CN116504392A - Intelligent auxiliary diagnosis prompt system based on data analysis - Google Patents
Intelligent auxiliary diagnosis prompt system based on data analysis Download PDFInfo
- Publication number
- CN116504392A CN116504392A CN202310489073.0A CN202310489073A CN116504392A CN 116504392 A CN116504392 A CN 116504392A CN 202310489073 A CN202310489073 A CN 202310489073A CN 116504392 A CN116504392 A CN 116504392A
- Authority
- CN
- China
- Prior art keywords
- data
- inquiry
- influence
- inspection
- analysis
- 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.)
- Withdrawn
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 238000007405 data analysis Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 56
- 238000004458 analytical method Methods 0.000 claims abstract description 49
- 238000007781 pre-processing Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000007689 inspection Methods 0.000 claims description 67
- 238000001514 detection method Methods 0.000 claims description 9
- 230000010354 integration Effects 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000002558 medical inspection Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 7
- 238000011156 evaluation Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 abstract description 3
- 208000019693 Lung disease Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002432 robotic surgery Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an intelligent auxiliary diagnosis prompt system based on data analysis, belonging to the technical field of auxiliary diagnosis; through carrying out inquiry monitoring and medical data statistics on targets from the aspects of inquiry and medical examination, data support in the aspects of inquiry and medical examination can be provided for subsequent integral analysis and evaluation, through preprocessing each item of data of inquiry statistics, the corresponding inquiry influence degree and examination influence degree are obtained through carrying out integrated calculation on the data items preprocessed in each aspect, and the integral of the inquiry and examination aspects can be analyzed based on the inquiry influence degree and the examination influence degree to obtain corresponding evaluation results, so that reference results with different dimensions can be provided; the method and the device are used for solving the technical problem that in the existing scheme, data statistics, data processing and data analysis are not carried out on the target from different dimensions, and the analysis results of the different dimensions are integrated and prompted, so that the overall effect of the auxiliary diagnosis prompt is poor.
Description
Technical Field
The invention relates to the technical field of auxiliary diagnosis, in particular to an intelligent auxiliary diagnosis prompt system based on data analysis.
Background
The intelligent medical auxiliary diagnosis plays an increasingly important role, and has wide application scenes from clinical medical auxiliary diagnosis, helping clinical reading, identifying tissue and organ focuses, to application of a robotic surgery system and an intelligent medical decision system, clinical health condition assessment, health medical treatment, auxiliary focus screening, community intelligent health auxiliary examination, detection and the like.
When the traditional auxiliary diagnosis prompting scheme is implemented, the data acquired by inquiry is subjected to preliminary judgment by virtue of the experience of doctors, and the defect of large error judgment caused by artificial experience influence or working state influence exists; or judging whether the data item obtained by monitoring is normal or not by matching the data item obtained by monitoring with the corresponding standard data item in sequence; however, data statistics, data processing and data analysis are not performed on the target from different dimensions, and the analysis results of different dimensions are integrated to prompt, so that the overall effect of the auxiliary diagnosis prompt is poor.
Disclosure of Invention
The invention aims to provide an intelligent auxiliary diagnosis prompt system based on data analysis, which is used for solving the technical problem that in the existing scheme, data statistics, data processing and data analysis are not carried out on targets from different dimensions, and analysis results of different dimensions are integrated to prompt, so that the overall effect of the auxiliary diagnosis prompt is poor.
The aim of the invention can be achieved by the following technical scheme:
an intelligent auxiliary diagnosis prompt system based on data analysis comprises a target data statistics module, a data analysis module and a data analysis module, wherein the target data statistics module is used for carrying out inquiry and medical examination on a target to obtain a target statistics set containing inquiry data and examination data; the inquiry data comprises a plurality of inquiry topics, corresponding answer keywords and topic weights; the inspection data comprises medical images obtained by medical inspection;
the target data preprocessing module is used for respectively carrying out data preprocessing and image preprocessing on the inquiry data and the inspection data in the target statistics set to obtain a statistics processing set containing inquiry processing data and inspection processing data;
the data integration analysis module is used for integrating and analyzing the data with different dimensionalities in the statistical processing set to obtain inquiry analysis data corresponding to the inquiry data and inspection analysis data corresponding to the inspection data;
the auxiliary diagnosis prompting module is used for integrating data analysis results in different dimensions to generate an auxiliary diagnosis report and prompting; comprising the following steps:
and respectively acquiring a query tag in the query analysis data and an inspection tag in the inspection analysis data, performing association combination with an identity mark corresponding to the target to generate an auxiliary diagnosis report, and prompting query influence and inspection influence corresponding to the query tag and the inspection tag.
Preferably, the step of obtaining the target statistics set includes:
performing inquiry on the target through a preset inquiry theme, and recording and associating a reply keyword corresponding to the target reply inquiry theme;
sequentially matching a plurality of questioning subjects with a questioning subject weight table pre-stored in an auxiliary database to obtain corresponding subject weights;
arranging a plurality of inquiry topics, corresponding answer keywords and topic weights according to a preset sequence and carrying out association combination with the identity marks corresponding to the targets to obtain inquiry data;
acquiring a medical image obtained by medical examination of a target, and performing association combination on the medical image of the target and a corresponding identity mark to obtain examination data;
the inquiry data and the examination data form a target statistics set and are uploaded to an auxiliary database.
Preferably, the step of obtaining the statistical processing set includes:
acquiring inquiry data in a target statistics set; when data preprocessing is carried out on a plurality of data items in the inquiry data, marking a plurality of ordered inquiry subjects; obtaining answer keywords and topic weights corresponding to a plurality of questioning topics in the questioning data;
marking topic weight corresponding to the questioning topic; matching a plurality of answer keywords of the questioning subject with a corresponding standard answer keyword library, marking the answer keywords successfully matched as selected keywords, and simultaneously obtaining and marking the keyword weights associated with the selected keywords; counting and marking the total number of the selected keywords;
and arranging and combining all the marked data according to the corresponding sequence to obtain inquiry processing data.
Preferably, medical images in the inspection processing data are acquired, preprocessing of the images is carried out, main body features in the medical images after the image preprocessing are extracted by using a convolutional neural network, and the main body features are divided according to preset dividing proportions to obtain a plurality of sub-features;
the method comprises the steps of arranging and numbering a plurality of sub-features according to a preset arrangement sequence to obtain sub-feature ordering data, and marking a plurality of adjacent sub-features of the sub-features as associated features according to the numbering sequence in the sub-feature ordering data;
sequentially acquiring gray values corresponding to the sub-features sequenced in the sub-feature sequencing data and associated gray scale ratios; and matching the acquired gray values and the associated gray scale with the standard gray values and the associated standard gray scale ranges corresponding to the sub-features respectively to obtain a first gray value or a second gray value.
Preferably, if the obtained gray value is different from the plurality of standard gray values corresponding to the sub-features, marking the gray value as a first gray value, and marking a gray scale corresponding to the first gray value as a first gray scale;
if the acquired gray value is the same as one of a plurality of standard gray values corresponding to the sub-features, but the corresponding gray scale does not belong to the standard gray scale range, marking the gray value as a second gray value, and marking the gray scale corresponding to the second gray value as a second gray scale; marking the corresponding sub-feature as the selected sub-feature according to the first gray value or the second gray value;
arranging and combining a plurality of selected sub-features and corresponding first gray values or second gray values according to a corresponding sequence to obtain inspection processing data;
the inquiry processing data and the examination processing data form a statistical processing set and are uploaded to an auxiliary database.
Preferably, the working steps of the data integration analysis module include:
acquiring inquiry processing data in a statistics processing set, extracting numerical values of a plurality of marked data items in the inquiry processing data, and vertically integrating the numerical values to acquire inquiry influence degree corresponding to the inquiry data, wherein the inquiry influence degree is a numerical value for integrating all data in the aspect of inquiry to integrally evaluate the influence in the aspect of inquiry;
when the analysis of the inquiry influence is carried out from the aspect of inquiry according to the inquiry influence degree, the inquiry influence degree is matched with a preset inquiry influence threshold value, so that inquiry analysis data comprising an influence-free inquiry label, a low-influence inquiry label, a medium-influence inquiry label and a high-influence inquiry label are obtained and uploaded to an auxiliary database.
Preferably, acquiring inspection processing data in the statistical processing set, extracting a plurality of selected sub-features in the inspection processing data and corresponding first gray values or second gray values, counting the total number of the selected sub-features and marking; respectively marking a first gray scale corresponding to the first gray values and a second gray scale corresponding to the second gray values; the method comprises the steps of extracting values of a first gray scale and a second gray scale corresponding to a plurality of selected sub-features of a mark, and vertically integrating the values in parallel to obtain detection influence corresponding to detection data, wherein the detection influence is a value for integrating different gray scale data in the aspect of the sub-features to integrally evaluate the detection influence of the sub-features; analysis of the influence of the examination is performed from the examination aspect according to the degree of influence of the examination.
Preferably, when the analysis of the inspection influence is performed in terms of inspection according to the inspection influence, the inspection influence is matched with a preset inspection influence range, and inspection analysis data including the no-influence inspection tag, the low-influence inspection tag, the medium-influence inspection tag, and the high-influence inspection tag is obtained and uploaded to the auxiliary database.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the inquiry monitoring and the medical data statistics are carried out on the target from the inquiry aspect and the medical examination aspect, so that the data support in the inquiry aspect and the medical examination aspect can be provided for the subsequent integral analysis and evaluation, and each item of data of the inquiry statistics can be standardized and normalized by preprocessing, so that the accuracy of the subsequent data integration calculation analysis can be effectively improved; the data items preprocessed in each aspect are integrated and calculated to obtain corresponding inquiry influence degree and checking influence degree, and the whole inquiry aspect and the whole checking aspect can be analyzed to obtain corresponding evaluation results based on the inquiry influence degree and the checking influence degree, so that reference results with different dimensions can be provided.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a block diagram of an intelligent auxiliary diagnostic hint system based on data analysis of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the invention provides an intelligent auxiliary diagnosis prompt system based on data analysis, which comprises a target data statistics module, a weight construction module, a target data preprocessing module, a data integration analysis module, an auxiliary diagnosis prompt module and an auxiliary database;
the target data statistics module is used for carrying out inquiry and medical examination on the target to obtain a target statistics set containing inquiry data and examination data; comprising the following steps:
performing inquiry on the target through a preset inquiry theme, and recording and associating a reply keyword corresponding to the target reply inquiry theme;
wherein, the target can be a patient with lung disease, the questioning subject is the conventional questioning problem of the existing lung disease, and the target can be the physical reaction, feeling and the like of the patient; the reply keywords corresponding to the target reply questioning subjects can be realized through manual recording or can be realized based on the existing intelligent voice recognition equipment, and the two modes are combined;
sequentially matching a plurality of questioning subjects with a questioning subject weight table pre-stored in an auxiliary database to obtain corresponding subject weights;
arranging a plurality of inquiry topics, corresponding answer keywords and topic weights according to a preset sequence and carrying out association combination with the identity marks corresponding to the targets to obtain inquiry data; the identity mark can be an identity card number;
acquiring a medical image obtained by medical examination of a target, and performing association combination on the medical image of the target and a corresponding identity mark to obtain examination data; the medical image may be a CT slice;
the inquiry data and the examination data form a target statistical set and are uploaded to an auxiliary database;
according to the embodiment of the invention, the data support of the inquiry aspect and the medical examination aspect can be provided for the subsequent integral analysis and evaluation by carrying out the inquiry monitoring and the medical data statistics on the target from the inquiry aspect and the medical examination aspect.
The weight construction module is used for presetting different questioning subjects to correspond to different subject weights, sequentially arranging and combining a plurality of preset questioning subjects and associated subject weights to obtain a questioning subject weight table, and uploading the questioning subject weight table to the auxiliary database for storage;
it should be noted that the topic weight is used for digitally representing the text type questioning topics, and simultaneously can represent that the importance and the influence of different questioning topics are different so as to realize the differential analysis and evaluation of the response of different follow-up questioning topics;
the target data preprocessing module is used for respectively carrying out data preprocessing and image preprocessing on the inquiry data and the inspection data in the target statistics set to obtain a statistics processing set containing inquiry processing data and inspection processing data; comprising the following steps:
acquiring inquiry data in a target statistics set;
when data preprocessing is carried out on a plurality of data items in the inquiry data, marking a plurality of ordered inquiry topics as i, i= [1,2,3, … …, n ]; n is a positive integer, expressed as the total number;
obtaining answer keywords and topic weights corresponding to a plurality of questioning topics in the questioning data;
marking the topic weight corresponding to the questioning topic as ZQi;
matching a plurality of answer keywords of the questioning subject with a corresponding standard answer keyword library, marking the answer keywords successfully matched as selected keywords, and simultaneously acquiring keyword weights associated with the selected keywords of the questioning subject and marking the keyword weights as GQi; wherein, the keyword weight can be customized through experience of related practitioners; counting the total number of selected keywords corresponding to the questioning subjects and marking as GZi;
the marked data are arranged and combined according to the corresponding sequence to obtain inquiry processing data;
in the embodiment of the invention, each item of data of inquiry statistics is preprocessed, so that each item of data is standardized and normalized, and the accuracy of the subsequent data integration calculation analysis can be effectively improved.
Acquiring medical images in inspection processing data, preprocessing the images, extracting main body features in the medical images subjected to image preprocessing by using a convolutional neural network, and dividing the main body features according to preset dividing proportions to obtain a plurality of sub-features; the body feature may be an integral feature of the lung;
it should be explained that preprocessing of the image includes, but is not limited to, gray scale variation, geometric correction, image enhancement, image filtering, etc.; the preset dividing ratio can be customized through experience of related practitioners; the main body characteristics are divided according to the preset dividing proportion, so that the main body characteristics are subjected to modularized treatment, the local parts of the main body characteristics can be analyzed more efficiently, and the overall effect of the main body characteristic analysis can be effectively improved based on the local analysis and combination of the main body characteristics;
the method comprises the steps of arranging and numbering a plurality of sub-features according to a preset arrangement sequence, wherein the preset arrangement sequence can be from left to right and from top to bottom, sub-feature ordering data are obtained, and a plurality of sub-features adjacent to the sub-features are marked as associated features according to the numbering sequence in the sub-feature ordering data;
sequentially acquiring gray values corresponding to the sub-features sequenced in the sub-feature sequencing data and associated gray scale ratios; matching the obtained gray values and the associated gray scale with the standard gray values and the associated standard gray scale ranges corresponding to the sub-features respectively;
the gray scale ratio of gray scale value association is the ratio of all gray scale values in the sub-feature occupied by the same gray scale value;
if the obtained gray value is different from a plurality of standard gray values corresponding to the sub-features, marking the gray value as a first gray value, and marking a gray scale corresponding to the first gray value as a first gray scale;
if the acquired gray value is the same as one of a plurality of standard gray values corresponding to the sub-features, but the corresponding gray scale does not belong to the standard gray scale range, marking the gray value as a second gray value, and marking the gray scale corresponding to the second gray value as a second gray scale; marking the corresponding sub-feature as the selected sub-feature according to the first gray value or the second gray value;
arranging and combining a plurality of selected sub-features and corresponding first gray values or second gray values according to a corresponding sequence to obtain inspection processing data;
the inquiry processing data and the examination processing data form a statistical processing set and are uploaded to an auxiliary database;
in the embodiment of the invention, by preprocessing the data with different dimensions and preprocessing and judging the image, reliable data support can be provided for the subsequent data integration analysis with different dimensions and the image local analysis;
the data integration analysis module is used for integrating and analyzing the data with different dimensionalities in the statistical processing set to obtain inquiry analysis data corresponding to the inquiry data and inspection analysis data corresponding to the inspection data; comprising the following steps:
acquiring inquiry processing data in the statistical processing set, extracting a plurality of topic weights ZQi, keyword weights GQi and numerical values of the total number GZi of selected keywords marked in the inquiry processing data, and integrating the numerical values in parallel through a formulaCalculating the inquiry influence WY corresponding to the acquired inquiry data;
note that the influence of the inquiry is a numerical value for integrating each item of data of the inquiry to evaluate the influence of the inquiry as a whole; the larger the influence of the inquiry is, the higher the influence of the corresponding inquiry is;
in addition, in the embodiment of the invention, the inquiry influence degree corresponding to the inquiry data is calculated by a formula, in practice, the sample inquiry data can be trained by an algorithm model in advance to obtain a sample model, and the value obtained by training the pretreated inquiry processing data by the sample model is named as the inquiry influence degree;
when analysis of inquiry influence is carried out according to inquiry influence degree from inquiry aspect, the inquiry influence degree WY is matched with a preset inquiry influence threshold WYY;
if WY is less than WYY and W1%, W1 is a real number less than one hundred, judging that the corresponding inquiry influence is not related and does not influence the inquiry label;
if WYY is more than or equal to 1% and less than WYY, judging that the corresponding inquiry influence is low and correlating low influence inquiry labels;
if WYY is less than or equal to WY and less than WYY is W2%, and W2 is a real number which is more than one hundred, judging that the corresponding inquiry influence is moderate and associating the inquiry label with the moderate influence;
if WY is more than or equal to WYY, W2%, judging that the corresponding inquiry influence is high and associating a high influence inquiry label;
the influence degree of the inquiry and the corresponding no-influence inquiry label, low-influence inquiry label, medium-influence inquiry label and high-influence inquiry label form inquiry analysis data and are uploaded to an auxiliary database;
in the implementation of the invention, the corresponding inquiry effect degree is obtained by integrating and calculating the inquiry data of different types in inquiry, and the inquiry result corresponding to the target is evaluated based on the inquiry effect degree, so that the analysis prompt effect in the aspect of inquiry can be effectively improved;
acquiring inspection processing data in the statistical processing set, extracting a plurality of selected sub-features and corresponding first gray values or second gray values in the inspection processing data, counting the total number of the selected sub-features and marking as k, k= [1,2,3, … …, m]The method comprises the steps of carrying out a first treatment on the surface of the m is a positive integer, expressed as the total number; marking the first gray scale corresponding to the first gray values and the second gray scale corresponding to the second gray values as YHk and EHk respectively; the values of the first gray scale YHk and the second gray scale EHk corresponding to the selected sub-features of the extracted mark are integrated in parallel and vertically, and are calculated by the formulaCalculating and acquiring the checking influence degree JY corresponding to the checking data; wherein j1 and j2 are preset different proportion coefficients, and j1 is more than 10 and less than or equal to j2; YH0 is a preset standard abnormal proportion, EHk0 is a standard gray scale proportion range corresponding to the second gray valueIs a median value of (2);
it should be noted that the inspection influence degree is a numerical value for integrating different gray data in terms of sub-features to integrally evaluate the inspection influence of the sub-features; the larger the inspection influence degree is, the larger the inspection influence of the corresponding sub-feature is;
in addition, the checking influence degree can be obtained by other methods, such as the method based on the algorithm model training;
when analysis of the inspection influence is performed from the aspect of inspection according to the inspection influence, the inspection influence JY is matched with a preset inspection influence range [ JYY, JYY ];
if JY < JYY1 x J1, J1 is a real number smaller than one hundred, judging that the corresponding checking influence is not related and does not influence the checking label;
if JYY is less than or equal to 1.J1% and less than or equal to JY < JYY1, judging that the corresponding checking influence is low and correlating with a low influence checking label;
if JYY < JY < JYY 2.J2%, J2 is a real number greater than one hundred, judging that the corresponding checking influence is moderate and associating the checking label with the moderate influence;
if JY is more than or equal to JYY2 x J2%, judging that the corresponding checking influence is high and associating the high influence checking label;
checking influence degree, and corresponding non-influence checking label, low-influence checking label, medium-influence checking label and high-influence checking label to form checking analysis data and uploading the checking analysis data to an auxiliary database;
in the embodiment of the invention, the data items preprocessed in each aspect are integrated and calculated to obtain the corresponding inquiry influence degree and checking influence degree, and the whole inquiry aspect and checking aspect can be analyzed to obtain the corresponding evaluation result based on the inquiry influence degree and checking influence degree, so that the reference results of different dimensions can be provided.
The auxiliary diagnosis prompting module is used for integrating data analysis results in different dimensions to generate an auxiliary diagnosis report and prompting; comprising the following steps:
and respectively acquiring a query tag in the query analysis data and an inspection tag in the inspection analysis data, performing association combination with an identity mark corresponding to the target to generate an auxiliary diagnosis report, and prompting query influence and inspection influence corresponding to the query tag and the inspection tag.
In addition, the formulas related in the above are all formulas with dimensions removed and numerical values calculated, and are a formula which is obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and the proportionality coefficient in the formulas and each preset threshold value in the analysis process are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data; the size of the scaling factor is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, and the size of the scaling factor depends on the number of sample data and the corresponding processing coefficient is preliminarily set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected.
In the several embodiments provided by the present invention, it should be understood that the disclosed system may be implemented in other ways. For example, the above-described embodiments of the invention are merely illustrative, and for example, the division of modules is merely a logical function division, and other manners of division may be implemented in practice.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module. The integrated modules may be implemented in hardware or in hardware plus software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the essential characteristics thereof.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (8)
1. The intelligent auxiliary diagnosis prompt system based on the data analysis is characterized by comprising a target data statistics module, a target analysis module and a data analysis module, wherein the target data statistics module is used for carrying out inquiry and medical examination on a target to obtain a target statistics set containing inquiry data and examination data; the inquiry data comprises a plurality of inquiry topics, corresponding answer keywords and topic weights; the inspection data comprises medical images obtained by medical inspection;
the target data preprocessing module is used for respectively carrying out data preprocessing and image preprocessing on the inquiry data and the inspection data in the target statistics set to obtain a statistics processing set containing inquiry processing data and inspection processing data;
the data integration analysis module is used for integrating and analyzing the data with different dimensionalities in the statistical processing set to obtain inquiry analysis data corresponding to the inquiry data and inspection analysis data corresponding to the inspection data;
the auxiliary diagnosis prompting module is used for integrating data analysis results in different dimensions to generate an auxiliary diagnosis report and prompting; comprising the following steps:
and respectively acquiring a query tag in the query analysis data and an inspection tag in the inspection analysis data, performing association combination with an identity mark corresponding to the target to generate an auxiliary diagnosis report, and prompting query influence and inspection influence corresponding to the query tag and the inspection tag.
2. The intelligent aided diagnosis and guidance system based on data analysis of claim 1, wherein the step of obtaining the target statistics set includes:
performing inquiry on the target through a preset inquiry theme, and recording and associating a reply keyword corresponding to the target reply inquiry theme;
sequentially matching a plurality of questioning subjects with a questioning subject weight table pre-stored in an auxiliary database to obtain corresponding subject weights;
arranging a plurality of inquiry topics, corresponding answer keywords and topic weights according to a preset sequence and carrying out association combination with the identity marks corresponding to the targets to obtain inquiry data;
acquiring a medical image obtained by medical examination of a target, and performing association combination on the medical image of the target and a corresponding identity mark to obtain examination data;
the inquiry data and the examination data form a target statistics set and are uploaded to an auxiliary database.
3. The intelligent aided diagnosis and guidance system based on data analysis of claim 1, wherein the step of obtaining the statistical processing set includes:
acquiring inquiry data in a target statistics set; when data preprocessing is carried out on a plurality of data items in the inquiry data, marking a plurality of ordered inquiry subjects; obtaining answer keywords and topic weights corresponding to a plurality of questioning topics in the questioning data;
marking topic weight corresponding to the questioning topic; matching a plurality of answer keywords of the questioning subject with a corresponding standard answer keyword library, marking the answer keywords successfully matched as selected keywords, and simultaneously obtaining and marking the keyword weights associated with the selected keywords; counting and marking the total number of the selected keywords;
and arranging and combining all the marked data according to the corresponding sequence to obtain inquiry processing data.
4. The intelligent auxiliary diagnosis prompt system based on data analysis of claim 3, wherein medical images in the inspection processing data are acquired and preprocessed, main body features in the medical images preprocessed by the images are extracted by using a convolutional neural network, and the main body features are divided according to a preset division ratio to obtain a plurality of sub-features;
the method comprises the steps of arranging and numbering a plurality of sub-features according to a preset arrangement sequence to obtain sub-feature ordering data, and marking a plurality of adjacent sub-features of the sub-features as associated features according to the numbering sequence in the sub-feature ordering data;
sequentially acquiring gray values corresponding to the sub-features sequenced in the sub-feature sequencing data and associated gray scale ratios; and matching the acquired gray values and the associated gray scale with the standard gray values and the associated standard gray scale ranges corresponding to the sub-features respectively to obtain a first gray value or a second gray value.
5. The intelligent auxiliary diagnosis prompt system based on data analysis of claim 4, wherein if the obtained gray value is different from the plurality of standard gray values corresponding to the sub-feature, the gray value is marked as a first gray value, and the gray scale corresponding to the first gray value is marked as a first gray scale;
if the acquired gray value is the same as one of a plurality of standard gray values corresponding to the sub-features, but the corresponding gray scale does not belong to the standard gray scale range, marking the gray value as a second gray value, and marking the gray scale corresponding to the second gray value as a second gray scale; marking the corresponding sub-feature as the selected sub-feature according to the first gray value or the second gray value;
arranging and combining a plurality of selected sub-features and corresponding first gray values or second gray values according to a corresponding sequence to obtain inspection processing data;
the inquiry processing data and the examination processing data form a statistical processing set and are uploaded to an auxiliary database.
6. The intelligent aided diagnosis and guidance system based on data analysis of claim 1, wherein the working steps of the data integration analysis module include:
acquiring inquiry processing data in a statistics processing set, extracting numerical values of a plurality of marked data items in the inquiry processing data, and vertically integrating the numerical values to acquire inquiry influence degree corresponding to the inquiry data, wherein the inquiry influence degree is a numerical value for integrating all data in the aspect of inquiry to integrally evaluate the influence in the aspect of inquiry;
when the analysis of the inquiry influence is carried out from the aspect of inquiry according to the inquiry influence degree, the inquiry influence degree is matched with a preset inquiry influence threshold value, so that inquiry analysis data comprising an influence-free inquiry label, a low-influence inquiry label, a medium-influence inquiry label and a high-influence inquiry label are obtained and uploaded to an auxiliary database.
7. The intelligent auxiliary diagnosis prompt system based on data analysis of claim 6, wherein the method comprises the steps of obtaining inspection processing data in a statistical processing set, extracting a plurality of selected sub-features in the inspection processing data and corresponding first gray values or second gray values, counting the total number of the selected sub-features, and marking; respectively marking a first gray scale corresponding to the first gray values and a second gray scale corresponding to the second gray values; the method comprises the steps of extracting values of a first gray scale and a second gray scale corresponding to a plurality of selected sub-features of a mark, and vertically integrating the values in parallel to obtain detection influence corresponding to detection data, wherein the detection influence is a value for integrating different gray scale data in the aspect of the sub-features to integrally evaluate the detection influence of the sub-features; analysis of the influence of the examination is performed from the examination aspect according to the degree of influence of the examination.
8. The intelligent auxiliary diagnostic hint system based on data analysis of claim 7, wherein when the analysis of the inspection influence is performed from the aspect of inspection according to the inspection influence, the inspection influence is matched with a preset inspection influence range, and inspection analysis data including a no-influence inspection tag, a low-influence inspection tag, a medium-influence inspection tag and a high-influence inspection tag is obtained and uploaded to the auxiliary database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310489073.0A CN116504392A (en) | 2023-05-04 | 2023-05-04 | Intelligent auxiliary diagnosis prompt system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310489073.0A CN116504392A (en) | 2023-05-04 | 2023-05-04 | Intelligent auxiliary diagnosis prompt system based on data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116504392A true CN116504392A (en) | 2023-07-28 |
Family
ID=87319900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310489073.0A Withdrawn CN116504392A (en) | 2023-05-04 | 2023-05-04 | Intelligent auxiliary diagnosis prompt system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116504392A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116741360A (en) * | 2023-08-16 | 2023-09-12 | 深圳市微能信息科技有限公司 | Doctor inquiry and service quality evaluation system based on intelligent terminal |
| CN116881670A (en) * | 2023-09-01 | 2023-10-13 | 国网江苏省电力有限公司扬州供电分公司 | Communication optical cable attachment checking method based on GIS map |
| CN116881670B (en) * | 2023-09-01 | 2024-06-11 | 国网江苏省电力有限公司扬州供电分公司 | Communication optical cable attachment checking method based on GIS map |
-
2023
- 2023-05-04 CN CN202310489073.0A patent/CN116504392A/en not_active Withdrawn
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116741360A (en) * | 2023-08-16 | 2023-09-12 | 深圳市微能信息科技有限公司 | Doctor inquiry and service quality evaluation system based on intelligent terminal |
| CN116741360B (en) * | 2023-08-16 | 2023-12-19 | 深圳市微能信息科技有限公司 | Doctor inquiry and service quality evaluation system based on intelligent terminal |
| CN116881670A (en) * | 2023-09-01 | 2023-10-13 | 国网江苏省电力有限公司扬州供电分公司 | Communication optical cable attachment checking method based on GIS map |
| CN116881670B (en) * | 2023-09-01 | 2024-06-11 | 国网江苏省电力有限公司扬州供电分公司 | Communication optical cable attachment checking method based on GIS map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110680326B (en) | Pneumoconiosis identification and grading judgment method based on deep convolutional neural network | |
| CN103249358B (en) | Medical image-processing apparatus | |
| Slovic et al. | Analyzing use of diagnostic signs | |
| CN116504392A (en) | Intelligent auxiliary diagnosis prompt system based on data analysis | |
| CN110223784A (en) | Clinical test patient's matching process | |
| CN115578372A (en) | Bone age assessment method, device and medium based on target detection and convolution transformation | |
| US20200065967A1 (en) | Computer system, method, and program for diagnosing subject | |
| CN114240874A (en) | Bone age assessment method and device based on deep convolutional neural network and feature fusion and computer readable storage medium | |
| CN112862749A (en) | Automatic identification method for bone age image after digital processing | |
| CN116864062B (en) | Health physical examination report data analysis management system based on Internet | |
| CN113052227A (en) | Pulmonary tuberculosis identification method based on SE-ResNet | |
| CN116350203B (en) | Physical testing data processing method and system | |
| CN112690815A (en) | System and method for assisting in diagnosing lesion grade based on lung image report | |
| CN116580801A (en) | Ultrasonic inspection method based on large language model | |
| US20230060794A1 (en) | Diagnostic Tool | |
| CN116484290A (en) | Depression recognition model construction method based on Stacking integration | |
| CN114240934B (en) | Image data analysis method and system based on acromegaly | |
| CN113889274B (en) | Method and device for constructing risk prediction model of autism spectrum disorder | |
| CN114925196A (en) | Diabetes blood test abnormal value auxiliary removing method under multilayer perception network | |
| CN114864086A (en) | Disease prediction method based on lung function report template | |
| Ajad et al. | CV-CXR: A Method for Classification and Visualisation of Covid-19 virus using CNN and Heatmap | |
| CN117476219B (en) | Auxiliary method and auxiliary system for positioning CT (computed tomography) tomographic image based on big data analysis | |
| Elepo et al. | Statistical Analysis on Students’ Performance | |
| Rassmann et al. | Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias | |
| Priyadharshini et al. | Automatic identification and classification of brain tumor using MRI images through transfer learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230728 |