to be processed, the text information of the medical record information to be processed can be split according to words, each word is coded, and a word vector can be generated by using a structure of a convolutional neural network to obtain text characteristic representation; for modeling of the entity information of the disease state, a medical knowledge graph can be constructed through the co-occurrence relation of the entity information of the disease state and diagnosis in a large number of medical records, and a derivative graph corresponding to each medical record is generated on the basis of the medical knowledge graph, wherein the derivative graph is formed by combining a plurality of sub-graphs, and each sub-graph describes a set of one type of disease state of the patient in the current visit. The sub-map is then encoded based on a hierarchical attention mechanism to obtain a condition entity characteristic representation of the medical record. Therefore, based on the text feature representation and the disease state entity information feature representation, at least one candidate diagnosis and the recall probability of each candidate diagnosis can be obtained, and the recall probability of each candidate diagnosis can be recorded as Pr。
And 103, acquiring the region ordering characteristics of the current region where the clinical assistant decision-making diagnosis recommendation system is deployed.
Optionally, in some embodiments of the present application, the region ranking characteristics of the current region may be obtained from a region ranking characteristics library by determining current region information for deploying the clinical assistant decision diagnosis recommendation system. Specific implementation can be seen in the description of the following embodiments.
And 104, ranking at least one candidate diagnosis based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis, and performing diagnosis self-learning according to the ranking result.
Optionally, in some embodiments of the present application, at least one candidate diagnosis may be ranked based on the region ranking features of the current region and the recall probability of each candidate diagnosis; acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result; acquiring a real diagnosis result aiming at medical record information to be processed; and performing diagnosis self-learning according to the diagnosis recommendation result and the real diagnosis result. Specific implementation can be seen in the description of the following embodiments.
According to the clinical assistant decision-making diagnosis self-learning method, the medical record information to be processed which embodies the diagnosis characteristics of the current region is subjected to structured processing, the medical condition entity information of the medical record information to be processed is obtained, deep learning modeling is carried out on the basis of the text information and the medical condition entity information of the medical record information to be processed, and at least one candidate diagnosis and the recall probability of each candidate diagnosis are obtained; and sequencing at least one candidate diagnosis based on the region sequencing characteristics of the current region and the recall probability of each candidate diagnosis to obtain a sequencing result suitable for the candidate diagnosis of the current region, and performing diagnosis self-learning according to the sequencing result, so that the diagnosis recommendation result is more in line with the diagnosis characteristics of the current region, the problem of region differentiation of diagnosis recommendation is solved to a certain extent, and the accuracy of clinical auxiliary decision diagnosis is improved.
It should be noted that, since the incidence of disease and the probability of the co-occurrence of the disease condition and the diagnosis in the medical record are important indicators of the regional localization ranking, in some embodiments of the present application, the regional ranking features may include the incidence of disease and the probability of the co-occurrence of the disease condition and the diagnosis in the medical record. As an example, as shown in fig. 2, an implementation process for obtaining a region ranking feature of a current region where a clinical assistant decision-making diagnosis recommendation system is deployed according to an embodiment of the present application may include the following steps:
Since the incidence probability of each disease may be different in different regions, the disease incidence may be an important index for the regional ranking, including the incidence characteristics such as the population and sex. In addition, the co-occurrence probability of the medical record condition and the diagnosis also represents the regional characteristics of the diagnosis, such as symptoms, signs, examination and the like. Disease incidence and co-occurrence probability of the condition and diagnosis are two important indicators in regional ranking. As an example, as shown in fig. 3, the implementation process of self-learning medical record logs based on bayesian statistics to obtain co-occurrence probability of disease incidence, disease state and diagnosis in medical records according to the embodiment of the present application may include the following steps:
Optionally, in some embodiments of the present application, structured and structured field statistics can be performed on the base level CDSS medical record log through the CDSS central control, so as to obtain the condition entity information and the structured field statistics of the medical record log. Wherein, the condition entity information may include: diagnosis (standard name), history of medical history, positive symptoms, abnormal signs, sex of patient, age of patient, and pregnancy status.
