44 results about "Medication risk" patented technology

The invention discloses an interpretable clinical decision support system based on label generation and a knowledge graph. The method comprises the following steps: based on a breast cancer domain knowledge enhanced version Qwen-BrCaAdapt of a general large language model Qwen, analyzing an unstructured medical record text of a patient, and generating a structured result containing tags, values, evidences and explanations; calculating a reasoning label through a path matching engine by utilizing an editable structured path rule table, and matching a candidate treatment scheme according to the reasoning label; and taking the matched treatment scheme as a central node, calling a medical knowledge graph to bind entity information including clinical evidence, recommendation levels, medical insurance information, medication risks, usage and dosage, and generating a traceable JSON structure and a visual report. The method has the beneficial effects that the accuracy and efficiency of tag generation in the breast cancer field are improved, the rule maintenance cost is reduced, the interpretability and traceability of a clinical decision scheme are enhanced, and the acceptability of a doctor to a recommendation result is improved.

The invention relates to the technical field of medical care informatics, in particular to a nephropathy medication interaction risk screening system which comprises a data acquisition unit, an SOC chip processing and analysis unit, a risk early warning unit and a man-machine interaction and communication unit. Through multi-source data access, dynamic weight scheduling and Kalman filtering fusion correction, accurate and on-demand acquisition of nephropathy core indexes is realized, and real-time intelligent discrimination of personalized medication risks is realized by relying on knowledge base support, adaptive path adjustment and a safe atomization updating mechanism, so that the risk of the nephropathy is accurately determined. Therefore, the problems that traditional system data acquisition lacks specialized pertinence, risk assessment personalization is insufficient, and model updating is lagged are effectively solved, and the accuracy and timeliness of nephropathy medication interaction risk screening are remarkably improved.

The invention relates to the technical field of medical information, in particular to a medication safety management method, device and equipment and a readable medium. The method comprises the following steps: acquiring electronic prescription data containing medicine names, specifications, dosage, usage, medication time and basic information of patients; performing multi-dimensional risk analysis on the electronic prescription data based on the medication safety knowledge base, including incompatibility analysis, dose safety analysis, medication time conflict analysis and special usage suitability analysis, and generating medication risk prompt information and a personalized medication guidance scheme; the medication guidance scheme comprises a text abstract and instruction data used for generating a two-dimensional code; driving label printing equipment to print the intelligent medication two-dimensional code; a detailed text, a voice interpretation file or a medicine use demonstration video file in the medicine use guidance scheme is associated with the two-dimensional code and stored in a server; a user can access the multimedia guidance file by scanning the two-dimensional code through terminal equipment, so that the medication compliance and safety of a patient are improved.

The invention discloses a medical prescription auditing and medication safety management and control method, device and equipment and a storage medium, and relates to the technical field of medical informatization and health big data, the method comprises the following steps: obtaining drug information, patient allergy history and multi-dimensional health data in a target prescription, and constructing a prescription data set; in combination with a medicine knowledge base and a taboo database, intelligent verification is carried out on the medication rationality of the prescription by utilizing a Duros rule engine and a graph neural network model, and a verification result and verification detail data are output; if the verification result is unreasonable, marking the prescription as a risk prescription, generating a medication risk assessment report and a prescription modification suggestion based on verification detail data, and pushing the report and the suggestion to a corresponding doctor terminal; and if the verification result is reasonable, generating personalized medication guidance through prescription-patient feature matching, and sending the personalized medication guidance to the doctor terminal, the patient terminal and the pharmacy terminal. According to the application, intelligent prescription checking and medication safety guarantee can be realized through risk assessment and personalized adaptation.

The invention relates to the field of medical health and artificial intelligence, and discloses a tumor-chronic disease co-disease medication dynamic risk early warning method fusing AI and a rule engine, and the method comprises the steps: S1, collecting multi-source data of a co-disease patient, and generating unified feature data; s2, constructing a risk prediction model comprising a rule engine and a few-sample learning model; the rule engine performs preliminary judgment on the drug use risk; carrying out refined risk probability prediction on the few-sample learning model by utilizing a global category representation and feature matching mechanism constructed by the few-sample learning model; carrying out weighted fusion on prediction results of the two; s3, dynamically optimizing parameters of the few-sample learning model by adopting a meta-heuristic optimization algorithm; and S4, based on the optimized risk prediction model, carrying out real-time risk early warning on the medication data of the co-patient. According to the method, the technical problems of difficulty in prediction of a few-sample scene, low parameter optimization efficiency, unreliable early warning result and the like are effectively solved, and real-time monitoring, accurate evaluation and individualized early warning of the medication risk of the co-patient are realized.

This invention discloses a method, apparatus, device, and storage medium for medication risk assessment during pregnancy, relating to the interdisciplinary fields of medical information technology and clinical pharmacy. The method includes: receiving patient information and proposed medication regimen information, whereby the patient information includes gestational age and information on multiple comorbidities; calling the corresponding gestational age adaptive risk weight matrix based on gestational age, weighting the patient features to generate a weighted feature vector, and inputting this vector into a machine learning model to obtain an initial medication risk score; based on a constructed heterogeneous knowledge graph, using entities corresponding to multiple comorbidities and medication regimen information as query starting points, performing multi-hop reasoning to determine the existence and severity of conflicting paths; if a conflicting path is detected, revising the initial medication risk score according to the severity of the conflict to generate a final risk score. This application enables individualized, interpretable, and evidence-based intelligent risk assessment of proposed medication regimens for pregnant women with multiple comorbidities.

The invention belongs to the technical field of medical information, and particularly relates to a newly diagnosed HIV infected person antiviral treatment intelligent decision support system which comprises a multi-source data integration module, a medicine knowledge module, an individualized decision support module, an interactive output module, a knowledge optimization module and a safety and privacy protection module. The system replaces doctors to query and integrate patient data across multiple systems, clinical time is saved, key information omission is avoided, comprehensive data support is provided for treatment decisions, experience decisions are converted into systematic analysis and graded risk prompts are generated by means of an individualized decision support module, scheme deviation is effectively reduced, the medication risk is reduced, and the treatment efficiency is improved. The method assists the basic level in improving the treatment normalization, allows doctors to input new experience and new achievements summarized in practice into the system after double-blind auditing, and provides continuously iterative knowledge support for the scientificity of the antiviral treatment decision of the newly diagnosed HIV infected person.

The embodiment of the invention discloses a Crohn disease longitudinal queue course prediction system based on time perception Transform, and relates to the technical field of medical data processing, the system comprises a data preprocessing module, an input embedding layer, a Transform encoder and a multi-task multi-time window prediction header, the system breaks through the limitation that only baseline data is used for prediction of a traditional model, and the prediction efficiency is improved. According to the method, the full-cycle longitudinal data (such as inflammation indexes and medication records of each treatment) of the patient from the morbidity to the prediction can be integrated, and the disease progress, operation and medication risks of 1 year / 3 years / 5 years can be dynamically output. And reference is provided for clinicians.

The invention discloses an interactive safe medication suggestion method and system oriented to medicine-diagnosis cross check, and belongs to the technical field of medical artificial intelligence and clinical decision support (CDSS). According to the method, an intelligent probe is implanted into a writing interface of an electronic medical record (EMR), so that full-dimensional context information such as structured diagnosis, unstructured texts (such as chief complaint) and past medicine history of a patient is sensed in real time. At the moment when a doctor inputs a prescription, the system concurrently executes'drug-disease 'taboo verification and'drug-drug' interaction verification by using a pre-constructed heterogeneous medical knowledge graph. Once a potential medication risk is detected, the system immediately triggers a blocking mechanism, and automatically generates compliant alternative drug suggestions which are pharmacologically equivalent and conform to the physiological characteristics of the current patient based on graph embedding vector similarity and a multi-objective optimization sorting algorithm.

