CN114822753A - Prescription auditing method and device, electronic equipment and storage medium - Google Patents
Prescription auditing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114822753A CN114822753A CN202210487149.1A CN202210487149A CN114822753A CN 114822753 A CN114822753 A CN 114822753A CN 202210487149 A CN202210487149 A CN 202210487149A CN 114822753 A CN114822753 A CN 114822753A
- Authority
- CN
- China
- Prior art keywords
- prescription
- audit
- information
- auditing
- sample
- 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
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The disclosure relates to a prescription auditing method, a prescription auditing device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring text information of a prescription to be checked, wherein the text information comprises patient information and medicine information corresponding to the prescription to be checked; constructing sample characteristics of the prescription to be checked according to the text information; and processing the sample characteristics by using an audit model obtained by pre-training to obtain an audit result of the prescription to be audited, wherein the audit result is used for indicating whether the medicine information is matched with the patient information. Therefore, sample characteristics can be extracted from the prescription to be audited, and then the sample characteristics are analyzed based on the audit model obtained through pre-training to obtain the audit result, namely, different audit models can be flexibly trained according to different audit dimensions to audit the prescription to be audited, so that the audit of the prescription is more accurate and efficient, and the possibility of error of the audit result is reduced.
Description
Technical Field
The present disclosure relates to the field of data analysis, and in particular, to a prescription auditing method and apparatus, an electronic device, and a storage medium.
Background
In a medical service scenario, doctors diagnose the condition of patients, and then determine corresponding prescriptions according to fixed medication schemes of the diseases suffered by the patients to prescribe medicines to the patients, however, due to the lack of knowledge of medication safety of many doctors, the medicines in the prescriptions may not be suitable for the patients, such as prescribing adult doses to children.
In the prior art, a prescription auditing system can be used to audit a prescription issued by a doctor, wherein the prescription auditing system is usually based on the usage rule of a medicine, for example, the single dosage of an ibuprofen sustained-release capsule is set to be one capsule at a time, and if two capsules appear in the prescription once, an early warning is triggered, and the like.
However, since it is difficult to completely display information such as prohibition of use, combing of indications, and the like of any medicine in the usage rules of any medicine, the prescription auditing system has poor auditing effect in dimensions such as medicine prohibition, medicine caution, medicine indications, and the like, and there is still a possibility of errors in approved prescriptions, thereby affecting the treatment effect of patients.
Disclosure of Invention
The disclosure provides a prescription auditing method, a device, electronic equipment and a storage medium, which are used for at least solving the problems that in the related art, the prescription auditing system has poor auditing effect in dimensions of drug forbidding, drug contraindications, drug cautions, drug indications and the like, and errors still exist in approved prescriptions, so that the treatment effect of a patient is influenced. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a prescription auditing system method, including:
acquiring text information of a prescription to be audited, wherein the text information comprises patient information and medicine information corresponding to the prescription to be audited;
constructing sample characteristics of the prescription to be audited according to the text information;
and processing the sample characteristics by using an audit model obtained by pre-training to obtain an audit result of the prescription to be audited, wherein the audit result is used for indicating whether the medicine information is matched with the patient information.
Optionally, the sample features include a first sample feature and a second sample feature, and the constructing the sample features of the prescription to be reviewed according to the text information includes:
performing feature extraction on the text information to obtain text features of the prescription to be audited, wherein the text features comprise a first text feature and a second text feature, the first text feature is a text feature corresponding to the patient information, and the second text feature is a text feature corresponding to the medicine information;
combining any one second text characteristic with each first text characteristic to obtain a first sample characteristic of the prescription to be audited;
and combining any two second text characteristics to obtain a second sample characteristic of the prescription to be audited.
Optionally, the obtaining the audit result of the prescription to be audited includes:
respectively processing the sample characteristics by using the plurality of binary classification models to obtain a classification result corresponding to each binary classification model, wherein the classification result is used for indicating whether the prescription to be checked passes the corresponding checking dimension;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
Optionally, the audit dimensions include at least two serial audit dimensions, and the processing the sample features by using the two classification models respectively to obtain the classification result corresponding to each of the two classification models includes:
and sequentially processing the sample characteristics by using the two classification models corresponding to the serial audit dimensions until the classification result corresponding to the two classification models corresponding to any serial audit dimension is that the audit is not passed, and determining the classification results corresponding to the two classification models corresponding to other unprocessed serial audit dimensions as that the audit is not passed.
Optionally, the auditing model is a multi-classification model, and the processing of the sample features by using the auditing model obtained by pre-training to obtain the auditing result of the prescription to be audited includes:
processing the sample characteristics by using the multi-classification model to obtain classification results of the sample characteristics in different auditing dimensions;
and analyzing the classification result, and determining an auditing result of the prescription to be audited.
Optionally, after the sample features are processed by using the pre-trained audit model to obtain the audit result of the prescription to be audited, the method further includes:
and inquiring and displaying description information corresponding to the medicine information under the condition that the audit result is that the medicine information is not matched with the patient information.
Optionally, the querying and displaying description information corresponding to the medicine information includes:
identifying an approval document number in the drug information;
under the condition that the approval document number is identified, inquiring and displaying description information corresponding to the medicine information according to the approval document number;
and under the condition that the approval document number is not identified, identifying the universal name of the medicine in the medicine information, and inquiring and displaying the description information corresponding to the medicine information according to the universal name of the medicine.
Optionally, the audit model includes a plurality of audit dimensions respectively corresponding to different audit dimensions, and the querying and displaying the description information corresponding to the drug information includes:
determining that the audit result is a target audit model of which the medicine information is not matched with the patient information, and taking an audit dimension corresponding to the target audit model as a target audit dimension;
and inquiring and displaying the description information corresponding to the medicine information and the target audit dimension.
Optionally, before the processing the sample features by using the pre-trained audit model to obtain the audit result of the prescription to be audited, the method further includes:
obtaining pre-labeled sample information, wherein the pre-labeled sample information is obtained by labeling an audit result of the sample information in a preset audit dimension, and the preset audit dimension includes but is not limited to: forbidden, contraindicated, cautious and adapted to drugs;
and training a preset neural network model by using the pre-labeled sample information to obtain the auditing model.
According to a second aspect of an embodiment of the present disclosure, there is provided a prescription auditing apparatus including:
the system comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is configured to execute acquisition of text information of a prescription to be verified, and the text information comprises patient information and medicine information corresponding to the prescription to be verified;
the construction unit is configured to construct the sample characteristics of the prescription to be audited according to the text information;
and the auditing unit is configured to execute an auditing model obtained by pre-training, process the sample characteristics and obtain an auditing result of the prescription to be audited, wherein the auditing result is used for indicating whether the medicine information is matched with the patient information.
Optionally, the sample features include a first sample feature and a second sample feature, and the constructing unit is specifically configured to perform:
performing feature extraction on the text information to obtain text features of the prescription to be audited, wherein the text features comprise a first text feature and a second text feature, the first text feature is a text feature corresponding to the patient information, and the second text feature is a text feature corresponding to the medicine information;
combining any one second text characteristic with each first text characteristic to obtain a first sample characteristic of the prescription to be audited;
and combining any two second text characteristics to obtain a second sample characteristic of the prescription to be audited.
Optionally, the audit model includes a plurality of two-class models, each two-class core model corresponds to an audit dimension, and the audit unit is specifically configured to execute:
respectively processing the sample characteristics by using the plurality of binary classification models to obtain a classification result corresponding to each binary classification model, wherein the classification result is used for indicating whether the prescription to be checked passes the corresponding checking dimension;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
Optionally, the audit dimension includes at least two serial audit dimensions, and the audit unit is specifically configured to execute:
and sequentially processing the sample characteristics by using the two classification models corresponding to the serial audit dimensions until the classification result corresponding to the two classification models corresponding to any serial audit dimension is that the audit is not passed, and determining the classification results corresponding to the two classification models corresponding to other unprocessed serial audit dimensions as that the audit is not passed.
Optionally, the audit model is a multi-classification model, and the audit unit is configured to perform:
processing the sample characteristics by using the multi-classification model to obtain classification results of the sample characteristics in different auditing dimensions;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
Optionally, the apparatus further comprises:
and the display unit is configured to query and display description information corresponding to the medicine information under the condition that the audit result is that the medicine information is not matched with the patient information.
Optionally, the presentation unit is configured to perform:
identifying an approval document number in the drug information;
under the condition that the approval document number is identified, inquiring and displaying description information corresponding to the medicine information according to the approval document number;
and under the condition that the approval document number is not identified, identifying the universal name of the medicine in the medicine information, and inquiring and displaying the description information corresponding to the medicine information according to the universal name of the medicine.
Optionally, the audit model includes a plurality of audit dimensions, and the audit models respectively correspond to different audit dimensions, and the presentation unit is configured to perform:
determining that the audit result is a target audit model of which the medicine information is not matched with the patient information, and taking an audit dimension corresponding to the target audit model as a target audit dimension;
and inquiring and displaying the description information corresponding to the medicine information and the target audit dimension.
Optionally, the apparatus further comprises:
a training unit configured to perform obtaining of pre-labeled sample information, where the pre-labeled sample information is obtained by labeling an audit result of sample information in a preset audit dimension, where the preset audit dimension includes but is not limited to: the drugs are forbidden, prohibited, cautious and indicated; and training a preset neural network model by using the pre-labeled sample information to obtain the auditing model.
According to a third aspect of embodiments of the present disclosure, there is provided a prescription auditing electronic device, including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the prescription auditing method of the first item.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium having instructions which, when executed by a processor of a prescription auditing electronic device, enable the prescription auditing electronic device to perform the prescription auditing method of the first item described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer programs/instructions which, when executed by a processor, implement the prescription auditing method of the first item described above.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
acquiring text information of a prescription to be checked, wherein the text information comprises patient information and medicine information corresponding to the prescription to be checked; constructing sample characteristics of the prescription to be checked according to the text information; and processing the sample characteristics by using an audit model obtained by pre-training to obtain an audit result of the prescription to be audited, wherein the audit result is used for indicating whether the medicine information is matched with the patient information.
Therefore, sample characteristics can be extracted from the prescription to be audited, and then the sample characteristics are analyzed based on the audit model obtained through pre-training to obtain the audit result, namely, different audit models can be flexibly trained according to different audit dimensions to audit the prescription to be audited, so that the audit of the prescription is more accurate and efficient, and the possibility of error of the audit result is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a flow diagram illustrating a recipe review method according to an exemplary embodiment.
FIG. 2 is a block diagram illustrating a prescription auditing apparatus according to an exemplary embodiment.
FIG. 3 is a block diagram illustrating an electronic device for prescription auditing according to an exemplary embodiment.
FIG. 4 is a block diagram illustrating an apparatus for prescription auditing according to an exemplary embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
FIG. 1 is a flow chart illustrating a recipe auditing method, according to an exemplary embodiment, for application to an electronic device, as shown in FIG. 1, the recipe auditing method including the following steps.
In step S11, text information of the prescription to be reviewed is obtained, where the text information includes patient information and medicine information corresponding to the prescription to be reviewed.
In the medical service scene, a doctor diagnoses the state of illness of a patient, and then determines a corresponding prescription according to a fixed medication scheme of the patient suffering from the illness and dispenses the medicine for the patient. The prescription usually includes patient information such as age, sex, diagnosis, department, etc. of the patient, and medicine information such as medicines and corresponding usage amounts.
The prescription to be audited given by the doctor may have errors, for example, the dose for adults is prescribed for children, or the ibuprofen sustained-release capsule is forbidden for patients with gastrointestinal bleeding, so the prescription to be audited needs to be audited, and the cure rate of the patients is improved.
In step S12, a sample feature of the prescription to be reviewed is constructed based on the text information.
In this step, the patient information and the drug information are text information, which can be converted into numerical features, i.e., text features, and then sample features are constructed according to the text features. The word bag model can be constructed by using onehot characteristics of word granularity or word granularity, or word embedding characteristics can be used by using the word granularity or the word granularity, and the method is not limited specifically. For example, enumerated types such as administration mode, drug unit, medication time, etc., use onehot characteristics; the numerical type of the single dosage, the frequency of medication and the like of the medicine is not converted and the numerical characteristics of the medicine are still used.
In one implementation, the sample feature includes a first sample feature and a second sample feature, and the constructing the sample feature of the prescription to be reviewed according to the text information includes:
performing feature extraction on the text information to obtain text features of the prescription to be checked, wherein the text features comprise first text features and second text features, the first text features are text features corresponding to the patient information, and the second text features are text features corresponding to the medicine information; combining any one second text characteristic with each first text characteristic to obtain a first sample characteristic of the prescription to be audited; and combining any two second text characteristics to obtain a second sample characteristic of the prescription to be audited.
The first sample feature and the second sample feature may respectively correspond to different audit dimensions, and the audit dimensions corresponding to the first sample feature may include, but are not limited to: gender, age, gestational period, lactation period, menstrual period, pregnancy preparation period, drug allergy, drug contraindication, drug cautions, diagnosis inconsistency, single dose, single daily dose, administration mode, administration frequency, total amount prescribed, dosage unit, administration time, etc. These auditor dimensions audit the issues of drugs used to audit patients.
That is, for a prescription, there may be a plurality of drugs, each of which is associated with patient information to form a training sample, the first text feature may include the age of the patient, the sex of the patient, the diagnosis of the patient, and the department, and the second text feature may include the name of the drug, the size of the drug, the administration mode, the single dose of the drug, the frequency of administration, the time of administration, the total amount of medication, and so on.
The corresponding audit dimension of the second sample feature may include, but is not limited to: drug interactions, drug class interactions, drug component interactions, vehicle dosage, incompatibility, repeated common names, drug classes, repeated components, and the like. These audit dimensions are used to audit issues with drug combinations.
That is, for a prescription, the medicines constitute a training sample between each two medicines. The second textual characteristic may include a drug name, a drug specification, a mode of administration, a bolus dose of the drug, a frequency of administration, a total amount prescribed and a drug name of another drug, a drug specification, a mode of administration, a bolus dose of the drug, a frequency of administration, a total amount prescribed, and so forth.
In step S13, the sample features are processed by using the pre-trained audit model to obtain an audit result of the prescription to be audited, where the audit result is used to indicate whether the drug information matches the patient information.
In one implementation, the auditing model includes a plurality of two-class models, each two-class kernel model corresponds to an auditing dimension, and the auditing model obtained by pre-training is used to process the sample characteristics to obtain the auditing result of the prescription to be audited, including:
respectively processing the sample characteristics by utilizing a plurality of two classification models to obtain a classification result corresponding to each two classification model, wherein the classification result is used for indicating whether the prescription to be checked passes through the corresponding checking dimension; and analyzing the classification result to determine an auditing result of the prescription to be audited.
By way of example, the audit dimension may include, but is not limited to: gender, age, gestational period, lactation period, menstrual period, pregnancy preparation period, drug allergy, drug forbidding, drug contraindication, drug cautionary use, diagnosis inconsistency, single dose, single daily dose, administration mode, administration frequency, total drug prescription amount, dosage unit, administration time, drug interaction, drug category interaction, drug component interaction, solvent dose, compatibility contraindication, repeated common name, same type of drug and repeated component.
And respectively training a two-classification model for each audit dimension, if the output result of the two-classification model is 1, indicating that the audit of the dimension passes, and if the output result of the two-classification model is 0, indicating that the audit of the dimension does not pass. The binary model may be an xgboost model or a neural network model, and when the xgboost model is used, the tree depth is set to be more than 8 layers.
The method comprises the following steps that the auditing dimensionality comprises at least two serial auditing dimensionalities, the sample characteristics are respectively processed by utilizing a plurality of two classification models, and classification results corresponding to the two classification models are obtained, and the method comprises the following steps:
and sequentially processing the sample characteristics by using the two classification models corresponding to the serial auditing dimensions until the classification result corresponding to the two classification models corresponding to any serial auditing dimension is not approved, and determining the classification results corresponding to the two classification models corresponding to other unprocessed serial auditing dimensions as not approved.
The serial auditing dimensions have certain relevance, so that after any serial auditing dimension passes auditing, the next dimension does not need to be audited, and the auditing efficiency can be improved. For example, after the single-dose and frequency of administration are approved, the single daily dose is definitely approved and is not approved.
In another implementation manner, the auditing model is a multi-classification model, and the method for processing the sample characteristics by using the auditing model obtained by pre-training to obtain the auditing result of the prescription to be audited includes: processing the sample characteristics by using a multi-classification model to obtain classification results of the sample characteristics in different auditing dimensions; and analyzing the classification result, and determining an auditing result of the prescription to be audited.
In the method and the device, after the characteristics of the sample are processed by using the pre-trained auditing model to obtain the auditing result of the prescription to be audited, and the description information corresponding to the medicine information is inquired and displayed under the condition that the auditing result is that the medicine information is not matched with the patient information.
The description information is a semi-structured drug description using an approval character number as a main key and a semi-structured drug description using a common name as a main key, and if a plurality of drug descriptions exist under one common name, the drug description with the latest date is selected as the drug description of the common name.
Specifically, inquiring and displaying the description information corresponding to the medicine information includes:
identifying an approval document number in the drug information; under the condition that the approved document number is identified, inquiring and displaying the description information corresponding to the medicine information according to the approved document number; and under the condition that the approval document number is not identified, identifying the universal name of the medicine in the medicine information, and inquiring and displaying the description information corresponding to the medicine information according to the universal name of the medicine.
That is, the medicine specification is searched according to the approved document number in the prescription, if the prescription has no approved document number, the medicine specification is searched by using the common name of the medicine, and then the corresponding paragraph in the specification is found according to the dimension of the examined prescription.
In addition, under the condition that the audit model comprises a plurality of audit dimensions which respectively correspond to different audit dimensions, the description information corresponding to the medicine information is inquired and displayed, and the audit model comprises the following steps:
determining a target audit model with an audit result that the medicine information is not matched with the patient information, and taking an audit dimension corresponding to the target audit model as a target audit dimension; and inquiring and displaying the description information corresponding to the medicine information and the target audit dimension.
For example, sex, age, gestational period, lactation period, menstruation period, pregnancy preparation period, and drug use with caution, and these several questions are returned to the original text of the instructions. The dimensions of the prescription of drug allergy, drug forbidding and drug contraindication return the original text of the instruction for forbidding the use with cautions. The diagnosis does not conform to the original text of the indications returned. The dosage of single administration, the dosage of single daily administration, the administration mode, the administration frequency, the total amount of the prescribed drugs, the dosage unit and the administration time are returned to the original text of the usage and dosage of the instruction book. Drug interactions, drug class interactions, drug component interactions, vehicle dose, incompatibility, return to the manual drug interactions or pharmacokinetic original.
In the application, before processing the sample characteristics by using the pre-trained auditing model to obtain the auditing result of the prescription to be audited, the method further comprises:
obtaining pre-labeled sample information, wherein the pre-labeled sample information is obtained by labeling the auditing result of the sample information in a preset auditing dimension, and the preset auditing dimension includes but is not limited to: forbidden, contraindicated, cautious and adapted to drugs; and training the preset neural network model by using the pre-labeled sample information to obtain an audit model.
The pre-marked sample information is manually checked, if the check is passed, the pre-marked sample information is marked with 0, otherwise, the number corresponding to the problem of the prescription is marked, and the number is label. For example, the audit dimension may be numbered from 1 to 27, each number being a label of the model. A qualified prescription label of 0.
In the preset neural network model, the number of neurons in the first layer and the number of features can be preset to be the same, the number of data of neurons in the second layer is 300, and the number of neurons in the third layer is two, namely the result of the second classification. With the iteration parameter set to 50.
As can be seen from the above, according to the technical scheme provided by the embodiment of the disclosure, the sample characteristics can be extracted from the prescription to be audited, and then the sample characteristics are analyzed based on the audit model obtained by pre-training to obtain the audit result, that is, different audit models can be flexibly trained for different audit dimensions to audit the prescription to be audited, so that the audit of the prescription is more accurate and efficient, and the possibility of error of the audit result is reduced.
Fig. 2 is a block diagram of a prescription auditing apparatus according to an exemplary embodiment, applied to an electronic device, the apparatus including:
the acquiring unit 201 is configured to perform acquiring text information of a prescription to be audited, wherein the text information includes patient information and medicine information corresponding to the prescription to be audited;
a constructing unit 202 configured to execute constructing a sample feature of the prescription to be audited according to the text information;
the auditing unit 203 is configured to execute an auditing model obtained by pre-training to process the sample features to obtain an auditing result of the prescription to be audited, where the auditing result is used to indicate whether the medicine information matches with the patient information.
In one implementation, the sample features include a first sample feature and a second sample feature, and the constructing unit is specifically configured to perform:
performing feature extraction on the text information to obtain text features of the prescription to be audited, wherein the text features comprise a first text feature and a second text feature, the first text feature is a text feature corresponding to the patient information, and the second text feature is a text feature corresponding to the medicine information;
combining any one second text characteristic with each first text characteristic to obtain a first sample characteristic of the prescription to be audited;
and combining any two second text characteristics to obtain a second sample characteristic of the prescription to be audited.
In one implementation, the audit model includes a plurality of two-class models, each two-class core model corresponds to an audit dimension, and the audit unit is specifically configured to perform:
respectively processing the sample characteristics by using the plurality of binary classification models to obtain a classification result corresponding to each binary classification model, wherein the classification result is used for indicating whether the prescription to be checked passes the corresponding checking dimension;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
In one implementation, the audit dimensions include at least two serial audit dimensions, and the audit unit is specifically configured to perform:
and sequentially processing the sample characteristics by using the two classification models corresponding to the serial audit dimensions until the classification result corresponding to the two classification models corresponding to any serial audit dimension is that the audit is not passed, and determining the classification results corresponding to the two classification models corresponding to other unprocessed serial audit dimensions as that the audit is not passed.
In one implementation, the auditing model is a multi-classification model, and the auditing unit is configured to perform:
processing the sample characteristics by using the multi-classification model to obtain classification results of the sample characteristics in different auditing dimensions;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
In one implementation, the apparatus further includes:
and the display unit is configured to query and display description information corresponding to the medicine information under the condition that the audit result is that the medicine information is not matched with the patient information.
In one implementation, the presentation unit is configured to perform:
identifying an approval document number in the drug information;
under the condition that the approval document number is identified, inquiring and displaying description information corresponding to the medicine information according to the approval document number;
and under the condition that the approval document number is not identified, identifying the universal name of the medicine in the medicine information, and inquiring and displaying the description information corresponding to the medicine information according to the universal name of the medicine.
In one implementation manner, the audit model includes a plurality of audit dimensions, and the audit models respectively correspond to different audit dimensions, and the display unit is configured to perform:
determining that the audit result is a target audit model of which the medicine information is not matched with the patient information, and taking an audit dimension corresponding to the target audit model as a target audit dimension;
and inquiring and displaying the description information corresponding to the medicine information and the target audit dimension.
In one implementation, the apparatus further includes:
a training unit configured to perform obtaining of pre-labeled sample information, where the pre-labeled sample information is obtained by labeling an audit result of sample information in a preset audit dimension, where the preset audit dimension includes but is not limited to: the drugs are forbidden, prohibited, cautious and indicated; and training a preset neural network model by using the pre-labeled sample information to obtain the auditing model.
As can be seen from the above, according to the technical scheme provided by the embodiment of the disclosure, the sample characteristics can be extracted from the prescription to be audited, and then the sample characteristics are analyzed based on the audit model obtained by pre-training to obtain the audit result, that is, different audit models can be flexibly trained for different audit dimensions to audit the prescription to be audited, so that the audit of the prescription is more accurate and efficient, and the possibility of error of the audit result is reduced.
FIG. 3 is a block diagram illustrating an electronic device for prescription auditing according to an exemplary embodiment.
In an exemplary embodiment, a computer-readable storage medium comprising instructions, such as a memory comprising instructions, executable by a processor of an electronic device to perform the above-described method is also provided. Alternatively, the computer-readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical prescription auditing apparatus, and the like.
In an exemplary embodiment, a computer program product is also provided, which, when run on a computer, causes the computer to carry out the above-described method of prescription review.
As can be seen from the above, according to the technical scheme provided by the embodiment of the disclosure, the sample characteristics can be extracted from the prescription to be audited, and then the sample characteristics are analyzed based on the audit model obtained by pre-training to obtain the audit result, that is, different audit models can be flexibly trained for different audit dimensions to audit the prescription to be audited, so that the audit of the prescription is more accurate and efficient, and the possibility of error of the audit result is reduced.
FIG. 4 is a block diagram illustrating an apparatus 800 for prescription auditing according to an exemplary embodiment.
For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast electronic device, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 4, the apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices, 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 or optical disks.
A power supply component 807 provides power to the various components of the device 800. The power components 807 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the apparatus 800.
The multimedia component 808 includes a screen that provides an output interface between the device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed state of the device 800, the relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or a component of the apparatus 800, the presence or absence of user contact with the apparatus 800, orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communications between the apparatus 800 and other devices in a wired or wireless manner. The apparatus 800 may access a wireless network based on a communication standard, such as WiFi, an operator network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the methods of the first and second aspects.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the device 800 to perform the above-described method is also provided. Alternatively, for example, the storage medium may be a non-transitory computer-readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical prescription auditing device, and the like.
In an exemplary embodiment, there is also provided a computer program product containing instructions which, when run on a computer, cause the computer to perform the prescription auditing method described in the first of the above embodiments.
As can be seen from the above, according to the technical scheme provided by the embodiment of the disclosure, the sample characteristics can be extracted from the prescription to be audited, and then the sample characteristics are analyzed based on the audit model obtained by pre-training to obtain the audit result, that is, different audit models can be flexibly trained for different audit dimensions to audit the prescription to be audited, so that the audit of the prescription is more accurate and efficient, and the possibility of error of the audit result is reduced.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (21)
1. A prescription auditing method, comprising:
acquiring text information of a prescription to be audited, wherein the text information comprises patient information and medicine information corresponding to the prescription to be audited;
constructing sample characteristics of the prescription to be audited according to the text information;
and processing the sample characteristics by using an audit model obtained by pre-training to obtain an audit result of the prescription to be audited, wherein the audit result is used for indicating whether the medicine information is matched with the patient information.
2. The prescription auditing method of claim 1, where the sample features include a first sample feature and a second sample feature, where constructing the sample features of the prescription to be audited from the textual information includes:
performing feature extraction on the text information to obtain text features of the prescription to be audited, wherein the text features comprise a first text feature and a second text feature, the first text feature is a text feature corresponding to the patient information, and the second text feature is a text feature corresponding to the medicine information;
combining any one second text characteristic with each first text characteristic to obtain a first sample characteristic of the prescription to be audited;
and combining any two second text characteristics to obtain a second sample characteristic of the prescription to be audited.
3. The prescription auditing method of claim 1, wherein the audit model comprises a plurality of two-class models, each two-class kernel model corresponds to an audit dimension, and the processing of the sample features using the audit model obtained by pre-training to obtain the audit result of the prescription to be audited comprises:
respectively processing the sample characteristics by using the plurality of binary classification models to obtain a classification result corresponding to each binary classification model, wherein the classification result is used for indicating whether the prescription to be checked passes the corresponding checking dimension;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
4. The prescription auditing method of claim 3, wherein the auditing dimensions include at least two serial auditing dimensions, and the obtaining the classification result corresponding to each of the two classification models by processing the sample features using the two classification models comprises:
and sequentially processing the sample characteristics by using the two classification models corresponding to the serial audit dimensions until the classification result corresponding to the two classification models corresponding to any serial audit dimension is that the audit is not passed, and determining the classification results corresponding to the two classification models corresponding to other unprocessed serial audit dimensions as that the audit is not passed.
5. The prescription auditing method of claim 1, where the auditing model is a multi-classification model, and where the processing of the sample features to obtain the audit result of the prescription to be audited using an auditing model obtained by pre-training comprises:
processing the sample characteristics by using the multi-classification model to obtain classification results of the sample characteristics in different auditing dimensions;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
6. The prescription auditing method of claim 1, after the sample features are processed using the pre-trained audit model to obtain the audit result of the prescription to be audited, the method further comprising:
and inquiring and displaying description information corresponding to the medicine information under the condition that the audit result is that the medicine information is not matched with the patient information.
7. The prescription auditing method of claim 6, wherein said querying and presenting descriptive information corresponding to the drug information comprises:
identifying an approval document number in the drug information;
under the condition that the approval document number is identified, inquiring and displaying description information corresponding to the medicine information according to the approval document number;
and under the condition that the approval document number is not identified, identifying the universal name of the medicine in the medicine information, and inquiring and displaying the description information corresponding to the medicine information according to the universal name of the medicine.
8. The prescription auditing method of claim 6, wherein the auditing model includes a plurality of auditing dimensions that respectively correspond to different auditing dimensions, and the querying and presenting descriptive information corresponding to the drug information includes:
determining that the audit result is a target audit model of which the medicine information is not matched with the patient information, and taking an audit dimension corresponding to the target audit model as a target audit dimension;
and inquiring and displaying the description information corresponding to the medicine information and the target audit dimension.
9. The prescription auditing method of claim 1, before processing the sample features using the pre-trained audit model to obtain an audit result of the prescription to be audited, the method further comprising:
obtaining pre-labeled sample information, wherein the pre-labeled sample information is obtained by labeling an audit result of the sample information in a preset audit dimension, and the preset audit dimension includes but is not limited to: forbidden, contraindicated, cautious and adapted to drugs;
and training a preset neural network model by using the pre-labeled sample information to obtain the auditing model.
10. A prescription audit device, comprising:
the system comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is configured to execute acquisition of text information of a prescription to be verified, and the text information comprises patient information and medicine information corresponding to the prescription to be verified;
the construction unit is configured to construct the sample characteristics of the prescription to be audited according to the text information;
and the auditing unit is configured to execute an auditing model obtained by pre-training, process the sample characteristics and obtain an auditing result of the prescription to be audited, wherein the auditing result is used for indicating whether the medicine information is matched with the patient information.
11. Prescription auditing device according to claim 10, characterized in that the sample characteristics include a first sample characteristic and a second sample characteristic, the construction unit being specifically configured to perform:
performing feature extraction on the text information to obtain text features of the prescription to be audited, wherein the text features comprise a first text feature and a second text feature, the first text feature is a text feature corresponding to the patient information, and the second text feature is a text feature corresponding to the medicine information;
combining any one second text characteristic with each first text characteristic to obtain a first sample characteristic of the prescription to be audited;
and combining any two second text characteristics to obtain a second sample characteristic of the prescription to be audited.
12. The prescription auditing device of claim 10, where the auditing model comprises a plurality of two-class models, each two-class model corresponding to an auditing dimension, and where the auditing unit is specifically configured to perform:
respectively processing the sample characteristics by utilizing the plurality of two classification models to obtain a classification result corresponding to each two classification models, wherein the classification result is used for indicating whether the prescription to be audited passes through a corresponding audit dimensionality;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
13. Prescription auditing apparatus according to claim 12, characterized in that the audit dimensions include at least two serial audit dimensions, the auditing unit being specifically configured to perform:
and sequentially processing the sample characteristics by using the two classification models corresponding to the serial audit dimensions until the classification result corresponding to the two classification models corresponding to any serial audit dimension is that the audit is not passed, and determining the classification results corresponding to the two classification models corresponding to other unprocessed serial audit dimensions as that the audit is not passed.
14. The prescription auditing device of claim 10, wherein the auditing model is a multi-classification model, and the auditing unit is configured to perform:
processing the sample characteristics by using the multi-classification model to obtain classification results of the sample characteristics in different auditing dimensions;
and analyzing the classification result to determine an auditing result of the prescription to be audited.
15. A prescription auditing device according to claim 10, the device further comprising:
and the display unit is configured to query and display description information corresponding to the medicine information under the condition that the audit result is that the medicine information is not matched with the patient information.
16. The prescription auditing apparatus of claim 15, where the presentation unit is configured to perform:
identifying an approval document number in the drug information;
under the condition that the approval document number is identified, inquiring and displaying description information corresponding to the medicine information according to the approval document number;
and under the condition that the approval document number is not identified, identifying the universal name of the medicine in the medicine information, and inquiring and displaying the description information corresponding to the medicine information according to the universal name of the medicine.
17. Prescription auditing apparatus according to claim 15, characterized in that the audit model comprises a plurality of and respectively corresponding to different audit dimensions, the presentation unit being configured to perform:
determining that the audit result is a target audit model of which the medicine information is not matched with the patient information, and taking an audit dimension corresponding to the target audit model as a target audit dimension;
and inquiring and displaying the description information corresponding to the medicine information and the target audit dimension.
18. A prescription auditing device according to claim 10, the device further comprising:
a training unit configured to perform obtaining of pre-labeled sample information, where the pre-labeled sample information is obtained by labeling an audit result of sample information in a preset audit dimension, where the preset audit dimension includes but is not limited to: forbidden, contraindicated, cautious and adapted to drugs; and training a preset neural network model by using the pre-labeled sample information to obtain the auditing model.
19. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement a prescription review method as claimed in any one of claims 1 to 9.
20. A computer-readable storage medium, wherein instructions in the computer-readable storage medium, when executed by a processor of a prescription review electronic device, enable the prescription review electronic device to perform the prescription review method of any of claims 1-9.
21. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements a prescription auditing method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210487149.1A CN114822753A (en) | 2022-05-06 | 2022-05-06 | Prescription auditing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210487149.1A CN114822753A (en) | 2022-05-06 | 2022-05-06 | Prescription auditing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114822753A true CN114822753A (en) | 2022-07-29 |
Family
ID=82510576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210487149.1A Pending CN114822753A (en) | 2022-05-06 | 2022-05-06 | Prescription auditing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114822753A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117558400A (en) * | 2024-01-12 | 2024-02-13 | 天津医科大学总医院 | Prescription auditing method and system based on feedback information |
-
2022
- 2022-05-06 CN CN202210487149.1A patent/CN114822753A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117558400A (en) * | 2024-01-12 | 2024-02-13 | 天津医科大学总医院 | Prescription auditing method and system based on feedback information |
| CN117558400B (en) * | 2024-01-12 | 2024-03-15 | 天津医科大学总医院 | Prescription auditing method and system based on feedback information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170052947A1 (en) | Methods and devices for training a classifier and recognizing a type of information | |
| CN110910976A (en) | Medical record detection method, device, equipment and storage medium | |
| US11170484B2 (en) | Recognition of suspicious activities in medication administration | |
| CN111599488A (en) | Intelligent inquiry implementing method, system and storage medium | |
| CN108257676B (en) | Medical case information processing method, device and equipment | |
| US9883831B1 (en) | Digital medical evaluation and testing on a touch screen device | |
| CN110444288A (en) | Auxiliary diagnostic equipment, method and readable storage medium storing program for executing based on complex network | |
| US20150120313A1 (en) | Apparatus and method for collecting adverse drug event data over network | |
| CN109522705B (en) | Authority management method, device, electronic equipment and medium | |
| CN110598695A (en) | Medicine identification method and device for medicine identification | |
| CN114822753A (en) | Prescription auditing method and device, electronic equipment and storage medium | |
| CN113849723A (en) | Search method and search device | |
| CN109243617B (en) | Method and device for auditing prescription of antibacterial drug, storage medium and electronic equipment | |
| CN112000775A (en) | Data processing method and device based on triage | |
| CN115512829A (en) | Method, device and medium for acquiring disease diagnosis related group | |
| CN109636642A (en) | Recognition methods, device, equipment and the readable storage medium storing program for executing of Misuse adjuvant | |
| CN111527515A (en) | Computer system, medication recommendation method, and program | |
| CN110619936B (en) | Prescription treatment method and device for prescription treatment | |
| CN111840081B (en) | Medication reminding method and system and computer equipment | |
| US20200211715A1 (en) | Method for recruiting patients, and patient recruitment system | |
| KR101632054B1 (en) | System and method for providing inquiry service of the medical supplies information using a mobile terminal | |
| KR20210094827A (en) | The apparatus and method of recognizing a drug | |
| CN112992302A (en) | Data processing method, device, equipment and storage medium | |
| CN115376647A (en) | Medicine usage amount recommendation method and device, electronic equipment and storage medium | |
| GB2544338A (en) | Electonic method and system for data provision |
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 |