It should be noted that, in some embodiments of the present application, the condition may include symptoms, abnormal signs, examinations, tests, and other information, the diagnosis and the condition are related to each other by screening, and irrelevant relationships are filtered to obtain the relationship information of the diagnosis and the condition statistically.
And step 303, voting and counting the structured field statistical information and the relationship information between diagnosis and disease state based on Bayesian statistics to obtain the disease incidence and the co-occurrence probability between disease state and diagnosis in the medical record.
In the examples of this application, the incidence of disease in a medical record can be recorded as P1Co-occurrence of the condition with the diagnosisProbability is denoted as P2。
Therefore, the medical record logs can be self-learned through the steps 301 to 303 based on the bayesian statistics, so that the co-occurrence probability of disease incidence, disease state and diagnosis in the regional medical record learned in the self-learning stage is continuously updated into the regional ranking feature library, and the features in the regional ranking feature library can play a forward role in the ranking stage.
And step 203, updating the disease incidence, the disease state and the diagnosis co-occurrence probability in the medical record into a regional sequencing feature library.
And step 204, determining the current region information of the clinical assistant decision diagnosis recommendation system.
In some embodiments of the present application, the ranking probability of each candidate diagnosis may be calculated based on a ranking probability calculation model, and diagnosis self-learning may be performed according to the ranking result, adjusting parameters in the ranking probability calculation model. As an example, as shown in fig. 4, an implementation process of ranking at least one candidate diagnosis based on a region ranking characteristic of a current region and a recall probability of each candidate diagnosis and performing diagnostic self-learning according to a ranking result provided by an embodiment of the present application may include the following steps:
Alternatively, in the embodiment of the present application, the following ranking probability calculation model may be used to calculate the ranking probability P of each candidate diagnosisfinal：
Pfinal＝σrPr+σ1P1+σ1P2
Wherein, PrProbability of recall for a candidate diagnosis, σrProbability of recall P for candidate diagnosisrWeight of (1), P1Disease incidence, σ, for candidate diagnosis1For candidate diagnosisIncidence of disease P1Weight of (1), P2Probability of co-occurrence of condition and diagnosis as candidate diagnosis2Probability of co-occurrence of condition and diagnosis for candidate diagnosis2The weight of (c).
And step 403, acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result.
Optionally, in some embodiments of the present application, the ranking probability P in the ranking result may be determinedfinalAnd the candidate diagnosis with the maximum value is used as a diagnosis recommendation result of the medical record information to be processed.
As an example, in some embodiments of the present application, the physician will refer to the diagnosis recommendation obtained from the ranking results, in combination with the actual condition and the correct diagnosis made from the examination results.
And step 405, calculating a loss value according to the diagnosis recommendation result and the real diagnosis result.
And step 406, adjusting model parameters in the ranking probability calculation model according to the loss values.
That is, the recall probability P for the candidate diagnosis in the ranking probability calculation model is adjusted according to the loss valuerWeight σ ofrDisease incidence P of candidate diagnosis1Weight σ of1Probability of co-occurrence P of candidate diagnosed condition and diagnosis2Weight σ of2. And diagnosis self-learning is carried out according to the sequencing result, so that the coincidence rate of the diagnosis recommendation result given by the sequencing probability calculation model and the real diagnosis result given by an expert can be improved. The coincidence rate means that the diagnosis recommendation result given by the ranking probability calculation model is consistent with the real diagnosis result given by the expert, is an alias of each other or is in a top-bottom relationship with each other.
In the embodiment of the present application, whether to perform the region ranking on the candidate diagnoses may be selected according to the actual situation of each region. As an example, as shown in FIG. 5, the clinical assistant decision making diagnosis self-learning method provided by the embodiment of the present application may include the following steps:
and step 501, performing structuring processing on medical record information to be processed to obtain entity information of the medical condition of the medical record information to be processed.
And step 503, selecting whether to perform area self-learning. If the regional self-learning is performed, go to step 504; if the region self-learning is not selected, step 505 is executed.
As an example, in some embodiments of the present application, a button may be provided in the model application to select whether region self-learning is required according to the actual conditions of the region.