Embodiments of the present disclosure relate to the technical field of medical data processing, and specifically to a nutritional preparation medication information processing method, device, equipment and medium. The main steps of the foregoing method include: in response to an audit request for a medication prescription, retrieving and obtaining clinical diagnosis data corresponding to the medication prescription, extracting a disease keyword from the clinical diagnosis data, matching and analyzing the disease keyword with preset parenteral nutrition indication information to obtain a matching result, when the matching result indicates a matching success, auditing the medication prescription according to a first medication standard, and when the matching result indicates a matching failure, determining a second medication standard according to a nutritional risk score, gastrointestinal disorder information and a preset decision matrix, and auditing the medication prescription according to the second medication standard. The foregoing method can improve the efficiency of prescription auditing, improve the accuracy and rationality of the nutritional preparation medication prescription audit result, and reduce the medication risk of the nutritional preparation medication prescription.

The embodiment of the invention provides an autonomous medicine delivery and safety monitoring method and robot, and the method comprises the steps: responding to a received medicine delivery instruction, and preloading a historical complexion health index database of a user; controlling the robot to move to a target user position of the user, and performing identity verification at the target user position; when the identity verification is passed, calling a personalized medication scheme and a historical complexion health index database of the user; collecting blood pressure, heart rate and body temperature data of the user to obtain a current-day complexion health index of the user; comparing the current-day complexion health index with a historical complexion health index database to obtain the complexion health degree of the user; fusing the complexion health degree, the physiological data and the drug taboo information to generate a drug use risk result; and adjusting the personalized medication scheme based on the medication risk result, and dynamically generating and outputting target medication guidance information. According to the method, the accuracy, the interactive experience and the safety of the medicine delivery service are improved.

The invention discloses a pharmacogenomics report generation method and device, a medium and a product, and relates to the field. The method comprises the following steps: in response to the completion of a drug genome experiment of a first object, obtaining experimental result data of the drug genome experiment, and determining experimental result interpretation data based on a first drug gene association database; inputting the experimental result interpretation data, the object attribute information corresponding to the first object, the medical record information and the first medicine information into a pre-trained medication risk assessment model to obtain a medication risk assessment result of the first object; and generating a pharmacogenomics report of the first object based on the medication risk assessment result, the experimental result interpretation data, the object attribute information, the medical record information and the first drug information. According to the technical scheme of the invention, the problems of high threshold and low efficiency of the existing pharmacogenomics report generation are solved, the pharmacogenomics report can be automatically generated, the accuracy of the report content is improved, and the report generation cost is reduced.

The application discloses a model for predicting lactation medication risk, wherein when the model is used to predict the lactation medication risk, human trials are not needed for the to-be-tested drug, the lactation risk can be predicted based on the molecular structure of the to-be-tested drug, and when the lactation medication risk is predicted, the ROC_AUC value of 10-fold cross-validation reaches 0.80, indicating that the model has excellent prediction performance and generalization ability. The model can provide a rapid lactation medication risk evaluation tool for doctors and pharmacists, assist in formulating a safe medication scheme, avoid unnecessary weaning, reduce the adverse reaction risk of breastfed infants, and improve the medication safety level of mothers and infants. Meanwhile, the model can be combined to accurately evaluate the early safety of a new drug, identify and avoid potential lactation medication risks, guide molecular optimization in the new drug research and development process, and reduce the research and development cost and time.

The invention discloses a construction method and application of a safety evaluation risk prediction model after child medication marketing, and the method comprises the steps: constructing a three-level index system, and determining the weight of each level of index through an analytic hierarchy process; based on the three-level index system, determining a risk feature set, constructing a three-level model architecture, and performing model training by adopting a machine learning algorithm; collecting multi-source real world data, and establishing a standardized data pool; the performance of the model is improved through hyper-parameter optimization and integrated learning, the performance of the model is verified and evaluated by adopting internal cross validation and an external independent data set, and the transparency of the model is enhanced through an interpretability technology; and establishing a dynamic updating mechanism, deploying the model as a cloud API service, and realizing risk prediction and early warning functions. According to the invention, multi-source real world data can be effectively integrated, the children medication safety risk can be accurately identified, the method is used for safety evaluation after children medication is listed, and the method is of great significance to supplement clinical test insufficiency before children medication is listed, reduce medication risk and guarantee children medication safety.

