CN117995409A - Patient medication risk evaluation method, system, terminal and medium - Google Patents
Patient medication risk evaluation method, system, terminal and medium Download PDFInfo
- Publication number
- CN117995409A CN117995409A CN202410237798.5A CN202410237798A CN117995409A CN 117995409 A CN117995409 A CN 117995409A CN 202410237798 A CN202410237798 A CN 202410237798A CN 117995409 A CN117995409 A CN 117995409A
- Authority
- CN
- China
- Prior art keywords
- medication
- patient
- risk evaluation
- data
- medication risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 282
- 229940079593 drug Drugs 0.000 title claims abstract description 279
- 238000011156 evaluation Methods 0.000 title claims abstract description 75
- 238000013210 evaluation model Methods 0.000 claims abstract description 77
- 238000011282 treatment Methods 0.000 claims abstract description 55
- 238000003745 diagnosis Methods 0.000 claims abstract description 50
- 238000012549 training Methods 0.000 claims abstract description 37
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000013135 deep learning Methods 0.000 claims abstract description 15
- 206010067484 Adverse reaction Diseases 0.000 claims abstract description 13
- 230000006838 adverse reaction Effects 0.000 claims abstract description 13
- 206010061623 Adverse drug reaction Diseases 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 49
- 230000006870 function Effects 0.000 claims description 31
- 230000008569 process Effects 0.000 claims description 29
- 238000012502 risk assessment Methods 0.000 claims description 19
- 238000004140 cleaning Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000001131 transforming effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 3
- 238000001647 drug administration Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002483 medication Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010013710 Drug interaction Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the field of medication risk evaluation, and particularly discloses a patient medication risk evaluation method, a system, a terminal and a medium, wherein historical medical data are collected from various data source systems, and the medical data comprise patient diagnosis and treatment data and medication adverse reaction feedback data; analyzing feedback data of adverse drug reaction and classifying medication risk levels; constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level; training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm; inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient; and according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed. According to the invention, the medication risk is evaluated by considering the individuation information of the patient, and the accuracy of the evaluation result of the medication risk of the patient is improved.
Description
Technical Field
The invention relates to the field of medication risk evaluation, in particular to a patient medication risk evaluation method, a system, a terminal and a medium.
Background
In the medical field, rational medication is a key link in ensuring that patients are effectively treated. However, rational administration is a challenging problem due to the variety of drugs and complex interactions. Conventional rational medication monitoring systems often only consider interactions between medications, and do not consider individualized information of patients. For example, patent application publication number CN115019930a discloses a medication risk assessment method comprising: obtaining first medication path information in a medication database relating to a first medication combination; obtaining second medication path information relating to a second combination of medications in the medication database; acquiring overlapped medication information between the first medication path information and the second medication path information; judging whether the overlapped medication information accords with a noise elimination condition or not; and if the overlapped medication information accords with the noise elimination condition, establishing a risk assessment model according to the rest medication path information in the medication database on the premise of not considering the first medication path information, wherein the risk assessment model is used for assessing the use risk of at least one drug in the medication database.
Different patient information may exhibit different drug responses to the same drug, and the existing rational medication monitoring system does not consider the personalized information of the patient, resulting in lower accuracy of medication risk assessment results for the patient.
Disclosure of Invention
In order to solve the problems, the invention provides a patient medication risk evaluation method, a system, a terminal and a medium, which are used for evaluating medication risk by considering individual information of a patient and improving the accuracy of a medication risk evaluation result of the patient.
In a first aspect, the present invention provides a method for evaluating risk of medication for a patient, including the steps of:
Collecting historical medical data from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions;
analyzing feedback data of adverse drug reaction and classifying medication risk levels;
constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level;
Training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm;
Inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient;
And according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
In an alternative embodiment, the historical medical data is collected from various data source systems, including:
collecting basic information, medical history, examination results and diagnosis results of a patient from a hospital information system;
Collecting medical history, examination results, diagnosis results and treatment schemes of a patient from an electronic medical record system;
medication records and medication adverse reaction feedback data of patients are collected from the medication management system.
