CN112070150B - Method for establishing CT enhanced contrast agent intelligent matching model - Google Patents

Method for establishing CT enhanced contrast agent intelligent matching model Download PDF

Info

Publication number
CN112070150B
CN112070150B CN202010926659.5A CN202010926659A CN112070150B CN 112070150 B CN112070150 B CN 112070150B CN 202010926659 A CN202010926659 A CN 202010926659A CN 112070150 B CN112070150 B CN 112070150B
Authority
CN
China
Prior art keywords
contrast agent
allergic
enhancement
factor
correlation
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010926659.5A
Other languages
Chinese (zh)
Other versions
CN112070150A (en
Inventor
李真林
彭婉琳
徐旭
宋彬
赵武
曲建明
张金戈
胡斯娴
刘科伶
曾令明
曾文
夏春潮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
West China Hospital of Sichuan University
Original Assignee
West China Hospital of Sichuan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by West China Hospital of Sichuan University filed Critical West China Hospital of Sichuan University
Priority to CN202010926659.5A priority Critical patent/CN112070150B/en
Publication of CN112070150A publication Critical patent/CN112070150A/en
Application granted granted Critical
Publication of CN112070150B publication Critical patent/CN112070150B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images

Abstract

The invention discloses a method for establishing an intelligent matching model of a CT enhanced contrast agent, which belongs to the field of medical big data analysis, and comprises the steps of carrying out data standardization treatment, and carrying out statistics on the allergic number of patients and contrast agent allergic reaction index data of CT enhanced examination; aggregating the allergic population number of the patient subjected to CT enhancement examination and the contrast agent allergic reaction index data; predicting which contrast agent used by future CT enhancement inspectors has anaphylactic reaction by using a Bayesian ridge regression model; calculating the correlation between the prediction sequence and the real contrast agent allergy population sequence to obtain the correlation degree between the influence factor and the contrast agent anaphylactic reaction, and obtaining the key factor influencing the contrast agent according to the analysis result; and obtaining the weight of the independent variable through logistic regression analysis, and determining the grade of the key factor. The invention ensures that the use of the contrast agent is more scientific and standardized, can effectively reduce the occurrence of medical accidents, can reduce the probability of harm of the contrast agent to patients, and can improve the service level of hospitals.