The present invention discloses a method and system for dynamic risk assessment of medication for elderly patients, relating to the technical field of medication risk assessment. The method comprises collecting static factor data and dynamic factor data of elderly patients, pre-processing the collected static factor data and dynamic factor data, and generating a feature vector for risk assessment; calculating a comprehensive risk score based on the feature vector using preset assessment rules; comparing the comprehensive risk score with a preset risk grading threshold to determine the medication compliance risk level of the elderly patients. The system comprises data collection, pre-processing, risk assessment, and grading modules. The present application realizes multi-dimensional risk assessment by integrating static and dynamic data, thereby improving the comprehensiveness and timeliness of medication compliance risk assessment for elderly patients and providing technical support for medication intervention.

The invention belongs to the technical field of artificial intelligence, and relates to a data processing method, which comprises the following steps: acquiring multi-dimensional physiological data and drug combination data of a target patient; calling a target prediction model issued by the central server; performing prediction processing on the multi-dimensional physiological data and the drug combination data based on the target prediction model to obtain corresponding adverse reaction evaluation data; judging whether the adverse reaction evaluation data is smaller than a preset dynamic safety threshold value or not; if yes, target drugs corresponding to the drug combination data are grabbed based on a drug dispensing tool; and generating medicine taking information corresponding to the target medicine, and displaying the medicine taking information. The invention further provides a data processing device, computer equipment and a storage medium. In addition, the medicine taking information can be stored in the block chain. The method can be applied to a medication management scene in the field of medical science and technology, and improves the efficiency and accuracy of medication risk assessment processing and medicine distribution processing.

The embodiment of the invention provides a method and a device for detecting medication safety, and aims to detect the medication safety in medication suggestions and obtain the medication suggestions and user health portraits. The method comprises the following steps: acquiring a drug name in a drug use suggestion, and then aligning the drug name with a standard drug name in a drug knowledge base based on multiple alignment approaches; thirdly, through user portrait information and the aligned standard medicine names, an information graph at least containing disease entities, medicine entities and the incidence relation between the disease entities and the medicine entities is constructed; and based on the information graph, performing graph retrieval in a pre-constructed drug use knowledge graph, and determining whether the drug use suggestions have drug use safety risks or not by using drug use risk knowledge in the drug use knowledge graph. Therefore, the drug use risk in a complex scene can be identified.

This invention discloses a method for medication risk warning and dynamic intervention using a smart pillbox for elderly patients with chronic diseases, relating to the fields of intelligent medical devices and chronic disease management technology. The method first constructs four types of chronic disease knowledge graphs: medication behavior, physiological indicators, drug interactions, and environmental conditions. Then, it processes the graphs using a GNN module with a GRU-like gating mechanism, weightedly fusing multi-time-step features using a time-step attention mechanism, and integrating similar patient features based on Jaccard similarity to generate comprehensive risk features. During the training phase, the risk level and type are output after feature optimization using a collaborative attention mechanism. In the inference phase, a similarity propagation mechanism is used to address the cold-start problem for newly enrolled patients, matching a three-level intervention rule base to generate personalized strategies, and iteratively optimizing the model based on intervention feedback. This invention achieves proactive and precise warning and dynamic intervention, improving risk assessment performance and patient medication adherence in different scenarios.

This application provides a method, device, and electronic device for assessing medication risks during pregnancy. Through automated knowledge graph querying and risk calculation, a risk assessment report can be quickly generated, reducing the time and cognitive load required for doctors to manually review literature and memorize complex rules. Simultaneously, it can match the current stage of medication risk to the patient's specific gestational age and perform comprehensive, real-time risk assessment based on the pregnant patient's real-time physiological indicators. This avoids the shortcomings of risk assessments that fail to consider gestational changes and individual patient differences, improving the accuracy of risk assessment. Furthermore, by acquiring medication information and physiological indicators, it can continuously and in real-time calculate the risk of medication use based on the patient's actual medication behavior and changes in physiological state during medication. Based on the real-time risk assessment results, medication guidance can be provided to patients, enhancing their understanding of the medication regimen and reducing the risks of medication use during pregnancy.

The embodiment of the invention relates to the technical field of medical data processing, in particular to a nutrition preparation medication information processing method and device, equipment and a medium. The method mainly comprises the steps that in response to an auditing request for a medication prescription, clinical diagnosis data corresponding to the medication prescription are retrieved and obtained, disease keywords in the clinical diagnosis data are extracted, matching analysis is conducted on the disease keywords and preset parenteral nutrition indication information, and a matching result is obtained; when the matching result shows that matching succeeds, the medication prescription is audited according to the first medication standard, and when the matching result shows that matching fails, a second medication standard is determined according to the nutrition risk score, the gastrointestinal disorder information and a preset decision matrix, and the medication prescription is audited according to the second medication standard. By adopting the method, the prescription checking efficiency can be improved, the accuracy and rationality of the nutrition preparation medication prescription checking result can be improved, and the medication risk of the nutrition preparation medication prescription can be reduced.

The invention relates to the technical field of clinical medication, and discloses a clinical medication intelligent reminding system which comprises an information acquisition module, a data preprocessing module, a feature fusion module, a medication execution module and an optimization module. Through cooperative operation of an information acquisition module, a data preprocessing module and a feature fusion module, the system does not need to depend on a medicine identification technology, but binds a unique ID of a patient through an RFID wristband, and combines rapid processing of real-time physiological data through edge calculation, so that accurate association of patient information and a medication plan is realized, and the accuracy of the medication plan is improved. Meanwhile, the reminding sequence is dynamically optimized based on the improved Dijkstra algorithm, medicine identification errors are avoided, the timeliness and adaptability of clinical medication reminding are remarkably improved, and the medication risk caused by information mismatching is effectively reduced.

The invention relates to a method for applying a medical big language model of an integrated knowledge graph to drug analysis and diagnosis support. The method comprises the steps of performing streaming analysis and entity recognition on a structured pharmaceutical database file, generating a drug record set containing standardized biomedical entity annotations, and constructing a graph structure knowledge base and a vector index base in parallel; receiving a natural language query, extracting drugs and disease entities and mapping the drugs and disease entities into standardized identifiers; synchronously retrieving the structured evidence set and the text evidence set; assembling an enhanced prompt text containing the task instruction, the verified evidence and the query according to the template; and inputting the large language model subjected to biomedical task fine tuning, and generating a binding response. By adopting the method, the problems of static stiffness, pure language model illusion and insufficient interaction of a structured knowledge base of a traditional system can be solved, reliable decision assistance is provided for replacement treatment and interaction review under the condition of drug shortage, and the drug use risk is reduced.

The invention relates to the technical field of drug recommendation, in particular to an adverse drug reaction advanced prediction and substitution recommendation system, which comprises a data acquisition module for acquiring patient state data, the patient state data comprises basic information, used drug information, current drug information and latest examination index values; the risk prediction module is used for inputting the collected patient state data into a pre-trained risk prediction model to obtain a medication risk result; if the medication risk exists, inputting the patient state data into a pre-trained adverse reaction causal analysis model to obtain an adverse reaction causal pair, the adverse reaction causal pair comprising causes and results; the alternative link analysis module can generate alternative link analysis information containing scores and calculation modes of all metabolic pathways of all drugs in alternative drug use information, a recommendation basis is clearly presented, medical staff can visually verify risk relevance and alternative rationality, and trust to the system is established.

The invention discloses a drug sensitivity test drug recommendation system, method and device based on an AI large model and a medium, relates to the technical field of drug sensitivity tests, is applied to a computer device, and comprises a medical object information collection module used for collecting medical feature information from initial medical information of a medical object by using a feature information extraction AI large model; the medical feature information comprises basic information of a medical object, current and past drug allergy information and disease information; the drug recommendation module is used for determining a preliminary drug recommendation result according to a drug sensitive test result of the medical object and a preset expert database constructed based on a drug use industry standard; the medication recommendation module is used for inputting the medical feature information, the preliminary medication recommendation result and a medication database into a medication recommendation AI large model and outputting a target medication recommendation conclusion; the target drug use recommendation conclusion at least comprises recommended drugs, drug use risk information of the recommended drugs and drug use details. And more accurate and practical drug recommendation is realized.

This invention relates to the field of medical and health information technology and discloses a home-based pain monitoring system for malignant tumor patients. The invention collects various data related to home care of malignant tumor patients, forming pain datasets, medication datasets, and vital sign datasets. Based on these three datasets, pain risk indices, medication risk indices, and vital sign risk indices are obtained. These are then weighted and summed to obtain a comprehensive risk index. Effective correlation and collaborative analysis of multi-dimensional data improve the accuracy of the comprehensive risk index. The system determines whether to issue an alert based on the comprehensive risk index. If the comprehensive risk index reaches a threshold, three different levels of alerts (red, orange, and yellow) are issued and sent to both the patient-side interaction module and the medical staff-side interaction module. Upon receiving the alert, medical staff immediately review the patient's current condition report, analyze it, and receive timely improvement suggestions to help the patient improve their current condition, thus improving the efficiency of home care.

The invention relates to the technical field of medical record management, in particular to a patient medication risk multi-terminal intelligent early warning system based on full-process collaboration, which comprises an attribute vector mapping module, an allergy risk operation module, a data state monitoring module, a real-time abnormal fusing module and a doctor's advice interaction authentication module. According to the method, chemical components of drugs are analyzed, orthogonalized attribute vectors are constructed, discrete allergy history texts are converted into computable sensitization feature dimensions, the allergy risk hierarchy is accurately quantified by utilizing logic operation among the vectors, a finite-state machine architecture is introduced to establish a full-life-cycle risk monitoring link, and the risk monitoring accuracy is improved. When it is monitored that an abnormal signal of allergen data triggers a self-checking reevaluation mechanism and reverse transition of a logic state is executed, a system risk state is forcibly locked, the physical operation authority and the identity authentication level of terminal equipment are dynamically adjusted in combination with a real-time evaluation numerical value, an execution path of high-risk drug use operation is blocked on the physical level, and the safety of the system is improved. And active dynamic fusing defense is realized.

The invention discloses a medication data supervision and evaluation system based on artificial intelligence, and belongs to the technical field of medication data supervision. The method and the device are used for solving the technical problems of poor active supervision reliability and poor active optimization iteration effect of drug administration data supervision evaluation in an existing scheme. Credible label values in the standardized matrix can provide clear input for subsequent risk assessment; through weighted integration of multi-dimensional factors of dosage, solvent and pathology, quantitative processing of medication risks is realized, a matching degree algorithm based on historical optimal prescriptions and real-time guide update enables a system to dynamically adapt to clinical changes, and through construction of a three-dimensional evaluation tensor, complex data can be converted into visual scores, so that the accuracy of evaluation is improved. Unnecessary intervention of low-risk prescriptions is reduced; the credible label value, the medication risk index and the rule adaptation degree are subjected to conjoint analysis and judgment, and a hierarchical optimization mechanism is dynamically triggered according to a judgment result, so that active optimization management on implementation of an existing supervision and evaluation scheme is realized.

The invention provides a self-adaptive digital comprehensive intervention method and system for schizophrenia with metabolic syndrome patients, and relates to the technical field of medical health management. Metabolic indexes such as diet, exercise, body weight, blood pressure and blood sugar are collected, and a metabolic risk assessment model is constructed in combination with drug use types and doses in an electronic medical record so as to determine a metabolic risk level; according to a cognitive score self-adaptive interface presentation mode, the intervention scheme is split into micro-tasks to be pushed and executed; when the patient completes the micro-task, a result is synchronized to the family supporter, and integral incentive is carried out; in the follow-up visit stage, metabolic index changes are continuously monitored, abnormal trends are recognized, early warning reports are generated, and the early warning reports are pushed to medical staff after being confirmed by patients so as to trigger timely medical intervention. According to the invention, closed-loop intervention integrating metabolism management, medication risk adjustment, cognitive adaptation interaction and family support excitation is realized, and the accuracy and effectiveness of metabolism risk control are improved.

The embodiment of the invention provides a children sirolimus administration dosage prediction method, equipment, a medium and a program product, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring prediction parameter information of a to-be-detected sample, wherein prediction parameters comprise weight, age, platelet count and creatinine; inputting the prediction parameter information into the dose prediction model, and calculating the predicted dose of sirolimus; the predicted dose is the daily average dose in the stable treatment period. The application develops an administration dosage prediction model aiming at three clinical problems of dosage error caused by development dynamics, high-risk group medication risk and passive decision mode in children sirolimus administration.