Individualized medication method, device, computing device, and storage medium

Abstract

The application provides an individualized medication method, device, computing equipment and storage medium, wherein the method comprises: collecting personal information of a patient and collecting gene detection data of the patient; prioritizing gene sites contained in the gene detection data, and generating primary medication information based on a prioritization result and a pre-constructed gene-drug guideline database; constructing a blood drug concentration-time curve based on the personal information and the primary medication information; obtaining precise medication information based on the blood drug concentration-time curve and the primary medication information; collecting actual medication information of the patient, adjusting the precise medication information based on the actual medication information, and obtaining target medication information. The application realizes a precision medicine mode of customizing an exclusive medication scheme for a patient based on individual characteristics of the patient, combining a drug-gene correlation rule and a clinical guideline, and achieving one person, one drug and one dose, so that the efficacy is improved and the risk of adverse reactions is reduced.

Description

Technical Field

[0001] This application relates to the field of medical information engineering technology, and in particular to a personalized medication method, device, computing equipment, and storage medium. Background Technology

[0002] Drug therapy is a crucial means of treating clinical diseases. However, traditional medication regimens are often based on population averages and do not fully consider individual patient differences, such as gene polymorphisms and physiological characteristics. This leads to problems such as poor efficacy and high incidence of adverse reactions in some patients. With the development of precision medicine and the deepening of gene testing technology and drug-gene association research, personalized medicine based on gene information has become a key direction for improving treatment outcomes and reducing medication risks.

[0003] Currently, some technologies have attempted to combine genetic information to develop medication plans. By acquiring patient disease information and genetic testing results, a medication review plan is generated after two interpretations. However, existing technologies still have many shortcomings. First, the sources of drug-gene guidelines are scattered. For authoritative international databases such as PharmGKB, CPIC, and FDA, there is a lack of systematic data quality control processes and algorithms for handling conflicts between multiple guidelines. Second, the medication plan development does not fully consider the synergistic effects of multiple genes / locus sites, and only uses simple linear weighted merging of results, lacking quantitative comprehensive decision-making algorithms, resulting in insufficient scientific rigor in the comprehensive recommendations. Third, the dosage plan is based on fixed-weight calculations and does not incorporate blood drug concentration simulation models and quantitative algorithms, resulting in low accuracy. Fourth, there is a lack of personalized reminder functions that are deeply integrated with the medication plan, making it difficult to ensure patient medication adherence. Summary of the Invention

[0004] In view of this, embodiments of this application provide a personalized medication method to address the technical deficiencies in the prior art. Embodiments of this application also provide a personalized medication device, a computing device, and a computer-readable storage medium.

[0005] According to a first aspect of the embodiments of this application, a personalized medication method is provided, comprising: Collect the patient's personal information and collect the patient's genetic testing data; The gene loci contained in the gene detection data are prioritized and sorted, and primary medication information is generated based on the priority sorting results and a pre-constructed gene drug guide database. Based on the personal information and the primary medication information, a blood drug concentration-time curve is constructed. Based on the blood drug concentration-time curve and the primary medication information, precise medication information is obtained; Collect the patient's actual medication information, and adjust the precision medication information based on the actual medication information to obtain the target medication information.

[0006] Optionally, the collection of the patient's genetic testing data includes: Collect initial gene testing data from the patient; Based on the detection method of the initial gene detection data, extract the corresponding gene loci and genotype information from the initial gene detection data; The gene loci and genotype data are preprocessed to obtain the gene detection data.

[0007] Optionally, the process of constructing the gene drug guide database includes: Obtain data from international databases; The international database data is subjected to integrity checks, error value checks, invalid value checks, duplicate value checks, consistency checks, and a final review in sequence to obtain standard data; The standard data is extracted and constructed according to a preset storage logic to form the gene drug guide database.

[0008] Optionally, prioritizing the gene loci included in the gene detection data includes: Determine the detection method associated with the gene detection data; If the detection method is single-gene detection, the gene loci contained in the gene detection data shall be used as the target gene loci. If the detection method is multi-gene detection, the gene loci contained in the gene detection data are queried, and the corresponding data source in the gene drug guideline database is obtained; based on the data source, a first weight is assigned; the gene loci contained in the gene detection data are queried, and the corresponding clinical recommendation data in the gene drug guideline database is obtained; based on the clinical recommendation data, a second weight is assigned; based on the first weight and the second weight, the priority score corresponding to the gene locus is determined, and based on all the priority scores, all the gene loci are prioritized.

[0009] Optionally, the generation of primary medication information based on the priority ranking results and a pre-built gene drug guide database includes: If the detection method is the single gene detection, the gene drug guide database is queried using the target gene locus, and the primary medication information is generated based on the query results. If the detection method is multi-gene detection, the highest score among the priority scores corresponding to the gene loci is compared with a first threshold. If the highest score is greater than or equal to the first threshold, the gene locus corresponding to the highest score is locked as the target gene locus, and the gene drug guide database is queried using the target gene locus. The primary medication information is generated based on the query results. If the highest score is less than the first threshold, all gene loci with priority scores greater than a second threshold are selected to form a high-risk gene set. If the high-risk gene set is not empty, the gene drug guide database is queried based on the gene loci contained in the high-risk gene set, and the primary medication information is determined based on the query results. If the high-risk gene set is empty, a ranking weight is configured for each priority score based on the priority scores corresponding to all gene loci. A comprehensive recommendation score is calculated based on the priority scores and the ranking weights. Based on the comprehensive recommendation score, corresponding clinical recommendation information is selected from the query results corresponding to the gene drug guide database as the primary medication information.

[0010] Optionally, constructing a blood drug concentration-time curve based on the personal information and the primary medication information includes: Based on the personal information and the primary medication information, the blood drug concentration-time curve is constructed using a population pharmacokinetic model.

[0011] Optionally, obtaining precise medication information based on the blood drug concentration-time curve and the primary medication information includes: Using the therapeutic window blood drug concentration contained in the primary medication information as the target, actual medication information is derived based on the blood drug concentration curve. Based on the patient's blood drug concentration monitoring data within a preset time period, the primary medication information is corrected using a Bayesian feedback algorithm, and unreasonable dosage recommendations are eliminated based on a preset safe dosage range to obtain the precise medication information.

[0012] According to a second aspect of the embodiments of this application, a personalized medication device is provided, comprising: The data acquisition module is configured to collect the patient's personal information and the patient's genetic testing data. The primary medication generation module is configured to prioritize the gene loci contained in the gene detection data and generate primary medication information based on the priority ranking results and a pre-built gene drug guide database. The module is configured to construct a blood drug concentration-time curve based on the personal information and the primary medication information; The precision medication generation module is configured to obtain precision medication information based on the blood drug concentration-time curve and the primary medication information; The target medication generation module is configured to collect the patient's actual medication information, and adjust the precision medication information based on the actual medication information to obtain the target medication information.

[0013] According to a third aspect of the embodiments of this application, a computing device is provided, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor executes the computer-executable instructions to implement the steps of the personalized medication method.

[0014] According to a fourth aspect of the embodiments of this application, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the personalized medication method.

[0015] According to a fifth aspect of the present application, a chip is provided that stores a computer program, which, when executed by the chip, implements the steps of the personalized medication method.

[0016] The personalized medication method provided in this application involves collecting the patient's personal information and genetic testing data; prioritizing the gene loci contained in the genetic testing data; generating primary medication information based on the priority ranking results and a pre-constructed gene drug guideline database; constructing a blood drug concentration-time curve based on the personal information and the primary medication information; obtaining precise medication information based on the blood drug concentration-time curve and the primary medication information; collecting the patient's actual medication information; and adjusting the precise medication information based on the actual medication information to obtain target medication information. This method integrates standardized sample information collection, unified guideline processing, scientific protocol formulation, precise dose simulation, and personalized reminders for individualized medication guidance. It achieves a precision medicine model that customizes exclusive medication plans for patients based on individual patient characteristics, combined with drug-gene correlation patterns and clinical guidelines, realizing one person, one drug, one dosage, improving efficacy, and reducing the risk of adverse reactions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1This is a flowchart of a personalized medication method provided in one embodiment of this application; Figure 2 This is a system architecture diagram of a personalized medication method provided in one embodiment of this application; Figure 3 This is a schematic diagram of the structure of a personalized medication device provided in one embodiment of this application; Figure 4 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation

[0019] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0020] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a,” “the,” and “the” used in one or more embodiments of this application and in the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0021] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first.

[0022] This application provides a method for personalized medication. This application also relates to a personalized medication device, a computing device, and a computer-readable storage medium, which will be described in detail in the following embodiments.

[0023] Figure 1 A flowchart of a personalized medication method according to an embodiment of this application is shown, which specifically includes the following steps: Step S102: Collect the patient's personal information and collect the patient's gene testing data; Step S104: Prioritize the gene loci contained in the gene detection data, and generate primary medication information based on the priority ranking results and the pre-constructed gene drug guide database. Step S106: Based on the personal information and the primary medication information, construct a blood drug concentration-time curve; Step S108: Based on the blood drug concentration-time curve and the primary medication information, obtain precise medication information; Step S110: Collect the patient's actual medication information, and adjust the precision medication information based on the actual medication information to obtain the target medication information.

[0024] Among them, patient personal information refers to various basic personal and physiological information related to the patient's medication, including but not limited to age, gender, weight, diagnosis of comorbidities, height, liver and kidney function, past medical history, allergy history, other medications currently in use, and lifestyle habits. This information affects the absorption, distribution, metabolism, and excretion of drugs in the body and is an important foundation for personalized medication. Genetic testing data refers to the dataset obtained after detecting genes related to drug metabolism and efficacy in the patient's body through methods such as PCR and NGS. It contains key information such as gene loci and genotypes and can reflect the patient's metabolic capacity, sensitivity, and risk of adverse reactions to specific drugs. It is the core genetic basis for accurately determining the medication regimen. For example, CYP450 family gene testing data can reflect the patient's metabolic rate of multiple drugs. Gene locus priority ranking refers to the process of classifying multiple drug-related gene loci in the genetic testing data into different priorities according to their degree of influence on the efficacy and safety of medication. Prioritize the gene loci that have the greatest impact on medication decisions, provide key basis for the generation of subsequent medication information, and avoid irrelevant gene loci interfering with decision-making efficiency.

[0025] Furthermore, the gene drug guideline database refers to a pre-constructed database storing the correspondence between gene loci and drugs, clinical drug use guidelines, and drug efficacy and safety data. It integrates authoritative international and domestic pharmacological research findings and clinical practice data, such as standardized data from international databases like PharmGKB, CPIC, and FDA, providing data support for gene loci interpretation and medication recommendation generation. Primary medication information refers to preliminary medication recommendations generated based on gene loci priority ranking results and the gene drug guideline database. This includes basic information such as drug type, initial dose, and frequency of use, forming the basis for subsequent precision medication information optimization. It has not yet been adjusted based on individual patient physiological characteristics and blood drug concentration data. Blood drug concentration-time curves, plotted with time on the horizontal axis and blood drug concentration on the vertical axis, reflect the changes of a drug in the patient's body over time. They visually present the drug's absorption rate, time to peak concentration, elimination rate, and other pharmacokinetic characteristics, serving as a basis for judging drug efficacy. The core basis for adjusting medication dosage is the body's metabolic status. Precision medication information refers to the medication regimen obtained by optimizing dosage and frequency based on primary medication information and combining it with blood drug concentration-time curves. It can better adapt to the patient's pharmacokinetic characteristics, reduce the risk of adverse reactions, and improve the efficacy of medication. Compared with primary medication information, it is more targeted and scientific. Actual medication information refers to relevant information recorded by the patient during actual medication, including the actual dosage of the drug taken, the time of administration, the body's response after administration, and the results of blood drug concentration monitoring. It is the practical basis for feedback on medication effects and further adjustment of the medication regimen. Target medication information refers to the final medication regimen obtained by dynamically adjusting precision medication information based on actual medication information. It can adapt to the patient's actual medication feedback and changes in physical condition, realize the continuous optimization of the medication regimen, and ensure the safety, effectiveness, and applicability of medication. It is the final output of individualized medication.

[0026] Therefore, existing personalized medication decision-making methods have significant technical shortcomings, making it difficult to meet the core requirements of scientific rigor, personalization, and practicality of medication regimens in precision medicine scenarios. Specific deficiencies include a lack of guideline data processing, unscientific decision-making algorithms, a lack of dosage quantification algorithms, and limitations in functionality and application scenarios. Specifically, the lack of guideline data processing manifests in the absence of systematic guideline data quality control processes for authoritative international databases such as PharmGKB, CPIC, and FDA, making it impossible to handle issues such as missing, incorrect, and duplicate data. It also lacks quantitative algorithms for handling conflicts between multiple source guidelines, relying solely on subjective judgment when recommendations from different sources contradict each other, without any scientific arbitration logic. The unscientific nature of decision-making algorithms is reflected in the fact that multi-gene / locus comprehensive decision-making only employs… The simple linear weighting method fails to consider nonlinear interactions between genes and lacks clear weight allocation standards and conflict arbitration algorithms. Medication recommendations are vague and do not clearly correspond to specific actions such as dose adjustments or drug changes, resulting in insufficient clinical applicability. The lack of a dose quantification algorithm is evident in the fact that it does not incorporate blood drug concentration simulation models, relying solely on fixed baseline feature values ​​and weights to calculate dose recommendations. It does not include individual characteristics such as patient age, weight, and liver and kidney function, lacking a precise dose derivation algorithm and thus failing to achieve quantitative optimization. Functional and scenario limitations include only generating medication review plans without corresponding personalized medication reminders, failing to form a decision-making-execution closed loop, having a single output format, and not integrating with clinical medical systems, leading to low efficiency for doctors.

[0027] Based on this, comprehensive patient data is collected, including personal information and genetic testing data. Personal information is collected through electronic medical records, patient questionnaires, and physical examinations to ensure its completeness and accuracy. Genetic testing data is obtained by collecting peripheral blood and saliva samples from patients and using PCR and / or NGS to acquire gene loci and genotype information related to drug metabolism and efficacy, providing a genetic basis for subsequent analysis. The gene loci in the genetic testing data are prioritized and combined with a pre-constructed gene drug guideline database to generate primary medication information. Specifically, by analyzing the impact of each gene locus on drug efficacy and safety, a priority order is determined, focusing on the gene loci with the greatest impact. Based on the ranking results, corresponding clinical medication recommendations are queried from the gene drug guideline database to preliminarily determine the drug type, initial dosage, and other primary medication information, achieving an initial integration of genetic information and clinical medication.

[0028] Subsequently, based on patient information and initial medication information, a blood drug concentration-time curve was constructed. Combining patient information such as age, weight, liver and kidney function, and parameters like drug dosage and frequency from the initial medication information, pharmacokinetic analysis was used to simulate the absorption, distribution, metabolism, and excretion of the drug in the patient's body, generating the blood drug concentration-time curve to visually represent the dynamic changes of the drug in the body. Based on the blood drug concentration-time curve and initial medication information, precise medication information was optimized. Specifically, this involved analyzing the peak concentration, time to peak concentration, and elimination half-life of the blood drug concentration-time curve. Parameters such as drug decay are used to determine whether the initial medication information is suitable for the patient's pharmacokinetic characteristics. Adjustments are made to the dosage and frequency of medication to ensure that the drug concentration in the body is maintained within the effective therapeutic range and to reduce the risk of adverse reactions. The patient's actual medication information is collected, and the precise medication information is dynamically adjusted to obtain the target medication information. Specifically, actual medication information is collected through patient medication records, blood drug concentration monitoring, and adverse reaction feedback. The difference between the actual medication effect and the expected effect is compared and analyzed, and the precise medication information is adjusted in a targeted manner to ensure that the medication regimen is always suitable for the patient's actual physical condition.

[0029] Therefore, this study establishes a standardized process for patient sample information collection and gene testing quality control, coupled with quantitative quality control algorithms to ensure the accuracy of basic data; constructs a collection and quality control system for multi-source authoritative drug-gene guidelines, designs quantitative conflict resolution algorithms to address data quality issues and conflicts between different database guidelines; designs a multi-gene / locus priority arbitration decision algorithm, clarifies weight allocation standards, and outputs scientifically unified primary medication recommendations; combines blood drug concentration simulation models with individual patient characteristics to develop personalized dosage quantification algorithms for precise medication dosage plans; and develops personalized reminder functions linked to personalized medication plans to improve patient medication adherence. This approach achieves customized medication plans for patients based on their unique physiological and genetic characteristics and medication feedback, differing from the traditional one-size-fits-all standardized medication model. It uses precise drug administration with a personalized plan for each individual, maximizing adaptation to individual patient differences and improving medication safety and efficacy.

[0030] Furthermore, the process of collecting patients' genetic testing data is specifically implemented in this embodiment as follows: Collect the patient's initial gene testing data; based on the detection method of the initial gene testing data, extract the corresponding gene loci and genotype information from the initial gene testing data; preprocess the gene loci and genotype data to obtain the gene testing data.

[0031] Initial gene testing data refers to the raw data directly obtained through gene testing technology, without any screening, cleaning, or processing. It contains a large amount of gene information unrelated to drug metabolism, testing noise, and redundant data, such as genotype data of drug-metabolizing enzyme genes, transporter genes, target genes, and adverse reaction-related genes. It is the original source of gene testing data. Specific testing methods include PCR and NGS. PCR is polymerase chain reaction, and NGS is high-throughput sequencing. Gene loci refer to the specific location of a gene on a chromosome. Each gene locus corresponds to specific genetic information. Gene loci related to drug metabolism and efficacy have different genotypes that directly affect a patient's ability and sensitivity to drug metabolism. They are the core analysis object of gene testing data. Genotype information refers to the specific genetic sequence type at a gene locus, that is, the combination of alleles. Different genotypes correspond to different enzyme activities, thus affecting drug metabolism efficiency.

[0032] Based on this, such as Figure 2 The system architecture diagram of a personalized medication method is shown. For the patient sample information collection and quality control module, if the detection method corresponds to PCR platform data, the gene loci and corresponding genotype information in the detection results are directly extracted and included in the subsequent quality control process. If the detection method corresponds to NGS data, the raw data is processed through a standardized bioinformatics analysis process including sequence alignment and variant calling. After screening to obtain the gene loci-genotype correspondence, it enters the quality control process.

[0033] The quality control process includes data integrity checks and data consistency checks. Data integrity checks verify whether fields such as gene loci and genotype are missing and remove invalid data with missing information. Data consistency checks cross-reference genotype results for the same gene locus if a patient has both PCR and NGS test data to ensure that the data is consistent. Inconsistent data must be manually reviewed and corrected before being included in the analysis.

[0034] For example, in the data consistency check, there are both PCR and NGS test data, as shown in Table 1 below: Table 1 Data Consistency Checklist

[0035] Subsequently, the genetic testing data entries that pass quality control, namely genetic testing data containing sample number, gene locus, and genotype, are stored in a database that has passed the Level 3 certification of the National Information Security Protection System to ensure data security.

[0036] For example, the genetic testing data that has passed quality control is shown in Table 2 below: Table 2. Gene testing data that passed quality control.

[0037] Therefore, standardized collection and high-quality processing of gene testing data have been achieved, providing reliable data support for subsequent personalized medicine analysis. Specifically, the quality and accuracy of gene testing data have been improved, eliminating noise and errors in the raw data. Preprocessing steps remove invalid data, correct incorrect genotypes, and delete duplicate records, effectively avoiding interference from redundant and erroneous information in subsequent analysis and ensuring the scientific validity of subsequent gene locus prioritization and medication information generation. Standardized integration of data from different testing methods has been achieved, improving data versatility. By unifying gene locus naming rules and data formats, the problem of inconsistent data formats across different testing methods and platforms has been solved, enabling compatibility between various gene testing data. This allows for direct matching with data in the gene drug guideline database, facilitating the promotion and application of personalized medicine methods and making it suitable for gene data processing in different medical institutions and under different testing conditions. Furthermore, the complexity of subsequent analysis has been reduced, and the analytical efficiency has been improved. Efficiency is improved by preprocessing to remove irrelevant gene loci data, focusing on core data related to drug metabolism and efficacy. This reduces the computational load of subsequent gene loci prioritization, shortens analysis time, and improves the efficiency of clinical medication decisions. The traceability of gene testing data is ensured, facilitating clinical validation and subsequent optimization. By recording information such as testing methods and instruments, as well as various operations during preprocessing, the entire process of gene testing data is traceable. If problems such as poor medication efficacy occur later, the data source and processing process can be traced, facilitating the identification of causes and optimization of the treatment plan. A stable and reliable data source is provided for subsequent steps such as gene loci prioritization and primary medication information generation, laying the foundation for the accuracy of personalized medication plans, indirectly improving medication efficacy and safety, and reducing medication errors caused by inaccurate data.

[0038] Furthermore, the construction process of the gene therapy guide database is specifically implemented as follows in this embodiment: Acquire data from an international database; perform integrity checks, error value checks, invalid value checks, duplicate value checks, consistency checks, and re-checks on the international database data in sequence to obtain standard data; extract data from the standard data and construct the gene drug guide database according to a preset storage logic.

[0039] Among them, international database data refers to data from authoritative international pharmacology and genomics databases, including but not limited to PharmGKB, CPIC, FDA pharmacogenomics database, EMC database, NCBI Gene database, etc. These databases integrate global gene-drug association research results, clinical drug use guidelines, drug efficacy and safety data, gene locus information, etc., and are the core data source for building gene drug guideline databases. For example, the PharmGKB database already covers relevant information on 715 drugs and 1761 genes.

[0040] Completeness verification refers to checking the acquired international database data to confirm its integrity and identify any missing key information, such as the correspondence between gene loci and drugs, clinical recommendations, data sources, and study sample sizes. This ensures the data meets the needs of subsequent analysis and application, avoiding inaccurate medication recommendations due to missing data. Error value verification involves checking for erroneous numerical values, labeling, or logical errors in the international database data, such as incorrect gene locus naming, incorrect drug dosage units, or discrepancies between efficacy data and clinical reality. This allows for the timely identification and marking of erroneous data, providing a basis for subsequent correction. Invalid value verification involves checking for invalid data, such as blank values ​​or values ​​without a specified meaning. Symbols with unclear meanings and values ​​outside the reasonable range, such as negative drug dosages or efficacy scores exceeding the set range, cannot be used for subsequent analysis and must be removed or corrected. Duplication checks involve inspecting for duplicate records, such as multiple records of the same gene locus and drug correspondence, or repeated occurrences of the same clinical recommendations, to avoid analytical bias and data redundancy caused by duplicate data. Consistency checks involve verifying the logical consistency of relevant information in the data, such as whether the genotype of a gene locus matches the corresponding description of drug metabolism, whether clinical recommendations match drug efficacy data, and whether data of the same type from different sources are consistent, ensuring the logicality and reliability of the data.

[0041] Furthermore, standard data refers to high-quality, standardized data that has undergone integrity, error value, invalid value, duplicate value, consistency verification and review, and can be directly used for database construction. This eliminates various problems in the original international database data, ensuring the accuracy, integrity and consistency of the data. Data extraction refers to extracting core information related to personalized medicine from the standard data, including gene locus information, the relationship between genotype and drug metabolism, clinical medication recommendations, drug efficacy and adverse reaction data, etc., while eliminating redundant information unrelated to personalized medicine. Pre-set storage logic refers to the pre-defined database data storage rules and structure, including data classification methods, index creation, and relationship definition. For example, drug information and clinical recommendations are stored according to gene loci, and an index is established to link gene loci with drugs and clinical recommendations, facilitating subsequent quick querying and retrieval of data.

[0042] For example, such as Figure 2 The system architecture diagram of the provided personalized medication method is shown. In the process of acquiring international database data, the core sources include international authoritative databases such as PharmGKB, CPIC, and FDA drug label databases, which collect drug-gene association guidelines. The content of the international database data collected includes key information such as drug name, associated gene / site, genotype-drug relationship, evidence level, issuing institution, and update time.

[0043] Subsequently, the integrity check algorithm is as follows: Core field missing rate = (number of records with missing core fields / total number of records) × 100%. Core fields include drug name, gene / locus, genotype, medication recommendation, evidence level, and update time. Records with a missing rate > 5% are marked as needing completion, and those that cannot be completed are directly discarded. Error value check first performs standardized preprocessing on the text, automatically extracting core entities such as drug, disease, gene locus, genotype, and efficacy description. Then, it performs genotype comparison logic verification, standard genotype legality verification, drug-regimen matching verification, semantic redundancy verification, and disease-drug indication verification, automatically identifying comparison groups. Errors such as duplicate genotypes, invalid genotypes, terminological mismatches, and semantic redundancy are identified and automatically corrected according to the pharmacogenomics standard knowledge base and preset correction rules. This includes deleting duplicate genotypes for comparison, standardizing terminology, simplifying redundant content, and unifying formatting to ensure data accuracy and compliance. For example, the statement "Compared to patients with the CT genotype, patients with colon cancer of the CT genotype may respond better to capecitabine, leucovorin, oxaliplatin, or fluorouracil. Other genetic and clinical factors may also affect patient responses to capecitabine, leucovorin, oxaliplatin, and fluorouracil" is corrected during genotype comparison logic validation by comparing the pre-CT genotype. ==The compared genotype (CT) is a duplicate comparison genotype; this text information will be deleted and not included in subsequent analysis. For invalid value verification, an invalid value threshold is first set, including unclear evidence level, no specific adjustment direction for medication recommendations, and publication time exceeding 10 years without update. If any condition is met, it is judged as an invalid value and removed. For duplicate value verification, a hash algorithm is used to calculate the hash value of each record using drug name + gene / locus + genotype as a unique identifier. Records with the same hash value are judged as duplicates, and the entry with the highest evidence level and the most recent update time is retained. For consistency verification, a logical consistency check formula is used for the same drug-genome within the same database. Consistency of medication recommendations = (Number of consistent medication recommendation records / Total number of records for this drug and gene combination) × 100%. A consistency threshold is preset. If <90%, the recommendations are marked as high-risk conflict reviews. The review, also known as high-risk conflict review, involves automated hierarchical arbitration for items that cannot be determined after integrity checks, error value checks, invalid value checks, duplicate value checks, and consistency checks. The arbitration is based on the priority of the issuing institution > the priority of the evidence level > the priority of the update time > the priority of the clinical impact. The unique and optimal item is automatically retained and conflicting data is removed. Items that still cannot be determined after arbitration are automatically marked as unreliable data and directly excluded from the medication decision database.

[0044] The standard data obtained after the above processing is stored according to a preset storage logic, namely, drug-gene / locus-genotype-medication recommendation-evidence level-update time-source. Data is fully synchronized every preset synchronization time, such as every 3 months, using an incremental update algorithm: new record count = total number of records synchronized this time - historical storage record count. New records undergo a quality control and manual review process before being included in the database. The standard data obtained after processing is stored according to the preset storage logic as shown in Table 3 below: Table 3. Gene Drug Guide Database with Pre-defined Storage Logic

[0045] Therefore, the accuracy, completeness, and consistency of the database data were ensured, providing a reliable guarantee for the generation of primary medication information. Through multiple rounds of verification and review, erroneous, invalid, and duplicate data in the original international database were effectively eliminated, and missing information was supplemented, avoiding medication recommendations errors caused by data issues and ensuring the scientific nature of primary medication information. Data standardization and structuring were achieved, improving data query and retrieval efficiency. By unifying data formats, standardizing data classification, and establishing reasonable storage logic and relational indexes, data can be quickly retrieved according to gene loci, providing corresponding drug information and clinical recommendations. This significantly improved the efficiency of primary medication information generation and met the needs of rapid clinical medication decision-making. The timeliness and scalability of the database data were also ensured. By regularly synchronizing with the latest data from the international database, the latest clinical research results were promptly added. The database, along with medication guidelines, ensures that its data keeps pace with medical advancements and adapts to the application of new drugs and gene testing technologies. Simultaneously, its rational structure facilitates the addition of new data types and expansion of database functions, such as adding drug interaction data and patient prognosis data, thereby enhancing the database's usability. It also reduces the difficulty of database construction and maintenance, facilitating widespread application. The standardized database construction process reduces the subjectivity of manual operations and lowers the technical threshold for database construction. Furthermore, the regular update and maintenance mechanism ensures the long-term stable operation of the database, making it suitable for medical and research institutions of different sizes. Finally, it provides systematic and comprehensive data support for subsequent steps such as gene locus prioritization and the generation of primary medication information, laying the foundation for the accuracy of personalized medicine plans and promoting the standardization and normalization of personalized medicine technology.

[0046] Furthermore, the process of prioritizing the gene loci contained in the gene testing data is specifically implemented in this embodiment as follows: The detection method associated with the gene detection data is determined; if the detection method is single-gene detection, the gene loci contained in the gene detection data are used as target gene loci; if the detection method is multi-gene detection, the gene loci contained in the gene detection data are queried to correspond to the data source in the gene drug guideline database; based on the data source, a first weight is assigned; the gene loci contained in the gene detection data are queried to correspond to the clinical recommendation data in the gene drug guideline database; based on the clinical recommendation data, a second weight is assigned; based on the first weight and the second weight, the priority score corresponding to the gene loci is determined, and based on all the priority scores, all the gene loci are prioritized.

[0047] Furthermore, the process of generating primary medication information based on the priority ranking results and the pre-built gene drug guide database is specifically implemented as follows in this embodiment: If the detection method is single-gene detection, the gene drug guide database is queried using the target gene locus, and the primary medication information is generated based on the query results. If the detection method is multi-gene detection, the highest score among the priority scores corresponding to the gene locus is compared with a first threshold. If the highest score is greater than or equal to the first threshold, the gene locus corresponding to the highest score is locked as the target gene locus, and the gene drug guide database is queried using the target gene locus, and the primary medication information is generated based on the query results. If the highest score is less than the first threshold, all gene loci with priority scores greater than a second threshold are selected to form a high-risk gene set. If the high-risk gene set is not empty, the gene drug guide database is queried based on the gene loci contained in the high-risk gene set, and the primary medication information is determined based on the query results. If the high-risk gene set is empty, a ranking weight is configured for each priority score based on the priority scores corresponding to all gene loci, a comprehensive recommendation score is calculated based on the priority scores and the ranking weights, and the corresponding clinical recommendation information is selected from the query results corresponding to the gene drug guide database based on the comprehensive recommendation score as the primary medication information.

[0048] The data sources correspond to different international databases, and the reliability and authority of these sources vary. For example, data from international medication guidelines is considered more authoritative than ordinary clinical research literature. The first weight refers to the weight assigned to a gene locus based on the authority and reliability of the data source. A higher weight indicates more reliable data analysis for that gene locus and a greater impact on medication decisions; for example, the first weight for international medication guidelines is higher than that for ordinary clinical research literature. Clinical recommendation data refers to clinical medication-related recommendations corresponding to gene loci in the gene drug guideline database, including recommendations on drug selection, dosage adjustment, adverse reaction prevention, and medication monitoring, directly reflecting the degree of influence of the gene locus on the medication regimen. The two weights refer to the weight value assigned to a gene locus based on the importance and relevance of the corresponding clinical recommendation data. The higher the weight value, the greater the guiding significance of the clinical recommendation for medication decision-making. The priority score is a score obtained by using a preset calculation formula based on the first and second weights to measure the degree of influence of the gene locus on medication decision-making. The higher the score, the higher the priority of the gene locus, and the more likely it should be used as a reference for medication decision-making. Priority ranking refers to the process of arranging the gene loci in all gene testing data from high to low according to their respective priority scores, clarifying the order of influence of different gene loci on medication decision-making, and facilitating subsequent focus on high-priority gene loci to generate accurate primary medication information.

[0049] Furthermore, the highest score refers to the highest priority score among all gene loci, indicating that the gene locus with that score has the greatest impact on medication decisions and serves as the core reference for these decisions. The first threshold is a pre-set critical value used to determine whether the highest-scoring gene locus has an absolute dominant role. This threshold is set based on clinical practice data and information from the gene drug guideline database. When the highest score exceeds this threshold, it indicates that the gene locus's impact on medication decisions is far greater than other gene loci, and it can be used as the sole core reference. The target gene locus is the gene locus with the highest priority score identified when the highest score exceeds the first threshold. This gene locus has the most significant impact on medication efficacy and safety and is the core basis for generating primary medication information. Subsequent searches will focus on this gene locus within the gene drug guideline database. (Ranking) Weight refers to the weight assigned to the priority score of each gene locus when the highest score is no greater than the first threshold. It is used to measure the contribution of gene loci with different priority scores. The higher the priority score, the greater the ranking weight. The comprehensive recommendation score is the comprehensive score calculated by weighted summation based on the priority score and corresponding ranking weight of each gene locus when the highest score is no greater than the first threshold. It is used to comprehensively measure the overall impact of all gene loci on medication decisions and reflects the synergistic effect of multiple gene loci. Clinical recommendation information refers to the medication recommendations corresponding to the gene locus retrieved from the gene drug guideline database. It includes drug type, dosage, frequency of use, contraindications, and adverse reaction prevention. It is the direct basis for generating primary medication information. The corresponding clinical recommendation information is selected according to the comprehensive recommendation score to ensure the comprehensiveness and scientific nature of the primary medication information.

[0050] Based on this, continuing with the previous example, such as Figure 2The system architecture diagram of the proposed personalized medication method is shown. The corresponding primary medication plan generation module calculates gene priority based on guideline evidence weight and clinical risk coefficient. Through quantile threshold arbitration, global system score and weighted fusion of the top N genes, the conflict resolution and final decision of multi-gene medication recommendations are completed, and a standardized personalized primary medication plan is output. Specifically, taking PharmGKB, CPIC, and FDA drug labeling databases as examples, for single-gene / locus medication recommendations, since they do not include multi-gene synergy, the integrated pharmacogenetic guideline database, i.e., the gene-pharmaceutical guideline database, is used to match the patient's genotype with the relevant genes / locus of the target drug, directly outputting standardized medication recommendations. Standardized medication recommendations include using according to the instructions, increasing the dosage, decreasing the dosage, and changing the drug. For multi-gene synergy, a gene weighting table is constructed using a two-dimensional approach of guideline source and evidence level. Quantitative values ​​are assigned based on differences in the authority, evidence quality, and clinical applicability of international pharmacogenomics guidelines. For example, the FDA, as the U.S. Food and Drug Administration, has the strongest legal force and is clinically mandatory, so it has the highest weight; CPIC, as the international authoritative pharmacogenomics consortium, has the most standardized guidelines and the most solid evidence, so it has the second highest weight; PharmGKB, as a comprehensive research database, has weights decreasing in that order. The level of evidence represents the quality of the study and its clinical credibility. The higher the level, the larger the sample size, the more rigorous the design, the higher the reproducibility, and the stronger the clinical applicability. The lower the level, the more preliminary the study, the smaller the sample size, and the less stable the conclusions. The weights are allocated according to the above principles. The specific weight allocation depends on the actual use scenario and is not limited in this embodiment.

[0051] The genetic evidence weights are obtained by assigning weight coefficients based on the drug-gene evidence level. The allocation table, also known as the first weight table, is shown in the form of Table 4 below: Table 4 First Weighting Table

[0052] For each gene / locus, medication recommendations, including those for use as directed, increasing dosage, decreasing dosage, and changing medication, are first calculated based on a priority score. The medication recommendations for each gene / locus are derived from the evidence level in the guidelines, and the evidence weights for calculating the priority scores are derived from the gene evidence weights in Table 4. Allocation table; Clinical impact coefficient C, i.e., the second weight, is set according to the priority of clinical necessity and safety. The priority score is calculated as: Evidence weight × Clinical impact coefficient. Here, the evidence weight corresponds to the first weight, and the clinical impact coefficient corresponds to the second weight. In the second weight, changing the drug corresponds to the highest clinical risk, reducing / increasing the dosage corresponds to the moderate clinical risk, and following the instructions corresponds to the basic clinical risk. For example, in the second weight, changing the drug is assigned a value of 2.0, reducing / increasing the dosage is assigned a value of 1.5, and following the instructions is assigned a value of 1.0. The final priority score S is calculated as follows. i =W ei ×C i , among which, S i W represents the priority score corresponding to the i-th gene / site. ei The first weight, C, represents the i-th gene / site. i The second weight represents the i-th gene / locus. The credibility of the guideline evidence level is fused with the importance of the medication recommendation using a priority score. S i The larger the value, the stronger the clinical binding force of the gene.

[0053] Then, all genes are sorted from highest to lowest priority score to obtain a gene priority sequence. If there are a total of n related gene loci, their corresponding priority scores are represented as S1, S2, ..., S... n If the sorting result is S1≥S2≥…≥S n Calculate the total score Sum = S1 + S2 + ... + S n .

[0054] Then set the first threshold T 95 With the second threshold T 75 First threshold T 95 The second threshold T represents the 95th percentile of all priority scores. 75 The 75th percentile represents all priority scores. It should be noted that the values ​​of the first and second thresholds are not fixed and are determined by the actual user needs in the specific use case. For each gene i, its corresponding priority score is first normalized to obtain the normalized priority score W. i =S i / Sum, satisfying ∑W i =1. Further calculation of the system weighted composite score S_system, S_system= This represents the overall risk intensity of the entire polygenic system.

[0055] Based on the sorted gene sequences, if the priority score of the first-ranked gene (i.e., the highest score) is greater than the first threshold, then the suggestion of that gene will be used as the final suggestion.

[0056] In addition, if a priority score is greater than the second threshold, the medication recommendation for that gene will be included in the high-risk gene set G_high. If the medication recommendations in G_high are completely consistent, the consistent recommendation will be adopted directly. If the recommendations are inconsistent, the recommendation with the highest priority score in G_high will be adopted.

[0057] If all priority scores are less than the second threshold, a comprehensive decision is made, selecting the top N genes in the core reference criteria, prioritizing the top 3 genes, and determining whether the medication recommendations for the 3 genes are consistent. If they are consistent, they are directly used as the final comprehensive recommendation; otherwise, the comprehensive recommendation score S_final is calculated. Specifically, if the priority scores of the top 3 genes are S1, S2, and S3, and S1 ≥ S2 ≥ S3, the total score of the top 3 genes is calculated as Sum3 = S1 + S2 + S3. Then the normalized priority scores are W1 = S1 / Sum3, W2 = S2 / Sum3, and W3 = S3 / Sum3. The weighted score of the top 3 genes, S_top3, is W1 × S1 + W2 × S2 + W3 × S3. The comprehensive recommendation score S_final is... ×S_top3+(1 )×S_system, decision coefficients =Sum3 / Sum.

[0058] By calculating different quantiles of the priority scores for all genes, a first comprehensive score threshold and a second comprehensive score threshold are established. For example, the 90th percentile is used as the first comprehensive score threshold, and the 70th percentile as the second comprehensive score threshold. When the comprehensive recommendation score is greater than or equal to the first comprehensive score threshold, the corresponding clinical recommendation information suggests changing the medication; when the comprehensive recommendation score is less than the first comprehensive score threshold but greater than or equal to the second comprehensive score threshold, the corresponding clinical recommendation information suggests adjusting the dosage; when the comprehensive recommendation score is less than the second comprehensive score threshold, the corresponding clinical recommendation information suggests taking the medication as directed in the instructions. Furthermore, for the dosage adjustment recommendation corresponding to the clinical recommendation information, it is necessary to determine the weight of the recommended dose reduction and W_down among the top 3 genes, and the weight of the recommended dose increase and W_up among the top 3 genes. If W_down > W_up, the dosage is reduced; if W_up > W_down, the dosage is increased.

[0059] Furthermore, the process of constructing blood drug concentration-time curves based on personal information and primary medication information is specifically implemented in this embodiment as follows: Based on the personal information and the primary medication information, the blood drug concentration-time curve is constructed using a population pharmacokinetic model.

[0060] For the initial medication information obtained, such as the initial medication recommendation for propranolol being a dose reduction, with an initial recommended dose of 37.5 mg / dose, it is necessary to further calculate and determine the specific dose reduction range through the precise dosage regimen generation module in order to output an individualized precise dosing dose.

[0061] In the population pharmacokinetic model, also known as the PPK model, taking a one-compartment model as an example, the drug elimination rate constant k = CL / V, where CL is the clearance rate and V is the volume of distribution. The formula for the plasma concentration-time curve is as follows. , Where D is the dose, F is the bioavailability, t is the time after administration, and e is the Euler constant. This indicates that the drug is eliminated exponentially over time, meaning that the larger the elimination rate constant k and the longer the time t, the better. The smaller the value, the faster the blood drug concentration decreases.

[0062] Furthermore, the process of obtaining precise medication information based on blood drug concentration-time curves and primary medication information is specifically implemented as follows in this embodiment: Using the therapeutic window blood drug concentration contained in the primary medication information as the target, actual medication information is derived based on the blood drug concentration curve; based on the patient's blood drug concentration monitoring data within a preset time period, the primary medication information is corrected through a Bayesian feedback algorithm, and based on a preset safe dosage range, unreasonable dosage recommendations are eliminated to obtain the precise medication information.

[0063] Among them, such as Figure 2 The system architecture diagram of the proposed personalized medication method is shown below. Corresponding to the precise dosage regimen generation module, the Bayesian feedback algorithm corrects the model parameters based on patient blood drug concentration monitoring data, as shown in the formula. , in, These are the corrected parameter estimates. To monitor blood drug concentration, i.e., blood drug concentration monitoring data, For the prior distribution of parameters, It is a differential element (a small change in the parameter space) of the pharmacokinetic parameter θ.

[0064] Specifically, by inputting patient personal information, genetic testing data, and initial medication information, a PPK model is used to simulate blood drug concentration-time curves, using the therapeutic window blood drug concentration recommended by the gene drug guideline database. That is, using the therapeutic window blood drug concentration as the target, and working backwards to deduce actual medication information. The formula is: , in, This refers to the dosing interval. The preset time is based on data set according to actual usage scenarios, preferably 7-14 days. Every 7-14 days, based on the patient's blood drug concentration monitoring data, parameters such as CL and V are corrected using a Bayesian feedback algorithm to optimize the dosage regimen and obtain the corrected actual medication information. Based on the specified safe dosage range, dosage recommendations that exceed the range are eliminated, triggering manual intervention. Based on the final elimination results and actual medication information, accurate medication information is obtained.

[0065] Continuing with the previous example, if the dosage regimen output shows the initial medication information for propranolol, the recommended dosage is to reduce the dose, with an initial recommended dose of 37.5 mg / dose. The precise dosage regimen generation module then corrects the initial dose to 30 mg / dose and obtains the dosing interval, as shown in Table 5 below. Table 5. Precision Medication Information Output Table

[0066] Furthermore, the process in step S110, which involves collecting the patient's actual medication information and adjusting the precision medication information based on this information to obtain the target medication information, can be understood as follows: based on the precision medication information, a medication reminder module generates and pushes personalized medication reminders, achieving standardized prompts and real-time notifications regarding medication time, dosage, and administration method. Figure 2 The system architecture diagram of the proposed personalized medication method shows that the medication reminder module needs to interface with external tools, such as smart medical apps, hospital HIS systems, and smart wearable devices, to support multi-channel reminder pushes. Personalized reminders are generated based on the precise dosage plan corresponding to accurate medication information. The reminder information format is shown in the table below: Table 6 Reminder Message Format Table

[0067] Subsequently, a composite adherence assessment model was constructed based on patients' multi-dimensional medication behavior data. Adherence was obtained by weighted fusion of basic on-time rate, time deviation adherence, and cycle continuity index.

[0068] Specifically, the basic on-time compliance rate The calculation formula is as follows: , Time Deviation Compliance The calculation formula is as follows: , Where N represents the total number of medications required, and the periodicity index is... The calculation formula is as follows: , The overall adherence weights are allocated based on the clinical importance of each indicator, its impact on medication safety and efficacy, and data reliability. Basic on-time adherence rate is the core indicator for determining adherence, with the highest weight; time deviation adherence is an important auxiliary indicator, with the second highest weight; and the periodic continuity index is a long-term trend reference indicator, with the lowest weight. The specific weight values ​​are determined by the actual needs of users in the actual use scenario, and this embodiment does not impose limitations. If the weights corresponding to basic on-time adherence rate, time deviation adherence, and periodic continuity index are configured as 0.5, 0.3, and 0.2 respectively, then the final overall adherence C is calculated as follows. final ,as follows, , Based on the calculated overall compliance C final Adjust the reminder frequency. If the compliance rate is less than the compliance threshold, such as <80%, increase the frequency of pop-up reminders. At the same time, synchronize the information to the accurate dosage plan generation module for dosage optimization to obtain target medication information.

[0069] Therefore, for data from different testing platforms such as PCR and NGS, a standardized quality control process for gene testing data covering multiple testing types is established by first performing differentiated preprocessing, and then integrating multi-level quality control such as data integrity verification, data consistency cross-comparison, and manual review to ensure the accuracy and reliability of basic data. This includes quantitative algorithms such as integrity missing rate, error value matching rate, and duplicate value hash verification to ensure the reliability of guideline data. Combined with evidence level weighted scoring, timestamp correction, and manual review as a safety net, scientific arbitration of conflicts between multiple guidelines is achieved. Clear gene weight allocation standards are defined, and unified medication recommendations are output through weighted calculation adjusted by evidence level. A PPK+Bayesian feedback fusion algorithm, combining population pharmacokinetic models and individual blood drug concentration data, achieves precise dosage quantification and dynamic optimization. The frequency of reminders is adjusted based on medication adherence data.

[0070] Corresponding to the above method embodiments, this application also provides embodiments of personalized medication devices. Figure 3 A schematic diagram of a personalized medication device according to an embodiment of this application is shown. Figure 3 As shown, the device includes: The data acquisition module 302 is configured to collect the patient's personal information and the patient's genetic testing data; The primary medication generation module 304 is configured to prioritize the gene loci contained in the gene detection data and generate primary medication information based on the priority ranking results and a pre-built gene drug guide database. Module 306 is configured to construct a blood drug concentration-time curve based on the personal information and the primary medication information; The precision medication generation module 308 is configured to obtain precision medication information based on the blood drug concentration-time curve and the primary medication information; The target medication generation module 310 is configured to collect the patient's actual medication information, and adjust the precision medication information based on the actual medication information to obtain the target medication information.

[0071] In an optional embodiment, the acquisition module 302 is further configured to: Collect the patient's initial gene testing data; based on the detection method of the initial gene testing data, extract the corresponding gene loci and genotype information from the initial gene testing data; preprocess the gene loci and genotype data to obtain the gene testing data.

[0072] In an optional embodiment, the personalized medication device further includes: The database construction module is configured to acquire international database data; perform integrity checks, error value checks, invalid value checks, duplicate value checks, consistency checks, and re-checks on the international database data in sequence to obtain standard data; extract data from the standard data and construct the gene drug guide database according to a preset storage logic.

[0073] In an optional embodiment, the primary medication generation module 304 is further configured to: The detection method associated with the gene detection data is determined; if the detection method is single-gene detection, the gene loci contained in the gene detection data are used as target gene loci; if the detection method is multi-gene detection, the gene loci contained in the gene detection data are queried to correspond to the data source in the gene drug guideline database; based on the data source, a first weight is assigned; the gene loci contained in the gene detection data are queried to correspond to the clinical recommendation data in the gene drug guideline database; based on the clinical recommendation data, a second weight is assigned; based on the first weight and the second weight, the priority score corresponding to the gene loci is determined, and based on all the priority scores, all the gene loci are prioritized.

[0074] In an optional embodiment, the primary medication generation module 304 is further configured to: If the detection method is single-gene detection, the gene drug guide database is queried using the target gene locus, and the primary medication information is generated based on the query results. If the detection method is multi-gene detection, the highest score among the priority scores corresponding to the gene locus is compared with a first threshold. If the highest score is greater than or equal to the first threshold, the gene locus corresponding to the highest score is locked as the target gene locus, and the gene drug guide database is queried using the target gene locus, and the primary medication information is generated based on the query results. If the highest score is less than the first threshold, all gene loci with priority scores greater than a second threshold are selected to form a high-risk gene set. If the high-risk gene set is not empty, the gene drug guide database is queried based on the gene loci contained in the high-risk gene set, and the primary medication information is determined based on the query results. If the high-risk gene set is empty, a ranking weight is configured for each priority score based on the priority scores corresponding to all gene loci, a comprehensive recommendation score is calculated based on the priority scores and the ranking weights, and the corresponding clinical recommendation information is selected from the query results corresponding to the gene drug guide database based on the comprehensive recommendation score as the primary medication information.

[0075] In an optional embodiment, the building module 306 is further configured to: Based on the personal information and the primary medication information, the blood drug concentration-time curve is constructed using a population pharmacokinetic model.

[0076] In an optional embodiment, the precision medication generation module 308 is further configured to: Using the therapeutic window blood drug concentration contained in the primary medication information as the target, actual medication information is derived based on the blood drug concentration curve; based on the patient's blood drug concentration monitoring data within a preset time period, the primary medication information is corrected through a Bayesian feedback algorithm, and based on a preset safe dosage range, unreasonable dosage recommendations are eliminated to obtain the precise medication information.

[0077] The personalized medication device provided in this application collects the patient's personal information and genetic testing data; prioritizes the gene loci contained in the genetic testing data; and generates primary medication information based on the priority ranking results and a pre-constructed gene drug guideline database; constructs a blood drug concentration-time curve based on the personal information and the primary medication information; obtains precise medication information based on the blood drug concentration-time curve and the primary medication information; collects the patient's actual medication information; and adjusts the precise medication information based on the actual medication information to obtain target medication information. This device integrates standardized sample information collection, unified guideline processing, scientific protocol formulation, precise dose simulation, and personalized reminders for individualized medication guidance. It achieves a precision medicine model that customizes exclusive medication plans for patients based on individual patient characteristics, combined with drug-gene correlation patterns and clinical guidelines, realizing one person, one drug, one dosage, improving efficacy, and reducing the risk of adverse reactions.

[0078] The above is an illustrative scheme of a personalized medication device according to this embodiment. It should be noted that the technical solution of this personalized medication device and the technical solution of the aforementioned personalized medication method belong to the same concept. Details not described in detail in the technical solution of the personalized medication device can be found in the description of the technical solution of the aforementioned personalized medication method. Furthermore, the components in the device embodiment should be understood as functional modules necessary to implement each step of the program flow or each step of the method; these functional modules are not actual functional divisions or separations. The device claims defined by such a set of functional modules should be understood as a functional module architecture that primarily implements the solution through the computer program described in the specification, and not as a physical device that primarily implements the solution through hardware.

[0079] Figure 4 A structural block diagram of a computing device 400 according to an embodiment of this application is shown. The components of the computing device 400 include, but are not limited to, a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and a database 450 is used to store data.

[0080] The computing device 400 also includes an access device 440, which enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of wired or wireless network interface (e.g., a Network Interface Card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) interface, a Wi-MAX interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, and so on.

[0081] In one embodiment of this application, the aforementioned components of the computing device 400 and Figure 4 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 4 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.

[0082] The computing device 400 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or PCs. The computing device 400 can also be a mobile or stationary server.

[0083] The processor 420 is used to execute computer-executable instructions for each step of the personalized medication method.

[0084] The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the personalized medication method described above belong to the same concept. For details not described in detail in the technical solution of the computing device, please refer to the description of the technical solution of the personalized medication method described above.

[0085] An embodiment of this application also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, are used to implement the steps of the personalized medication method.

[0086] The above is an illustrative embodiment of a computer-readable storage medium. It should be noted that the technical solution of this storage medium and the technical solution of the aforementioned personalized medication method belong to the same concept. Details not described in detail in the technical solution of the storage medium can be found in the description of the technical solution of the aforementioned personalized medication method.

[0087] An embodiment of this application also provides a chip that stores a computer program, which, when executed by the chip, implements the steps of the personalized medication method.

[0088] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0090] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0091] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0092] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A personalized medication method, characterized in that, include: Collect the patient's personal information and collect the patient's genetic testing data; The gene loci contained in the gene detection data are prioritized and sorted, and primary medication information is generated based on the priority sorting results and a pre-constructed gene drug guide database. Based on the personal information and the primary medication information, a blood drug concentration-time curve is constructed. Based on the blood drug concentration-time curve and the primary medication information, precise medication information is obtained; Collect the patient's actual medication information, and adjust the precision medication information based on the actual medication information to obtain the target medication information.

2. The method according to claim 1, characterized in that, The collection of the patient's genetic testing data includes: Collect initial gene testing data from the patient; Based on the detection method of the initial gene detection data, extract the corresponding gene loci and genotype information from the initial gene detection data; The gene loci and genotype data are preprocessed to obtain the gene detection data.

3. The method according to claim 1, characterized in that, The construction process of the gene therapy guide database includes: Obtain data from international databases; The international database data is subjected to integrity checks, error value checks, invalid value checks, duplicate value checks, consistency checks, and a final review in sequence to obtain standard data; The standard data is extracted and constructed according to a preset storage logic to form the gene drug guide database.

4. The method according to claim 3, characterized in that, The priority sorting of gene loci contained in the gene detection data includes: Determine the detection method associated with the gene detection data; If the detection method is single-gene detection, the gene loci contained in the gene detection data shall be used as the target gene loci. If the detection method is multi-gene detection, the gene loci contained in the gene detection data are queried, and the corresponding data source in the gene drug guideline database is obtained; based on the data source, a first weight is assigned; the gene loci contained in the gene detection data are queried, and the corresponding clinical recommendation data in the gene drug guideline database is obtained; based on the clinical recommendation data, a second weight is assigned; based on the first weight and the second weight, the priority score corresponding to the gene locus is determined, and based on all the priority scores, all the gene loci are prioritized.

5. The method according to claim 4, characterized in that, The generation of primary medication information based on the priority ranking results and a pre-built gene drug guide database includes: If the detection method is the single gene detection, the gene drug guide database is queried using the target gene locus, and the primary medication information is generated based on the query results. If the detection method is multi-gene detection, the highest score among the priority scores corresponding to the gene loci is compared with a first threshold. If the highest score is greater than or equal to the first threshold, the gene locus corresponding to the highest score is locked as the target gene locus, and the gene drug guide database is queried using the target gene locus. The primary medication information is generated based on the query results. If the highest score is less than the first threshold, all gene loci with priority scores greater than a second threshold are selected to form a high-risk gene set. If the high-risk gene set is not empty, the gene drug guide database is queried based on the gene loci contained in the high-risk gene set, and the primary medication information is determined based on the query results. If the high-risk gene set is empty, a ranking weight is configured for each priority score based on the priority scores corresponding to all gene loci. A comprehensive recommendation score is calculated based on the priority scores and the ranking weights. Based on the comprehensive recommendation score, corresponding clinical recommendation information is selected from the query results corresponding to the gene drug guide database as the primary medication information.

6. The method according to claim 1, characterized in that, The step of constructing a blood drug concentration-time curve based on the personal information and the primary medication information includes: Based on the personal information and the primary medication information, the blood drug concentration-time curve is constructed using a population pharmacokinetic model.

7. The method according to claim 1, characterized in that, The process of obtaining precise medication information based on the blood drug concentration-time curve and the primary medication information includes: Using the therapeutic window blood drug concentration contained in the primary medication information as the target, actual medication information is derived based on the blood drug concentration curve. Based on the patient's blood drug concentration monitoring data within a preset time period, the primary medication information is corrected using a Bayesian feedback algorithm, and unreasonable dosage recommendations are eliminated based on a preset safe dosage range to obtain the precise medication information.

8. A personalized medication administration device, characterized in that, include: The data acquisition module is configured to collect the patient's personal information and the patient's genetic testing data. The primary medication generation module is configured to prioritize the gene loci contained in the gene detection data and generate primary medication information based on the priority ranking results and a pre-built gene drug guide database. The module is configured to construct a blood drug concentration-time curve based on the personal information and the primary medication information; The precision medication generation module is configured to obtain precision medication information based on the blood drug concentration-time curve and the primary medication information; The target medication generation module is configured to collect the patient's actual medication information, and adjust the precision medication information based on the actual medication information to obtain the target medication information.

9. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the steps of the personalized medication method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer instructions, characterized in that, When executed by the processor, this instruction implements the steps of the personalized medication method according to any one of claims 1 to 7.

Images