And step 504, judging whether the regional self-learning requirement is met. If the regional self-learning requirement is met, executing step 507; if the regional self-learning requirement is not satisfied, step 505 is executed.
As an example, in some embodiments of the present application, the regional self-learning requirement may be that the case sample reaches some preset threshold. If the number of case samples is too small, regional self-learning based on historical cases cannot be performed.
And 505, sorting at least one candidate diagnosis according to the recall probability of each candidate diagnosis.
And step 506, acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result.
That is, if the region self-learning is not required or the region self-learning condition is not satisfied, the diagnosis recommendation result may be obtained by ranking based on the recall probability.
And step 507, acquiring a medical record log in the current area.
And step 508, carrying out structured and structured field statistics on the medical record log to obtain the entity information of the medical conditions and the structured field statistical information of the medical record log.
And 510, voting and counting the structured field statistical information and the relationship information between diagnosis and disease state based on Bayesian statistics to obtain the disease incidence and the co-occurrence probability between disease state and diagnosis in the medical record.
And step 512, determining the current region information for deploying the clinical assistant decision diagnosis recommendation system.
And 514, calculating the ranking probability of each candidate diagnosis by adopting a ranking probability calculation model based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis.
And 516, acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result.
And 517, acquiring a real diagnosis result aiming at the medical record information to be processed.
And 518, calculating a loss value according to the diagnosis recommendation result and the real diagnosis result.
And step 519, adjusting model parameters in the sequencing probability calculation model according to the loss values.
In this embodiment of the present application, steps 501 to 502, and steps 507 to 519 may be implemented by any one of the manners in the embodiments of the present application, and this application is not specifically limited and will not be described again.
According to the clinical assistant decision-making diagnosis self-learning method, the medical record information to be processed which embodies the diagnosis characteristics of the current region is subjected to structured processing, the medical condition entity information of the medical record information to be processed is obtained, deep learning modeling is carried out on the basis of the text information and the medical condition entity information of the medical record information to be processed, and at least one candidate diagnosis and the recall probability of each candidate diagnosis are obtained; selecting whether to perform regional self-learning according to the actual condition of the current region, if not, sequencing at least one candidate diagnosis according to the recall probability of each candidate diagnosis, and acquiring a diagnosis recommendation result of medical record information to be processed according to the sequencing result; if the regional self-learning is carried out, judging whether the regional self-learning requirement is met, if the regional self-learning requirement is not met, if the medical record samples are not large in quantity and the regional self-learning cannot be carried out, sequencing according to the recall probability, and obtaining a diagnosis recommendation result of the medical record information to be processed; if the requirement of the regional self-learning is met, based on the regional ranking characteristics of the current region and the recall probability of each candidate diagnosis, the ranking probability of each candidate diagnosis is calculated by adopting a ranking probability calculation model, at least one candidate diagnosis is ranked to obtain a ranking result suitable for the candidate diagnosis of the current region, the diagnostic self-learning is carried out according to the ranking result, and model parameters in the ranking probability calculation model are adjusted, so that the diagnosis recommendation result is more consistent with the diagnosis characteristics of the current region, the problem of regional differentiation of the diagnosis recommendation is solved to a certain extent, and the accuracy of the clinical auxiliary decision-making diagnosis is improved.
FIG. 6 is a block diagram of a clinical assistant decision making diagnosis self-learning device according to an embodiment of the present application. As shown in FIG. 6, the clinical assistant decision making diagnosis self-learning apparatus may include a structured processing module 601, a recall module 602, an acquisition module 603 and a self-learning module 604.
Specifically, the structured processing module 601 is configured to perform structured processing on medical record information to be processed, so as to obtain entity information of a medical condition of the medical record information to be processed.
The recall module 602 is configured to obtain at least one candidate diagnosis and a recall probability of each candidate diagnosis according to text information and medical condition entity information of medical record information to be processed.
An obtaining module 603 configured to obtain a region ranking feature of a current region where the clinical assistant decision making diagnosis recommendation system is deployed.