Description

Method for establishing CT enhanced contrast agent intelligent matching model
Technical Field
The invention belongs to the technical field of medical big data analysis, and particularly relates to a method for establishing an intelligent matching model of a CT enhanced contrast agent.
Background
Contrast agents are currently widely used in the medical examination field, such as enhanced CT, various angiograms, pyelography, bronchography, gastroenterography, and the like.
When a patient is subjected to CT enhancement examination, a contrast agent is required. Contrast agents can make the test results more accurate and are very common in medical examinations. However, since the contrast agent used for CT enhancement contains a certain amount of iodine, it may affect the human body at the same time of use, and may cause allergic reaction, renal function impairment, and the like. Severe persons may even experience shock, failure of the respiratory cycle, etc., which are life threatening.
Currently, the choice of CT contrast enhancement is mainly based on the accumulated experience of the physician for the examination category and subject, and is matched according to the specific situation of each patient. However, doctors at different levels may match different contrast agents to the same patient, and differential judgment increases the probability of adverse events for the patient, which may adversely affect doctors, patients, and society.
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention aims to provide a method for establishing an intelligent matching model of a CT-enhanced contrast agent, so that the use of the contrast agent is more scientific and standardized, the occurrence of medical accidents can be effectively reduced, the probability of harm of the contrast agent to patients can be reduced, and the service level of hospitals can be improved.
In a first aspect, the present invention provides a method for establishing an intelligent matching model of CT contrast enhancement, comprising the following steps:
carrying out data standardization treatment, namely counting the allergic number of patients and contrast agent allergic reaction index data of CT enhancement examination;
aggregating the allergic number of patients subjected to CT enhancement examination and contrast agent allergic reaction index data, searching for strong correlation among variables to obtain an optimal influence factor, and aggregating different allergic conditions according to the optimal influence factor;
predicting which contrast agent used by future CT enhancement inspectors has anaphylactic reaction by using a Bayesian ridge regression model;
calculating the correlation between the prediction sequence and the real contrast agent allergy population sequence to obtain the correlation degree between the influence factor and the contrast agent anaphylactic reaction, and obtaining the key factor influencing the contrast agent according to the analysis result;
and obtaining the weight of the independent variable through logistic regression analysis, and determining the grade of the key factor.
Preferably, the data normalization process includes the steps of:
screening the patient medical record for the CT enhancement exam under study;
counting the number of allergic patients of the CT enhancement examination type every day;
and acquiring contrast agent allergic reaction index data according to the medical record condition of the allergic patient.
Preferably, the polymerization comprises the steps of:
the number of allergic people in the daily CT enhancement examination according to different time granularity mtAnd single factor index data XtCarrying out polymerization:
Yt＝Yt-1+Yt-2+...+Yt-m，
Xt＝Xt-1+Xt-2+...+Xt-m；
measurement of number of allergic reactions in daily CT enhancement examination by Pearson correlation coefficienttAnd factor index data XtThe strong correlation between the two correlation coefficients, the pearson correlation coefficient r, is expressed as follows:
Figure BDA0002668653600000031
wherein the content of the first and second substances,
Figure BDA0002668653600000037
is a factor after a certain polymerizationThe historical mean of the subject data is,
Figure BDA0002668653600000038
the average number of CT examination people, n is the total length of the sequence;
determining the optimal influence factor M by r:
Figure BDA0002668653600000032
finding out the optimal polymerization of different factors and carrying out polymerization operation.
Further, the predicting comprises the following steps:
predicting the number sequence Y of the allergic people in the CT enhancement examination by Bayesian ridge regression according to a Bayesian ridge regression model as the combined modeltLet Y betAbout
Figure BDA0002668653600000033
Obeying a gaussian distribution:
Figure BDA0002668653600000034
Figure BDA0002668653600000035
the prior parameter ω of the probabilistic model obeys a spherical gaussian distribution:
Figure BDA0002668653600000036
wherein, Xt allIs the combined characteristic value of the multi-factor index data fitted by Bayesian ridge regression, omega is the weight parameter vector, alpha-1Is the variance, beta, of the corresponding set of multifactor index data-1The variance of the gaussian distribution of ω.
Further, calculating the correlation includes the steps of: and after the number sequence of the allergic persons is detected through the predicted CT enhancement, calculating a correlation coefficient between the predicted sequence and the real sequence to obtain the correlation degree between the factor index and the number of the persons detecting the allergic persons, wherein the larger the absolute value of the correlation coefficient is, the stronger the correlation degree is, and thus, the influence of the key factor and the number of the persons detecting the allergic persons through the CT enhancement is evaluated.
Preferably, a logistic regression algorithm is adopted for historical data to divide key factors of the contrast agent into four grades according to the body constitution of a patient, and a contrast agent expert knowledge base is established according to different grades and matching of the used contrast agent.
In a second aspect, the present invention provides an intelligent matching model for CT enhanced contrast agent, wherein the key factors affecting the contrast agent include four levels, 1, 2, 3 and 4; grade 1 is an absolute contraindication factor, and patients who contain the grade 1 factor cannot be enhanced; levels 2, 3 and 4 are relative contraindication factors, patients containing the level 2 factor must use an isotonic contrast agent iodixanol, and patients containing the level 3 factor adopt any one of hypertonic contrast agents, hypotonic contrast agents and isotonic contrast agents; wherein patients containing one grade 4 factor use any one of hypertonic, hypotonic and isotonic contrast agents, and patients containing two or more grade 4 factors use the isotonic contrast agent iodixanol; wherein the grade 1 factor comprises hyperthyroidism and iodine allergy; the level 2 factor comprises eGFR < 45 mls/min; the grade 3 factor comprises that the number of allergens is more than or equal to 3; grade 4 factors include bilateral kidney injury, asthma, myeloma, gout, congestive heart failure, dehydration, diabetes, and an eGFR of 45mls/min or less than 60 mls/min.
In a third aspect, the present invention provides a computer device, comprising a memory, a processor and a transceiver, which are communicatively connected in sequence, wherein the memory is used for storing a computer program, the transceiver is used for transceiving data, and the processor is used for reading the computer program and executing the method as described in the first aspect or any one of the possible designs of the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon instructions which, when run on a computer, perform a method as set forth in the first aspect or any one of the possible designs of the first aspect.
The invention has the beneficial effects that:
1. the method for establishing the CT contrast agent intelligent matching model enables the use of the contrast agent to be more scientific and standardized, can effectively reduce the occurrence of medical accidents, can reduce the probability of harm of the contrast agent to patients, and can improve the service level of hospitals.
2. By using the CT contrast enhancement agent intelligent matching model established by the invention, the contrast agent which accords with the characteristics of the patient can be more accurately matched for the patient, the influence of contrast agent ion unbalance, liver and kidney function damage and the like on the patient is reduced to the maximum extent, and the occurrence of the conditions of allergy, shock, respiratory cycle failure and the like is effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for establishing an intelligent matching model of CT contrast enhancement provided by the present invention.
Fig. 2 is a schematic flow chart of a preferred data normalization processing method provided by the present invention.
FIG. 3 is a schematic flow diagram of a preferred polymerization process provided by the present invention.
Fig. 4 is a schematic structural diagram of a computer device provided by the present invention.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. Specific structural and functional details disclosed herein are merely illustrative of example embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, for the character "/" that may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
It will be understood that when an element is referred to herein as being "connected," "connected," or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may be present. Conversely, if a unit is referred to herein as being "directly connected" or "directly coupled" to another unit, it is intended that no intervening units are present. In addition, other words used to describe the relationship between elements should be interpreted in a similar manner (e.g., "between … …" versus "directly between … …", "adjacent" versus "directly adjacent", etc.).
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
It should be understood that specific details are provided in the following description to facilitate a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques may be shown without unnecessary detail in order to avoid obscuring example embodiments.
Example 1:
as shown in fig. 1 to 3, the method for establishing the intelligent matching model of CT contrast enhancement agent provided in this embodiment may include, but is not limited to, the following steps S100 to S500.
S100, data standardization processing is carried out, and the number of allergic people of the patient who carries out CT enhancement examination and contrast agent allergic reaction index data are counted. The data normalization process can be processed by the existing method, but the following steps are more recommended:
s101, screening the CT enhancement examination to be researched on the patient medical record;
s102, counting the number of allergic patients of the CT enhancement examination type every day;
s103, acquiring contrast agent allergic reaction index data according to the medical record condition of the allergic patient.
S200, aggregating the allergic number of the patient subjected to CT enhancement examination and contrast agent allergic reaction index data, searching for strong correlation among variables to obtain an optimal influence factor, and aggregating different allergic conditions according to the optimal influence factor. The polymerization treatment may be carried out by a conventional method, but the following steps are more recommended:
s201, according to different time granularity m, the number Y of people allergic to daily CT enhancement examinationtAnd single factor index data XtCarrying out polymerization:
Yt＝Yt-1+Yt-2+...+Yt-m，
Xt＝Xt-1+Xt-2+...+Xt-m；
s202, measuring the number Y of allergic persons in daily CT enhancement examination by using Pearson correlation coefficienttAnd factor index data YtThe strong correlation between the two correlation coefficients, the pearson correlation coefficient r, is expressed as follows:
Figure BDA0002668653600000071
wherein the content of the first and second substances,
Figure BDA0002668653600000086
is the historical average of some aggregated factor index data,
Figure BDA0002668653600000087
the average number of CT examination people, n is the total length of the sequence;
s203, determining the optimal influence factor M through r:
Figure BDA0002668653600000081
and S204, finding out the optimal aggregation of different factors in sequence and carrying out aggregation operation.
S300, predicting which contrast agent used by the CT enhancement inspectors has anaphylactic reaction by using a Bayesian ridge regression model. The prediction process may be performed by an existing method, but the following method is more recommended: according to Bayesian ridge regression model as the combined modelPredicting the number sequence Y of the allergic people in CT enhancement examination by Bayesian ridge regressiontLet Y betAbout
Figure BDA0002668653600000082
Obeying a gaussian distribution:
Figure BDA0002668653600000083
Figure BDA0002668653600000084
the prior parameter ω of the probabilistic model obeys a spherical gaussian distribution:
Figure BDA0002668653600000085
wherein, Xt allIs the combined characteristic value of the multi-factor index data fitted by Bayesian ridge regression, omega is the weight parameter vector, alpha-1Is the variance, beta, of the corresponding set of multifactor index data-1The variance of the gaussian distribution of ω.
S400, calculating the correlation between the prediction sequence and the real contrast agent allergy population sequence to obtain the correlation degree between the influence factor and the contrast agent allergy reaction, and obtaining the key factor influencing the contrast agent according to the analysis result. Specifically, after the number sequence of the number of the allergic persons in the CT enhanced examination is predicted, the correlation coefficient between the predicted sequence and the real sequence is calculated, the correlation degree between the factor index and the number of the allergic persons in the CT enhanced examination is obtained, and the larger the absolute value of the correlation coefficient is, the stronger the correlation degree is, so that the influence of the key factor and the number of the allergic persons in the CT enhanced examination is evaluated.
S500, obtaining the weight of the independent variable through logistic regression analysis, and determining the grade of the key factor. The key factors of the contrast agent are divided into four grades according to the body constitution of a patient, and a contrast agent expert knowledge base is established according to which contrast agent is matched and used in different grades.
Example 2:
in the intelligent matching model for CT contrast enhancement provided by this embodiment, the derivation process of each key factor is as follows:
s100: and (5) carrying out data standardization treatment, and counting the number of CT enhancement examination people and factor index data every day according to the electronic medical record. Here, the influence factors are analyzed, and the influence factor indexes are selected as follows: uncontrolled symptom hyperthyroidism patients, bilateral kidney injury, asthma, myeloma, gout, congestive heart failure, dehydration, diabetes, eGFR, age, severe adverse reaction with iodine contrast agent, slight allergy to iodine, known number of allergens, taking kidney injury class of drugs, and history of bilateral kidney surgery.
S101: screening medical records subjected to CT enhancement examination on patient medical records;
s102: counting the number of people who do CT enhancement examination every day;
and S103, counting the data of the allergic person to obtain contrast agent allergic reaction index data.
S200, constructing a data aggregation unit according to the standardized data acquired in S100:
s201, according to different time granularity m, the number Y of people allergic to daily CT enhancement examinationtAnd single factor index data XtCarrying out polymerization:
Yt＝Yt-1+Yt-2+...+Yt-m，
Xt＝Xt-1+Xt-2+...+Xt-m；
s202, measuring the number Y of allergic persons in daily CT enhancement examination by using Pearson correlation coefficienttAnd factor index data XtThe strong correlation between the two correlation coefficients, the pearson correlation coefficient r, is expressed as follows:
Figure BDA0002668653600000101
wherein the content of the first and second substances,
Figure BDA0002668653600000104
is the historical average of some aggregated factor index data,
Figure BDA0002668653600000105
the average number of CT examination people, n is the total length of the sequence;
s203, determining the optimal influence factor M through r:
Figure BDA0002668653600000102
s204, finding out the aggregation days between the last hospitalization record and the current enhanced CT examination interval of different influence factors in sequence through experiments, and obtaining the following results:
patients with uncontrolled symptoms of hyperthyroidism: 40 days, bilateral kidney injury: 32 days, asthma: 30 days, myeloma: 33 days, gout: 31 days, congestive heart failure: and (4) 41 days, dehydration: day 44, diabetes: day 33, eGFR: day 29, age: 35 days, iodine contrast agent was severely adverse: day 34, iodine mildly allergic: 31 days, number of known allergens, 33 days, renal injury drugs were taken: 30 days, history of bilateral kidney surgery: for 40 days.
S205: time delay processing is carried out according to the data aggregated in the S204, and the strongest acting days between the correlation factor hospitalization record and the enhanced CT examination are analyzed.
S206. for single influence factor sequence X after polymerizationtAnd (3) performing shift processing to form time delay:
Xt＝Xt-d，d＝0,1,2,3…
s207, calculating the number of hospitalized people per day YtAnd influence factor index data XtThe correlation coefficient r with the highest absolute value is obtained, so that the influence period with the strongest influence factor is determined, and the formula is as follows:
Figure BDA0002668653600000103
s208, finding out the strongest influence periods of different influence shadows through experiments as follows:
the patient with uncontrolled hyperthyroidism is delayed for 10 days, bilateral kidney injury is delayed for 10 days, asthma is delayed for 7 days, myeloma is delayed for 5 days, gout is delayed for 10 days, congestive heart failure is delayed for 20 days, dehydration is delayed for 5 days, diabetes is delayed for 10 days, eGFR is delayed for 10 days, age is delayed for 9 days, iodine contrast agent severe adverse reaction is delayed for 10 days, iodine slight allergy is delayed for 8 days, known allergen number is delayed for 10 days, kidney injury type medicine is delayed for 10 days, and bilateral kidney operation history is delayed for 10 days.
The correlation between different influencing factors and the single allergic factor is as follows:
association of uncontrolled symptom Hyperthyroid Patients (HPWUS) with allergy: 0.8145, respectively;
asthma (asthma) is associated with allergies: 0.3085, respectively;
association of myeloma (myeloma) with allergy: 0.2858, respectively;
gout (gout) is associated with allergies: 0.3032, respectively;
congestive Heart Failure (CHF) is associated with allergies: 0.2502, respectively;
dehydration (dehydration) and allergy association: 0.2261, respectively;
diabetes (diabetes) and allergy association: 0.2797, respectively;
correlation of 45mls/min ≤ eGFR < 60mls/min with allergy: 0.4260;
0.6250 is the relevance of eGFR less than 45mls/min and allergy;
age >70 years: 0.2260, respectively;
the association of iodine contrast agent severe adverse reactions (sarocicm) with allergies: 0.9260, respectively;
iodine mild allergy (SIA) and allergy association: 0.3360;
the number of allergens (Sensitive) known to be associated with allergy: 0.3240, respectively;
the association of taking renal injury drugs (TKID) with allergy: 0.2153, respectively;
association of bilateral renal surgery History (HOKS) with allergies: 0.2262.
s300, constructing a Bayesian ridge regression prediction unit. And predicting which contrast agent has anaphylactic reaction for the CT enhancement examiner in the future by using a Bayesian ridge regression model. Specifically, the method comprises the following steps: according to a Bayesian ridge regression modelType as the combined model, predicting the number sequence Y of the allergic people in CT enhancement examination by Bayesian ridge regressiontLet Y betAbout
Figure BDA0002668653600000121
Obeying a gaussian distribution:
Figure BDA0002668653600000122
Figure BDA0002668653600000123
the prior parameter ω of the probabilistic model obeys a spherical gaussian distribution:
Figure BDA0002668653600000124
wherein, Xt allIs the combined characteristic value of the multi-factor index data fitted by Bayesian ridge regression, omega is the weight parameter vector, alpha-1Is the variance, beta, of the corresponding set of multifactor index data-1The variance of the gaussian distribution of ω.
Bayesian incremental learning process: by the previous data set Dt-1A posterior probability p (ω | D)t-1) Multiply by new sample points
Figure BDA0002668653600000125
Get the new set DtA posterior probability p (ω | D)t)：
Figure BDA0002668653600000126
The experimental results are as follows:
Yt allergy (S)＝0.257*Xt HPWUS-0.268*Xt asthma-0.054*Xt myeloma-0.873*Xt gout-0.147*Xt CHF-0.510*Xt dehydration-0.291*Xt diabetes+0.235*Xt 45mls/min≤eGFR＜60mls/min+0.257*Xt eGFR＜45mls/min+0.324*Xt age+0.259*Xt SAROICM+0.157*Xt SIA+0.267*Xt Sensitive+0.237*Xt TKID-0.357*Xt HOKS。
S400, calculating the correlation between the prediction sequence and the real contrast agent allergy population sequence to obtain the correlation degree between the influence factor and the contrast agent allergy reaction, and obtaining the key factor influencing the contrast agent according to the analysis result. Determining the effect of the influencing factor on the allergy of the patient. In the experimental process, 70% of data is used for training a model, 30% of data is used for predicting and calculating correlation (Pearson correlation calculation), and the multi-factor correlation coefficient of the final predicted sequence and the real sequence is as follows: 0.7021, the experiment proves that the influence factors have positive correlation with the allergy, and the more the influence factors, the more the allergic people can be increased obviously.
S500, obtaining the weight of the independent variable through logistic regression analysis, and determining the grade of the key factor. The key factors of the contrast agent are divided into four grades according to the body constitution of a patient, and a contrast agent expert knowledge base is established according to which contrast agent is matched and used in different grades.
Wherein the key factors influencing the contrast agent comprise four grades of 1, 2, 3 and 4; grade 1 is an absolute contraindication factor, and patients who contain the grade 1 factor cannot be enhanced; levels 2, 3 and 4 are relative contraindication factors, patients containing the level 2 factor must use an isotonic contrast agent iodixanol, and patients containing the level 3 factor adopt any one of hypertonic contrast agents, hypotonic contrast agents and isotonic contrast agents; wherein patients containing one grade 4 factor use any one of hypertonic, hypotonic and isotonic contrast agents, and patients containing two or more grade 4 factors use the isotonic contrast agent iodixanol; wherein the grade 1 factor comprises hyperthyroidism and iodine allergy; the level 2 factor comprises eGFR < 45 mls/min; the grade 3 factor comprises that the number of allergens is more than or equal to 3; class 4 factors include bilateral kidney injury, asthma, myeloma, gout, congestive heart failure, dehydration, diabetes, and an eGFR of 45mls/min or less than 60 mls/min; see in particular the table below.
Figure BDA0002668653600000131
Example 3:
as shown in fig. 4, this embodiment provides a computer device for executing the method for establishing an intelligent matching model of CT-enhanced contrast medium according to embodiment 1, which includes a memory, a processor and a transceiver, which are sequentially and communicatively connected, wherein the memory is used for storing a computer program, the transceiver is used for transceiving data, and the processor is used for reading the computer program and executing the method according to embodiment 1. By way of specific example, the Memory may include, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Flash Memory (Flash Memory), a first-in-first-out Memory (FIFO), a first-in-last-out Memory (FILO), and/or the like; the transceiver may include, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a GPRS (General Packet Radio Service) wireless transceiver, and/or a ZigBee (ZigBee protocol, low power local area network protocol based on ieee802.15.4 standard) wireless transceiver, etc.; the processor may not be limited to the microprocessor of the model number employing the STM32F105 family. In addition, the computer device may also include, but is not limited to, a power module, an input device, a display screen, and other necessary components.
For the working process, the working details, and the technical effects of the foregoing computer device provided in this embodiment, reference may be made to the method described in embodiment 1, which is not described herein again.
Example 4:
this embodiment provides a computer-readable storage medium storing a method for creating an intelligent matching model of CT enhanced contrast media according to embodiment 1, that is, the computer-readable storage medium has instructions stored thereon, and when the instructions are executed on a computer, the method for creating an intelligent matching model of CT enhanced contrast media according to embodiment 1 is performed. The computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, floppy disks, optical disks, hard disks, flash memories, flash disks and/or Memory sticks (Memory sticks), etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, the working details and the technical effects of the foregoing computer-readable storage medium provided in this embodiment, reference may be made to the method described in embodiment 1, which is not described herein again.
The various embodiments described above are merely illustrative, and may or may not be physically separate, as they relate to elements illustrated as separate components; if reference is made to a component displayed as a unit, it may or may not be a physical unit, and may be located in one place or distributed over a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: modifications of the technical solutions described in the embodiments or equivalent replacements of some technical features may still be made. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Finally, it should be noted that the present invention is not limited to the above alternative embodiments, and that various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.

Claims (7)

  1. The method for establishing the intelligent matching model of the CT enhanced contrast agent is characterized by comprising the following steps of:
    carrying out data standardization treatment, namely counting the allergic number of patients and contrast agent allergic reaction index data of CT enhancement examination;
    aggregating the allergic number of patients subjected to CT enhancement examination and contrast agent allergic reaction index data, searching for strong correlation among variables to obtain an optimal influence factor, and aggregating different allergic conditions according to the optimal influence factor;
    the polymerization comprises the following steps:
    the number of allergic people in the daily CT enhancement examination according to different time granularity mtAnd single factor index data XtCarrying out polymerization:
    Yt＝Yt-1+Yt-2+...+Yt-m，
    Xt＝Xt-1+Xt-2+...+Xt-m；
    measurement of number of allergic reactions in daily CT enhancement examination by Pearson correlation coefficienttAnd factor index data XtThe strong correlation between the two correlation coefficients, the pearson correlation coefficient r, is expressed as follows:
    Figure FDA0002985897250000011
    wherein the content of the first and second substances,
    Figure FDA0002985897250000012
    is the historical average of some aggregated factor index data,
    Figure FDA0002985897250000013
    the average number of CT examination people, n is the total length of the sequence;
    determining the optimal influence factor M by r:
    Figure FDA0002985897250000014
    finding out the optimal polymerization of different factors in turn and carrying out polymerization operation;
    predicting which contrast agent used by future CT enhancement inspectors has anaphylactic reaction by using a Bayesian ridge regression model;
    calculating the correlation between the prediction sequence and the real contrast agent allergy population sequence to obtain the correlation degree between the influence factor and the contrast agent anaphylactic reaction, and obtaining the key factor influencing the contrast agent according to the analysis result;
    and obtaining the weight of the independent variable through logistic regression analysis, and determining the grade of the key factor.
  2. 2. The method for building the intelligent matching model of CT enhanced contrast agent according to claim 1, wherein: the data normalization process comprises the following steps:
    screening the patient medical record for the CT enhancement exam under study;
    counting the number of allergic patients of the CT enhancement examination type every day;
    and acquiring contrast agent allergic reaction index data according to the medical record condition of the allergic patient.
  3. 3. The method for building an intelligent matching model of CT enhanced contrast agent as recited in claim 2, wherein said predicting comprises the steps of:
    predicting the number sequence Y of the allergic people in the CT enhancement examination by Bayesian ridge regression according to the Bayesian ridge regression model as a combined modeltLet Y betAbout
    Figure FDA0002985897250000021
    Obeying a gaussian distribution:
    Figure FDA0002985897250000022
    Figure FDA0002985897250000023
    priori parameters of probabilistic modelThe number ω follows a spherical gaussian distribution:
    Figure FDA0002985897250000024
    wherein, Xt allIs the combined characteristic value of the multi-factor index data fitted by Bayesian ridge regression, omega is the weight parameter vector, alpha-1Is the variance, beta, of the corresponding set of multifactor index data-1The variance of the gaussian distribution of ω.
  4. 4. The method for building the intelligent matching model of CT enhanced contrast agent according to claim 3, wherein the calculating the correlation comprises the following steps: and after the number sequence of the allergic persons is detected through the predicted CT enhancement, calculating a correlation coefficient between the predicted sequence and the real sequence to obtain the correlation degree between the factor index and the number of the persons detecting the allergic persons, wherein the larger the absolute value of the correlation coefficient is, the stronger the correlation degree is, and thus, the influence of the key factor and the number of the persons detecting the allergic persons through the CT enhancement is evaluated.
  5. 5. The method for building the intelligent matching model of CT enhanced contrast agent according to claim 4, wherein: a logistic regression algorithm is adopted for historical data to divide key factors of the contrast agent into four grades according to the body constitution of a patient, and a contrast agent expert knowledge base is established according to which contrast agent is matched and used in different grades.
  6. 6. A computer device, characterized by: the system comprises a memory, a processor and a transceiver which are sequentially connected in a communication mode, wherein the memory is used for storing a computer program, the transceiver is used for transmitting and receiving data, and the processor is used for reading the computer program and executing the method according to any one of claims 1-5.
  7. 7. A computer-readable storage medium characterized by: the computer-readable storage medium having stored thereon instructions which, when executed on a computer, perform the method of any of claims 1-5.
CN202010926659.5A 2020-09-07 2020-09-07 Method for establishing CT enhanced contrast agent intelligent matching model Active CN112070150B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010926659.5A CN112070150B (en) 2020-09-07 2020-09-07 Method for establishing CT enhanced contrast agent intelligent matching model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010926659.5A CN112070150B (en) 2020-09-07 2020-09-07 Method for establishing CT enhanced contrast agent intelligent matching model

Publications (2)

Publication Number Publication Date
CN112070150A CN112070150A (en) 2020-12-11
CN112070150B true CN112070150B (en) 2021-05-14

Family

ID=73662952

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010926659.5A Active CN112070150B (en) 2020-09-07 2020-09-07 Method for establishing CT enhanced contrast agent intelligent matching model

Country Status (1)

Country Link
CN (1) CN112070150B (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2715825C (en) * 2008-02-20 2017-10-03 Mcmaster University Expert system for determining patient treatment response
CN109783646B (en) * 2019-02-12 2022-08-12 四川大学华西医院 Data processing method and device

Also Published As

Publication number Publication date
CN112070150A (en) 2020-12-11

Similar Documents

Publication Publication Date Title
Zhao et al. Predicting outcomes of chronic kidney disease from EMR data based on Random Forest Regression
WO2020181807A1 (en) Health prompting method and apparatus, and computer device and storage medium
US11640852B2 (en) System for laboratory values automated analysis and risk notification in intensive care unit
CN110364259B (en) Method, system, medium and electronic device for predicting altitude disease
Roy et al. Statistical methods for cohort studies of CKD: prediction modeling
CN107145715B (en) Clinical medicine intelligence discriminating gear based on electing algorithm
CN114783580B (en) Medical data quality evaluation method and system
Martín‐Rodríguez et al. Accuracy of prehospital point‐of‐care lactate in early in‐hospital mortality
US8417541B1 (en) Multi-stage model for predicting probabilities of mortality in adult critically ill patients
Foti et al. Digit preference in office blood pressure measurements, United States 2015–2019
US11676722B1 (en) Method of early detection, risk stratification, and outcomes prediction of a medical disease or condition with machine learning and routinely taken patient data
CN112070150B (en) Method for establishing CT enhanced contrast agent intelligent matching model
CN112542219A (en) Patient admission management method and device, management equipment and readable storage medium
US20230060794A1 (en) Diagnostic Tool
CN111292322A (en) Medical image processing method, device, equipment and storage medium
CN113012803A (en) Computer device, system, readable storage medium and medical data analysis method
AU2019238388A1 (en) Methods for screening a subject for the risk of chronic kidney disease and computer-implemented method
CN108346471B (en) Pathological data analysis method and device
CN115862839A (en) Method and device for establishing autism risk assessment model and electronic equipment
JP2006018532A (en) System and method for analyzing hospital management information, computer readable storage medium and computer program
CN114203301A (en) Method and system for tracking health condition of patient after diagnosis
Raz et al. Uptake of Pap smears among women in a large Israeli HMO between 2006 and 2008
CN113017568A (en) Method and system for predicting physiological changes and death risks of severely wounded patients
CN114334161B (en) Model training method, data processing method, device, medium and electronic equipment
McCormack et al. Integrating testing for sexually transmissible infections into annual health assessments for Aboriginal and Torres Strait Islander young people: a cross-sectional analysis

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant