46 results about "Pharmacokinetic modeling" patented technology

The invention relates to a mechanism and data combined dynamic PET-CT pharmacokinetic fusion modeling method, and belongs to the technical field of pharmacokinetic modeling, and the method comprises the steps: obtaining original image data of a historical case, and constructing a training data set according to the original image data; constructing a dynamic pharmacokinetic model based on a mechanism model and a data-driven network, and completing the training of the dynamic pharmacokinetic model according to the training data set; collecting actual image data of the current subject in a period of time; and inputting the actual image data into a trained dynamic pharmacokinetic model to obtain a prediction result. According to the method, the mechanism model and the data driving network are fused, the complete pharmacokinetic process can be accurately predicted only through image data in a short time in the early stage, the problems that a traditional model depends on long-time scanning and is easily interfered by motion artifacts and the like are solved, the parameter analysis efficiency and accuracy are greatly improved, and the method is suitable for clinical rapid diagnosis.

The invention discloses a construction method of a rivaroxaban population pharmacokinetic model and application of the rivaroxaban population pharmacokinetic model in an individualized medication prediction model, and relates to the field of biological information. According to the invention, a high performance liquid chromatography-tandem mass spectrometry method is adopted to determine the blood concentration of a rivaroxaban taking person, and a DNA sequencing method is adopted to determine the gene polymorphism of related metabolic enzymes CYP3A4 and CYP3A5 and transporters ABCB1 and ABCG2 of the rivaroxaban taking person; collecting data to establish a rivaroxaban group pharmacokinetic model, performing internal verification, and evaluating the stability and prediction performance of the model; in the final PPK model, the influence of the creatinine clearance rate, the ABCB1rs1045642 and the health condition on the clearance rate is the greatest; the experimental verification result shows that the model has good predictability and is accurate and reliable; the method can be applied to an individualized medication prediction model.

The present disclosure provides, inter alia, methods for treating hemophilia A as well as computer-based-systems, including software-based pharmacokinetic model systems, and their use to determine dosing information for subjects who have hemophilia A.

To provide a method and device for predicting plasma concentration transition in combination of multiple drugs, by easily determining Ki, fm in vivo, and making them into a database, since, there has been dynamic prediction using a physiologic medicine speed theory (PBPK) model, as a prediction method of a drug interaction for medical products, however, prediction using an inhibition constant (Ki) of in vitro data and a contribution ratio (fm) of a metabolic enzyme, do not always match increase of clinical AUC.SOLUTION: There is provided a method for determining a parameter of a compartment model from a pharmacokinetic parameter of an interacted drug and interaction drug, then converting the compartment parameter into a PBPK model parameter, then determining by simulation using the PBPK model, a Ki value and fm being AUC increase ratios observed clinically. The acquired parameter is made into a database, and simulation of blood concentration transition of the interacted drug and interaction drug is performed.SELECTED DRAWING: Figure 1

The invention discloses a method for adjusting administration dosage according to adverse reaction risk based on a joint model, and is applied to the field of intelligent medical treatment. In the prior art, the relationship between the sirolimus steady-state valley concentration and the specific adverse reaction cannot be quantified, so that the defect of lack of accurate guidance for clinical medication is caused. Through systematic research, the method determines the individual target valley concentration range through a BKMR model for the first time, obtains individual pharmacokinetic parameters of a patient through a group pharmacokinetic model, and finally determines the medication time and the medication dosage of the patient through Bayesian negative feedback simulation, and the medication time and the medication dosage are used for adjusting a medication scheme. According to the invention, prospective risk prediction of adverse reactions of sirolimus is realized, the treatment safety of children with vascular diseases is remarkably improved, and long-term prognosis of patients is improved.

A method may include training a machine learning model to determine a first pharmacokinetic parameter and a second pharmacokinetic parameter for a molecule. The machine learning model may be trained by at least determining, based at least on an input including one or more pharmacokinetic models associated with the molecule, a first value of the first pharmacokinetic parameter, determining, based at least on the input, a second value of the first pharmacokinetic parameter, and determining, based at least on the first value and the second value of the first pharmacokinetic parameter, a third value of the second pharmacokinetic parameter. The method may also include applying the trained machine learning model to determine, based at least on a sparsely sampled pharmacokinetic model associated with the molecule, the first pharmacokinetic parameter and / or the second pharmacokinetic parameter. Related methods and articles of manufacture are also disclosed.

The invention relates to the field of tumor growth prediction, and discloses a tumor growth prediction method and system based on digital twinning, and the method comprises the steps: constructing a first digital twinning model of brain image data, clinical data and physiological data of a patient; constructing a second digital twinborn model of the blood brain barrier data, the drug interaction data and the dynamic microenvironment data of the patient; determining a first treatment prediction result according to the treatment scheme of the patient through the first digital twinborn model; determining a second treatment prediction result according to the treatment scheme of the patient through a second digital twinborn model; and through a treatment scheme correction model, according to the treatment scheme of the patient, the first treatment prediction result and the second treatment prediction result, determining a correction treatment scheme of the patient. The accuracy of tumor growth prediction is improved through the pharmacokinetic model, interaction mechanism simulation between drugs and dynamic microenvironment parameters.

The invention relates to a pabolizumab population pharmacokinetic model construction method and application thereof. The method comprises the following steps: collecting structured data at least comprising the concentration of pabolizumab in a blood sample; establishing a basic model of group pharmacokinetics; screening covariables based on the structured data to obtain an optimal covariable; and combining the optimal covariable and the basic model to construct and obtain the group pharmacokinetic model. According to the invention, the optimization and adjustment of the drug dosage can be guided, and the safety and effectiveness of treatment can be improved.

A computer system, computer program product and method for determining a probability of attaining a PK-PD target associated with efficacy for a patient that includes a processor obtaining information identifying an infection and based on the information, generating and displaying, by the one or more processors, a list comprising one or more pathogens consistent with the information, the processor then obtaining a first indication designating at least one pathogen from the list comprising one or more pathogens and based on at the obtaining of the least one pathogen, generating a list comprising one or more drug therapies utilized to treat the at least one pathogen. The method also includes the processor obtaining, descriptive information relating to a patient and based on the one or more drug therapies, selecting a pharmacokinetic model and the processor applying the pharmacokinetic model and utilizing the information relating to the patient to determine, for each of the one or more drug therapies, a probability of attaining a PK-PD target associated with efficacy for the patient with the infection.

According to the remazolam target control infusion analysis method and system, a three-chamber model is adopted to construct an individualized pharmacokinetic model, and plasma concentration response of unit dose of remazolam is characterized through the individualized pharmacokinetic model; constructing an infusion pump control model, wherein the infusion pump control model characterizes the plasma drug concentration through a time function; defining a state variable for the infusion pump control model, and calculating the plasma drug concentration state variable at the moment t + delta t according to the plasma drug concentration state variable at the current moment t and the drug infusion amount within the interval from the current moment t to the moment t + delta t; and the infusion pump control model determines the medicine infusion rate required for the plasma medicine concentration to reach the target concentration CT according to the plasma medicine concentration state variable at the current moment t and the plasma medicine concentration state variable at the moment t + delta t. Individual medication can be achieved, cardiovascular adverse events of a patient are reduced, and a comfortable and safe infusion scheme is provided for the patient.

The invention provides a method for predicting the dosage of an antituberculous drug, which comprises the following steps of: establishing a group pharmacokinetic model of the antituberculous drug by adopting a nonlinear mixed effect model, a two-atrioventricular model and a mixed residual model through plasma concentration analysis, and calculating the pharmacokinetic parameters of the corresponding model; and the established model is verified based on a graphical method, a visual prediction test method and a nonparametric bootstrap method, and the steps of stability and prediction capability evaluation and the like are completed. According to the anti-tuberculosis drug population pharmacokinetic model established by the invention, individual pharmacokinetic parameters can be estimated, a specific population administration scheme is optimized, the drug curative effect is improved, the adverse reaction risk is reduced, and individualized administration of the anti-tuberculosis drug is realized.

This invention discloses a dosage analysis method for anesthetic drugs during surgery in patients with hypertension, hyperlipidemia, and hyperglycemia. This method integrates multi-source heterogeneous health data from the patient over the past five years to construct a personalized, structured health record. During anesthesia induction, based on the patient's individualized pharmacokinetic model and assessed drug interaction risks, it calculates and recommends precisely adjusted induction doses. During anesthesia maintenance, it innovatively decodes specific EEG signals to establish a dynamic mapping relationship between neurophysiological characteristics and pharmacokinetics. Based on EEG characteristics reflecting drug sensitivity and pain perception, it automatically and in real-time adjusts the predicted concentration of the target drug, achieving closed-loop precise control based on direct feedback from the central nervous system. The system automatically identifies all medications used by the patient, generates a drug interaction risk assessment report using a massive knowledge base, and dynamically updates the risk level and sends warnings during surgery based on real-time vital signs.

The invention provides an oxytocin injection precise administration method based on physiological pharmacokinetics (PBPK) model optimization, and relates to the technical field of individualized drug administration. According to the method, firstly, individual physiological parameter information of a target receptor is collected, an individual PBPK model is constructed, simulation operation is carried out in combination with drug characteristics of oxytocin, and in-vivo drug distribution under different drug administration schemes is predicted. By evaluating the drug concentration, the drug administration duration and the uterine contraction reaction predicted value of each scheme in the uterine tissue and system circulation, the optimal drug administration parameter combination meeting the drug efficacy and safety requirements at the same time is screened from the drug concentration, the drug administration duration and the uterine contraction reaction predicted value. An injection control command is generated based on the combination, and precise infusion is performed through an injector system with a program control function. According to the method, individualized precise regulation and control based on model driving are achieved, and the safety and clinical effect of oxytocin medication are effectively improved.

The invention discloses a cardiovascular drug dose regulation and control system based on reinforcement learning, and relates to the technical field of medical artificial intelligence, and the system comprises a data acquisition module which collects physiological data, metabolic parameters, a drug interaction matrix and a current drug combination of a patient in real time; the adjustment factor calculation module calculates a drug metabolism rate adjustment factor through a pharmacokinetic model; the interaction modulation module adjusts the interaction intensity according to the adjustment factor; the risk score calculation module calculates the adverse reaction risk of the patient based on the adjusted interaction matrix, the drug combination and the physiological data; the first processing module judges whether the risk score exceeds the standard or not, and if yes, the risk is reduced through medicine replacement or dosage reduction; if the risk score is lower than a second threshold value, the second processing module maintains the current dose, otherwise, a dose adjustment strategy is optimized based on reinforcement learning; according to the method, the medicine dosage adjustment can be more fit with the actual metabolic characteristics of the patient, and the accuracy and individualization degree of treatment are improved.

The invention discloses a medical aid decision-making method and system fusing multiple modes and a deep network, and relates to the technical field of intelligent medical treatment.The method comprises the steps that first data of a user is collected and analyzed, and a physiological stage is judged; and calling a sub-library corresponding to the dynamic feature library, and matching and screening out a first physiological feature with high correlation. Second data are collected, the first physiological features are fused to construct individualized feature vectors, and a feature incidence matrix is generated. Third data are collected in real time, the incidence matrix is combined, the medicine in-vivo process is simulated through a physiological pharmacokinetic model, and an individualized treatment scheme is generated. According to the invention, through the full-process design of dynamic stage determination, multi-mode association mining, real-time dose optimization and continuous evolution iteration, core pain points in early-maturing diagnosis and treatment of children and adolescents are accurately broken, and transformation from an empirical general scheme to a data-driven individualized decision is realized; safer, more accurate and more timely medical support is provided for premature individuals.

The invention discloses an accurate dose control method and system for brucellosis traditional Chinese and western medicine combined medication, and relates to the technical field of medical treatment. According to the method, individualized data of a patient is obtained through a multi-modal data acquisition technology, a population pharmacokinetic-pharmacodynamic model is constructed by using the data, the population pharmacokinetic-pharmacodynamic model comprises a western medicine module, a traditional Chinese medicine module and a coupling interface, and pharmacokinetic modeling of traditional Chinese medicine and western medicine combined medication is achieved. By monitoring the physiological indexes and symptom data of a patient in real time and combining a traditional Chinese medicine syndrome dynamic scoring algorithm and a reinforcement learning dynamic dose adjustment algorithm, the real-time accurate adjustment of the drug dose is realized. In addition, the method further comprises a traditional Chinese and western medicine synergistic effect optimization step, a synergistic index is calculated based on the knowledge graph and the graph attention network, and a dosage optimization rule is formulated, and the implementation of the method is beneficial for improving the treatment effect of brucellosis and reducing side effects.

The application discloses a drug interaction prediction and dose reference information generation method, system and device, and the method comprises the following steps: acquiring parameters of a Bruton's tyrosine kinase inhibitor as a target drug and an antiretroviral drug as an interaction drug; constructing and verifying a basic physiological pharmacokinetic model of each drug; integrating inhibition or induction parameters of the interaction drug on corresponding enzymes, constructing and verifying an interaction prediction model; running the verified model to simulate and calculate predicted exposure data of the target drug when the drugs are used in combination; and generating dose reference information meeting preset bioequivalence conditions by iteratively adjusting dose parameters of the target drug and re-simulating. The application realizes automatic, quantitative prediction and personalized dose scheme generation of specific drug combination interactions, and can provide key decision support for clinical combination drug use.

Provided are a method and system for determining a population pharmacokinetic model of propofol and derivatives thereof. The method comprises determining a formula as a population pharmacokinetic model of a compound of formula (I) or propofol: wherein the formula of the pharmacokinetic parameters in the population pharmacokinetic model of the compound of formula (I) comprises: and the formula of the pharmacokinetic parameters in the population pharmacokinetic model of propofol comprises: formula (I).

The invention discloses an insulin pump control method and system based on blood glucose data, and relates to the technical field of insulin infusion control, and the method comprises the steps: obtaining real-time blood glucose sequence data and historical infusion record data, and carrying out the preprocessing; constructing an insulin pharmacokinetic attenuation model to calculate an in-transit insulin residual activity value; inputting the standardized blood glucose time series data into a Bayesian neural network prediction model to generate prediction uncertainty distribution parameters; calculating a prediction confidence index according to the prediction variance and comparing the prediction confidence index with a threshold value to obtain a confidence judgment result; selecting a dose optimization strategy or a conservative control strategy according to a confidence coefficient judgment result to calculate an insulin infusion dose; infusion is executed, and historical records are updated; the prediction uncertainty is quantified through the Bayesian neural network, the in-transit insulin activity is accurately modeled in combination with the pharmacokinetic model, and the control strategy is dynamically switched according to the confidence, so that the control error amplification caused by prediction misjudgment is effectively avoided, and the delayed hypoglycemia caused by the insulin superposition effect is prevented.

Provided herein are systems and methods for optimizing a biological therapy regimen for a subject. The subject may be a patient diagnosed with an immune mediated inflammatory disease. In some embodiments, the systems and methods may involve inputting patient data into a model to forecast a drug concentration level in a patient and establish a dosing regimen for maintaining a pre-specified threshold drug concentration level in the patient. The pre-specified threshold may be a target concentration level for effective treatment of the immune mediated inflammatory disease in the patient.

The invention relates to the technical field of medical control, and discloses an anesthesia assisting method for promoting postoperative rapid recovery, which comprises the following steps: constructing a basic pharmacokinetic model for a selected anesthetic; intraoperative multi-modal data of a patient are collected in real time; calculating a temperature-metabolism correction coefficient based on the thermodynamic data, and calculating a volume-dilution correction coefficient based on the hemodynamic data; correcting the basic plasma clearance rate in real time by using the temperature-metabolism correction coefficient, and correcting the basic central ventricle distribution volume in real time by using the volume-dilution correction coefficient; the corrected plasma clearance rate and the corrected central ventricle distribution volume are substituted into the basic pharmacokinetic model, and the medicine infusion rate needed for maintaining the preset target concentration is calculated. According to the method, the parameters of the pharmacokinetic model are dynamically corrected according to the real-time thermal dynamics and hemodynamics data, medicine accumulation is effectively avoided, and the postoperative awakening time is shortened.

A computer implemented method for determining a dosage of Cagrisema for administering to a patient for the treatment of obesity, the method comprising: receiving patient data relating to a patient, wherein the patient data includes patient weight data; processing the patient data including the patient weight data with a dosage calculator to determine the dosage of Cagrisema for administering to the patient wherein the dosage calculator is derived from a pharmacokinetic, PK, model; and indicating the dosage.

A system and method for intelligently controlling an individualized infusion is described. A machine learning model is trained to simulate progression of a plurality of conditions across a patient population under a care of a plurality of physicians, and to determine how the progression of each condition is affected by respective medication decisions made by one or more physicians regarding (i) dosing of one or more medications and (ii) a respective pharmacokinetic model of the one or more medications. A condition to be treated is selected for a patient and the system monitors patient biomarkers and determines, in real time, a dose of a medication to administer to the patient to maintain at least one of the biomarkers in a predetermined effective range. The system causes an infusion pump to administer the dose of the medication to the patient and adjusts the dose continuously based on reevaluation of the biomarkers.

This invention relates to the field of vancomycin pharmacokinetic technology, specifically to the design of a vancomycin clearance prediction scheme based on a VPB ensemble model. This method, based on an ensemble learning strategy, constructs a blending ensemble model to predict vancomycin clearance in adult Chinese patients. First, a variational autoencoder is used to amplify the original sample data to increase data diversity. Then, a particle swarm optimization algorithm is introduced to optimize the parameters of multiple base learners, and the prediction results of the optimized base learners are used as new feature inputs. Finally, a support vector regression machine is used as a meta-learner to integrate and model the above features, forming the final vancomycin clearance prediction model. The VPB model constructed in this invention achieves a determination coefficient R² exceeding 0.9 on both the test and training sets, demonstrating superior prediction accuracy compared to population pharmacokinetic models.

Provided are a method and system for determining a population pharmacokinetic model of propofol and a derivative thereof. The method comprises determining a population pharmacokinetic model of a compound of formula (I) or propofol, wherein an equation of pharmacokinetic parameters in the population pharmacokinetic model of the compound of formula (I) comprises: CLi=exp(4.20÷0.349·log(WT / 63.9)−0.749·log(TP / 72.4)+0.238·SITE+ηCL,i); an equation of pharmacokinetic parameters in the population pharmacokinetic model of propofol comprises: CLi=exp(4.56÷ηCL,i).

This invention relates to the field of medical information technology, specifically disclosing an intelligent follow-up and re-examination reminder system for outpatients throughout their entire treatment cycle. Targeting the management of chronic brain diseases, this invention integrates personalized pharmacokinetic modeling and a cross-validation mechanism of subjective and objective data. By continuously collecting and analyzing patients' micro-movement and vital sign data, combined with an individualized drug concentration theoretical model, it achieves accurate assessment of changes in the patient's condition. Simultaneously, it utilizes subjective and objective cross-validation to ensure data reliability and adopts an event-driven model, transforming traditional periodic follow-up into real-time response management based on key pathological events. The system also features an intelligent re-examination scheduling function, which can automatically adjust the re-examination plan and generate emergency re-examination reminders based on changes in the patient's condition and drug efficacy assessment results, forming a fully automated closed-loop management process. This invention improves the accuracy, timeliness, and patient satisfaction of chronic brain disease management, bringing a new breakthrough to the field of medical information technology.

The invention relates to the technical field of biological medicine, discloses a method and a system for determining the dose of an exogenous blood coagulation factor, and aims to solve the problems of large individual dose prediction deviation and adjustment lag caused by dependence on a population pharmacokinetic mean value and lack of dynamic feedback and multi-source data fusion capability in the prior art. The method comprises the following steps: collecting physiological parameters and gene information of a patient, and inputting an individualized pharmacokinetic model to generate a metabolic curve; in combination with a clinical treatment target, an initial dose is calculated through a multi-constraint numerical solution algorithm. According to the application, by integrating individual physiological and genetic characteristics, dynamic clinical feedback and an international guide knowledge graph, a closed-loop optimization system with self-learning ability is constructed, accurate and intelligent recommendation of the blood coagulation factor dose is realized, and the treatment safety and individualized level are improved.

The invention relates to the technical field of nuclear medicine, and discloses a nuclear medicine medicine intelligent injection robot system which comprises a multi-source physiological parameter acquisition module used for acquiring early medicine distribution dynamic data after injection; the physiological pharmacokinetic parameter real-time estimation module is used for calculating key pharmacokinetic parameters based on the drug distribution early-stage characteristics; the multi-organ synergistic metabolism network module is used for establishing a complete pharmacokinetic model; the dysfunction early-stage detection module is used for identifying an abnormal drug metabolism mode; the multi-level safety intervention execution module is used for automatically implementing intervention measures of different levels; the personalized alternative scheme generation module is used for generating and executing a personalized alternative injection scheme; according to the method, the potential dysfunction of the patient can be recognized in the early stage of radioactive drug injection and intervened in time, the safety of nuclear medicine examination is improved, the occurrence rate of adverse reactions is reduced, and a personalized precise administration scheme is provided for the patient with liver and kidney dysfunction.

The application discloses a genetic polymorphism-based oxcarbazepine quantitative pharmacological model and a construction method thereof, and belongs to the field of pharmacokinetics. The model construction method is characterized by the following steps: collecting steady-state blood drug concentration data and clinical data of epilepsy children patients, adopting a nonlinear mixed effect model method to establish a population pharmacokinetic model of an active metabolite of oxcarbazepine, and quantitatively investigating the influence of physiological factors, combined medication and genetic factors on pharmacokinetic characteristic parameters of the drug; and finally, the final model is internally verified and evaluated by using a goodness-of-fit diagram, a bootstrap method and an intuitive prediction test. The quantitative pharmacological model constructed by the application has stable and accurate prediction performance; the body weight and the genetic polymorphism ABCC2rs2273697 are determined as effective covariates influencing MHD CL / F; and an oxcarbazepine dose optimization scheme is established based on the body weight and the genotype of the patients, so that the treatment effect of the oxcarbazepine is improved, and the occurrence of adverse reactions is avoided.