CN115662656B - Evaluation method and system for side effects of medicine and electronic equipment - Google Patents
Evaluation method and system for side effects of medicine and electronic equipment Download PDFInfo
- Publication number
- CN115662656B CN115662656B CN202211378013.3A CN202211378013A CN115662656B CN 115662656 B CN115662656 B CN 115662656B CN 202211378013 A CN202211378013 A CN 202211378013A CN 115662656 B CN115662656 B CN 115662656B
- Authority
- CN
- China
- Prior art keywords
- side effect
- drug
- gene
- adverse reaction
- detection data
- 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
Links
- 230000000694 effects Effects 0.000 title claims abstract description 213
- 239000003814 drug Substances 0.000 title claims abstract description 199
- 238000011156 evaluation Methods 0.000 title claims abstract description 93
- 229940079593 drug Drugs 0.000 claims abstract description 170
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 118
- 238000001514 detection method Methods 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 28
- 206010067484 Adverse reaction Diseases 0.000 claims description 76
- 230000006838 adverse reaction Effects 0.000 claims description 76
- 230000002974 pharmacogenomic effect Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 201000010099 disease Diseases 0.000 abstract description 7
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 14
- 230000002068 genetic effect Effects 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 231100000957 no side effect Toxicity 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000000857 drug effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000002483 medication Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 206010061623 Adverse drug reaction Diseases 0.000 description 1
- 208000032140 Sleepiness Diseases 0.000 description 1
- 206010041349 Somnolence Diseases 0.000 description 1
- 206010047700 Vomiting Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001647 drug administration Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000144 pharmacologic effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004579 scanning voltage microscopy Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 229940126585 therapeutic drug Drugs 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a method, a system and electronic equipment for evaluating side effects of a drug, and relates to the technical field of information, wherein the method comprises the steps of constructing a side effect index model; acquiring gene detection data of a patient and the name of a drug to be detected; substituting the gene detection data and the name of the drug to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected; and summarizing all side effect evaluation indexes related to the patient, and quantitatively analyzing different medicines of the same disease, so that doctors can intuitively know the risk condition of the medicines, and assist the doctors to select specific medicines.
Description
Technical Field
The present application relates to the field of information technologies, and in particular, to a method, a system, and an electronic device for evaluating side effects of a drug.
Background
At present, according to detection data of preset gene loci and preset judgment logic, genotype data are corresponding and classified through manual judgment, only partial potential adverse reactions and side effect types of medicines are given, and side effect risk assessment and comparison among different medicines are absent, so that overall assessment on multiple side effect risks of a single medicine cannot be achieved, quantitative analysis cannot be carried out on different medicines, and the assistance of a doctor in formulating a treatment scheme is limited.
Therefore, an evaluation method, system and electronic device for side effects of a drug are provided.
Disclosure of Invention
The specification provides a method, a system and electronic equipment for evaluating side effects of a drug, which are characterized in that gene detection data and names of the drug to be tested are substituted into a side effect index model to obtain a side effect evaluation index of the drug to be tested, and specific drug is selected in an auxiliary mode.
The method for evaluating the side effects of the medicine provided by the application adopts the following technical scheme that:
constructing a side effect index model;
acquiring gene detection data of a patient and the name of a drug to be detected;
substituting the gene detection data and the name of the drug to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected;
all side effect assessment indices associated with the patients were pooled to aid in assessing potential medication risk.
Optionally, substituting the gene detection data and the information of the drug to be detected into the side effect index model to obtain the side effect evaluation index of the drug to be detected includes:
according to the gene detection data and the drug information to be detected, a plurality of scoring parameters of the drug to be detected are called;
and scoring the side effect of the drug to be tested according to a plurality of scoring parameters to obtain a side effect evaluation index.
Optionally, scoring the side effect of the drug to be tested according to a plurality of scoring parameters to obtain a side effect evaluation index, including:
the scoring parameters include one or more of an adverse reaction weight alpha, an adverse reaction rating beta and a genetic role status gamma;
and calculating according to index=F (alpha, beta, gamma) to obtain the side effect evaluation Index of the drug to be tested.
Optionally, the constructing the side effect index model includes:
collecting follow-up data of side effects of the drug;
calculating the occurrence rate and the severity of the side effects according to the occurrence condition of each side effect of the medicine in the follow-up data;
combining expert evaluation results to obtain adverse reaction weight alpha of the medicine;
and establishing the association relation between the medicine and the adverse reaction weight alpha.
Optionally, the constructing the side effect index model includes:
collecting and extracting names of side effects and corresponding side effect scores according to clinical feedback data of historical patients;
collecting gene detection data of the historical patient, and determining an adverse reaction rating beta by combining the side effect score and the gene detection data of the historical patient;
and establishing the association relation between the side effect and the adverse reaction rating beta.