In an alternative embodiment, constructing a sample set from the patient diagnosis and treatment data and the corresponding medication risk level specifically includes:
Performing cleaning treatment, standardization treatment and pretreatment on the historical medical data; wherein the cleaning process includes a duplicate data removal process, a missing value process, and an outlier process; the normalization process includes converting data from different sources into the same format; preprocessing comprises selecting target features, and transforming, normalizing and classifying the target features;
and constructing a sample set from the processed data.
In an alternative embodiment, based on a deep learning neural network algorithm, training a medication risk evaluation model by using a sample set specifically includes:
Constructing a medication risk evaluation model framework, which comprises a selection neural network layer and an activation function;
initializing the weight and bias of a medication risk evaluation model;
inputting a training sample set into a medication risk evaluation model, performing forward propagation through a neural network layer structure, and calculating the difference between a prediction result and a real label, namely the value of a loss function;
Gradient calculation is carried out on the medication risk evaluation model parameters by using the loss function, and the weight and the bias are updated by a back propagation algorithm so as to minimize the loss function;
Repeating the steps of forward propagation and backward propagation until the performance of the medication risk evaluation model meets the requirements;
evaluating the performance of the model by using a verification sample set, and adjusting the structure, super parameters or training strategy of the drug risk evaluation model according to the evaluation result;
And testing the medication risk evaluation model by using the test sample set to evaluate the generalization performance of the medication risk evaluation model.
In a second aspect, the present invention provides a patient medication risk assessment system, comprising,
Historical data acquisition module: collecting historical medical data from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions;
Risk level classification module: analyzing feedback data of adverse drug reaction and classifying medication risk levels;
Model training module: constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level; training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm;
Drug administration risk evaluation module: inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient;
And an evaluation result output module: and according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
In an alternative embodiment, the historical data collection module collects historical medical data from various data source systems, and specifically includes:
collecting basic information, medical history, examination results and diagnosis results of a patient from a hospital information system;
Collecting medical history, examination results, diagnosis results and treatment schemes of a patient from an electronic medical record system;
medication records and medication adverse reaction feedback data of patients are collected from the medication management system.
In an alternative embodiment, the model training module constructs a sample set from the patient diagnosis and treatment data and the corresponding medication risk level, and specifically includes:
Performing cleaning treatment, standardization treatment and pretreatment on the historical medical data; wherein the cleaning process includes a duplicate data removal process, a missing value process, and an outlier process; the normalization process includes converting data from different sources into the same format; preprocessing comprises selecting target features, and transforming, normalizing and classifying the target features;
and constructing a sample set from the processed data.
In an alternative embodiment, the model training module trains the medication risk evaluation model based on a deep learning neural network algorithm by using a sample set, and specifically comprises:
Constructing a medication risk evaluation model framework, which comprises a selection neural network layer and an activation function;
initializing the weight and bias of a medication risk evaluation model;
inputting a training sample set into a medication risk evaluation model, performing forward propagation through a neural network layer structure, and calculating the difference between a prediction result and a real label, namely the value of a loss function;
Gradient calculation is carried out on the medication risk evaluation model parameters by using the loss function, and the weight and the bias are updated by a back propagation algorithm so as to minimize the loss function;
Repeating the steps of forward propagation and backward propagation until the performance of the medication risk evaluation model meets the requirements;
evaluating the performance of the model by using a verification sample set, and adjusting the structure, super parameters or training strategy of the drug risk evaluation model according to the evaluation result;
And testing the medication risk evaluation model by using the test sample set to evaluate the generalization performance of the medication risk evaluation model.
In a third aspect, a technical solution of the present invention provides a terminal, including:
a memory for storing a patient medication risk assessment program;
a processor for implementing the steps of the patient medication risk assessment method as defined in any one of the preceding claims when executing the patient medication risk assessment program.
In a fourth aspect, the present invention provides a computer readable storage medium, on which a patient medication risk assessment program is stored, which when executed by a processor, implements the steps of the patient medication risk assessment method according to any one of the above.
Compared with the prior art, the patient medication risk evaluation method, system, terminal and medium provided by the invention have the following beneficial effects: firstly, acquiring historical medical data about patient individuation information from various data source systems, then constructing a medication risk evaluation model according to the historical medical data containing the patient individuation information, and evaluating the medication risk of a target patient by using the model. According to the invention, the medication risk is evaluated by considering the individuation information of the patient, and the accuracy of the evaluation result of the medication risk of the patient is improved.
