CN116798597B - Diagnostic information deducing method, device, electronic equipment and storage medium - Google Patents

Diagnostic information deducing method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN116798597B
CN116798597B CN202210247725.5A CN202210247725A CN116798597B CN 116798597 B CN116798597 B CN 116798597B CN 202210247725 A CN202210247725 A CN 202210247725A CN 116798597 B CN116798597 B CN 116798597B
Authority
CN
China
Prior art keywords
information
medical
focus
preset
diagnosis
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.)
Active
Application number
CN202210247725.5A
Other languages
Chinese (zh)
Other versions
CN116798597A (en
Inventor
肖月庭
阳光
郑超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shukun Beijing Network Technology Co Ltd
Original Assignee
Shukun Beijing Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shukun Beijing Network Technology Co Ltd filed Critical Shukun Beijing Network Technology Co Ltd
Priority to CN202210247725.5A priority Critical patent/CN116798597B/en
Publication of CN116798597A publication Critical patent/CN116798597A/en
Application granted granted Critical
Publication of CN116798597B publication Critical patent/CN116798597B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The embodiment of the application discloses a diagnostic information deducing method, a diagnostic information deducing device, electronic equipment and a storage medium, belonging to the field of computers; the embodiment of the application can acquire focus description information of the object; screening a plurality of target medical information with association relations from a plurality of medical detection information based on focus description information; identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information; the focus description information of the object is deduced by utilizing the commonality information to obtain a deduction result aiming at the focus description information, so that comprehensive analysis and diagnosis of lesions at one or more positions of a patient can be realized across departments or parts.

Description

Diagnostic information deducing method, device, electronic equipment and storage medium
Technical Field
The present application relates to the field of computer technologies, and in particular, to a diagnostic information inference method, apparatus, electronic device, and storage medium.
Background
In the current medical field, when diagnosing a disease condition of a patient, the medical science usually performs diagnosis only for a certain local area (site, organ or tissue, etc.) or a certain system (nervous system, blood system, etc.) of the patient, so that an analysis conclusion (diagnosis conclusion) and a treatment suggestion are given according to the pathological condition of the local area. However, the etiology of a certain part of a patient may sometimes be caused by the occurrence of etiology in other parts, and if a doctor only diagnoses and treats a focus according to a certain part of the patient, a better treatment result cannot be obtained. In the prior art, comprehensive analysis and diagnosis of lesions at one or more places of a patient can not be realized across departments or parts.
Disclosure of Invention
The embodiment of the application provides a diagnostic information deducing method, a diagnostic information deducing device, electronic equipment and a storage medium, which can realize comprehensive analysis and diagnosis of lesions at one or more places of a patient across departments or parts.
The embodiment of the application provides a diagnostic information deducing method, which comprises the following steps:
Obtaining focus description information of a subject;
Screening a plurality of target medical information with association relations from a plurality of medical detection information based on the focus description information;
Identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information;
And carrying out deduction processing on the focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
Correspondingly, the embodiment of the application also provides a diagnostic information deducing device, which comprises:
an acquisition unit configured to acquire focus description information of a subject;
The screening unit is used for screening a plurality of target medical information with association relations from a plurality of medical detection information based on the focus description information;
The identification unit is used for identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information;
And the deduction unit is used for deducting the focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
In an embodiment, the screening unit may include:
The medical detection information association judging subunit is used for carrying out association judging processing on the plurality of medical detection information based on the focus description information to obtain judging results;
and the second screening subunit is used for screening a plurality of target medical information with association relations from the plurality of medical detection information based on the judging result.
In an embodiment, the association discriminating subunit may include:
The identification module is used for identifying the plurality of medical detection information to obtain focus description information of the plurality of medical detection information;
The dividing module is used for dividing the medical detection information into reference medical information and medical information to be distinguished based on focus description information of the medical detection information;
And the judging module is used for judging the relationship between the reference medical information and the medical information to be judged by utilizing a preset association relationship table to obtain the judging result.
In an embodiment, the diagnostic information inference apparatus further includes:
an information acquisition unit configured to acquire attribute information of an object;
and the information screening unit is used for screening a plurality of pieces of medical detection information conforming to the attribute information from a plurality of pieces of preset medical information based on the attribute information.
In an embodiment, the identifying unit may include:
the matching sub-unit is used for carrying out information matching processing on the focus description information of the plurality of target medical information with association relation by utilizing a preset medical data set to obtain a matching result;
a third screening subunit, configured to screen, based on the matching result, a plurality of common medical information with a common relationship from the plurality of target medical information
And the information extraction subunit is used for extracting information from focus description information of the plurality of pieces of common medical information to obtain the common information.
In an embodiment, the deduction unit may include:
the matching subunit is used for matching the commonality information with preset focus diagnosis information of a preset commonality relation table to obtain a matching result;
The searching subunit is used for searching a focus diagnosis rule matched with the commonality information in the preset commonality relation table based on the matching result;
the diagnosis deduction subunit is used for performing diagnosis deduction on the focus description information of the object by utilizing the focus diagnosis rule to obtain a deduction result aiming at the focus description information.
In an embodiment, the deduction unit may further include:
The collecting subunit is used for collecting a plurality of focus diagnosis information of a plurality of different parts;
the information mining subunit is used for carrying out information mining processing on the plurality of focus diagnosis information of the part to obtain focus diagnosis rules of the part;
the analysis subunit is used for analyzing and processing the focus diagnosis rules and the focus diagnosis information to obtain focus diagnosis conclusions of the parts;
and the storage subunit is used for storing the focus diagnosis information, the focus diagnosis rule and the focus diagnosis conclusion of each part into a preset storage table to obtain the preset commonality relation table.
In an embodiment, the diagnostic information inference apparatus may further include:
The data acquisition unit is used for acquiring focus auxiliary analysis data corresponding to the focus description information;
The information mining unit is used for mining information of the deduction result of the focus description information and the focus auxiliary analysis data to obtain medical experience information after mining;
and the information adding unit is used for adding the mined medical experience information to a preset medical experience set.
Correspondingly, the embodiment of the application also provides electronic equipment, which comprises a memory and a processor; the memory stores a computer program, and the processor is configured to run the computer program in the memory to execute the diagnostic information inference method provided in any one of the embodiments of the present application.
Accordingly, an embodiment of the present application further provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the diagnostic information inference method provided in any one of the embodiments of the present application.
The embodiment of the application can acquire focus description information of the object; screening a plurality of target medical information with association relations from a plurality of medical detection information based on focus description information; identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information; the focus description information of the object is deduced by utilizing the commonality information to obtain a deduction result aiming at the focus description information, so that comprehensive analysis and diagnosis of lesions at one or more positions of a patient can be realized across departments or parts.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of a diagnostic information inference method according to an embodiment of the present application;
FIG. 2 is a flow chart of a diagnostic information inference method provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart of a diagnostic information inference method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a diagnostic information inference apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which embodiments of the application are shown, however, in which embodiments are shown, by way of illustration, only, and not in any way all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
The embodiment of the application provides a diagnostic information deducing method which can be executed by a diagnostic information deducing device which can be integrated in an electronic device. The electronic device may include at least one of a terminal, a server, and the like. That is, the diagnostic information estimation method may be executed by the terminal or the server.
The terminal may include a smart television, a smart phone, a smart home, a wearable electronic device, a VR/AR product, an on-board computer, a smart computer, and the like.
The server may be an interworking server between a plurality of heterogeneous systems or a background server of a product verification test system, may be an independent physical server, may be a server cluster or a distributed system formed by a plurality of physical servers, and may also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, basic cloud computing services such as big data and an artificial intelligent platform, and the like.
In an embodiment, as shown in fig. 1, the diagnostic information inference apparatus may be integrated on an electronic device such as a terminal or a server, so as to implement the diagnostic information inference method according to the embodiment of the present application. Specifically, the electronic device may obtain lesion description information of the object; screening out a target medical information sequence from a plurality of medical detection information based on the focus description information, wherein the target medical information sequence comprises a plurality of target medical information which accords with the focus description information; identifying a plurality of target medical information to obtain common information among the plurality of target medical information; and carrying out deduction processing on focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
The following detailed description is given, respectively, of the embodiments, and the description sequence of the following embodiments is not to be taken as a limitation of the preferred sequence of the embodiments.
The embodiments of the present application will be described in terms of a diagnostic information inference apparatus that may be integrated in an electronic device, which may include a terminal, a server, or the like.
As shown in fig. 2, a diagnostic information inference method is provided, and the specific flow includes:
101. Focal description information of the subject is obtained.
Wherein the subject may comprise a patient to be diagnosed. For example, the subject may include a patient who needs to diagnose what problems with the body.
The lesion description information may include information describing a lesion area, among other things. For example, lesion descriptive information may include type of lesion, benign malignancy, lesion size and lesion extent, and so forth.
In one embodiment, when an abnormality occurs in the body of a patient, the condition of the body is often diagnosed by scientific and technical means. For example, the condition of the body can be diagnosed by scientific and technical means such as nuclear magnetic resonance examination and B-ultrasonic examination.
In an embodiment, when the subject diagnoses the physical condition through scientific and technical means, the diagnostic information deducing means may obtain corresponding medical information and focus description information corresponding to the medical information.
Wherein the medical information may include information having relevance to a medical diagnosis.
For example, the medical information may include medical image and/or medical chart data, and so forth.
Wherein the medical image may comprise an image having information related to a medical diagnosis. For example, the medical images may include electronic computed tomography (Computed Tomography, CT) images, magnetic resonance examination (Magnetic Resonance, MR) images, ultrasound images, and so forth. As another example, the medical image may be a physiological tissue image, or the like. The physiological tissue may include, among others, heart, brain, lung, liver, etc. For example, the medical image may be a CT image of the heart of the patient. For another example, the medical image may be an MR map of the brain of the patient, or the like.
Wherein the medical chart data may comprise charts related to medical diagnosis. For example, the medical chart data may be obtained by detecting a physiological structure or region of a human target by an electrocardiographic device, an electroencephalographic device, a digital radiography (Digital Radiography, DR) device, an endoscopic device, or the like.
102. And screening a plurality of target medical information with association relations from the plurality of medical detection information based on the focus description information.
In an embodiment, in order to perform deduction processing on the focus description information by using multiple aspects of knowledge to obtain a deduction result of the focus description information, after obtaining focus description information of a subject, a plurality of target medical information with association relations may be screened out from a plurality of medical detection information based on the focus description information.
The medical detection information may include information that may have an association with the lesion description information. For example, the medical detection information may include all medical information that has been generated. For example, the medical examination information may include information previously stored in a server or a diagnostic device. For another example, the medical examination information may include information previously stored in an on-line medical information base, and so on.
The target medical information may include medical information that may have an association with lesion description information of the subject. The association may include a causal relationship, a parallel relationship, or an inclusion relationship, among others.
For example, if the lesion descriptive information of the subject is descriptive information for the myocardium, the target medical information may be medical information having an association relationship with the myocardium. For another example, if the lesion descriptive information of the subject is descriptive information for the brain, the target medical information may be information that may have an association relationship with the brain.
In an embodiment, each medical examination information has corresponding lesion description information, which is information describing the medical information. For example, lesion descriptive information of medical test information may indicate what the content of the medical test information is, which information of the patient's body is presented. For example, lesion description information of medical examination information may indicate the type of lesion, benign and malignant, lesion size and lesion extent, etc. of the medical examination information. For example, lesion descriptive information of medical test information may indicate that the medical test information is stomach-related information, and so on.
In an embodiment, in order to improve the screening efficiency, a plurality of medical detection information conforming to the attribute information may be first screened out from a plurality of preset medical information by coarse screening. And then, screening out target medical information from the medical detection information of the plurality of medical detection information through fine screening.
Specifically, before the step of "screening a plurality of target medical information having an association relationship among a plurality of medical detection information based on the lesion description information", it may include:
acquiring attribute information of an object;
and screening a plurality of pieces of medical detection information conforming to the attribute information from a plurality of pieces of preset medical information based on the attribute information.
Wherein the attribute information may include information related to the object. For example, the attribute information of the object may include a location of interest of the object, a circulatory system, an organization structure, an object identification (Identity document, ID) of the object, lesion description information of the object, and the like. The corresponding plurality of medical detection information can be screened and processed based on the attribute information to form a medical data set to be processed, so that the candidate processing speed is improved.
In an embodiment, information extraction may be performed on the attribute information to obtain key information of the attribute information. And then, matching the key information with preset key information of preset medical information to obtain a matching result. Medical test information may then be determined from the matching results.
Wherein the key information of the attribute information may be a keyword in the attribute information, and the like. For example, the attribute information is "cervical: normal size, smooth ", the key information of which may be" cervical ".
For another example, the attribute information of the object and the attribute information of the preset medical information may be directly matched. When the attribute information of the object and the attribute information of the medical detection information are matched, the preset medical information may be determined as the medical detection information of the object.
For example, attribute information of the object may be identified to obtain a lesion type of the object. The focus description information of each preset medical information can be identified, and the focus type of the preset medical information is obtained. Then, matching the focus type of the object with the focus type of the preset medical information to obtain a matching result, and screening medical detection information according to the matching result. For example, when the lesion type of the subject and the preset medical information are the same, the preset medical information may be determined as medical detection information.
In an embodiment, after the plurality of medical detection information is screened, the target medical information may be screened out of the plurality of medical detection information based on the lesion description information. Specifically, the step of screening a plurality of target medical information having an association relationship from a plurality of medical detection information based on lesion description information may include:
based on focus description information, carrying out association judgment processing on a plurality of medical detection information to obtain a judgment result;
And screening a plurality of target medical information with association relations from the plurality of medical detection information based on the discrimination result.
Medical detection information in one embodiment, a plurality of medical detection information may be subjected to association discrimination processing based on focus description information to obtain discrimination result medical detection information. Wherein, performing the association discriminating processing on the plurality of medical detection information may refer to determining whether or not there is a possibility of an association relationship between the plurality of medical detection information.
For example, the focus description information between the medical detection information may be compared by using a preset association table, so as to determine whether there is an association between the medical detection information.
The preset association relation table can explain what association relation is possible between the focus description information.
For example, "coronary artery" is recorded in a preset association table; fat index; high; a blood vessel; plaque is vulnerable; and the content of the causal relation is that when focus description information of a plurality of medical detection information is compared according to a preset association relation table, if the focus description information of the medical detection information is detected to be accordant with the content in the preset association relation table, the association relation among the medical detection information can be determined.
For another example, a plurality of target medical information having an association relationship may be searched out based on lesion description information of each medical detection information. Specifically, the step of performing association discrimination processing on a plurality of medical detection information based on focus description information to obtain a discrimination result may include:
identifying a plurality of medical detection information to obtain focus description information of the medical detection information;
Dividing the plurality of medical detection information into reference medical information and medical information to be discriminated based on focus description information of the plurality of medical detection information;
And judging the relationship between the reference medical information and the medical information to be judged by using a preset association relationship table, and obtaining the judging result.
The reference medical information may refer to medical detection information as a criterion for judging an association relationship. For example, the baseline medical information may include medical detection information with the most focus description information. For another example, the reference medical information may include medical detection information of highest importance, and so on.
The medical information to be discriminated may include medical detection information that judges whether there is an association relationship with the reference medical information and what association relationship there is. For example, the medical information to be discriminated may refer to information other than the reference medical information among the plurality of target medical information.
For example, there is 100 pieces of medical detection information. Wherein, one of the medical detection information is classified as the reference medical information, and the remaining 99 medical detection information may be classified as the medical information to be discriminated.
In an embodiment, after the reference medical information and the medical information to be distinguished are classified, the target medical information having relevance with the reference medical information may be searched for in the medical information to be distinguished by using a preset association table.
For example, "coronary artery" is recorded in a preset association table; fat index; high; a blood vessel; plaque is vulnerable; and the content of the causal relation is that when the focus description information of the reference medical information and the focus description information of the medical information to be distinguished are compared according to a preset association relation table, if the focus description information of the reference medical information and the focus description information of the medical information to be distinguished are detected to accord with the content in the preset association relation table, the association relation between the reference medical information and the medical information to be distinguished can be determined, and the medical information to be distinguished can be distinguished as having the association relation with the reference medical information.
In an embodiment, for example, a pre-trained lesion recognition model may be used to identify each medical test information and obtain a lesion description of each medical test information. Then, the reference medical information and the plurality of medical information to be discriminated are divided among the plurality of medical detection information. And then, comparing focus description information of the reference medical information with target medical information which has association relation with the reference medical information in a plurality of medical information to be distinguished.
Wherein the lesion recognition model may be a deep learning model. For example, the lesion recognition model may include any of a convolutional neural network (Convolutional Neural Networks, CNN), a deconvolution neural network (De-Convolutional Networks, DN), a deep neural network (Deep Neural Networks, DNN), a deep convolutional inverse graph network (Deep Convolutional INVERSE GRAPHICS Networks, DCIGN), a Region-based convolutional network (Region-based Convolutional Networks, RCNN), a Region-based fast convolutional network (Faster Region-based Convolutional Networks, FASTER RCNN), and a bi-directional codec (Bidirectional Encoder Representations from Transformers, BERT) model, among others.
In an embodiment, when performing the association discriminating processing on the plurality of pieces of medical detection information, a plurality of sets of associated medical information may be obtained, where each set of associated medical information includes a plurality of pieces of target medical information having an association relationship.
For example, there are 100 pieces of medical examination information. When the correlation discrimination processing is performed on the 100 pieces of medical detection information, 5 sets of correlated medical information are obtained. Wherein each set of associated medical information includes a plurality of target medical information having an associated relationship.
Then, a plurality of target medical information having an association relationship may be screened out from the plurality of medical detection information based on the discrimination result. For example, the discrimination result indicates that, among the plurality of pieces of medical detection information, the medical detection information a, the medical detection information B, and the medical detection information C have an association relationship, and the medical detection information a, the medical detection information B, and the medical detection information C are selected as the association relationship.
In an embodiment, in addition to the focus description information, a plurality of target medical information with association relationships may be screened out from the plurality of medical detection information, and a plurality of target medical information with association relationships may be screened out from the plurality of medical detection information based on other attribute information.
For example, a plurality of target medical information having an association relationship may be screened out from a plurality of medical detection information based on the object ID of the object. And identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information. And then, carrying out deduction processing on the attribute information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
When a plurality of target medical information with association relationship is selected from a plurality of medical detection information based on other attribute information, the steps may refer to the above steps, and the description thereof will not be repeated here.
In an embodiment, because the focus description information intuitively describes the disease condition of the subject, compared with other focus description information, a plurality of target medical information with association relations are screened out from a plurality of medical detection information based on the focus description information; identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information; and deducing the focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information, so that the accuracy of deducting the illness state of the object can be improved.
103. And identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information.
In an embodiment, after screening out the plurality of target medical information, the plurality of target medical information may be identified to obtain common information between the plurality of target medical information, so that the focus description information of the object may be deduced by using the common information.
Wherein the commonality information between the target medical information may account for the inherent relationship between the target medical information. For example, a lesion in a localized area (region, organ or tissue, etc.) of a patient may be due to problems in other areas, thereby affecting that area as well. At this time, there are internal relations between the local area where the lesion occurs and other areas where the lesion occurs, and these internal relations are described as common information.
For example, taking the example of myocardial presence abnormalities, the target medical information includes MR medical images and electrocardiography. The focus description information of the MR medical image is the region of myocardial abnormality and the size of the region. The focus description information of the electrocardiogram is an area where abnormal fluctuation exists in the electrocardiogram. Through the focus description information of the MR medical image and the focus description information of the electrocardiogram, the relation between the MR medical image and the electrocardiogram can be obtained as a parallel relation, namely, the MR medical image and the electrocardiogram describe the region of myocardial abnormality from different angles.
As another example, taking cerebral infarction ischemia as an example, the target medical information includes CTP information and CTA information. The focus description information of the CTP information comprises information such as an infarct range and an infarct degree of a cerebral infarction position. Lesion descriptive information for CTA information includes information on the location, extent, degree, etc. of arterial occlusion. The focus description information of CTP information and the focus description information of CTA information can be used for obtaining that the middle artery occlusion causes severe infarction of left brain, so that the relation between CTP information and CTA information is causal relation.
In one embodiment, there are various methods for performing association discrimination processing on a plurality of target medical information to obtain a plurality of associated medical information having an association relationship.
For example, the association discriminating process may be directly performed on the plurality of target medical information by using the preset association table, so as to obtain a plurality of associated medical information having an association relationship.
In an embodiment, after obtaining the target medical information with the association relationship, the plurality of associated medical information may be identified, so as to obtain the commonality information among the plurality of target medical information. That is, after obtaining the target medical information having the association relationship, it is possible to explore what the association relationship between the plurality of target medical information is in particular. Specifically, the step of identifying a plurality of target medical information having an association relationship to obtain common information among the plurality of target medical information may include:
performing information matching processing on focus description information of a plurality of target medical information with association relations by using a preset medical data set to obtain a matching result;
based on the matching result, screening out a plurality of common medical information with a common relation from a plurality of target medical information with a correlation relation;
And extracting information from focus description information of a plurality of pieces of common medical information to obtain common information.
The preset medical data set may be a set integrating existing medical knowledge. For example, the preset medical dataset may include information such as medical literature, diagnostic guidelines, or expert experience sets. The preset medical dataset may include what the cause of the lesion is when the local area appears.
In an embodiment, the information matching process may be performed on lesion description information of a plurality of target medical information using a preset medical dataset. Namely, through a preset medical data set, judging that the focus description information of the related medical information belongs to the pathological condition described in the preset medical data set.
In an embodiment, a plurality of common medical information having a common relationship may be screened out of a plurality of associated medical information based on the matching result. For example, when a plurality of associated medical information all belong to the same lesion condition, the plurality of associated medical information can be screened out as common medical information. And then extracting information from the plurality of pieces of common medical information to obtain common information. For example, lesion description information of common medical information may be integrated together to obtain common information.
In an embodiment, when there are multiple sets of associated medical information sets, the associated medical information in each set of associated medical information sets may be integrated to obtain common information corresponding to each set of associated medical information sets.
104. And carrying out deduction processing on focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
In an embodiment, after the commonality information is obtained, the deduction processing may be performed on the focus description information of the object by using the commonality information, so as to obtain a deduction result for the focus description information.
Specifically, the step of performing deduction processing on focus description information of the object by using the commonality information to obtain a deduction result for the focus description information may include:
matching the commonality information with preset focus diagnosis information of a preset commonality relation table to obtain a matching result;
Searching a focus diagnosis rule matched with the commonality information in a preset commonality relation table based on the matching result;
And diagnosing and deducting focus description information of the object by using a focus diagnosis rule to obtain a deduction result aiming at the focus description information.
Wherein, the preset commonality relation table records diagnosis experience with the contrary or larger difference of diagnosis process. The preset commonality relation table comprises preset focus diagnosis information, preset focus diagnosis rules and preset focus diagnosis conclusions. The preset focus diagnosis information records some information which an expert pays attention to in the diagnosis process. The preset focus diagnosis rules record the deduction process of the expert on diagnosis in the diagnosis process.
In an embodiment, the shared information may be matched with the preset focus diagnosis information in the preset commonality relation table, and a focus diagnosis rule matched with the commonality information may be searched in the preset commonality relation table based on a matching result. Then, diagnosis deduction can be carried out on focus description information of the object by using focus diagnosis rules, and deduction results aiming at the focus description information are obtained.
For example, lung lesions are taken as an example. The diagnostic information inference device acquires a DR image of the patient's lungs and a clinical laboratory sheet of the lungs. Wherein, the lung DR image shows that the focus descriptive information is a pneumonia focus. By using a preset commonality relation table, according to the index information recorded in the pneumonia focus and the laboratory sheet, the pneumonia focus belongs to viral pneumonia (usually, whether the pneumonia is caused by viral, bacterial or mycoplasma is not well judged, and an expert is required to comprehensively diagnose through information of various commonality relations so as to draw conclusions).
As another example, non-calcified plaque of the brain is taken as an example. Non-calcified plaque was detected in the brain CT images. According to the information of the detected non-calcified plaque in the brain CT image, a certain possible disease state can be preliminarily determined by utilizing a common relation table, but a conclusion is not directly drawn. At this time, the common medical information may be found during the concurrent examination of the patient according to a preset common relation table. During the search, the patient was found to have also found non-calcified plaque in the heart region, at which point the following can be concluded: blood has high lipid content, is easy to deposit, and needs to be treated for reducing blood fat.
In one embodiment, there are multiple commonalities when there are multiple sets of associated medical information. At this time, the target shared information may be first selected from the plurality of pieces of commonality information. Then, matching the target commonality information with preset focus diagnosis information of a preset commonality relation table to obtain a matching result; searching a focus diagnosis rule matched with the target commonality information in a preset commonality relation table based on the matching result; and diagnosing and deducting focus description information of the object by using a focus diagnosis rule to obtain a deduction result aiming at the focus description information.
In one embodiment, multiple aspects of lesion diagnostic information may be collected to form a pre-set commonality table. Specifically, before the step of matching the target commonality information with the preset focus diagnosis information of the preset commonality relation table to obtain the matching result, the method may further include:
Collecting a plurality of focus diagnosis information of a plurality of different parts;
performing information mining processing on a plurality of focus diagnosis information of the part to obtain focus diagnosis rules of the part;
Analyzing and processing focus diagnosis rules and focus diagnosis information to obtain focus diagnosis conclusion of the part;
and storing focus diagnosis information, focus diagnosis rules and focus diagnosis conclusions of each part into a preset storage table to obtain a preset commonality relation table.
For example, a plurality of lesion diagnostic information may be collected for a plurality of different body parts. And focus diagnosis information of a plurality of senior specialists in the diagnosis process can be collected in a focused mode. For example, diagnostic records for a plurality of senior citizens may be acquired and lesion diagnostic information may be collected in the diagnostic records.
In an embodiment, after focus diagnosis information is acquired, information mining processing may be performed on a plurality of focus diagnosis information of the location, so as to obtain focus diagnosis rules of the location.
For example, information mining can be performed on a plurality of focus diagnosis information of a plurality of senior specialists, so as to obtain focus diagnosis rules corresponding to each senior specialist. For example, a lesion diagnostic rule may be an association of which sites there is lesion formation between them; or which organs have a correlation between lesion formation; or which blood vessels there is a correlation of lesion formation, etc.
Then, the focus diagnosis rule and focus diagnosis information can be analyzed and processed to obtain focus diagnosis results of the part, namely, the focus diagnosis rule and focus diagnosis information are integrated. For example, what correlation exists between the lesion diagnostic information of different organs, and what diagnostic results are formed. Also for example, what associations are between different blood vessels, what diagnostic results are to be formed, and so on.
Then, the focus diagnosis information, focus diagnosis rule and focus diagnosis conclusion of each part can be stored in a preset storage table to obtain a preset commonality relation table.
In one embodiment, the preset commonality table may also be updated based on follow-up information or new expert experience. The follow-up information can refer to the change condition of the focus along with treatment obtained through regular tracking and observation of a patient.
In an embodiment, the deduction results for the lesion description information may be presented to the physician in a structured report. For example, the information to be displayed may be ranked and the ranked information may be presented to the physician.
In an embodiment, the information mining may be performed by using the deduction result of the obtained lesion description information and the lesion auxiliary analysis data to obtain new medical experience information. Specifically, the diagnostic information inference method provided by the embodiment of the application may further include:
Acquiring focus auxiliary analysis data corresponding to focus description information;
carrying out information mining on the deduction result of the focus description information and focus auxiliary analysis data to obtain medical experience information after mining;
the mined medical experience information is added to a preset medical experience set.
For example, the obtained analysis result and analysis data (such as laboratory sheets, detection reports and the like) in other dimensions are utilized for information mining, so that new medical experience conclusions are obtained. These new medical experience conclusions are supplemented to medical experience as the basis for subsequent medical diagnosis.
The diagnostic information deducing method provided by the embodiment of the application can acquire focus description information of the object; screening a plurality of target medical information with association relations from a plurality of medical detection information based on focus description information; identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information; the focus description information of the object is deduced by utilizing the commonality information to obtain a deduction result aiming at the focus description information, and comprehensive analysis and diagnosis of lesions at one or more positions of a patient can be realized across departments or parts.
According to the method described in the above embodiments, examples are described in further detail below.
The method of the embodiment of the application will be described by taking the example that the diagnostic information deducing method is integrated on the electronic equipment. For example, as shown in fig. 3, the diagnostic information inference method according to the embodiment of the present application may include:
201. The electronic device obtains lesion descriptive information of the subject.
In one embodiment, in the doctor diagnosis process, diagnosis is generally performed only for a certain local area (site, organ or tissue, etc.) or a certain system (nervous system, blood system, etc.), so that an analysis conclusion (diagnosis conclusion) and a treatment suggestion are given according to the pathological condition of the local area.
However, the patient does not know by himself whether a lesion in a certain local area is problematic in that area or that a serious lesion is present in that area due to the problem in other areas. Many diseases may be due to problems in multiple areas (parts, organs or tissues, etc.), which eventually lead to severe lesions in a certain local area.
At present, comprehensive analysis diagnosis of lesions at one or more places of a patient cannot be performed across departments or parts, and usually, the experience of comprehensive diagnosis is only mastered in the hands of some senior specialists. The related diagnosis information and the internal related part lesion information are required to be collected to form an automatic AI diagnosis method, so that doctors are assisted to give comprehensive diagnosis results and diagnosis and treatment suggestions of the target area disease by combining the disease changes of multiple areas of the human body.
Thus, the electronic device may obtain lesion description information of the subject. The lesion description information may include information describing a lesion area, among other things. For example, lesion descriptive information may include type of lesion, benign malignancy, lesion size and lesion extent, and so forth.
202. The electronic equipment screens out a plurality of target medical information with association relations from a plurality of medical detection information based on focus description information.
For example, the electronic device may screen out a plurality of target medical information having an association relationship according to a portion, a circulatory system, a tissue structure, and the like, which are focused by a doctor.
203. The electronic equipment identifies a plurality of target medical information with association relation to obtain common information among the plurality of target medical information.
204. The electronic equipment performs deduction processing on focus description information of the object by utilizing the commonality information to obtain deduction results aiming at the focus description information.
For example, the electronic device may perform deduction processing on the lesion description information of the object based on the commonality information by using a preset commonality relation table, so as to obtain a deduction result for the lesion description information.
In an embodiment, if the electronic device does not find the common information among the plurality of target medical information, the medical information of the patient in the same period may be retrieved, so as to find at least one medical information similar to the medical information, and correspondingly give out a deduction result (diagnosis conclusion).
Wherein, contemporaneous medical information may refer to: the medical information is contained within a certain short time frame, for example, within hours, days or months.
In the diagnostic information deducing method provided by the embodiment of the application, the electronic equipment can acquire focus description information of the object; screening a plurality of target medical information with association relations from a plurality of medical detection information based on focus description information; identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information; the focus description information of the object is deduced by utilizing the commonality information to obtain a deduction result aiming at the focus description information, and comprehensive analysis and diagnosis of lesions at one or more positions of a patient can be realized across departments or parts.
In order to better implement the diagnostic information inference method provided by the embodiment of the present application, in an embodiment, a diagnostic information inference device is also provided, and the diagnostic information inference device may be integrated in an electronic device. Where the meaning of a noun is the same as in the diagnostic information inference method described above, specific implementation details may be referred to in the description of the method embodiments.
In an embodiment, a diagnostic information inference apparatus is provided, which may be integrated in an electronic device in particular, as shown in fig. 4, the diagnostic information inference apparatus comprising: the acquisition unit 301, the screening unit 302, the identification unit 303, and the deduction unit 304 are specifically as follows:
an acquiring unit 301 configured to acquire focus description information of a subject;
A screening unit 302, configured to screen a plurality of target medical information with association relationships from a plurality of medical detection information based on the lesion description information;
an identifying unit 303, configured to identify a plurality of target medical information having an association relationship, so as to obtain commonality information among the plurality of target medical information;
And the deduction unit 304 is configured to perform deduction processing on the focus description information of the object by using the commonality information, so as to obtain a deduction result for the focus description information.
In an embodiment, the screening unit 302 may include:
The association judging subunit is used for carrying out association judging processing on the plurality of medical detection information based on the focus description information to obtain a judging result;
and the second screening subunit is used for screening a plurality of target medical information with association relations from the plurality of medical detection information based on the judging result.
In an embodiment, the association discriminating subunit may include:
The identification module is used for identifying the plurality of medical detection information to obtain focus description information of the plurality of medical detection information;
The dividing module is used for dividing the medical detection information into reference medical information and medical information to be distinguished based on focus description information of the medical detection information;
And the judging module is used for judging the relationship between the reference medical information and the medical information to be judged by utilizing a preset association relationship table to obtain the judging result.
In an embodiment, the diagnostic information inference apparatus further includes:
an information acquisition unit configured to acquire attribute information of an object;
and the information screening unit is used for screening a plurality of pieces of medical detection information conforming to the attribute information from a plurality of pieces of preset medical information based on the attribute information.
In an embodiment, the identifying unit 303 may include:
the matching sub-unit is used for carrying out information matching processing on the focus description information of the plurality of target medical information with association relation by utilizing a preset medical data set to obtain a matching result;
a third screening subunit, configured to screen, based on the matching result, a plurality of common medical information with a common relationship from the plurality of target medical information
And the information extraction subunit is used for extracting information from focus description information of the plurality of pieces of common medical information to obtain the common information.
In an embodiment, the deduction unit 304 may include:
the matching subunit is used for matching the commonality information with preset focus diagnosis information of a preset commonality relation table to obtain a matching result;
The searching subunit is used for searching a focus diagnosis rule matched with the commonality information in the preset commonality relation table based on the matching result;
the diagnosis deduction subunit is used for performing diagnosis deduction on the focus description information of the object by utilizing the focus diagnosis rule to obtain a deduction result aiming at the focus description information.
In an embodiment, the deduction unit 304 may further include:
The collecting subunit is used for collecting a plurality of focus diagnosis information of a plurality of different parts;
the information mining subunit is used for carrying out information mining processing on the plurality of focus diagnosis information of the part to obtain focus diagnosis rules of the part;
the analysis subunit is used for analyzing and processing the focus diagnosis rules and the focus diagnosis information to obtain focus diagnosis conclusions of the parts;
and the storage subunit is used for storing the focus diagnosis information, the focus diagnosis rule and the focus diagnosis conclusion of each part into a preset storage table to obtain the preset commonality relation table.
In an embodiment, the diagnostic information inference apparatus may further include:
The data acquisition unit is used for acquiring focus auxiliary analysis data corresponding to the focus description information;
The information mining unit is used for mining information of the deduction result of the focus description information and the focus auxiliary analysis data to obtain medical experience information after mining;
and the information adding unit is used for adding the mined medical experience information to a preset medical experience set.
In the implementation, each unit may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit may be referred to the foregoing method embodiment, which is not described herein again.
The diagnosis information deducing device can realize comprehensive analysis and diagnosis of lesions at one or more parts of a patient across departments or parts.
The embodiment of the application also provides electronic equipment, which can comprise a terminal or a server, for example, the electronic equipment can be used as a diagnosis information deducing terminal, and the diagnosis information deducing terminal can be a smart television or the like; for another example, the computer product may be a server, such as a diagnostic information inference server, or the like. As shown in fig. 5, a schematic structural diagram of a terminal according to an embodiment of the present application is shown, specifically:
The electronic device may include one or more processing cores 'processors 401, one or more computer-readable storage media's memory 402, power supply 403, and input unit 404, among other components. It will be appreciated by those skilled in the art that the electronic device structure shown in fig. 5 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components. Wherein:
the processor 401 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, and performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 402, and calling data stored in the memory 402, thereby performing overall monitoring of the electronic device. Optionally, processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user page, an application program, etc., and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 401.
The memory 402 may be used to store software programs and modules, and the processor 401 executes various functional applications and data processing by executing the software programs and modules stored in the memory 402. The memory 402 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the computer product, etc. In addition, memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.
The electronic device further comprises a power supply 403 for supplying power to the various components, preferably the power supply 403 may be logically connected to the processor 401 by a power management system, so that functions of managing charging, discharging, and power consumption are performed by the power management system. The power supply 403 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The electronic device may further comprise an input unit 404, which input unit 404 may be used for receiving input digital or character information and generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.
Although not shown, the electronic device may further include a typesetting unit and the like, which are not described herein. In particular, in this embodiment, the processor 401 in the electronic device loads executable files corresponding to the processes of one or more application programs into the memory 402 according to the following instructions, and the processor 401 executes the application programs stored in the memory 402, so as to implement various functions as follows:
Obtaining focus description information of a subject;
Screening a plurality of target medical information with association relations from a plurality of medical detection information based on the focus description information;
Identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information;
And carrying out deduction processing on the focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
According to one aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer product reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer product performs the methods provided in the various alternative implementations of the above embodiments.
It will be appreciated by those of ordinary skill in the art that all or part of the steps of the various methods of the above embodiments may be performed by a computer program, or by computer program control related hardware, which may be stored in a computer readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present application also provides a storage medium in which a computer program is stored, the computer program being capable of being loaded by a processor to perform the steps of any of the diagnostic information inference methods provided by the embodiments of the present application. For example, the computer program may perform the steps of:
Obtaining focus description information of a subject;
Screening a plurality of target medical information with association relations from a plurality of medical detection information based on the focus description information;
Identifying a plurality of target medical information with association relation to obtain common information among the plurality of target medical information;
And carrying out deduction processing on the focus description information of the object by utilizing the commonality information to obtain a deduction result aiming at the focus description information.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
The steps of any diagnostic information inference method provided by the embodiment of the present application can be executed by the computer program stored in the storage medium, so that the beneficial effects of any diagnostic information inference method provided by the embodiment of the present application can be achieved, which are detailed in the previous embodiments and are not described herein.
The above description of the method, the device, the electronic equipment and the storage medium for deducing diagnosis information provided by the embodiment of the present application is provided in detail, and specific examples are applied to illustrate the principle and implementation of the present application, and the description of the above embodiments is only used to help understand the method and the core idea of the present application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present application, the present description should not be construed as limiting the present application.

Claims (9)

1. A diagnostic information inference method, comprising:
Obtaining focus description information of a subject;
Screening a plurality of target medical information with association relations from a plurality of medical detection information based on the focus description information;
Performing information matching processing on focus description information of the plurality of target medical information with association relations by using a preset medical data set to obtain a matching result;
screening out a plurality of common medical information with a common relation from a plurality of target medical information based on the matching result;
extracting information from focus description information of the plurality of pieces of common medical information to obtain common information;
matching the commonality information with preset focus diagnosis information of a preset commonality relation table to obtain a matching result;
Searching a focus diagnosis rule matched with the commonality information in the preset commonality relation table based on the matching result;
And diagnosing and deducting focus description information of the object by utilizing the focus diagnosis rule to obtain a deduction result aiming at the focus description information.
2. The method of claim 1, wherein the screening a plurality of target medical information having an association relationship among a plurality of medical detection information based on the lesion description information comprises:
Based on the focus description information, carrying out association judgment processing on the plurality of medical detection information to obtain a judgment result;
and screening a plurality of target medical information with association relations from the plurality of medical detection information based on the discrimination result.
3. The method according to claim 2, wherein the performing the association discriminating process on the plurality of medical detection information to obtain a discriminating result includes:
Identifying the plurality of medical detection information to obtain focus description information of the plurality of medical detection information;
Dividing the plurality of medical detection information into reference medical information and medical information to be discriminated based on focus description information of the plurality of medical detection information;
And judging the relationship between the reference medical information and the medical information to be judged by using a preset association relationship table, and obtaining the judging result.
4. The method of claim 1, wherein before screening the plurality of target medical information having an association from the plurality of medical detection information based on the lesion description information, further comprising:
acquiring attribute information of an object;
and screening a plurality of pieces of medical detection information conforming to the attribute information from a plurality of pieces of preset medical information based on the attribute information.
5. The method according to claim 1, wherein said matching the commonality information with preset lesion diagnosis information of a preset commonality relation table, before obtaining a matching result, comprises:
Collecting a plurality of focus diagnosis information of a plurality of different parts;
Performing information mining processing on a plurality of focus diagnosis information of the part to obtain focus diagnosis rules of the part;
Analyzing and processing the focus diagnosis rule and the focus diagnosis information to obtain focus diagnosis conclusion of the part;
And storing focus diagnosis information, focus diagnosis rules and focus diagnosis conclusions of each part into a preset storage table to obtain the preset commonality relation table.
6. The method according to claim 1, wherein the method further comprises:
Acquiring focus auxiliary analysis data corresponding to the focus description information;
performing information mining on the deduction result of the focus description information and the focus auxiliary analysis data to obtain medical experience information after mining;
And adding the mined medical experience information to a preset medical experience set.
7. A diagnostic information inference apparatus, comprising:
an acquisition unit configured to acquire focus description information of a subject;
The screening unit is used for screening a plurality of target medical information with association relations from a plurality of medical detection information based on the focus description information;
The identification unit is used for carrying out information matching processing on focus description information of the plurality of target medical information with association relations by utilizing a preset medical data set to obtain a matching result; screening out a plurality of common medical information with a common relation from a plurality of target medical information based on the matching result; extracting information from focus description information of the plurality of pieces of common medical information to obtain common information;
The deduction unit is used for matching the commonality information with preset focus diagnosis information of a preset commonality relation table to obtain a matching result; searching a focus diagnosis rule matched with the commonality information in the preset commonality relation table based on the matching result; and diagnosing and deducting focus description information of the object by utilizing the focus diagnosis rule to obtain a deduction result aiming at the focus description information.
8. An electronic device comprising a memory and a processor; the memory stores a computer program, and the processor is configured to execute the computer program in the memory to perform the steps in the diagnostic information inference method as set forth in any one of claims 1 to 6.
9. A computer readable storage medium, characterized in that it stores a plurality of computer programs adapted to be loaded by a processor for performing the steps of the diagnostic information inference method according to any of claims 1 to 6.
CN202210247725.5A 2022-03-14 2022-03-14 Diagnostic information deducing method, device, electronic equipment and storage medium Active CN116798597B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210247725.5A CN116798597B (en) 2022-03-14 2022-03-14 Diagnostic information deducing method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210247725.5A CN116798597B (en) 2022-03-14 2022-03-14 Diagnostic information deducing method, device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN116798597A CN116798597A (en) 2023-09-22
CN116798597B true CN116798597B (en) 2024-04-19

Family

ID=88037326

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210247725.5A Active CN116798597B (en) 2022-03-14 2022-03-14 Diagnostic information deducing method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116798597B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021114736A1 (en) * 2020-07-07 2021-06-17 平安科技(深圳)有限公司 Medical consultation assistance method and apparatus, electronic device, and medium
CN113506622A (en) * 2021-07-12 2021-10-15 曹庆恒 Intelligent diagnosis and analysis system and use method thereof
CN113889236A (en) * 2021-10-08 2022-01-04 数坤(北京)网络科技股份有限公司 Medical image processing method and device and computer readable storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190287679A1 (en) * 2018-03-16 2019-09-19 Winston Center for Attention, Language & Learning Medical assessment system and method thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021114736A1 (en) * 2020-07-07 2021-06-17 平安科技(深圳)有限公司 Medical consultation assistance method and apparatus, electronic device, and medium
CN113506622A (en) * 2021-07-12 2021-10-15 曹庆恒 Intelligent diagnosis and analysis system and use method thereof
CN113889236A (en) * 2021-10-08 2022-01-04 数坤(北京)网络科技股份有限公司 Medical image processing method and device and computer readable storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
继发性肝脏淋巴瘤的MRI表现;程祝忠;阳宁静;任静;王闽;肖燕;杨宇洁;许国辉;;西部医学(12);全文 *

Also Published As

Publication number Publication date
CN116798597A (en) 2023-09-22

Similar Documents

Publication Publication Date Title
Mastoi et al. Automated diagnosis of coronary artery disease: a review and workflow
JP5553972B2 (en) Electronic medical record impact data acquisition, processing and display system and method
US7653227B2 (en) Hierarchical modeling in medical abnormality detection
Nogales et al. A survey of deep learning models in medical therapeutic areas
JP2018067303A (en) Diagnosis support method, program and apparatus
US20110075900A1 (en) Diagnosis assisting system, computer readable recording medium having diagnosis assisting program recorded thereon, and diagnosis assisting method
EP3654343A1 (en) Application of deep learning for medical imaging evaluation
JP2018060529A (en) Method and apparatus of context-based patient similarity
JP2003325458A (en) Disease candidate information output system
US20100217094A1 (en) Point-of-care enactive medical system and method
US8126228B2 (en) Determining efficacy of therapeutic intervention in neurosychiatric disease
WO2019193982A1 (en) Medical document creation assistance device, medical document creation assistance method, and medical document creation assistance program
Fu et al. Deep learning for head and neck CT angiography: stenosis and plaque classification
Nasimov et al. Deep learning algorithm for classifying dilated cardiomyopathy and hypertrophic cardiomyopathy in transport workers
EP3467770B1 (en) Method for analysing a medical imaging data set, system for analysing a medical imaging data set, computer program product and a computer-readable medium
Danala et al. Developing new quantitative CT image markers to predict prognosis of acute ischemic stroke patients
Andry et al. Electronic health record to predict a heart attack used data mining with Naïve Bayes method
CN116798597B (en) Diagnostic information deducing method, device, electronic equipment and storage medium
Chandrasekar et al. Performance and evaluation of data mining techniques in cancer diagnosis
Singh et al. Detection of Cardio Vascular abnormalities using gradient descent optimization and CNN
Zhang et al. A weakly supervised-guided soft attention network for classification of intracranial hemorrhage
JP5348998B2 (en) Image search apparatus and method
Montenegro et al. Evaluation of transfer learning to improve arrhythmia classification for a small ECG database
Hsu et al. Notable papers and new directions in sensors, signals, and imaging informatics
Wen et al. A novel method for classification of high-resolution nailfold capillary microscopy images

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