Optionally, the constructing the side effect index model includes:
according to the pharmacogenomics literature, matching a first gene locus related to the influence of a drug, and determining the gene role gamma of a first genotype, wherein the first genotype is the gene type on the first gene locus;
and establishing the association relation between the first genotype and the gene role position gamma.
Optionally, the constructing the side effect index model further includes:
constructing a plurality of basic classifiers;
training the voting weight of each basic classifier according to the scoring parameters;
integration of each base classifier using weighted averaging
Wherein w is i Is the weight of the basic classifier, and
the application provides a drug side effect evaluation system, which adopts the following technical scheme that:
the construction module is used for constructing a side effect index model;
the acquisition module is used for acquiring gene detection data of a patient and names of medicines to be detected;
the evaluation module is used for substituting the gene detection data and the name of the drug to be tested into the side effect index model to obtain the side effect evaluation index of the drug to be tested;
and the summarizing module is used for summarizing all side effect evaluation indexes related to the patient and assisting in evaluating potential medication risks.
Optionally, the evaluation module includes:
the invoking submodule is used for invoking a plurality of scoring parameters of the drug to be tested according to the gene detection data and the drug information to be tested;
and the evaluation molecular module is used for scoring the side effect of the drug to be tested according to a plurality of scoring parameters to obtain a side effect evaluation index.
Optionally, the evaluation module includes:
the scoring parameters include one or more of an adverse reaction weight alpha, an adverse reaction rating beta and a genetic role status gamma;
and a scoring unit for calculating and obtaining the side effect evaluation Index of the drug to be tested according to index=F (alpha, beta, gamma).
Optionally, the building module includes:
a first collection sub-module for collecting follow-up data of drug side effects;
a calculating sub-module, configured to calculate the occurrence rate of side effects and the severity of side effects according to the occurrence of each side effect of the drug in the follow-up data;
the weight determination submodule is used for combining expert evaluation results to obtain adverse reaction weight alpha of the medicine;
the first association submodule is used for establishing association relation between the medicine and the adverse reaction weight alpha.
Optionally, the building module includes:
the second collecting sub-module is used for collecting and extracting names of side effects and corresponding side effect scores according to clinical feedback data of historical patients;
the rating determination submodule is used for collecting gene detection data of the historical patient and determining an adverse reaction rating beta by combining the side effect score and the gene detection data of the historical patient;
and the second association submodule is used for establishing association relation between side effects and adverse reaction ratings beta.
Optionally, the building module includes:
a matching sub-module, configured to match a first genetic locus related to a drug effect according to a pharmacogenomic document, and determine a gene role status γ of a first genotype, where the first genotype is a gene type on the first genetic locus;
and the third correlation sub-module is used for establishing the correlation between the first genotype and the gene role position gamma.
Optionally, the building module includes:
the classifier construction submodule is used for constructing a plurality of basic classifiers;
the voting weight training sub-module is used for training the voting weight of each basic classifier according to the scoring parameters;
an integration calculation sub-module for integrating each basic classifier by using a weighted average method
Wherein w is i Is the weight of the basic classifier, and
the specification also provides an electronic device, wherein the electronic device includes:
a processor; the method comprises the steps of,
a memory storing computer executable instructions that, when executed, cause the processor to perform any of the methods described above.
The present specification also provides a computer readable storage medium storing one or more programs which when executed by a processor implement any of the methods described above.
In the application, a side effect index model is constructed; acquiring gene detection data of a patient and the name of a drug to be detected; substituting the gene detection data and the name of the drug to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected; and (3) summarizing all side effect evaluation indexes related to the patient, and quantitatively analyzing different medicines of the same disease, so that doctors (professionals) can intuitively know the risk condition of the medicines, and assist the doctors (professionals) to select specific medicines.
Drawings
FIG. 1 is a schematic diagram of a method for evaluating side effects of a drug according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of a method for evaluating side effects of drugs according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a system for evaluating side effects of a drug according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a computer readable medium according to an embodiment of the present disclosure.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the application. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art. The basic principles of the application defined in the following description may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the application.
Exemplary embodiments of the present application will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the application to those skilled in the art. The same reference numerals in the drawings denote the same or similar elements, components or portions, and thus a repetitive description thereof will be omitted.
The features, structures, characteristics or other details described in a particular embodiment do not exclude that may be combined in one or more other embodiments in a suitable manner, without departing from the technical idea of the application.
In the description of specific embodiments, features, structures, characteristics, or other details described in the present application are provided to enable one skilled in the art to fully understand the embodiments. However, it is not excluded that one skilled in the art may practice the present application without one or more of the specific features, structures, characteristics, or other details.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The term "and/or" and/or "includes all combinations of any one or more of the associated listed items.
In the present specification, "side effects" and "adverse reactions" refer to pharmacological actions other than the therapeutic purpose that occurs after a therapeutic amount of a drug is administered, and in the present specification, "side effects" and "adverse reactions" are equivalent.
Fig. 1 is a schematic diagram of a method for evaluating side effects of a drug according to an embodiment of the present disclosure, where the method includes:
s1, constructing a side effect index model;
s2, acquiring gene detection data of a patient and names of medicines to be detected;
s3, substituting the gene detection data and the name of the drug to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected;
s4 aggregates all side effect assessment indices associated with the patient, aiding in assessing potential medication risk.
The existing evaluation method of the side effects of the medicines generally only has qualitative description aiming at the medicines, such as high/low risks of specific side effects, and the like, not only lacks of total risk evaluation of the medicines, but also can not quantitatively compare the side effect risks of various different medicines in a transverse direction, the side effect influence of the medicines mainly depends on subjective evaluation of doctors, no uniform standard exists, and the side effect influence of the medicines needs to be judged in a long time. Therefore, in order to meet the market demand of accurate medical treatment and reduce the time for doctors (professionals) to evaluate the side effects of the medicines, an evaluation method for integrating clinical practice and doctor opinion and reflecting the commonality of doctor evaluation is provided; based on the gene detection data of the drug to be detected and the patient, the side effect of the drug to be detected is qualitatively and quantitatively analyzed through a side effect index model, so that the side effect index of each drug to be detected is obtained, and the drug reference can be provided with high efficiency, high accuracy and low cost. Specifically, as shown in fig. 2, the method includes:
s1, constructing a side effect index model;
in the present application, as shown in fig. 2, constructing the side effect index model specifically includes:
s11, determining scoring parameters;
in one embodiment of the present specification, the scoring parameters include key parameters including one or more of an adverse reaction weight α, an adverse reaction rating β, and a genetic role γ, and general parameters.
Specifically, S111 obtains the adverse reaction weight α, including:
collecting follow-up data of side effects of the drug;
the follow-up data includes patient numbers, patient names, and specific side effects (adverse reactions) of the patient, wherein the patient numbers are classified according to different corresponding symptoms, and the patient numbers of each patient are unique.
A drug library is constructed that includes the presently disclosed drug names, and a unique drug number is created for each drug.
In one embodiment of the present description, the follow-up data pattern is as shown in table 1:
(Table 1)
In Table 1, the number of occurrence times and occurrence rate of side effects of the drug are easy to record and calculate later by 0/1 indicating no/no side effects, i.e., no side effects are marked as 0 and no side effects are marked as 1.
"adverse reaction 1", "adverse reaction 2", etc. are specific side effects (adverse reactions), such as emesis, debilitation, somnolence, etc.
Calculating the occurrence rate and the severity of the side effects according to the occurrence condition of each side effect of the medicine in the follow-up data, and combining expert evaluation results to obtain the adverse reaction weight alpha of the medicine;
in one embodiment of the present specification, expert assessment results are shown in table 2:
(Table 2)
And scoring the occurrence probability level of the adverse reaction by 1-10 under the expert line, wherein the higher the score is, the higher the occurrence probability of the adverse reaction is, namely 1 is the lowest occurrence probability, and 10 represents the highest occurrence probability.
The overall severity of the adverse reaction was scored by 1-10 under expert line, with higher scores and higher overall severity of the adverse reaction, i.e., 1 being the slightest adverse reaction and 10 representing the worst adverse reaction.
In one embodiment of the present disclosure, the conditions of side effects, severity, occurrence probability, and the like of different drugs in actual clinical use may be sorted based on the drug database and follow-up data of the side effects of the drugs, the drugs are classified according to the comprehensive conditions of the side effects, the adverse reaction weight α corresponding to each drug is comprehensively calculated according to expert evaluation results, and the association relationship between the drug and the adverse reaction weight α is established, that is, the adverse reaction weight α corresponding to the drug may be found by the name of the drug or the internal number of the drug in later period.
S112 results in an adverse reaction rating β, comprising:
collecting and extracting names of side effects and corresponding side effect scores according to clinical feedback data of historical patients;
in one embodiment of the present description, the clinical feedback data is as shown in table 3:
(Table 3)
The clinical feedback data is the autonomous scoring of the doctor (professional), the higher the score, the more serious the side effects (adverse reactions), the higher the risk of side effects (adverse reactions), and the higher the degree of importance received in assigning a clinical regimen. The severity is classified into a plurality of grades according to actual conditions, and the grades can be classified according to the first grade, second grade … … and other words, and the grades can be classified according to the mild, moderate, severe … … and other words.
In one embodiment of the present description, the severity is classified into three levels, the severity classification including: mild, moderate and severe, with a percent scoring, where 1-19 corresponds to a severity scale of mild, 20-49 corresponds to a severity scale of moderate, and 50-100 corresponds to a severity scale of severe. In another embodiment of the present description, the severity is classified into four levels, the severity classification including: the first, second, third and fourth levels are scored using a percentile, wherein the severity levels for 0-25 are graded as first level, the severity levels for 26-50 are graded as second level, the severity levels for 51-75 are graded as first level, and the severity levels for 76-100 are graded as fourth level.
Collecting gene detection data of the historical patient, and determining an adverse reaction rating beta by combining the side effect score and the gene detection data of the historical patient;
in one embodiment of the present disclosure, the pattern of gene detection data for the historic patient is as shown in table 4:
(Table 4)
Wherein the historic patient is a patient who has been previously diagnosed and has received medication.
In one embodiment of the present specification, based on clinical feedback data of doctors (professionals) and gene detection databases of historic patients, side effects related to pharmacogenomics are rated or scored from the perspective of doctors and patients, and the severity rating beta of various adverse reactions is comprehensively obtained by combining expert opinions, so that the association relation between the side effects and the adverse reaction rating beta is established.
In one embodiment of the present disclosure, to ensure that the data is consistent with clinical practices and medication-related experience, the data of tables 3, 4 are comprehensively weighted and cross-validated and error calibrated in combination with the adverse reaction weights α and adverse reaction ratings β.
S113 obtains the gene role status γ including:
according to the pharmacogenomics literature, matching a first gene locus related to the influence of side effects of a drug, and determining the gene role status gamma of a first genotype in combination with gene detection data of historical patients using the same drug, wherein the first genotype is the gene type on the first gene locus;
specifically, according to the pharmacogenomic literature, determining a first gene name and/or a first gene locus name related to a drug, and determining the influence weight of a gene corresponding to the first gene and/or the first gene locus on side effects of the drug.
Table 5 is a genetic status literature questionnaire based on pharmacogenomic literature arrangement:
(Table 5)
Among these, the first gene locus is a gene locus according to pharmacogenomics, where there is sufficient clinical evidence to indicate the existence of a correlation with the existence of a specific drug/disease. In one embodiment of the present disclosure, the number of first loci is one or more, and the gene role status γ is calculated by linear weighted integration according to the influence weight of each first locus and according to the influence weight of the first genotype corresponding to each locus.
In one embodiment of the present disclosure, the pharmacogenomic literature includes drug descriptions, experimental records, order databases, etc., published papers, etc., and on the basis of the relevant genes/gene loci corresponding to the pharmacogenomics referred to in S112, the influence weights of the first gene loci on the side effects of various drugs are determined by the above-mentioned pharmacogenomic literature, and the specific influence sizes of the first genotypes on the first gene loci on the side effects of various drugs are determined to obtain the gene effect status γ, and the association relationship between the first genotypes and the gene effect status γ is established.
It should be noted that for the same drug, the magnitude of adverse effects of different genotypes at the same locus may be the same for the drug; the magnitude of the adverse effects of the drug on the same genotype at different loci may be different, so that the gene role status gamma is related to the specific genotype of the locus.
In the construction process of the model, adverse reaction weight alpha, adverse reaction rating beta and gene action status gamma enable the gene detection data of the treatment drug and the patient to be associated with potential side effect risks.
S12, training a side effect index model.
Specifically, a plurality of basic classifiers are constructed through machine learning methods such as ensemble learning;
each basic classifier learns individually and uses different learning modeling methods, such as learning by linear regression, random forest, SVM support vector machine, etc.;
training the voting weight of each basic classifier according to the obtained scoring parameters;
integration of each base classifier using weighted averaging
Wherein w is i Is the weight of the basic classifier, and
in one embodiment of the present specification, a portion of the clinical feedback data is used as a test set to verify the accuracy and effectiveness of the training. Preferably, the calculated side effect evaluation index can be further submitted to an off-line expert for verification to assist in verifying the accuracy and reliability of the side effect evaluation index.
In order to improve the accuracy of the side effect evaluation index, the side effect evaluation index accords with the latest clinical medical, experimental and scientific research results, and clinical data and related literature data are updated periodically so as to update scoring parameters such as adverse reaction weight alpha, adverse reaction rating beta, gene effect status gamma and the like, and model iteration and optimization are carried out. Because the model only needs to retrain by applying a relevant machine learning algorithm, and does not need to manually modify part of conclusion and add and delete the existing logic and architecture, the iterative optimization space is large, and the maintenance cost is effectively saved.
S2, acquiring gene detection data of a patient and names of medicines to be detected;
the gene detection data comprise gene loci and genotypes, and the gene loci and the genotypes are in one-to-one correspondence.
In order to improve data security, the patient's genetic testing data is stored in a database system that is protected by a national information security level for tertiary authentication.