Drawings
For a clearer description of embodiments of the invention or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a patient medication risk evaluation method according to an embodiment of the present invention.
Fig. 2 is a schematic block diagram of a patient medication risk evaluation system according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In order to better understand the aspects of the present invention, the present invention will be described in further detail with reference to the accompanying drawings and detailed description. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
Fig. 1 is a schematic flow chart of a patient medication risk evaluation method according to an embodiment of the present invention. The execution subject of fig. 1 may be a patient medication risk evaluation system. The patient medication risk evaluation method provided by the embodiment of the invention is executed by the computer equipment, and correspondingly, the patient medication risk evaluation system is operated in the computer equipment. The order of the steps in the flow chart may be changed and some may be omitted according to different needs.
As shown in fig. 1, the method includes the following steps.
S1, historical medical data are collected from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions.
S2, analyzing feedback data of adverse drug reaction and classifying the drug risk level.
S3, constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level.
And S4, training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm.
S5, inputting the diagnosis and treatment data of the current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient.
S6, according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
According to the patient medication risk evaluation method, first, historical medical data about patient individuation information is acquired from various data source systems, then a medication risk evaluation model is constructed according to the historical medical data containing the patient individuation information, and the medication risk of a target patient is evaluated by using the model. According to the method, the medication risk is evaluated by considering the individuation information of the patient, and the accuracy of the medication risk evaluation result of the patient is improved.
The present invention will be described in further detail below for further understanding of the present invention.
SS1, collecting historical medical data.
In this embodiment, the acquired medical data includes diagnosis and treatment data of the patient and feedback data of adverse drug reactions, and may be acquired from various data source systems. Specifically, basic information, medical history, examination results and diagnosis results of a patient are collected from a hospital information system; collecting medical history, examination results, diagnosis results and treatment schemes of a patient from an electronic medical record system; medication records and medication adverse reaction feedback data of patients are collected from the medication management system. It should be noted that, the feedback data of adverse drug reaction may be uploaded by the patient and its family members, or by the relevant doctor.
And SS2, analyzing the feedback data of adverse drug reaction and classifying the drug risk level.
In this embodiment, the evaluation of the medication risk is output in a hierarchical form, so after the medication adverse reaction feedback data is collected, the medication adverse reaction feedback data is analyzed and classified, and the process can be evaluated by a responsible doctor of a relevant patient after the medication management system obtains the medication adverse reaction feedback data, so that the classification result is collected while the historical medical data is collected, or classification rules are formulated in advance, and the collected medication adverse reaction feedback data is automatically evaluated.
And SS3, constructing a sample set of the deep learning neural network model.
In this embodiment, a sample set is constructed using patient diagnosis and treatment data and corresponding medication risk levels, the sample set including a training sample set, a verification sample set, and a test sample set.
Before the sample set is constructed, the collected historical medical data is processed, including cleaning, standardization and preprocessing, and the characteristic data related to medication is extracted to remove noise and redundant information in the data, so that a high-quality data set is provided for subsequent model training.
The historical medical data is subjected to cleaning treatment, standardization treatment and pretreatment. The cleaning process comprises repeated data removal, missing value processing and abnormal value processing, and if a plurality of repeated medication record data exist, the repeated data are removed. The standardized process includes converting data from different sources into the same format, such as date of admission format (year-month-day format), unified administration unit (milligrams per liter), and the like. Preprocessing includes selecting target features, and transforming, normalizing and classifying the target features, such as selecting age features, classifying age features, such as infants (under 1 year), young children (under 2 years), children (under 6 years), teenagers (under 14 years), young adults (under 35 years), middle-aged adults (under 60 years), and elderly adults (over 60 years).
Finally, the characteristic data related to the medication is extracted and comprises basic information (such as age, sex, height weight and the like) of the patient, medical history (such as past medical history, family medical history and the like), examination result (such as laboratory examination result, imaging examination result and the like), diagnosis result (such as disease name, stage and the like), treatment scheme (such as operation scheme, medication scheme and the like), medication record (such as medication name, dosage, usage and the like) and medication adverse reaction feedback data.
And SS4, training a drug risk evaluation model.
Training a deep learning model by using the processed data, and evaluating the medication risk, wherein the method specifically comprises the following steps.
And step 1, constructing a medication risk evaluation model framework, wherein the model framework comprises a selective neural network layer and an activation function.
The neural network layer comprises a full connection layer, a convolution layer, a circulation layer and the like. The method comprises the steps of selecting a proper neural network layer and an activation function, and determining the depth and complexity of the network.
And step 2, initializing the weight and bias of the medication risk evaluation model.
This may be accomplished by a specific initialization method Xavier initialization.
And step 3, inputting the training sample set into a medication risk evaluation model, performing forward propagation through a neural network layer structure, and calculating the difference between a predicted result and a real label, namely the value of a loss function.
And 4, carrying out gradient calculation on the medication risk evaluation model parameters by using the loss function, and updating weights and biases through a back propagation algorithm so as to minimize the loss function.
And 5, repeating the steps of forward propagation and backward propagation until the performance of the medication risk evaluation model meets the requirements.
For example, the performance of the model reaches a satisfactory level or is no longer significantly improved.
And 6, evaluating the performance of the model by using the verification sample set, and adjusting the structure, super parameters or training strategy of the drug risk evaluation model according to the evaluation result.
And 7, testing the medication risk evaluation model by using a test sample set to evaluate the generalization performance of the medication risk evaluation model.
And SS5, inputting the diagnosis and treatment data of the current patient into the trained medication risk evaluation model, and outputting the medication risk evaluation result of the current patient.
After the medication risk evaluation model is trained, the medication risk evaluation model is deployed in a production environment, and after the diagnosis and treatment data of a patient are input into the medication risk evaluation model, the medication risk evaluation model outputs the evaluated medication risk level, so that decision reference is provided for doctors. Patient diagnostic data includes patient basic information, medical history, examination results, diagnosis results, treatment regimens, and medication records.
And SS6, according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
And timely pushing relevant medicine knowledge according to the risk assessment result, and preventing occurrence of adverse medicine events. Such knowledge may include drug interactions, adverse reactions, rational medication recommendations, etc., to help doctors better understand medication risk and rational medication regimens. The medicine related knowledge is stored in the database and can be pushed in a pop-up window, a short message reminding mode and the like. The assessment results can also be presented to the doctor in the form of visual reports to assist the doctor in making more rational medication decisions. The visual report may include forms of charts, data, and recommended advice, etc., to facilitate a physician's better understanding of the assessment and to make reasonable medication decisions.
The embodiment of the invention provides a patient medication risk evaluation system corresponding to the method, and the embodiment of the invention further provides a patient medication risk evaluation method based on the patient medication risk evaluation method described in the embodiment.
Fig. 2 is a schematic block diagram of a patient medication risk evaluation system according to an embodiment of the present invention, in which a patient medication risk evaluation system 200 may be divided into a plurality of functional modules according to functions performed by the patient medication risk evaluation system, as shown in fig. 2. The functional module may include: the system comprises a historical data acquisition module 210, a risk level classification module 220, a model training module 230, a medication risk evaluation module 240 and an evaluation result output module 250. The module referred to in the present invention refers to a series of computer program segments capable of being executed by at least one processor and of performing a fixed function, stored in a memory.
Historical data acquisition module 210: historical medical data is collected from various data source systems, and the medical data comprises diagnosis and treatment data of patients and feedback data of adverse drug reactions.
Risk level classification module 220: and analyzing the feedback data of adverse drug reaction and classifying the drug risk level.
Model training module 230: constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level; based on a deep learning neural network algorithm, training a medication risk evaluation model by using a sample set.
Medication risk assessment module 240: and inputting the diagnosis and treatment data of the current patient into the trained medication risk evaluation model, and outputting the medication risk evaluation result of the current patient.
The evaluation result output module 250: and according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
In an alternative embodiment, the historical data collection module collects historical medical data from various data source systems, and specifically includes: collecting basic information, medical history, examination results and diagnosis results of a patient from a hospital information system; collecting medical history, examination results, diagnosis results and treatment schemes of a patient from an electronic medical record system; medication records and medication adverse reaction feedback data of patients are collected from the medication management system.
In an alternative embodiment, the model training module constructs a sample set from the patient diagnosis and treatment data and the corresponding medication risk level, and specifically includes: performing cleaning treatment, standardization treatment and pretreatment on the historical medical data; wherein the cleaning process includes a duplicate data removal process, a missing value process, and an outlier process; the normalization process includes converting data from different sources into the same format; preprocessing comprises selecting target features, and transforming, normalizing and classifying the target features; and constructing a sample set from the processed data.
In an alternative embodiment, the model training module trains the medication risk evaluation model based on a deep learning neural network algorithm by using a sample set, and specifically comprises: constructing a medication risk evaluation model framework, which comprises a selection neural network layer and an activation function; initializing the weight and bias of a medication risk evaluation model; inputting a training sample set into a medication risk evaluation model, performing forward propagation through a neural network layer structure, and calculating the difference between a prediction result and a real label, namely the value of a loss function; gradient calculation is carried out on the medication risk evaluation model parameters by using the loss function, and the weight and the bias are updated by a back propagation algorithm so as to minimize the loss function; repeating the steps of forward propagation and backward propagation until the performance of the medication risk evaluation model meets the requirements; evaluating the performance of the model by using a verification sample set, and adjusting the structure, super parameters or training strategy of the drug risk evaluation model according to the evaluation result; and testing the medication risk evaluation model by using the test sample set to evaluate the generalization performance of the medication risk evaluation model.
The patient medication risk evaluation system of the present embodiment is used to implement the foregoing patient medication risk evaluation method, so that the specific implementation of the system can be seen as the example part of the patient medication risk evaluation method, so that the specific implementation thereof can be referred to the description of the corresponding examples of the respective parts, and will not be further described herein.
In addition, since the patient medication risk evaluation system of the present embodiment is used to implement the foregoing patient medication risk evaluation method, the actions thereof correspond to those of the foregoing method, and will not be described herein.
Fig. 3 is a schematic structural diagram of a terminal 300 according to an embodiment of the present invention, including: a processor 310, a memory 320 and a communication unit 330. The processor 310 is configured to implement the patient medication risk assessment program stored in the memory 320 by implementing the following steps:
Collecting historical medical data from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions;
analyzing feedback data of adverse drug reaction and classifying medication risk levels;
constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level;
Training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm;
Inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient;
And according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
The terminal 300 includes a processor 310, a memory 320, and a communication unit 330. The components may communicate via one or more buses, and it will be appreciated by those skilled in the art that the configuration of the server as shown in the drawings is not limiting of the invention, as it may be a bus-like structure, a star-like structure, or include more or fewer components than shown, or may be a combination of certain components or a different arrangement of components.
The memory 320 may be used to store instructions for execution by the processor 310, and the memory 320 may be implemented by any type of volatile or non-volatile memory terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. The execution of the instructions in memory 320, when executed by processor 310, enables terminal 300 to perform some or all of the steps in the method embodiments described below.
The processor 310 is a control center of the storage terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by running or executing software programs and/or modules stored in the memory 320, and invoking data stored in the memory. The processor may be comprised of an integrated circuit (INTEGRATED CIRCUIT, simply referred to as an IC), for example, a single packaged IC, or may be comprised of multiple packaged ICs connected to one another for the same function or for different functions. For example, the processor 310 may include only a central processing unit (Central Processing Unit, CPU for short). In the embodiment of the invention, the CPU can be a single operation core or can comprise multiple operation cores.
And a communication unit 330 for establishing a communication channel so that the storage terminal can communicate with other terminals. Receiving user data sent by other terminals or sending the user data to other terminals.
The invention also provides a computer storage medium, which can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (random access memory, RAM) and the like.
The computer storage medium stores a patient medication risk assessment program which when executed by the processor performs the steps of:
Collecting historical medical data from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions;
analyzing feedback data of adverse drug reaction and classifying medication risk levels;
constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level;
Training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm;
Inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient;
And according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solution in the embodiments of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium such as a U-disc, a mobile hard disc, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, etc. various media capable of storing program codes, including several instructions for causing a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing disclosure is merely illustrative of the preferred embodiments of the invention and the invention is not limited thereto, since modifications and variations may be made by those skilled in the art without departing from the principles of the invention.
Claims (10)
1. A method for evaluating medication risk of a patient, comprising the steps of:
Collecting historical medical data from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions;
analyzing feedback data of adverse drug reaction and classifying medication risk levels;
constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level;
Training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm;
Inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient;
And according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
2. The patient medication risk assessment method according to claim 1, wherein the historical medical data is collected from various data source systems, specifically comprising:
collecting basic information, medical history, examination results and diagnosis results of a patient from a hospital information system;
Collecting medical history, examination results, diagnosis results and treatment schemes of a patient from an electronic medical record system;
medication records and medication adverse reaction feedback data of patients are collected from the medication management system.
3. The patient medication risk assessment method according to claim 2, wherein constructing a sample set from the patient diagnosis and treatment data and the corresponding medication risk level specifically comprises:
Performing cleaning treatment, standardization treatment and pretreatment on the historical medical data; wherein the cleaning process includes a duplicate data removal process, a missing value process, and an outlier process; the normalization process includes converting data from different sources into the same format; preprocessing comprises selecting target features, and transforming, normalizing and classifying the target features;
and constructing a sample set from the processed data.
4. The patient medication risk assessment method according to claim 3, wherein training the medication risk assessment model using a sample set based on a deep learning neural network algorithm specifically comprises:
Constructing a medication risk evaluation model framework, which comprises a selection neural network layer and an activation function;
initializing the weight and bias of a medication risk evaluation model;
inputting a training sample set into a medication risk evaluation model, performing forward propagation through a neural network layer structure, and calculating the difference between a prediction result and a real label, namely the value of a loss function;
Gradient calculation is carried out on the medication risk evaluation model parameters by using the loss function, and the weight and the bias are updated by a back propagation algorithm so as to minimize the loss function;
Repeating the steps of forward propagation and backward propagation until the performance of the medication risk evaluation model meets the requirements;
evaluating the performance of the model by using a verification sample set, and adjusting the structure, super parameters or training strategy of the drug risk evaluation model according to the evaluation result;
And testing the medication risk evaluation model by using the test sample set to evaluate the generalization performance of the medication risk evaluation model.
5. A patient medication risk evaluation system is characterized by comprising,
Historical data acquisition module: collecting historical medical data from various data source systems, wherein the medical data comprise diagnosis and treatment data of patients and feedback data of adverse drug reactions;
Risk level classification module: analyzing feedback data of adverse drug reaction and classifying medication risk levels;
Model training module: constructing a sample set from the diagnosis and treatment data of the patient and the corresponding medication risk level; training a medication risk evaluation model by using a sample set based on a deep learning neural network algorithm;
Drug administration risk evaluation module: inputting diagnosis and treatment data of a current patient into the trained medication risk evaluation model, and outputting a medication risk evaluation result of the current patient;
And an evaluation result output module: and according to the medication risk evaluation result, the medication related knowledge is called from the database, and the medication risk evaluation result and the medication related knowledge are pushed.
6. The patient medication risk assessment system according to claim 5, wherein the historical data collection module collects historical medical data from various types of data source systems, specifically comprising:
collecting basic information, medical history, examination results and diagnosis results of a patient from a hospital information system;
Collecting medical history, examination results, diagnosis results and treatment schemes of a patient from an electronic medical record system;
medication records and medication adverse reaction feedback data of patients are collected from the medication management system.
7. The patient medication risk assessment system according to claim 6, wherein the model training module constructs a sample set of patient diagnosis and treatment data and corresponding medication risk levels, specifically comprising:
Performing cleaning treatment, standardization treatment and pretreatment on the historical medical data; wherein the cleaning process includes a duplicate data removal process, a missing value process, and an outlier process; the normalization process includes converting data from different sources into the same format; preprocessing comprises selecting target features, and transforming, normalizing and classifying the target features;
and constructing a sample set from the processed data.
8. The patient medication risk assessment system according to claim 7, wherein the model training module trains the medication risk assessment model using a sample set based on a deep learning neural network algorithm, specifically comprising:
Constructing a medication risk evaluation model framework, which comprises a selection neural network layer and an activation function;
initializing the weight and bias of a medication risk evaluation model;
inputting a training sample set into a medication risk evaluation model, performing forward propagation through a neural network layer structure, and calculating the difference between a prediction result and a real label, namely the value of a loss function;
Gradient calculation is carried out on the medication risk evaluation model parameters by using the loss function, and the weight and the bias are updated by a back propagation algorithm so as to minimize the loss function;
Repeating the steps of forward propagation and backward propagation until the performance of the medication risk evaluation model meets the requirements;
evaluating the performance of the model by using a verification sample set, and adjusting the structure, super parameters or training strategy of the drug risk evaluation model according to the evaluation result;
And testing the medication risk evaluation model by using the test sample set to evaluate the generalization performance of the medication risk evaluation model.
9. A terminal, comprising:
a memory for storing a patient medication risk assessment program;
A processor for implementing the steps of the patient medication risk assessment method according to any one of claims 1-4 when executing the patient medication risk assessment program.
10. A computer readable storage medium, wherein a patient medication risk assessment program is stored on the readable storage medium, which when executed by a processor, implements the steps of the patient medication risk assessment method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410237798.5A CN117995409A (en) | 2024-03-01 | 2024-03-01 | Patient medication risk evaluation method, system, terminal and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410237798.5A CN117995409A (en) | 2024-03-01 | 2024-03-01 | Patient medication risk evaluation method, system, terminal and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117995409A true CN117995409A (en) | 2024-05-07 |
Family
ID=90895126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410237798.5A Pending CN117995409A (en) | 2024-03-01 | 2024-03-01 | Patient medication risk evaluation method, system, terminal and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117995409A (en) |
-
2024
- 2024-03-01 CN CN202410237798.5A patent/CN117995409A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11410758B2 (en) | Medical scan artifact detection system | |
| JP6066826B2 (en) | Analysis system and health business support method | |
| Vanbrabant et al. | Quality of input data in emergency department simulations: Framework and assessment techniques | |
| US8744867B2 (en) | Method for selecting a clinical treatment plan tailored to patient defined health goals | |
| US20030149597A1 (en) | System for supporting clinical decision-making | |
| JP2008532104A (en) | A method, system, and computer program product for generating and applying a prediction model capable of predicting a plurality of medical-related outcomes, evaluating an intervention plan, and simultaneously performing biomarker causality verification | |
| CN111145844A (en) | Comprehensive medical supervision platform | |
| DE112014000897T5 (en) | Learning health systems and procedures | |
| CN112151170A (en) | Method for calculating a score of a medical advice for use as a medical decision support | |
| US11529105B2 (en) | Digital twin updating | |
| US20200395119A1 (en) | Medical scan labeling quality assurance system | |
| CN106793957A (en) | Medical system and method for predicting patient care future outcomes | |
| US20210151140A1 (en) | Event Data Modelling | |
| KR20200022106A (en) | Oriental medicine diagnostic prescription service system and method | |
| KR20200022113A (en) | Oriental medicine prescription and health coordinator service system and method | |
| WO2021189958A1 (en) | Method and apparatus for collecting chronic disease follow-up visit records, and device and storage medium | |
| KR101565331B1 (en) | Analyzing system for medical informations using patterns and the method thereof | |
| US20090119323A1 (en) | Method and system for reducing a data set | |
| CN114420279A (en) | Medical resource recommendation method, device, equipment and storage medium | |
| CN117995409A (en) | Patient medication risk evaluation method, system, terminal and medium | |
| WO2021216988A1 (en) | Predictive adaptive intelligent diagnostics and treatment | |
| CN114649071A (en) | Real world data-based peptic ulcer treatment scheme prediction system | |
| KR20220091653A (en) | Companion animal disease type and probability analysis system using artificial intelligence-based analysis engine | |
| Muslim et al. | Expert mapping development system with disease searching sympthom based on ICD 10 | |
| Bozhenko et al. | Application of Data Preprocessing in Medical Research |
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 |