In some embodiments of the present application, the obtaining module 603 is specifically configured to: determining current region information for deploying a clinical assistant decision-making diagnosis recommendation system; and acquiring the region sorting feature of the current region from the region sorting feature library according to the current region information.
The self-learning module 604 is configured to rank at least one candidate diagnosis based on the region ranking features of the current region and the recall probability of each candidate diagnosis, and perform diagnosis self-learning according to the ranking result.
In some embodiments of the present application, the self-learning module 604 is specifically configured to: ranking at least one candidate diagnosis based on the region ranking features of the current region and the recall probability of each candidate diagnosis; acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result; acquiring a real diagnosis result aiming at medical record information to be processed; and performing diagnosis self-learning according to the diagnosis recommendation result and the real diagnosis result.
In some embodiments of the present application, the self-learning module 604 is further specifically configured to: calculating the ranking probability of each candidate diagnosis by adopting a ranking probability calculation model based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis; ranking the at least one candidate diagnosis according to the ranking probability of each candidate diagnosis.
In some embodiments of the present application, the self-learning module 604 is further specifically configured to: calculating a loss value according to the diagnosis recommendation result and the real diagnosis result; and adjusting model parameters in the sequencing probability calculation model according to the loss value.
Optionally, in some embodiments of the present application, the regional ranking features include disease incidence, co-occurrence probability of illness state and diagnosis in medical records, and as shown in fig. 7, the clinical assistant decision making diagnosis self-learning apparatus may further include a feature updating module 705. The feature update module 705 is specifically configured to: and acquiring medical record logs in the current region, self-learning the medical record logs based on Bayesian statistics to obtain the co-occurrence probability of disease incidence, disease state and diagnosis in the medical record, and updating the co-occurrence probability of disease incidence, disease state and diagnosis in the medical record into a region sequencing feature library.
In some embodiments of the present application, the feature update module 705 is specifically configured to: structured and structured field statistics are carried out on the medical record log to obtain the entity information of the disease state and the structured field statistical information of the medical record log; screening the correlation between diagnosis and the disease state according to the disease diagnosis relationship constructed based on the medical knowledge map and the entity information of the disease state in the medical record log so as to obtain the correlation information between diagnosis and the disease state by statistics; voting statistics is carried out on the structured field statistical information and the relation information between diagnosis and disease conditions based on Bayesian statistics to obtain the disease incidence and the co-occurrence probability between disease conditions and diagnosis in medical records.
Wherein 701-704 in fig. 7 and 601-604 in fig. 6 have the same functions and structures.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
According to the clinical auxiliary decision-making diagnosis self-learning device, the medical record information to be processed, which embodies the diagnosis characteristics of the current region, is subjected to structured processing to obtain the physical information of the medical record information to be processed, deep learning modeling is carried out on the basis of the text information and the physical information of the medical record information to be processed, and at least one candidate diagnosis and the recall probability of each candidate diagnosis are obtained; selecting whether to perform regional self-learning according to the actual condition of the current region, if not, sequencing at least one candidate diagnosis according to the recall probability of each candidate diagnosis, and acquiring a diagnosis recommendation result of medical record information to be processed according to the sequencing result; if the regional self-learning is carried out, judging whether the regional self-learning requirement is met, if the regional self-learning requirement is not met, if the medical record samples are not large in quantity and the regional self-learning cannot be carried out, sequencing according to the recall probability, and obtaining a diagnosis recommendation result of the medical record information to be processed; if the requirement of the regional self-learning is met, based on the regional ranking characteristics of the current region and the recall probability of each candidate diagnosis, the ranking probability of each candidate diagnosis is calculated by adopting a ranking probability calculation model, at least one candidate diagnosis is ranked to obtain a ranking result suitable for the candidate diagnosis of the current region, the diagnostic self-learning is carried out according to the ranking result, and model parameters in the ranking probability calculation model are adjusted, so that the diagnosis recommendation result is more consistent with the diagnosis characteristics of the current region, the problem of regional differentiation of the diagnosis recommendation is solved to a certain extent, and the accuracy of the clinical auxiliary decision-making diagnosis is improved.
There is also provided, in accordance with an embodiment of the present application, an electronic device, a readable storage medium, and a computer program product.
FIG. 8 is a block diagram of an electronic device for implementing a method for clinical assisted decision making, diagnostic, self-learning, according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 8, the electronic apparatus includes: one or more processors 801, memory 802, and interfaces for connecting the various components, including a high speed interface and a low speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). Fig. 8 illustrates an example of a processor 801.
The memory 802 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the clinical assistant decision diagnostic self-learning method provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the clinical assistant decision making diagnostic self-learning method provided herein.
The memory 802 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created by use of an electronic device to implement a clinical assistant decision making diagnostic self-learning method, and the like. Further, the memory 802 may include high speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 802 optionally includes memory located remotely from the processor 801, which may be connected via a network to an electronic device for implementing the clinical assistant decision making diagnostic self-learning method. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device to implement the clinical assistant decision making diagnostic self-learning method may further comprise: an input device 803 and an output device 804. The processor 801, the memory 802, the input device 803, and the output device 804 may be connected by a bus or other means, and are exemplified by a bus in fig. 8.
The input device 803 may receive input numeric or character information and generate key signal inputs related to user settings and function controls of an electronic device used to implement the clinical assisted decision making diagnostic self-learning method, such as an input device such as a touch screen, keypad, mouse, track pad, touch pad, pointer stick, one or more mouse buttons, track ball, joystick, or the like. The output devices 804 may include a display device, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: embodied in one or more computer programs that when executed by a processor implement the clinical assistant decision making, diagnostic, self-learning methods described in the embodiments above, the one or more computer programs being executable and/or interpretable on a programmable system including at least one programmable processor, which may be a special or general purpose programmable processor, may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), the internet, and blockchain networks.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The Server can be a cloud Server, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (17)
1. A clinical assistant decision making diagnostic self-learning method comprising:
structuring medical record information to be processed to obtain entity information of the medical conditions of the medical record information to be processed;
acquiring at least one candidate diagnosis and the recall probability of each candidate diagnosis according to the text information of the medical record information to be processed and the entity information of the disease state;
acquiring the region ordering characteristics of a current region where a clinical assistant decision-making diagnosis recommendation system is deployed;
and ranking the at least one candidate diagnosis based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis, and performing diagnosis self-learning according to the ranking result.
2. The method of claim 1, wherein the obtaining a region ordering feature of a current region in which the clinical assistant decision diagnostic recommendation system is deployed comprises:
determining current region information for deploying a clinical assistant decision-making diagnosis recommendation system;
and acquiring the region sorting feature of the current region from a region sorting feature library according to the current region information.
3. The method of claim 2, wherein the regional ranking features include disease incidence, co-occurrence probability of condition and diagnosis in medical records; the method further comprises the following steps:
acquiring a medical record log in the current area;
self-learning the medical record log based on Bayesian statistics to obtain disease incidence and co-occurrence probability of the disease state and diagnosis in the medical record;
and updating the disease incidence in the medical record and the co-occurrence probability of the disease state and diagnosis to the regional sequencing feature library.
4. The method of claim 3, wherein the self-learning of the medical record log based on Bayesian statistics to derive a probability of co-occurrence of disease incidence, the condition, and a diagnosis in the medical record comprises:
carrying out structured and structured field statistics on the medical record log to obtain the entity information of the state of illness and the structured field statistical information of the medical record log;
screening the correlation between diagnosis and the disease state according to the disease diagnosis relationship constructed based on the medical knowledge map and the entity information of the disease state in the medical record log so as to obtain the correlation information between diagnosis and the disease state by statistics;
and voting and counting the structured field statistical information and the relationship information between the diagnosis and the disease state based on Bayesian statistics to obtain the disease incidence and the co-occurrence probability between the disease state and the diagnosis in the medical record.
5. The method of claim 1, wherein ranking the at least one candidate diagnosis based on the region ranking features of the current region and the recall probability of each of the candidate diagnoses and performing diagnostic self-learning according to the ranking results comprises:
ranking the at least one candidate diagnosis based on a region ranking feature of the current region and a recall probability of each of the candidate diagnoses;
acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result;
acquiring a real diagnosis result aiming at the medical record information to be processed;
and carrying out diagnosis self-learning according to the diagnosis recommendation result and the real diagnosis result.
6. The method of claim 5, wherein said ranking said at least one candidate diagnosis based on region-ranking features of said current region and recall probability of each said candidate diagnosis comprises:
calculating a ranking probability of each candidate diagnosis by adopting a ranking probability calculation model based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis;
ranking the at least one candidate diagnosis according to the ranking probability of each candidate diagnosis.
7. The method of claim 6, wherein said performing diagnostic self-learning based on said diagnostic recommendation and said true diagnostic result comprises:
calculating a loss value according to the diagnosis recommendation result and the real diagnosis result;
and adjusting model parameters in the sequencing probability calculation model according to the loss value.
8. A clinical assistant decision making diagnostic self-learning device comprising:
the structured processing module is used for carrying out structured processing on medical record information to be processed to obtain entity information of the medical conditions of the medical record information to be processed;
the recall module is used for acquiring at least one candidate diagnosis and the recall probability of each candidate diagnosis according to the text information of the medical record information to be processed and the entity information of the disease state;
the acquisition module is used for acquiring the region ordering characteristics of the current region where the clinical assistant decision-making diagnosis recommendation system is deployed;
and the self-learning module is used for sequencing the at least one candidate diagnosis based on the region sequencing characteristics of the current region and the recall probability of each candidate diagnosis and performing diagnosis self-learning according to the sequencing result.
9. The apparatus of claim 8, wherein the acquisition module is specifically configured to:
determining current region information for deploying a clinical assistant decision-making diagnosis recommendation system;
and acquiring the region sorting feature of the current region from a region sorting feature library according to the current region information.
10. The apparatus of claim 9, wherein the regional ranking features include disease incidence, co-occurrence probability of condition and diagnosis in medical records; the device further comprises:
and the characteristic updating module is used for acquiring the medical record logs in the current region, self-learning the medical record logs based on Bayesian statistics to obtain the disease incidence in the medical record and the co-occurrence probability of the disease state and diagnosis, and updating the disease incidence in the medical record and the co-occurrence probability of the disease state and diagnosis to the regional ranking characteristic library.
11. The apparatus of claim 10, wherein the feature update module is specifically configured to:
carrying out structured and structured field statistics on the medical record log to obtain the entity information of the state of illness and the structured field statistical information of the medical record log;
screening the correlation between diagnosis and the disease state according to the disease diagnosis relationship constructed based on the medical knowledge map and the entity information of the disease state in the medical record log so as to obtain the correlation information between diagnosis and the disease state by statistics;
and voting and counting the structured field statistical information and the relationship information between the diagnosis and the disease state based on Bayesian statistics to obtain the disease incidence and the co-occurrence probability between the disease state and the diagnosis in the medical record.
12. The apparatus of claim 8, wherein the self-learning module is specifically configured to:
ranking the at least one candidate diagnosis based on a region ranking feature of the current region and a recall probability of each of the candidate diagnoses;
acquiring a diagnosis recommendation result aiming at the medical record information to be processed according to the sorting result;
acquiring a real diagnosis result aiming at the medical record information to be processed;
and carrying out diagnosis self-learning according to the diagnosis recommendation result and the real diagnosis result.
13. The apparatus of claim 12, wherein the self-learning module is specifically configured to:
calculating a ranking probability of each candidate diagnosis by adopting a ranking probability calculation model based on the region ranking characteristics of the current region and the recall probability of each candidate diagnosis;
ranking the at least one candidate diagnosis according to the ranking probability of each candidate diagnosis.
14. The apparatus of claim 13, wherein the self-learning module is specifically configured to:
calculating a loss value according to the diagnosis recommendation result and the real diagnosis result;
and adjusting model parameters in the sequencing probability calculation model according to the loss value.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when being executed by a processor, carries out the steps of the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111084156.9A CN113838573B (en) | 2021-09-14 | 2021-09-14 | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111084156.9A CN113838573B (en) | 2021-09-14 | 2021-09-14 | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113838573A true CN113838573A (en) | 2021-12-24 |
| CN113838573B CN113838573B (en) | 2022-10-21 |
Family
ID=78959407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111084156.9A Active CN113838573B (en) | 2021-09-14 | 2021-09-14 | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113838573B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117034202A (en) * | 2023-10-09 | 2023-11-10 | 北京医百科技有限公司 | Big data-based medication prompt method, system, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080228531A1 (en) * | 2007-03-16 | 2008-09-18 | Expanse Networks, Inc. | Insurance Optimization and Longevity Analysis |
| CN106682397A (en) * | 2016-12-09 | 2017-05-17 | 江西中科九峰智慧医疗科技有限公司 | Knowledge-based electronic medical record quality control method |
| CN111292848A (en) * | 2019-12-31 | 2020-06-16 | 同方知网(北京)技术有限公司 | Bayesian estimation-based medical knowledge map assisted reasoning method |
| CN111899884A (en) * | 2020-06-23 | 2020-11-06 | 北京左医科技有限公司 | Intelligent auxiliary inquiry method, device and storage medium |
| CN112951414A (en) * | 2021-03-26 | 2021-06-11 | 嘉兴市第二医院 | Primary medical clinical assistant decision-making system |
-
2021
- 2021-09-14 CN CN202111084156.9A patent/CN113838573B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080228531A1 (en) * | 2007-03-16 | 2008-09-18 | Expanse Networks, Inc. | Insurance Optimization and Longevity Analysis |
| CN106682397A (en) * | 2016-12-09 | 2017-05-17 | 江西中科九峰智慧医疗科技有限公司 | Knowledge-based electronic medical record quality control method |
| CN111292848A (en) * | 2019-12-31 | 2020-06-16 | 同方知网(北京)技术有限公司 | Bayesian estimation-based medical knowledge map assisted reasoning method |
| CN111899884A (en) * | 2020-06-23 | 2020-11-06 | 北京左医科技有限公司 | Intelligent auxiliary inquiry method, device and storage medium |
| CN112951414A (en) * | 2021-03-26 | 2021-06-11 | 嘉兴市第二医院 | Primary medical clinical assistant decision-making system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117034202A (en) * | 2023-10-09 | 2023-11-10 | 北京医百科技有限公司 | Big data-based medication prompt method, system, equipment and storage medium |
| CN117034202B (en) * | 2023-10-09 | 2024-01-05 | 北京医百科技有限公司 | Big data-based medication prompt method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113838573B (en) | 2022-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111681726B (en) | Processing method, device, equipment and medium of electronic medical record data | |
| US11763933B2 (en) | Medical report labeling system and method for use therewith | |
| US20200342267A1 (en) | Data processing apparatus and method, recognition apparatus, learning data storage apparatus, machine learning apparatus, and program | |
| Kwon et al. | Validation of deep-learning-based triage and acuity score using a large national dataset | |
| CN111710412B (en) | Diagnostic result verification method and device and electronic equipment | |
| JP6916310B2 (en) | Human-participatory interactive model training | |
| Dahrouj et al. | Artificial intelligence (AI) and retinal optical coherence tomography (OCT) | |
| CN113838573B (en) | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium | |
| CN111275121A (en) | Medical image processing method and device and electronic equipment | |
| CN112509691B (en) | Method and device for prompting differential diagnosis, electronic equipment and storage medium | |
| KR20130104883A (en) | Apparatus and method for prediction of cac score level change | |
| CN112530533B (en) | Medical record document detection method and device and electronic equipment | |
| CN114579626A (en) | Data processing method, data processing apparatus, electronic device, and medium | |
| CN110335679B (en) | Survival prediction method and system based on multi-granularity graph mode mining | |
| JP2022145573A (en) | Medical information processing device, medical information learning device, medial information display device, and medical information processing method | |
| JP2024066412A (en) | Medical learning device, medical learning method, and medical information processing system | |
| CN113096799A (en) | Quality control method and device |
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 |