Because the gene detection data directly influences the later evaluation result, after the gene detection data is extracted, quality control treatment is carried out to ensure the integrity and compliance of gene loci and genotype data, and each gene locus accords with preset effective data and can be analyzed and interpreted downstream, so that the accuracy of the evaluation index of side effects is improved.
The drug to be tested is a potentially adaptive drug (possibly medication) corresponding to the patient's disease. In one embodiment of the present description, the drug to be tested may be a drug that is determined directly by a doctor (professional) according to the condition of the patient.
In another embodiment of the present specification, basic information of a patient is obtained, the basic information including the cause of the patient, and all drugs for treating the disease are selected as drugs to be tested in a drug database according to the cause.
S3, substituting the gene detection data and the name of the drug to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected;
specifically, S31, according to the gene detection data and the information of the drug to be detected, invokes a plurality of scoring parameters of the drug to be detected;
in one embodiment of the present disclosure, according to the association between a drug and an adverse reaction weight α, searching for an adverse reaction weight α corresponding to the adverse reaction weight α according to information of a drug to be tested of a patient, where each drug to be tested corresponds to an adverse reaction weight α;
according to the association relation between the side effect and the adverse reaction rating beta, searching the adverse reaction rating beta corresponding to the side effect through the gene detection data of the patient;
according to the association relation between the first gene locus and the gene action position gamma, searching for the corresponding first gene locus according to the information of the medicine to be detected of the patient, and determining the corresponding gene action position gamma according to the first genotype corresponding to the first gene locus in the gene detection data of the patient.
After the adverse reaction weight alpha, the adverse reaction rating beta and the gene action status gamma corresponding to the patient and the drug to be tested are obtained, S32 scores the side effect of the drug to be tested according to a plurality of scoring parameters, and a side effect evaluation index is obtained.
In one embodiment of the present specification, the side effect evaluation Index of the drug to be tested is calculated from the side effect evaluation Index index=f (α, β, γ). Wherein F (α, β, γ) is a manually determined function. In one embodiment of the present description, the side effect evaluation Index is a percentage, the higher the score, the less the overall side effect is relatively.
The side effect evaluation index of the medicine to be tested can be obtained through the side effect index model, so that the time and labor cost of doctors (professionals) are saved.
In one embodiment of the present specification, according to the information of the drug to be tested, the side effect index model can also output the side effect related to the drug to be tested, so as to assist the doctor (professional) to make a decision.
S4 aggregates all side effect assessment indices associated with the patient, aiding in assessing potential medication risk.
For the same patient, one drug to be tested corresponds to one side effect evaluation index, namely n drugs to be tested correspond to n side effect evaluation indexes (n is more than or equal to 1). In order to achieve lateral comparison of different drugs against the same disease, various symptomatic potential therapeutic drugs are provided based on intuitive medication risk of pharmacogenomics-related theory and practice, summarizing n side effect evaluation indices related to the patient.
Because the side effect evaluation indexes of a plurality of medicaments to be tested for the same disease are higher, the side effects of the corresponding medicaments to be tested are lower, and in order to facilitate rapid selection of medicaments matched with patients, the n medicaments to be tested are ordered from high to low based on the n side effect evaluation indexes.
When a doctor (professional) prescribes, not only side effects of medicines but also conditions of metabolism, response of medicines and the like are considered, so that medicines with highest side effect evaluation indexes are not necessarily the medicines most suitable for the patient; however, the drug with low side effect evaluation index is often not suitable for the patient, and preferably, the drug to be tested is classified according to the side effect evaluation index, so that the decision interference caused by the index value is reduced.
Specifically, the side effect evaluation grades are classified according to the interval to which the side effect evaluation index belongs, and then the medicines to be tested are classified based on the side effect evaluation grades. The side effect evaluation level and the section to which the side effect evaluation index corresponding thereto belongs can be arranged by itself according to actual conditions.
In one embodiment of the specification, the side effect rating scale includes: "recommended regular medication", "doctor evaluated use", "cautious use or replacement of other medications" and "not recommended use, recommended replacement of other medications", in particular:
the side effect evaluation index interval corresponding to the recommended conventional drug administration is 76-100;
the corresponding side effect evaluation index interval of "doctor's use after evaluation" is 51-75;
the side effect evaluation index interval corresponding to "carefully use or replace other drugs" is 26-50;
the side effect evaluation index interval corresponding to "not recommended use, recommended replacement of other drugs" is 0-25.
By classifying the medicines to be tested, quantitative reference indexes can be provided for doctors to simply and directly recognize the side effect risks of various medicines, and on the other hand, accurate risk guidance instructions for personalized medicine use can be provided for patients according to the detection results of medicine genomics.
In addition, the side effect index model not only carries out qualitative description on high/low risk of specific side effects, but also contains the total side effect evaluation index of the medicines, can quantitatively carry out transverse comparison on the side effect risks of various different medicines, reduces possible errors in subjective analysis, and improves repeatability and reliability.
In order to facilitate the doctor (professional) to visually check the data result, a potential medication risk assessment table of the patient is generated according to the name of the drug to be tested, the side effect of high risk, the side effect assessment index and the side effect assessment grade, as shown in table 6:
(Table 6)
FIG. 3 is a schematic structural diagram of an evaluation system for side effects of a drug according to an embodiment of the present disclosure, the system comprising:
a construction module 301, configured to construct a side effect index model;
an acquisition module 302, configured to acquire gene detection data of a patient and a name of a drug to be tested;
the evaluation module 303 is configured to substitute the gene detection data and the name of the drug to be tested into the side effect index model to obtain a side effect evaluation index of the drug to be tested;
a summary module 304 for summarizing all side effect assessment indices associated with the patient, assisting in assessing potential medication risk.
Optionally, the evaluation module 303 includes:
the invoking submodule is used for invoking a plurality of scoring parameters of the drug to be tested according to the gene detection data and the drug information to be tested;
and the evaluation molecular module is used for scoring the side effect of the drug to be tested according to a plurality of scoring parameters to obtain a side effect evaluation index.
Optionally, the evaluation module includes:
the scoring parameters include one or more of an adverse reaction weight alpha, an adverse reaction rating beta and a genetic role status gamma;
and a scoring unit for calculating and obtaining the side effect evaluation Index of the drug to be tested according to index=F (alpha, beta, gamma).
Optionally, the constructing module 301 includes:
a first collection sub-module for collecting follow-up data of drug side effects;
a calculating sub-module, configured to calculate the occurrence rate of side effects and the severity of side effects according to the occurrence of each side effect of the drug in the follow-up data;
the weight determination submodule is used for combining expert evaluation results to obtain adverse reaction weight alpha of the medicine;
the first association submodule is used for establishing association relation between the medicine and the adverse reaction weight alpha.
Optionally, the constructing module 301 includes:
the second collecting sub-module is used for collecting and extracting names of side effects and corresponding side effect scores according to clinical feedback data of historical patients;
the rating determination submodule is used for collecting gene detection data of the historical patient and determining an adverse reaction rating beta by combining the side effect score and the gene detection data of the historical patient;
and the second association submodule is used for establishing association relation between side effects and adverse reaction ratings beta.
Optionally, the constructing module 301 includes:
a matching sub-module, configured to match a first genetic locus related to a drug effect according to a pharmacogenomic document, and determine a gene role status γ of a first genotype, where the first genotype is a gene type on the first genetic locus;
and the third correlation sub-module is used for establishing the correlation between the first genotype and the gene role position gamma.
Optionally, the constructing module 301 includes:
the classifier construction submodule is used for constructing a plurality of basic classifiers;
the voting weight training submodule is used for training the voting weight of each basic classifier according to the adverse reaction weight alpha, the adverse reaction rating beta and the gene role status gamma;
an integration calculation sub-module for integrating each basic classifier by using a weighted average method
/>
Wherein w is i Is the weight of the basic classifier, and
the functions of the apparatus according to the embodiments of the present application have been described in the foregoing method embodiments, so that the descriptions of the embodiments are not exhaustive, and reference may be made to the related descriptions in the foregoing embodiments, which are not repeated herein.
It will be apparent to those skilled in the art that embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. A method for evaluating side effects of a drug, comprising:
constructing a side effect index model; the constructing of the side effect index model comprises the following steps: determining scoring parameters; training a side effect index model; wherein the determining scoring parameters comprises: collecting follow-up data of side effects of the drug; calculating the occurrence rate and the severity of the side effects according to the occurrence condition of each side effect of the medicine in the follow-up data; combining expert evaluation results to obtain adverse reaction weight alpha of the medicine; collecting and extracting names of side effects and corresponding side effect scores according to clinical feedback data of historical patients; collecting gene detection data of the historical patient, and determining an adverse reaction rating beta by combining the side effect score and the gene detection data of the historical patient; according to the pharmacogenomics literature, matching a first gene locus related to the influence of a drug, and determining the gene role gamma of a first genotype, wherein the first genotype is the gene type on the first gene locus;
carrying out comprehensive weighted calculation on the clinical feedback data and the gene detection data of the historical patient, and carrying out cross verification and error calibration by combining the adverse reaction weight and the adverse reaction rating;
acquiring gene detection data of a patient and drug information to be detected;
substituting the gene detection data and the drug information to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected, wherein the side effect evaluation index corresponding to the side effect evaluation index is searched for by the drug information to be detected; searching the adverse reaction rating beta corresponding to the gene detection data; searching a corresponding first gene locus through the to-be-detected medicine information, and determining a gene action status gamma corresponding to the first gene locus according to the first genotype corresponding to the first gene locus in the gene detection data; obtaining a side effect evaluation index of the drug to be tested according to the adverse reaction weight alpha, the adverse reaction rating beta and the gene action status gamma;
summarizing all the side effect evaluation indexes related to the patient, dividing side effect evaluation grades according to the interval to which the side effect evaluation indexes belong, classifying the to-be-tested medicines according to the side effect evaluation indexes, and assisting in evaluating potential medication risks.
