CN117174293A - Critical value judging and extracting method based on patient test data - Google Patents
Critical value judging and extracting method based on patient test data Download PDFInfo
- Publication number
- CN117174293A CN117174293A CN202311152277.1A CN202311152277A CN117174293A CN 117174293 A CN117174293 A CN 117174293A CN 202311152277 A CN202311152277 A CN 202311152277A CN 117174293 A CN117174293 A CN 117174293A
- Authority
- CN
- China
- Prior art keywords
- test data
- critical value
- data
- test
- patient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 316
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 238000003556 assay Methods 0.000 claims description 35
- 230000002159 abnormal effect Effects 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 25
- 238000000605 extraction Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000003745 diagnosis Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010339 medical test Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000002251 Dissecting Aneurysm Diseases 0.000 description 1
- 208000010378 Pulmonary Embolism Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 206010002895 aortic dissection Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 201000003144 pneumothorax Diseases 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Classifications
-
- 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
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a critical value judging and extracting method based on patient test data, which comprises the following steps: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report; establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data; the critical condition of the patient is judged by combining critical value thresholds, and the critical value is judged by establishing a machine learning model through learning historical diagnostic data, so that the accuracy of the model and the accuracy of critical value judgment are improved.
Description
Technical Field
The application relates to the technical field of medical treatment, in particular to a critical value judging and extracting method based on patient test data.
Background
Critical values are also known as "Panic". When such test results appear, it is indicated that the patient may be in a life-threatening marginal state, where the patient's life may be saved if timely and effective treatment is administered; otherwise, adverse consequences may occur, so this is a test result that represents life threatening and is therefore referred to as critical value; the third-level hospital review rules of national defense and health committee require the emergency report time to be accurate to a minute, and the safety goal of the patients of China physicians' society is to strengthen the clinical critical value reporting system, and the international medical health institution authentication joint committee requires the establishment of an effective critical value reporting system. The effective discovery and transmission of critical values in medical images can gain valuable time for medical behaviors, the mortality rate and disability rate are reduced, at present, the result of the critical values in test results depends on judgment of doctors, and the transmission of the critical values depends on artificial phones and records, so that valuable treatment time of patients is influenced between the test results and the test results taken by the doctors;
the Chinese patent of publication No. CN108492874A discloses an intelligent critical value diagnosis and treatment system, which comprises a critical value screening module and a critical value transmission module, wherein: the critical value screening module establishes a critical value database, and trains and verifies the critical value database to obtain a critical value algorithm; the critical value screening module divides a critical value database into a critical value positive database and a critical value negative database, randomly divides the critical value positive database into a positive training database and a positive verification database according to a certain proportion, randomly divides the critical value negative database into a negative training database and a negative verification database according to a certain proportion, trains a critical value algorithm by utilizing the positive training database and the negative training database, and verifies the critical value algorithm by utilizing the positive verification database and the negative verification database; checking whether the data of the radiological image and the radiological report has critical symptoms or not through the critical value algorithm, if so, starting an alarm device after verification, and sending the alarm device to a clinician through the critical value transmission module; although the screening module and the transmission module are established in the patent, the screening module is only applied to pulmonary artery embolism critical value, aortic dissection critical value and pneumothorax critical value, and only one value is judged at the same time, the critical degree of the illness state of a patient cannot be judged through a plurality of test data.
Disclosure of Invention
In order to solve the above problems, the present application proposes a critical value judging and extracting method based on patient test data to more exactly solve the above problems.
The application is realized by the following technical scheme:
the application provides a critical value judging and extracting method based on patient test data, which comprises the following steps:
s1: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
s2: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
s3: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time;
s4: under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data and the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time when any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values.
Furthermore, the critical value judging and extracting method based on the test data of the patient, wherein the test is carried out on the patient by adopting standard medical detection equipment, all the test data are automatically recorded and stored, and the test report forming step comprises the following steps:
performing data cleaning and data standardization on the assay data, wherein the data cleaning process comprises the following steps of: removing one or more of abnormal value, null value and error data;
data normalization involves converting all data into a uniform format.
Furthermore, the critical value judging and extracting method based on the test data of the patient establishes a single critical value threshold according to clinical medical indexes, establishes a machine learning model at the same time, and sets a combined critical value threshold according to the correlation of the test data, wherein the step of setting comprises the following steps:
s21: preprocessing the diagnosis data in the medical database, and outputting related cases of critical value processing;
s22: constructing training data, and matching the test data in the related cases to obtain a test data matching group with the same abnormality;
s23: building a training model, putting the test data pairing group into a correlation model, and calculating the correlation between the test data;
s24: calculating a combined critical value threshold according to the correlation, and returning the combined critical value threshold to the training model for detection;
s25: if the obtained test data is not in the test data matched group, the loss between the calculated test data and the corresponding test data in the test data matched group is calculated, and the loss is uploaded to the training model until the accuracy of the training model reaches the standard.
Furthermore, the method for judging and extracting critical values based on the test data of the patient includes the steps of constructing training data, matching test data in related cases, and obtaining a matched set of test data with the same abnormality, wherein the matched set of test data comprises the following steps:
each pair of data in the paired set of assay data represents the same critical value condition.
Furthermore, the critical value judging and extracting method based on the test data of the patient includes the steps of constructing a training model, putting the test data pairing group into a correlation model, and calculating the correlation between the test data:
the correlation model includes:
the set of assay data one is x= { X 1 ,x 2 ,...,x n The collection of assay data two is: y= { Y 1 ,y 2 ,...,y n One for each assay data two, the correlation coefficient of which is expressed as:
wherein r is 1 Is a coefficient of correlation with the correlation coefficient,and->Respectively x 1 And y 1 The average correlation is obtained comprehensively as:
furthermore, the critical value judging and extracting method based on the patient test data includes the steps of:
providing a patient's test data is abnormal on test data one X and test data two Y, and the test data is X 1 The test data (X I Y) of the patient can be converted into (X) 1 I Rx 1 ) The method comprises the steps of carrying out a first treatment on the surface of the If y is satisfied 1 =Rx 1 The test data of the patient is proved to be critical values.
Further, the critical value judging and extracting method based on the patient test data includes the steps of:
where J represents loss.
Further, the critical value judging and extracting method based on the patient test data is applied to a critical value judging and extracting system based on the patient test data, and the system comprises:
and a data acquisition module: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
a threshold value establishment module: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
and an analysis module: analyzing that a plurality of test data are abnormal;
and a judging module: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time; under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data, the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time if any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values;
and a transmission module: the assay report is transmitted to the healthcare worker in real time.
A computer device comprising a memory and a processor, said memory having stored therein a computer program, characterized in that said processor, when executing said computer program, implements the steps of said method for critical value determination and extraction based on patient assay data.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the patient assay data based critical value determination and extraction method.
The application has the beneficial effects that:
according to the critical value judging and extracting method based on the patient test data, different critical value confirming modes are established, critical value confirmation is carried out on single test data, critical value confirmation is carried out on multiple test data, and the critical value judgment of the patient under different conditions is ensured to be more accurate;
according to the machine learning model, the correlation among the abnormality of the historical multi-test data is comprehensively obtained through learning the diagnosis data in the historical medical database, and meanwhile, the error in the training model is made up through the loss function, so that the output correlation coefficient is more accurate, and the accuracy and the efficiency of critical value judgment are improved.
Drawings
FIG. 1 is a flow chart of a method for critical value determination and extraction based on patient assay data according to the present application;
FIG. 2 is a flow chart of step S2 in the critical value determination and extraction method based on patient assay data according to the present application;
fig. 3 is a schematic structural diagram of a computer device implementing a critical value judgment and extraction method based on patient assay data according to the present application.
Detailed Description
In order to more clearly and completely describe the technical scheme of the application, the application is further described below with reference to the accompanying drawings.
Referring to fig. 1-3, the present application provides a critical value judging and extracting method based on patient test data.
In this embodiment, the present application provides a method for critical value judgment and extraction based on patient test data, comprising:
s1: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
s2: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
s3: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time;
s4: under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data and the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time when any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values.
In this embodiment, a standard-compliant medical test apparatus is used to perform an assay on a patient using a body fluid such as blood, urine, tissue samples, etc. that is capable of detecting an index in the patient's body; the data are finally consolidated into an assay report which is taken by the patient himself or by the attendant physician and used as a criterion for the diagnosis of the illness during the normal medical procedure; based on the existing clinical medical index, a threshold value of a critical value is set for each independent detection item, in short, which test results are normal and which are beyond the normal range and possibly form risks for a patient, meanwhile, a model is also established according to the relevance among a plurality of test data by utilizing a machine learning technology, the model can set a joint critical value threshold value, which means that not only a single test result exceeds the threshold value but also the joint state of a plurality of test results can be identified as critical, if only one test data is abnormal, the test result is judged as critical value if the single critical value threshold value set in the prior step S2 is exceeded or is lower, and once the test result is confirmed as critical value, relevant test reports can be transmitted to medical staff in real time so that the medical staff can evaluate and intervene on the patient rapidly; if two or more test data are abnormal, it is determined whether each test data exceeds or falls below the joint critical value threshold set in S2, if the test result is determined to be a critical value, and once the critical value is determined, the relevant test report is transmitted to the medical staff in real time.
Further, in the step of performing an assay on the patient using the standard medical detection device, automatically recording and storing all assay data, and forming an assay report, the method comprises the steps of:
performing data cleaning and data standardization on the assay data, wherein the data cleaning process comprises the following steps of: removing one or more of abnormal value, null value and error data;
data normalization involves converting all data into a uniform format.
Further, the step of setting the threshold of the combined critical value according to the correlation of the test data includes:
s21: preprocessing the diagnosis data in the medical database, and outputting related cases of critical value processing;
s22: constructing training data, and matching the test data in the related cases to obtain a test data matching group with the same abnormality;
s23: building a training model, putting the test data pairing group into a correlation model, and calculating the correlation between the test data;
s24: calculating a combined critical value threshold according to the correlation, and returning the combined critical value threshold to the training model for detection;
s25: if the obtained test data is not in the test data matched group, the loss between the calculated test data and the corresponding test data in the test data matched group is calculated, and the loss is uploaded to the training model until the accuracy of the training model reaches the standard.
Further, in the step of constructing training data and matching test data in related cases to obtain a matched set of test data with the same abnormality, the step of matching test data with the same abnormality includes:
each pair of data in the paired set of assay data represents the same critical value condition.
Further, in the step of constructing the training model, the step of placing the paired groups of test data into the correlation model and calculating the correlation between the test data includes:
the correlation model includes:
the set of assay data one is x= { X 1 ,x 2 ,...,x n The collection of assay data two is: y= { Y 1 ,y 2 ,...,y n One for each assay data two, the correlation coefficient of which is expressed as:
wherein r is 1 Is a coefficient of correlation with the correlation coefficient,and->Respectively x 1 And y 1 The average correlation is obtained comprehensively as:
further, the step of calculating the joint critical value threshold according to the correlation includes:
providing a patient's test data is abnormal on test data one X and test data two Y, and the test data is X 1 The test data (X I Y) of the patient can be converted into (X) 1 I Rx 1 ) The method comprises the steps of carrying out a first treatment on the surface of the If y is satisfied 1 =Rx 1 The test data of the patient is proved to be critical values.
Further, the step of losing between the calculated assay data and the corresponding assay data in the paired set of assay data comprises:
where J represents loss.
Further, the critical value judging and extracting method based on the patient test data is applied to a critical value judging and extracting system based on the patient test data, and the system comprises:
and a data acquisition module: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
a threshold value establishment module: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
and an analysis module: analyzing that a plurality of test data are abnormal;
and a judging module: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time; under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data, the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time if any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values;
and a transmission module: the assay report is transmitted to the healthcare worker in real time.
Referring to fig. 3, in an embodiment of the present application, there is further provided a computer device, which may be a server, and an internal structure thereof may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for data such as assay data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by the processor implements a critical value determination and extraction method based on patient test data.
It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present application further provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method for critical value judgment and extraction based on patient test data, specifically:
s1: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
s2: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
s3: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time;
s4: under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data and the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time when any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by hardware associated with a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present application and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that, in the present application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application or direct or indirect application in other related technical fields are included in the scope of the present application.
Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A method for critical value determination and extraction based on patient assay data, comprising:
s1: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
s2: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
s3: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time;
s4: under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data and the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time when any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values.
2. The method for critical value judgment and extraction based on patient test data according to claim 1, wherein in the step of automatically recording and saving all test data in the test performed on the patient using the standard medical test device, the step of forming a test report includes:
performing data cleaning and data standardization on the assay data, wherein the data cleaning process comprises the following steps of: removing one or more of abnormal value, null value and error data;
data normalization involves converting all data into a uniform format.
3. The method for determining and extracting critical value based on patient test data according to claim 1, wherein the step of setting the combined critical value threshold according to the correlation of the test data while establishing the single critical value threshold according to the clinical medical index while establishing the machine learning model comprises:
s21: preprocessing the diagnosis data in the medical database, and outputting related cases of critical value processing;
s22: constructing training data, and matching the test data in the related cases to obtain a test data matching group with the same abnormality;
s23: building a training model, putting the test data pairing group into a correlation model, and calculating the correlation between the test data;
s24: calculating a combined critical value threshold according to the correlation, and returning the combined critical value threshold to the training model for detection;
s25: if the obtained test data is not in the test data matched group, the loss between the calculated test data and the corresponding test data in the test data matched group is calculated, and the loss is uploaded to the training model until the accuracy of the training model reaches the standard.
4. The method for critical value judgment and extraction based on patient test data according to claim 3, wherein the step of pairing test data in related cases to obtain paired sets of test data having the same abnormality comprises:
each pair of data in the paired set of assay data represents the same critical value condition.
5. A method of critical value determination and extraction based on patient test data according to claim 3, wherein in said constructing a training model, placing the paired sets of test data into a correlation model, the step of calculating correlations between test data comprises:
the correlation model includes:
the set of assay data one is x= { X 1 ,x 2 ,...,x n The collection of assay data two is: y= { Y 1 ,y 2 ,...,y n One for each assay data two, the correlation coefficient of which is expressed as:
wherein r is 1 Is a coefficient of correlation with the correlation coefficient,and->Respectively x 1 And y 1 The average correlation is obtained comprehensively as:
6. the method of claim 5, wherein the step of calculating a joint critical value threshold from the correlation comprises:
providing a patient's test data is abnormal on test data one X and test data two Y, and the test data is X 1 The test data (X I Y) of the patient can be converted into (X) 1 I Rx 1 ) The method comprises the steps of carrying out a first treatment on the surface of the If y is satisfied 1 =Rx 1 The test data of the patient is proved to be critical values.
7. The method of claim 6, wherein the step of losing between the calculated test data and the corresponding test data in the test data paired set comprises:
where J represents loss.
8. The method for critical value determination and extraction based on patient test data according to claim 1, wherein the method for critical value determination and extraction based on patient test data is applied in a critical value determination and extraction system based on patient test data, the system comprising:
and a data acquisition module: testing the patient by adopting standard medical detection equipment, automatically recording and storing all test data to form a test report;
a threshold value establishment module: establishing a single critical value threshold according to clinical medical indexes, simultaneously establishing a machine learning model, and setting a combined critical value threshold according to the correlation of test data;
and an analysis module: analyzing that a plurality of test data are abnormal;
and a judging module: under the condition that only first test data are abnormal, comparing the preset critical value threshold value of the single body with the first test data, judging the size ratio of the first test data to the critical value threshold value of the first single body, and if the size ratio is larger than and/or smaller than the critical value threshold value of the first single body, judging the first test data to be the critical value and transmitting the test report to medical staff in real time; under the condition that the first test data, the second test data, the first test data and the nth test data are abnormal, comparing the first test data with a first combined dangerous value threshold value, judging that the first test data are dangerous values if the first test data are larger than and/or smaller than the first combined dangerous value threshold value, transmitting the first test data to medical staff, judging the second test data, the first test data, the nth test data if the first test data are not dangerous values, and transmitting the test report to the medical staff in real time if any test data of the first test data, the second test data, the first test data and the nth test data are dangerous values;
and a transmission module: the assay report is transmitted to the healthcare worker in real time.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the critical value judgment and extraction method based on patient assay data as claimed in any one of claims 1 to 8.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the critical value judgment and extraction method based on patient assay data as claimed in any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311152277.1A CN117174293A (en) | 2023-09-07 | 2023-09-07 | Critical value judging and extracting method based on patient test data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311152277.1A CN117174293A (en) | 2023-09-07 | 2023-09-07 | Critical value judging and extracting method based on patient test data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117174293A true CN117174293A (en) | 2023-12-05 |
Family
ID=88933332
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311152277.1A Pending CN117174293A (en) | 2023-09-07 | 2023-09-07 | Critical value judging and extracting method based on patient test data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117174293A (en) |
-
2023
- 2023-09-07 CN CN202311152277.1A patent/CN117174293A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR20190132290A (en) | Method, server and program of learning a patient diagnosis | |
CN114639478B (en) | Ultrasonic monitoring system based on valvular heart disease | |
CN116895372B (en) | Intelligent first-aid grading system based on large-scale language model and meta-learning | |
CN100472555C (en) | Method and system for detecting artifacts in ICU patient records by data fusion and hypothesis testing | |
CN110504037A (en) | The operating room digital operation station interconnected based on 5G technical information | |
CN114220514A (en) | Internet hospital patient diagnosis and treatment data analysis processing method, equipment and storage medium | |
Zhang et al. | Phase I study of surgical performances with risk-adjusted Shewhart control charts | |
CN114842935A (en) | Intelligent detection method and system for night ward round of hospital | |
CN112447293A (en) | VTE risk early warning system | |
CN113611428A (en) | Method and system for screening high-risk group suffering from cerebral apoplexy | |
Patel | Classification of COVID-19 from chest X-ray images using a deep convolutional neural network | |
CN117174293A (en) | Critical value judging and extracting method based on patient test data | |
CN106021920A (en) | Automatic diagnosis oriented medical data processing system and device based on neural network | |
CN114898859A (en) | Acute aortic dissection hospital internal prognosis prediction system | |
KR102541362B1 (en) | Apparatus for predicting intradialytic hypotension using AI and method thereof | |
CN114974590A (en) | Multi-dimensional monitoring critical patient prediction nursing method and system | |
CN114550896A (en) | Dizziness patient emergency pre-examination triage decision-making method, device and model based on artificial neural network | |
CN110910980A (en) | Sepsis early warning device, equipment and storage medium | |
CN110782990B (en) | Method, system and mobile platform for stroke risk assessment of basic public and satellite service | |
CN112712865B (en) | Multi-source heterogeneous doctor-patient experience abnormal data fusion working system and working method | |
CN116844684B (en) | Quality control processing method, device, equipment and medium for medical inspection result | |
CN113327655B (en) | Outlier detection method, device, equipment and medium for multidimensional data | |
CN116487049B (en) | Unplanned reentry event processing system based on decision analysis | |
CN117379009A (en) | Early warning and monitoring system for critical cardiovascular and cerebrovascular diseases of old people in community | |
CN117577295A (en) | Non-planned re-operation prediction method, device, equipment and storage medium |
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 |