2. The method according to claim 1, wherein substituting the gene detection data and the information of the drug to be tested into the side effect index model to obtain the side effect evaluation index of the drug to be tested comprises:
according to the gene detection data and the information of the to-be-detected medicine, a plurality of scoring parameters of the to-be-detected medicine are called;
and scoring the side effect of the drug to be tested according to a plurality of scoring parameters to obtain a side effect evaluation index.
3. The method according to claim 2, wherein scoring the side effects of the drug to be tested according to a plurality of scoring parameters to obtain a side effect score comprises:
the scoring parameters include one or more of the adverse reaction weight α, the adverse reaction rating β, and the gene role status γ;
and calculating according to index=F (alpha, beta, gamma), wherein F (alpha, beta, gamma) is a manually determined function, the Index of the side effect is a percentage, and the higher the score, the smaller the comprehensive side effect is relatively.
4. The method of claim 1, wherein training the side effect index model comprises:
constructing a plurality of basic classifiers;
training the voting weight of each basic classifier according to the scoring parameters;
for each foundationClassifier integration using weighted averaging；
Wherein,weights of the base classifier, and +.>。
5. A system for evaluating side effects of a drug, comprising:
the construction module is used for constructing a side effect index model; the constructing of the side effect index model comprises the following steps: determining scoring parameters; training a side effect index model; wherein the determining scoring parameters comprises: collecting follow-up data of side effects of the drug; calculating the occurrence rate and the severity of the side effects according to the occurrence condition of each side effect of the medicine in the follow-up data; combining expert evaluation results to obtain adverse reaction weight alpha of the medicine; collecting and extracting names of side effects and corresponding side effect scores according to clinical feedback data of historical patients; collecting gene detection data of the historical patient, and determining an adverse reaction rating beta by combining the side effect score and the gene detection data of the historical patient; according to the pharmacogenomics literature, matching a first gene locus related to the influence of a drug, and determining the gene role gamma of a first genotype, wherein the first genotype is the gene type on the first gene locus;
carrying out comprehensive weighted calculation on the clinical feedback data and the gene detection data of the historical patient, and carrying out cross verification and error calibration by combining the adverse reaction weight and the adverse reaction rating;
the acquisition module is used for acquiring gene detection data of a patient and drug information to be detected;
the evaluation module is used for substituting the gene detection data and the drug information to be detected into the side effect index model to obtain a side effect evaluation index of the drug to be detected, wherein the side effect evaluation index corresponding to the side effect evaluation index is searched for through the drug information to be detected; searching the adverse reaction rating beta corresponding to the gene detection data; searching a corresponding first gene locus through the to-be-detected medicine information, and determining a gene action status gamma corresponding to the first gene locus according to the first genotype corresponding to the first gene locus in the gene detection data; obtaining a side effect evaluation index of the drug to be tested according to the adverse reaction weight alpha, the adverse reaction rating beta and the gene action status gamma;
the summarizing module is used for summarizing all the side effect evaluation indexes related to the patient, dividing side effect evaluation grades according to the interval to which the side effect evaluation indexes belong, classifying the to-be-tested medicines according to the side effect evaluation indexes, and assisting in evaluating potential medication risks.
6. An electronic device, wherein the electronic device comprises:
a processor; the method comprises the steps of,
a memory storing computer executable instructions that, when executed, cause the processor to perform the method of any of claims 1-4.
7. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378013.3A CN115662656B (en) | 2022-11-04 | 2022-11-04 | Evaluation method and system for side effects of medicine and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211378013.3A CN115662656B (en) | 2022-11-04 | 2022-11-04 | Evaluation method and system for side effects of medicine and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115662656A CN115662656A (en) | 2023-01-31 |
| CN115662656B true CN115662656B (en) | 2023-11-07 |
Family
ID=85016018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211378013.3A Active CN115662656B (en) | 2022-11-04 | 2022-11-04 | Evaluation method and system for side effects of medicine and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115662656B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116072305B (en) * | 2023-02-17 | 2023-09-29 | 北京中兴正远科技有限公司 | Clinical trial data acquisition system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003288415A (en) * | 2002-03-27 | 2003-10-10 | Ntt Data Corp | Drug evaluation system |
| CN105279393A (en) * | 2015-10-12 | 2016-01-27 | 厦门大学 | Method for evaluating adverse drug reactions based on weighting network |
| CN107480443A (en) * | 2017-08-08 | 2017-12-15 | 复旦大学附属儿科医院 | A kind of clinical drug integrated evaluating method based on real world |
| CN111742370A (en) * | 2017-05-12 | 2020-10-02 | 密歇根大学董事会 | Individual and cohort pharmacological phenotype prediction platform |
| CN111863281A (en) * | 2020-07-29 | 2020-10-30 | 山东大学 | Personalized adverse drug reaction prediction method, system, equipment and medium |
-
2022
- 2022-11-04 CN CN202211378013.3A patent/CN115662656B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003288415A (en) * | 2002-03-27 | 2003-10-10 | Ntt Data Corp | Drug evaluation system |
| CN105279393A (en) * | 2015-10-12 | 2016-01-27 | 厦门大学 | Method for evaluating adverse drug reactions based on weighting network |
| CN111742370A (en) * | 2017-05-12 | 2020-10-02 | 密歇根大学董事会 | Individual and cohort pharmacological phenotype prediction platform |
| CN107480443A (en) * | 2017-08-08 | 2017-12-15 | 复旦大学附属儿科医院 | A kind of clinical drug integrated evaluating method based on real world |
| CN111863281A (en) * | 2020-07-29 | 2020-10-30 | 山东大学 | Personalized adverse drug reaction prediction method, system, equipment and medium |
Non-Patent Citations (4)
| Title |
|---|
| PD-1/PD-L1抗体临床药效标志物和CAR-T细胞临床前药效评价的特点及检测方法;贺庆;霍艳;高华;王军志;;药物分析杂志(第07期);全文 * |
| 两种他克莫司初始治疗方案治疗特发性膜性肾病的经济学评价;马静;孙绍伟;魏传梅;窦冕;于鹏飞;;中国医院用药评价与分析(第11期);全文 * |
| 基于层次分析法开展儿童用药循证综合评价;贾露露;药物流行病学杂志;第25卷(第10期);原文第601-605页 * |
| 贺庆 ; 霍艳 ; 高华 ; 王军志 ; .PD-1/PD-L1抗体临床药效标志物和CAR-T细胞临床前药效评价的特点及检测方法.药物分析杂志.2020,(第07期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115662656A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7461006B2 (en) | Method and system for the analysis and association of patient-specific and population-based genomic data with drug safety adverse event data | |
| CN111986770B (en) | Prescription medication auditing method, device, equipment and storage medium | |
| US9195952B2 (en) | Systems and methods for contextual mapping utilized in business process controls | |
| AU2002359549B2 (en) | Methods for the identification of genetic features | |
| US7917525B2 (en) | Analyzing administrative healthcare claims data and other data sources | |
| CN107169310B (en) | Gene detection knowledge base construction method and system | |
| US11842794B2 (en) | Variant calling in single molecule sequencing using a convolutional neural network | |
| CN115662656B (en) | Evaluation method and system for side effects of medicine and electronic equipment | |
| US11568302B2 (en) | Training machine learning algorithms with temporally variant personal data, and applications thereof | |
| US20100162029A1 (en) | Systems and methods for process improvement in production environments | |
| Norman et al. | Measuring the impact of screening automation on meta-analyses of diagnostic test accuracy | |
| US10990900B2 (en) | Scheduling machine learning tasks, and applications thereof | |
| CN112233810A (en) | Treatment scheme comprehensive curative effect evaluation method based on real world clinical data | |
| US20050149271A1 (en) | Methods and apparatus for complex gentics classification based on correspondence anlysis and linear/quadratic analysis | |
| CN114298484A (en) | Drug risk identification method, device, equipment and storage medium | |
| Gill et al. | The use of case studies in systems implementations within health care settings: A scoping review | |
| US20190311372A1 (en) | Normalizing Ingested Personal Data, and Applications Thereof | |
| Mölbert et al. | Adjustments to the reference dataset design improve cell type label transfer | |
| Schwabe | BayesTwin: An R package for Bayesian inference of item-level twin data | |
| CN109446192B (en) | Data testing method and device | |
| CN112189206A (en) | Processing personal data using machine learning algorithms and applications thereof | |
| CN116030890A (en) | Single-gene genetic disease phenotype-gene association matching method, device and storage medium | |
| Maranhão et al. | Challenges in design and creation of genetic openEHR-archetype | |
| Makris et al. | Classification model for predicting cost slippage in governmental ICT projects | |
| Sivakumar | Benchmarking the Performance of Machine Learning Algorithms for Record Linkage at Different Heterogeneity Rates in a New Setting |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method, system, and electronic device for evaluating drug side effects Granted publication date: 20231107 Pledgee: China Construction Bank Corporation Shanghai Xuhui sub branch Pledgor: SHANGHAI KANGLI MEDICAL LABORATORY Co.,Ltd. Registration number: Y2024310000231 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |