CN117457215A - Pediatric drug complications monitoring system - Google Patents
Pediatric drug complications monitoring system Download PDFInfo
- Publication number
- CN117457215A CN117457215A CN202311753319.7A CN202311753319A CN117457215A CN 117457215 A CN117457215 A CN 117457215A CN 202311753319 A CN202311753319 A CN 202311753319A CN 117457215 A CN117457215 A CN 117457215A
- Authority
- CN
- China
- Prior art keywords
- module
- analysis
- drug
- risk
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000003814 drug Substances 0.000 title claims abstract description 187
- 229940079593 drug Drugs 0.000 title claims abstract description 154
- 238000012544 monitoring process Methods 0.000 title claims abstract description 95
- 238000004458 analytical method Methods 0.000 claims abstract description 119
- 208000024891 symptom Diseases 0.000 claims abstract description 91
- 238000011282 treatment Methods 0.000 claims abstract description 82
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 78
- 238000005516 engineering process Methods 0.000 claims abstract description 68
- 238000011156 evaluation Methods 0.000 claims abstract description 64
- 201000010099 disease Diseases 0.000 claims abstract description 60
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 60
- 238000003909 pattern recognition Methods 0.000 claims abstract description 49
- 230000004044 response Effects 0.000 claims abstract description 48
- 206010013710 Drug interaction Diseases 0.000 claims abstract description 40
- 238000012502 risk assessment Methods 0.000 claims abstract description 40
- 238000005259 measurement Methods 0.000 claims abstract description 23
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 claims abstract description 21
- 238000012300 Sequence Analysis Methods 0.000 claims abstract description 21
- 238000006243 chemical reaction Methods 0.000 claims abstract description 21
- 206010061623 Adverse drug reaction Diseases 0.000 claims abstract description 18
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 14
- 238000003058 natural language processing Methods 0.000 claims abstract description 14
- 238000003066 decision tree Methods 0.000 claims abstract description 12
- 238000007619 statistical method Methods 0.000 claims abstract description 12
- 230000007787 long-term memory Effects 0.000 claims abstract description 7
- 238000010191 image analysis Methods 0.000 claims abstract description 6
- 230000006403 short-term memory Effects 0.000 claims abstract description 5
- 230000000694 effects Effects 0.000 claims description 76
- 238000001514 detection method Methods 0.000 claims description 33
- 230000036541 health Effects 0.000 claims description 31
- 230000005856 abnormality Effects 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 26
- 238000007405 data analysis Methods 0.000 claims description 20
- 230000003993 interaction Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 15
- 238000012482 interaction analysis Methods 0.000 claims description 15
- 238000007418 data mining Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 11
- 206010061818 Disease progression Diseases 0.000 claims description 10
- 230000005750 disease progression Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000013461 design Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 8
- 238000005065 mining Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 7
- 238000011002 quantification Methods 0.000 claims description 6
- 238000011269 treatment regimen Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000011221 initial treatment Methods 0.000 claims description 5
- 230000015654 memory Effects 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000013477 bayesian statistics method Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 4
- 210000004369 blood Anatomy 0.000 claims description 4
- 230000001364 causal effect Effects 0.000 claims description 4
- 238000007635 classification algorithm Methods 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000006740 morphological transformation Effects 0.000 claims description 4
- 230000036961 partial effect Effects 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000000611 regression analysis Methods 0.000 claims description 4
- 230000001932 seasonal effect Effects 0.000 claims description 4
- 238000010206 sensitivity analysis Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000012512 characterization method Methods 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 3
- 230000003902 lesion Effects 0.000 claims description 3
- 230000002265 prevention Effects 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 230000002829 reductive effect Effects 0.000 abstract description 2
- 230000008676 import Effects 0.000 description 7
- 238000012360 testing method Methods 0.000 description 4
- 238000010921 in-depth analysis Methods 0.000 description 3
- 238000012731 temporal analysis Methods 0.000 description 3
- 238000000700 time series analysis Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 206010067671 Disease complication Diseases 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- 239000000090 biomarker Substances 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000890 drug combination Substances 0.000 description 1
- 238000002651 drug therapy Methods 0.000 description 1
- 230000008821 health effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/26—Discovering frequent patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Pharmacology & Pharmacy (AREA)
- Chemical & Material Sciences (AREA)
- Biophysics (AREA)
- Medicinal Chemistry (AREA)
- Molecular Biology (AREA)
- Toxicology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of medical monitoring, in particular to a pediatric drug complication monitoring system, which comprises a symptom analysis module, a drug response evaluation module, a complication mode identification module, a drug interaction prediction module, a risk measurement module, a dynamic disease monitoring module, a personalized treatment scheme module and a drug side effect tracking module. According to the invention, natural language processing and pattern recognition are combined, the accuracy and efficiency of symptom analysis are improved, a decision tree and a probability statistical method predict drug reaction, misdiagnosis is reduced, a convolutional neural network and an image analysis technology accurately identify a medical image complication pattern, diagnosis accuracy is improved, an Apriori algorithm predicts drug interaction, risks are prevented, a Bayesian network and a risk assessment model quantify the complication risks, accurate risk assessment is provided, long-term and short-term memory network and a time sequence analysis technology dynamically monitor disease progress and complication risks, and a comprehensive pediatric drug complication monitoring system is constructed.
Description
Technical Field
The invention relates to the technical field of medical monitoring, in particular to a pediatric drug complications monitoring system.
Background
The technical field of medical monitoring is a field which is focused on monitoring the health condition and treatment response of patients by various technical means. Medical monitoring techniques are particularly important in pediatric applications because children react differently to drugs than adults and are more susceptible to drug side effects and complications. This area encompasses a variety of technologies ranging from basic vital sign monitoring to highly complex biomarker analysis. With the advancement of technology, medical monitoring devices have become more accurate, portable, and even capable of remote monitoring, thereby providing real-time data to doctors, helping them to better understand the health and therapeutic effects of patients.
Among other things, pediatric drug complications monitoring systems are systems designed to monitor and record the adverse effects and complications that occur in children during drug therapy. The main purpose of this system is to ensure the safety and effectiveness of the drug treatment, especially in pediatric treatments. By monitoring the drug response in real time, the system can identify any adverse reaction or potential health risk in time, so that doctors can quickly take measures, adjust the treatment scheme or perform necessary interventions. The ultimate goal is to reduce drug-related complications and improve the overall safety and effectiveness of the treatment. The system is typically implemented by integrating various sensors and monitoring devices. These devices can collect and analyze physiological data of the infant in real time, such as heart rate, blood pressure, respiratory rate, and other vital signs affected by the drug. In addition, the system includes integration of medication management records, patient symptom logs, and laboratory test results.
Conventional pediatric drug complications monitoring systems suffer from several drawbacks. The traditional system often depends on experience judgment of doctors in the aspect of symptom analysis, and lacks efficient technical support, so that symptom analysis is not accurate enough, and misdiagnosis risk is increased. Secondly, the assessment method for the drug response is not advanced enough, the response caused by the drug is difficult to accurately predict, and the risk of the patient for medication is increased. Conventional systems often lack effective image analysis tools in the identification of complication patterns, resulting in inaccuracy or delay in diagnosis. The prediction of drug interactions is not accurate enough and the risk brought by drug interactions cannot be effectively prevented. The lack of quantitative methods in terms of risk assessment makes risk management less accurate. In terms of monitoring disease progression and complications, conventional systems lack dynamic monitoring capabilities, and it is difficult to reflect disease changes in real time.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a pediatric drug complication monitoring system.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the pediatric drug complication monitoring system comprises a symptom analysis module, a drug response evaluation module, a complication mode identification module, a drug interaction prediction module, a risk measurement module, a dynamic disease monitoring module, a personalized treatment scheme module and a drug side effect tracking module;
The symptom analysis module is used for carrying out symptom analysis by adopting a natural language processing technology and a pattern recognition algorithm based on the symptom record of the patient, recognizing the severity of the symptom and generating a symptom analysis report;
the drug response evaluation module predicts and evaluates the response caused by the differentiated drugs based on the symptom analysis report by adopting a decision tree algorithm and a probability statistical method to generate drug response evaluation;
the complication pattern recognition module is used for analyzing the medical image of the patient by adopting a convolutional neural network and an image analysis technology based on drug response evaluation, recognizing a target complication pattern and generating a complication pattern recognition result;
the drug interaction prediction module predicts the interaction between drugs by adopting an Apriori association rule mining algorithm based on the drug usage record of the patient, and generates a drug interaction prediction report;
the risk measurement module quantifies the complication risk of the patient by adopting a Bayesian network and a risk assessment model based on the complication pattern recognition result to generate a risk measurement report;
the dynamic disease monitoring module dynamically monitors disease progress and complication risk by adopting a long-short-period memory network and a time sequence analysis technology based on the continuous health record of a patient, and generates a dynamic disease monitoring report;
The personalized treatment scheme module adopts a machine learning algorithm and a clinical decision support system to make a personalized treatment plan based on the risk measurement report and the dynamic disease monitoring report;
the drug side effect tracking module is used for tracking potential side effects of the drug by adopting an anomaly detection algorithm based on the drug interaction prediction report and treatment feedback of the patient, and generating a drug side effect tracking report.
As a further aspect of the present invention, the symptom analysis report includes symptom type classification, severity rating, and concurrent disease indication, the drug response assessment includes drug response likelihood analysis, potential risk assessment, and safety cues, the complications pattern recognition result includes lesion characterization, complications type recognition, and potential disease indication, the drug interaction prediction report includes interaction type determination, risk rating assessment, and prevention scheme, the risk metric report includes risk probability calculation, severity rating, and emergency intervention indicators, the dynamic disease monitoring report includes disease progression trend analysis, complications pre-warning signals, and health status real-time updates, the personalized treatment plan includes treatment scheme customization, drug selection optimization, and treatment effect prediction, and the drug side effect tracking report includes side effect event record, reaction severity assessment, and treatment scheme.
As a further aspect of the present invention, the symptom analysis module includes a text analysis sub-module, a pattern recognition sub-module, and a severity evaluation sub-module;
the text analysis submodule adopts a natural language processing technology to analyze the symptom text based on the symptom record of the patient, and performs text mining to generate a symptom text analysis result;
the pattern recognition submodule carries out recognition of a symptom pattern by adopting a pattern recognition algorithm based on a symptom text analysis result and carries out data analysis to generate a symptom pattern recognition result;
the severity evaluation sub-module adopts an evaluation algorithm to evaluate the severity of symptoms based on the symptom pattern recognition result, and carries out algorithm analysis to generate a symptom severity evaluation report;
the natural language processing technology comprises semantic analysis, part-of-speech tagging and entity recognition, the pattern recognition algorithm is specifically a support vector machine, a neural network and cluster analysis, and the evaluation algorithm comprises risk classification, decision analysis and trend prediction.
As a further scheme of the invention, the drug response evaluation module comprises a drug database sub-module, a response prediction sub-module and a drug safety evaluation sub-module;
The medicine database submodule integrates medicine information based on the symptom severity evaluation report by adopting a database matching technology, and performs medicine information retrieval to generate a medicine information comprehensive result;
the reaction prediction submodule predicts the reaction of the medicine based on the medicine information comprehensive result by adopting a decision tree algorithm and a probability statistical method, and performs data analysis to generate a medicine reaction prediction result;
the drug safety evaluation submodule adopts a risk evaluation method to evaluate the safety of the drug based on the drug reaction prediction result, and performs safety analysis to generate a drug safety evaluation report;
the database matching technology comprises data association, a matching algorithm and data fusion, wherein the decision tree algorithm and the probability statistical method are specifically information gain, a base index and Bayesian statistics, and the risk assessment method is specifically risk matrix analysis, sensitivity analysis and influence assessment.
As a further scheme of the invention, the complication pattern recognition module comprises an image processing sub-module, a feature extraction sub-module and a pattern classification sub-module;
the image processing sub-module is used for carrying out preliminary processing on the medical image by adopting an image preprocessing technology based on drug reaction evaluation, and generating a preprocessed medical image;
The feature extraction submodule is used for extracting key features by adopting a feature extraction algorithm based on preprocessing the medical image and generating medical image feature data;
the pattern classification submodule classifies and identifies the complication pattern by adopting a convolutional neural network based on the medical image characteristic data and generates a complication pattern identification result;
the image preprocessing technology comprises self-adaptive histogram equalization, gaussian blur filtering and morphological transformation, the feature extraction algorithm is specifically a local binary mode, a Gabor filter and Hough transformation, and the convolutional neural network comprises a deep learning hierarchical structure, a ReLU activation function and maximum pooling.
As a further scheme of the invention, the medicine interaction prediction module comprises a data mining sub-module, an interaction analysis sub-module and a prediction modeling sub-module;
the data mining sub-module analyzes historical data by adopting a data mining technology based on the drug use record of the patient, mines potential association among drugs and generates drug use association data;
the interaction analysis submodule analyzes interaction among medicines by adopting an Apriori algorithm based on the medicine use association data and generates medicine interaction analysis data;
The prediction modeling submodule predicts and models the drug interaction by adopting a prediction modeling technology based on the drug interaction analysis data and generates a drug interaction prediction report;
the data mining technology comprises time sequence analysis, cluster analysis and anomaly detection, the Apriori algorithm is specifically frequent item set discovery, confidence calculation and promotion degree evaluation, and the predictive modeling technology comprises a support vector machine, a random forest and logistic regression.
As a further scheme of the invention, the risk measurement module comprises a risk assessment sub-module, a probability building sub-module and a risk grading sub-module;
the risk assessment submodule carries out preliminary assessment on the risk of the complications of the patient by adopting a risk assessment model based on the identification result of the complications mode and generates preliminary risk assessment data;
the probability modeling sub-module performs probability modeling by adopting a Bayesian network based on the preliminary risk assessment data and generates probability quantification risk data;
the risk classification submodule adopts a risk classification method to carry out risk classification treatment based on probability quantification risk data and generates a risk measurement report;
the risk assessment model comprises quantitative risk assessment, qualitative risk assessment and risk probability analysis, the Bayesian network comprises network parameter learning, evidence reasoning and probability updating, and the risk classification method comprises risk classification, risk heat map analysis and risk priority determination.
As a further scheme of the invention, the dynamic disease monitoring module comprises a time sequence analysis sub-module, a disease progress monitoring sub-module and a risk early warning sub-module;
the time sequence analysis submodule is used for carrying out trend analysis on health data by adopting a time sequence analysis technology based on continuous health records of patients and generating a health data trend analysis result;
the disease progress monitoring submodule adopts a long-short-term memory network to dynamically monitor disease progress based on the health data trend analysis result and generates a disease progress monitoring result;
the risk early-warning submodule adopts a risk early-warning mechanism to early warn the risk of potential complications based on the disease progress monitoring result and generates a dynamic disease monitoring report;
the time sequence analysis technology comprises autocorrelation and partial autocorrelation analysis, trend decomposition and seasonal adjustment, the long-term and short-term memory network comprises a feedback neural network structure, a gating mechanism and state updating, and the risk early warning mechanism comprises dynamic threshold setting, pattern recognition and real-time early warning signal sending.
As a further scheme of the invention, the personalized treatment scheme module comprises a treatment scheme design sub-module, a personalized adjustment sub-module and an effect prediction sub-module;
The treatment scheme design submodule generates a preliminary treatment scheme by adopting a clinical decision support system based on the risk measurement report and the dynamic disease monitoring report;
the personalized adjustment submodule adopts a personalized adjustment strategy to carry out scheme adjustment based on the primary treatment scheme and generates a personalized treatment scheme;
the effect prediction submodule predicts the treatment effect by adopting a machine learning algorithm based on a personalized treatment scheme and generates a treatment effect prediction report;
the clinical decision support system comprises electronic health record data analysis, drug dose optimization and treatment path selection, the personalized adjustment strategy comprises genome data analysis, drug response prediction and life style factor consideration, and the machine learning algorithm comprises regression analysis, classification algorithm and model verification.
As a further scheme of the invention, the medicine side effect tracking module comprises a side effect monitoring sub-module, an abnormality detection sub-module and a feedback analysis sub-module;
the side effect monitoring sub-module is used for carrying out preliminary tracking of side effects by adopting a drug monitoring technology based on a drug interaction prediction report and treatment feedback of a patient and generating preliminary side effect data;
The abnormality detection submodule adopts an abnormality detection algorithm to deeply analyze potential side effects based on the preliminary side effect data and generates a side effect abnormality detection result;
the feedback analysis submodule carries out comprehensive evaluation and feedback analysis of side effects by adopting a data analysis technology based on the side effect abnormality detection result and generates a drug side effect tracking report;
the drug monitoring technology comprises drug blood concentration analysis, physiological signal monitoring and patient symptom recording, the abnormality detection algorithm comprises multivariate abnormality detection, time sequence abnormality recognition and group behavior analysis, and the data analysis technology comprises causal relationship analysis, side effect trend prediction and treatment effect evaluation.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, the symptom and the severity of the symptom can be more accurately analyzed and identified by combining a natural language processing technology and a pattern recognition algorithm, so that the accuracy and the efficiency of symptom analysis are improved. By using a decision tree algorithm and a probability statistical method to predict and evaluate the drug response, the response caused by the drug can be more effectively identified, and the misdiagnosis rate is reduced. The convolutional neural network and the image analysis technology are adopted to analyze the medical image, so that the complication mode can be more accurately identified, and the diagnosis precision is improved. And the Apriori association rule mining algorithm is utilized to predict the interaction between medicines, so that the risk brought by the interaction between medicines is prevented. The system quantifies the risk of complications through a Bayesian network and a risk assessment model, thereby providing more accurate risk assessment. The use of long-term memory networks and time series analysis techniques allows for more accurate dynamic monitoring of disease progression and risk of complications.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a schematic diagram of a system framework of the present invention;
FIG. 3 is a flow chart of a symptom analysis module according to the present invention;
FIG. 4 is a flow chart of a drug response assessment module of the present invention;
FIG. 5 is a flow chart of a complication pattern recognition module of the present invention;
FIG. 6 is a flow chart of a drug interaction prediction module of the present invention;
FIG. 7 is a flow chart of a risk measurement module of the present invention;
FIG. 8 is a flow chart of a dynamic disease monitoring module of the present invention;
FIG. 9 is a flow chart of a personalized treatment regimen module of the invention;
FIG. 10 is a flow chart of a drug side effect tracking module according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Embodiment one: referring to fig. 1 to 2, the pediatric drug complication monitoring system includes a symptom analysis module, a drug response evaluation module, a complication pattern recognition module, a drug interaction prediction module, a risk measurement module, a dynamic disease monitoring module, a personalized treatment scheme module, and a drug side effect tracking module;
the symptom analysis module is used for carrying out symptom analysis by adopting a natural language processing technology and a pattern recognition algorithm based on the symptom record of the patient, recognizing the severity of the symptom and generating a symptom analysis report;
the drug response evaluation module predicts and evaluates the response caused by the differentiated drugs based on the symptom analysis report by adopting a decision tree algorithm and a probability statistical method to generate drug response evaluation;
the complication pattern recognition module is used for analyzing the medical image of the patient by adopting a convolutional neural network and an image analysis technology based on drug response evaluation, recognizing a target complication pattern and generating a complication pattern recognition result;
the drug interaction prediction module predicts the interaction between drugs by adopting an Apriori association rule mining algorithm based on the drug usage record of the patient, and generates a drug interaction prediction report;
Based on the complexity pattern recognition result, the risk measurement module adopts a Bayesian network and a risk assessment model to quantify the complexity risk of the patient and generate a risk measurement report;
the dynamic disease monitoring module dynamically monitors disease progress and complication risk by adopting a long-term memory network and a time sequence analysis technology based on the continuous health record of a patient, and generates a dynamic disease monitoring report;
the personalized treatment scheme module adopts a machine learning algorithm and a clinical decision support system to make a personalized treatment plan based on the risk measurement report and the dynamic disease monitoring report;
the drug side effect tracking module tracks potential side effects of the drug based on the drug interaction prediction report and treatment feedback of the patient by adopting an anomaly detection algorithm, and generates a drug side effect tracking report.
Symptom analysis reports include symptom type classification, severity ratings, and concurrent disease indications, drug response assessment includes drug response likelihood analysis, potential risk assessment, and safety cues, complications pattern recognition results include lesion characterization, complications type identification, and potential disease indications, drug interaction prediction reports include interaction type decisions, risk rating assessment, and prevention schemes, risk metric reports include risk probability calculations, severity ratings, and emergency intervention indicators, dynamic disease monitoring reports include disease progression trend analysis, complications pre-warning signals, and health status real-time updates, personalized treatment plans include treatment scheme customization, drug selection optimization, and treatment effect prediction, and drug side effect tracking reports include side effect event records, reaction severity assessment, and treatment schemes.
The symptom analysis and drug response assessment module uses natural language processing and pattern recognition techniques to help doctors diagnose and assess drug responses more accurately. Next, through the complication pattern recognition and drug interaction prediction module, the system can discover and prevent potential complications and adverse drug reactions early, reducing patient health risks. The risk metric module provides a quantified risk assessment that assists the physician in better understanding the patient's health. The dynamic disease monitoring module realizes continuous tracking of the illness state of the patient through a long-term memory network and a time sequence analysis technology, and ensures real-time health monitoring. In addition, the personalized treatment plan module customizes the treatment plan for each patient, improving the individualization and effectiveness of the treatment. Finally, the medicine side effect tracking module ensures the safety of the patient by timely tracking the potential side effect of the medicine. In the whole, the system not only improves the accuracy and safety of treatment, but also enhances the individuation and the dynamics of medical services by integrating and applying various technologies, thereby remarkably improving the treatment effect and the overall health level of pediatric patients.
Referring to fig. 3, the symptom analysis module includes a text analysis sub-module, a pattern recognition sub-module, and a severity evaluation sub-module;
the text analysis submodule carries out symptom text analysis by adopting a natural language processing technology based on the symptom record of the patient, and carries out text mining to generate a symptom text analysis result;
the pattern recognition submodule carries out recognition of the symptom pattern by adopting a pattern recognition algorithm based on the symptom text analysis result and carries out data analysis to generate a symptom pattern recognition result;
the severity evaluation submodule adopts an evaluation algorithm to evaluate the severity of symptoms based on the symptom pattern recognition result, and carries out algorithm analysis to generate a symptom severity evaluation report;
the natural language processing technology comprises semantic analysis, part-of-speech tagging and entity recognition, the pattern recognition algorithm is specifically a support vector machine, a neural network and cluster analysis, and the evaluation algorithm comprises risk classification, decision analysis and trend prediction.
The text analysis sub-module works from the patient's symptom records and uses Natural Language Processing (NLP) techniques to perform in-depth analysis of the symptom text. This includes semantic analysis, part-of-speech tagging, and entity identification to accurately understand textual descriptions of symptoms. Then, key information such as the kind, frequency and duration of symptoms is extracted from these records by text mining technology, and detailed symptom text analysis results are generated.
The pattern recognition sub-module recognizes a symptom pattern using a pattern recognition algorithm such as a support vector machine, a neural network, and a cluster analysis based on the symptom text parsing result obtained from the text analysis sub-module. This step involves in-depth analysis of the symptom data to identify potential pathological patterns or signs of disease. Upon completion of this step, a symptom pattern recognition result is generated, which helps the doctor understand the type of disease to which the patient's symptoms are directed.
The severity assessment sub-module operates according to the identified symptom patterns, using risk classification, decision analysis, trend prediction, and like assessment algorithms to assess the severity of symptoms. The purpose of this step is to quantify the severity of the symptoms and predict the trend of symptoms. This provides a symptom severity assessment report to doctors, helping them to make appropriate treatment plans or take preventive measures.
Referring to fig. 4, the drug response evaluation module includes a drug database sub-module, a response prediction sub-module, and a drug safety evaluation sub-module;
the medicine database submodule integrates medicine information based on the symptom severity evaluation report by adopting a database matching technology, and performs medicine information retrieval to generate a medicine information comprehensive result;
The reaction prediction submodule predicts the reaction of the medicine based on the medicine information comprehensive result by adopting a decision tree algorithm and a probability statistical method, and performs data analysis to generate a medicine reaction prediction result;
the drug safety evaluation submodule adopts a risk evaluation method to evaluate the safety of the drug based on the drug reaction prediction result, and performs safety analysis to generate a drug safety evaluation report;
the database matching technology comprises data association, a matching algorithm and data fusion, wherein the decision tree algorithm and the probability statistical method are specifically information gain, a base index and Bayesian statistics, and the risk assessment method is specifically risk matrix analysis, sensitivity analysis and influence assessment.
The medication database submodule integrates various medication information based on the symptom severity assessment report using data correlation, matching algorithms, and data fusion techniques. This includes information on the composition, use, dosage, known side effects of the drug, etc. After the step is completed, the generated comprehensive result of the drug information provides necessary basic data for the subsequent drug response prediction.
After the drug information comprehensive result is obtained, the reaction prediction sub-module predicts the drug reaction by using a decision tree algorithm and a probability statistical method. Specific techniques involved in this step include information gain, base index and bayesian statistics. By analyzing the nature of the drug and the severity of the patient's symptoms, this module is able to predict the different responses that the drug elicits and generate a drug response prediction.
Based on the drug response prediction result, the drug safety evaluation sub-module adopts a risk evaluation method to evaluate the safety of the drug. This includes the use of risk matrix analysis, sensitivity analysis, and impact assessment to quantify the potential risk of drug use. After completion of these analyses, the module generates a drug safety assessment report, providing the physician with detailed information about the safety of the drug use.
Referring to fig. 5, the complication pattern recognition module includes an image processing sub-module, a feature extraction sub-module, and a pattern classification sub-module;
the image processing sub-module is used for carrying out preliminary processing on the medical image by adopting an image preprocessing technology based on drug reaction evaluation, and generating a preprocessed medical image;
the feature extraction submodule is used for extracting key features by adopting a feature extraction algorithm based on preprocessing the medical image and generating medical image feature data;
the pattern classification submodule classifies and identifies the complication pattern by adopting a convolutional neural network based on the medical image characteristic data and generates a complication pattern identification result;
the image preprocessing technology comprises self-adaptive histogram equalization, gaussian blur filtering and morphological transformation, a characteristic extraction algorithm is specifically a local binary mode, a Gabor filter and Hough transformation, and the convolutional neural network comprises a deep learning hierarchical structure, a ReLU activation function and maximum pooling.
The image processing sub-module performs preliminary processing on the medical image using an image preprocessing technique based on the drug response evaluation result. This includes applying adaptive histogram equalization techniques to improve the contrast of the image, removing noise using gaussian blur filtering, and applying morphological transformations to highlight key structures in the image. The purpose of this step is to optimize the image quality, which lays the foundation for deeper analysis. After these treatments are completed, a preprocessed medical image is generated.
After the image is preprocessed, the feature extraction sub-module uses a local binary pattern, a Gabor filter, hough transformation and other feature extraction algorithms to extract key features in the medical image. These features, including shape, texture, edges, etc. information in the image, are critical to identifying a particular complication pattern. After the extraction is completed, medical image feature data containing the key features is generated.
The pattern classification submodule analyzes the medical image characteristic data by using a Convolutional Neural Network (CNN). The deep learning hierarchy of CNNs, reLU activation functions, and max pooling techniques enable this module to effectively classify and identify different complications patterns. Through the advanced algorithms, the module can accurately identify various complications facing the patient and generate a complication pattern identification result.
Referring to fig. 6, the drug interaction prediction module includes a data mining sub-module, an interaction analysis sub-module, and a prediction modeling sub-module;
the data mining sub-module analyzes historical data by adopting a data mining technology based on the drug use record of the patient, mines potential association among drugs, and generates drug use association data;
the interaction analysis submodule analyzes interaction among medicines by adopting an Apriori algorithm based on the medicine use association data and generates medicine interaction analysis data;
the prediction modeling submodule predicts and models the drug interaction by adopting a prediction modeling technology based on the drug interaction analysis data and generates a drug interaction prediction report;
the data mining technology comprises time sequence analysis, cluster analysis and anomaly detection, the Apriori algorithm is specifically frequent item set discovery, confidence calculation and promotion degree evaluation, and the predictive modeling technology comprises a support vector machine, a random forest and logistic regression.
The data mining submodule utilizes a data mining technology to carry out historical data analysis on the drug usage records of patients, and adopts methods such as time sequence analysis, cluster analysis, anomaly detection and the like to mine potential association among drugs. By analyzing these data, the module can identify correlations and patterns that exist between different drugs and generate drug usage association data. This step provides the basis for identifying and understanding drug interactions.
The interaction analysis sub-module uses Apriori algorithm for deeper analysis based on drug use correlation data. The Apriori algorithm helps identify interactions between drugs through frequent item set discovery, confidence calculation, and elevation assessment. This process can reveal interactions of different drug combinations, generating drug interaction analysis data.
The predictive modeling submodule predicts and models drug interactions using predictive modeling techniques based on the drug interaction analysis data. The module adopts advanced prediction models such as a support vector machine, random forest, logistic regression and the like to carry out quantization and classification prediction on the drug interaction. By these techniques, the module is able to efficiently predict interactions between drugs and generate a drug interaction prediction report.
Referring to fig. 7, the risk measurement module includes a risk assessment sub-module, a probability modeling sub-module, and a risk classification sub-module;
the risk assessment submodule carries out preliminary assessment on the risk of the complications of the patient by adopting a risk assessment model based on the identification result of the complications mode and generates preliminary risk assessment data;
the probability modeling sub-module performs probability modeling by adopting a Bayesian network based on the preliminary risk assessment data and generates probability quantification risk data;
The risk classification submodule adopts a risk classification method to carry out risk classification treatment based on probability quantification risk data and generates a risk measurement report;
the risk assessment model comprises quantitative risk assessment, qualitative risk assessment and risk probability analysis, the Bayesian network comprises network parameter learning, evidence reasoning and probability updating, and the risk classification method comprises risk classification, risk heat map analysis and risk priority determination.
In the risk assessment sub-module, a logistic regression model is used to assess the risk of patient complications. The following is example code implemented using the scikit-learn library in Python:
from sklearn.linear_model import LogisticRegression；
from sklearn.model_selection import train_test_split；
from sklearn.metrics import classification_report；
import pandas as pd；
let df be the DataFrame containing the feature and the object;
x=df.drop ('target', axis=1) # feature;
y=df [ 'target' ] # target variable, representing the occurrence of complications;
dividing the data set, # and;
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)；
establishing a logistic regression model;
model = LogisticRegression()；
model.fit(X_train, y_train)；
# prediction and evaluation;
predictions = model.predict(X_test)；
print(classification_report(y_test, predictions))；
in the probabilistic modeling sub-module, a bayesian network is created and used for probabilistic modeling using a pgmpy library. The following are examples of bayesian network construction and reasoning:
from pgmpy.models import BayesianModel；
from pgmpy.estimators import MaximumLikelihoodEstimator；
from pgmpy.inference import VariableElimination；
setting data to learn the structure and parameters of the network;
data=pd.dataframe (data= { ' a [ ' low ', ' medium ', ' high ', ' low ', ' medium ', ' ], B [ ' yes ', ' no ', ' yes ', ' no ', ' C [ ' high ', ' low ', ' medium ', ' low ') };
Creating a model;
model=bayesian model ([ ('a', 'B'), ('B', 'C') ]) #a affects B, B affects C;
model.fit(data, estimator=MaximumLikelihoodEstimator)；
reasoning is carried out;
infer = VariableElimination(model)；
result=refer.query (variables= [ ' C ' ], evaluation= { ' a ': high ' };
print(result)；
in the risk classification sub-module, risks are classified according to the output of the probability model, and different risk classes are classified by setting thresholds. The following are example codes:
def risk_classification(risk_prob):
if risk_prob<0.3:
return 'low risk';
elif risk_prob<0.7:
return 'moderate risk';
else:
return 'high risk';
let risk_prob be the risk probability given by the probability model;
risk_prob=0.65# example probability;
risk_level = risk_classification(risk_prob)；
print (f' risk level: { risk_level });
referring to fig. 8, the dynamic disease monitoring module includes a time sequence analysis sub-module, a disease progress monitoring sub-module, and a risk early warning sub-module;
the time sequence analysis submodule is used for carrying out trend analysis on the health data by adopting a time sequence analysis technology based on the continuous health record of the patient and generating a health data trend analysis result;
the disease progress monitoring submodule adopts a long-short-term memory network to dynamically monitor the disease progress based on the health data trend analysis result and generates a disease progress monitoring result;
the risk early warning sub-module adopts a risk early warning mechanism to early warn the risk of the potential complications based on the disease progress monitoring result and generates a dynamic disease monitoring report;
The time sequence analysis technology comprises autocorrelation and partial autocorrelation analysis, trend decomposition and seasonal adjustment, the long-term and short-term memory network comprises a feedback neural network structure, a gating mechanism and state updating, and the risk early warning mechanism comprises dynamic threshold setting, pattern recognition and real-time early warning signal sending.
The time series analysis sub-module works based on the patient's continuous health record, employing time series analysis techniques including autocorrelation and partial autocorrelation analysis, trend decomposition, and seasonal adjustment to analyze long-term trends and patterns of health data. The purpose of this step is to identify the trend of the state of health, providing a basis for further monitoring of disease progression. And after the analysis is completed, generating a health data trend analysis result.
The disease progression monitoring sub-module works based on health data trend analysis results, using long short term memory network (LSTM), a special feedback neural network structure, to dynamically monitor disease progression. The gating mechanism and status updating function of LSTM make it particularly suitable for processing time series data, capable of effectively capturing dynamic changes in disease progression. After this step is completed, disease progression monitoring results are generated.
The risk early warning sub-module works based on the disease progress monitoring result, adopts a risk early warning mechanism comprising dynamic threshold setting, pattern recognition and real-time early warning signal sending to early warn the potential complication risk. The purpose of this module is to immediately notify the medical professionals when a critical transition in the disease occurs or a critical threshold is reached so that they can take timely intervention. After completion of these analyses, dynamic disease monitoring reports are generated.
Referring to fig. 9, the personalized treatment plan module includes a treatment plan design sub-module, a personalized adjustment sub-module, and an effect prediction sub-module;
the treatment scheme design submodule generates a preliminary treatment scheme by adopting a clinical decision support system based on the risk measurement report and the dynamic disease monitoring report;
the personalized adjustment submodule adopts a personalized adjustment strategy to carry out scheme adjustment based on the primary treatment scheme and generates a personalized treatment scheme;
the effect prediction submodule predicts the treatment effect by adopting a machine learning algorithm based on the personalized treatment scheme and generates a treatment effect prediction report;
the clinical decision support system comprises electronic health record data analysis, drug dosage optimization and treatment path selection, the individuation adjustment strategy comprises genome data analysis, drug response prediction and life style factor consideration, and the machine learning algorithm comprises regression analysis, classification algorithm and model verification.
The treatment plan design sub-module uses a clinical decision support system to design a preliminary treatment plan based on the risk metric report and the dynamic disease monitoring report. The clinical decision support system analyzes the patient's electronic health record data, taking into account drug dose optimization and appropriate treatment routes. The goal of this step is to formulate a comprehensive primary treatment regimen based on the patient's unique health and disease characteristics. After the design is completed, a preliminary treatment plan is generated.
The individuation adjustment submodule adopts an individuation adjustment strategy to finely adjust the scheme based on the primary treatment scheme. This includes analyzing the patient's genomic data, predicting drug response, and considering the patient's lifestyle factors. With this personalized adjustment, the module ensures that the treatment regimen is better able to accommodate the unique needs and conditions of each patient. After these adjustments are completed, a personalized treatment regimen is generated.
The effect prediction submodule predicts a treatment effect using a machine learning algorithm based on the personalized treatment plan. These algorithms include regression analysis, classification algorithms, and model verification, which can assess the potential success of a treatment regimen and predict the patient's response to treatment. This step aims at identifying treatment challenges or opportunities in advance and generating a treatment effect prediction report.
Referring to fig. 10, the drug side effect tracking module includes a side effect monitoring sub-module, an abnormality detection sub-module, and a feedback analysis sub-module;
the side effect monitoring sub-module is used for carrying out preliminary tracking of side effects by adopting a drug monitoring technology based on a drug interaction prediction report and treatment feedback of a patient and generating preliminary side effect data;
the abnormality detection sub-module adopts an abnormality detection algorithm to deeply analyze potential side effects based on the preliminary side effect data and generates a side effect abnormality detection result;
the feedback analysis submodule carries out comprehensive evaluation and feedback analysis of side effects by adopting a data analysis technology based on the side effect abnormality detection result and generates a drug side effect tracking report;
the drug monitoring technology comprises drug blood concentration analysis, physiological signal monitoring and patient symptom recording, the abnormality detection algorithm comprises multivariate abnormality detection, time sequence abnormality recognition and group behavior analysis, and the data analysis technology comprises causal relationship analysis, side effect trend prediction and treatment effect evaluation.
The side effect monitoring sub-module performs a preliminary tracking of side effects based on drug interaction prediction reports and patient treatment feedback, using drug monitoring techniques, including drug blood concentration analysis, physiological signal monitoring, and patient symptom logging, to identify and record possible drug side effects. This step generates preliminary side effect data, which provides the basis for in-depth analysis.
The abnormality detection sub-module adopts an abnormality detection algorithm to further analyze potential side effects based on the preliminary side effect data. This includes methods of multivariate anomaly detection, time series anomaly identification, and group behavior analysis to accurately identify and distinguish between normal drug responses and abnormal side effects. After completion of these analyses, a side effect abnormality detection result is generated.
The feedback analysis submodule carries out comprehensive evaluation and feedback analysis by using a data analysis technology based on the side effect abnormality detection result. This step involves causal relationship analysis, side effect trend prediction, treatment effect assessment, etc., aiming at comprehensively assessing side effects of the drug and generating drug side effect tracking reports.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (10)
1. Pediatric drug complications monitoring system, characterized in that: the system comprises a symptom analysis module, a drug response evaluation module, a complication mode identification module, a drug interaction prediction module, a risk measurement module, a dynamic disease monitoring module, a personalized treatment scheme module and a drug side effect tracking module;
the symptom analysis module is used for carrying out symptom analysis by adopting a natural language processing technology and a pattern recognition algorithm based on the symptom record of the patient, recognizing the severity of the symptom and generating a symptom analysis report;
the drug response evaluation module predicts and evaluates the response caused by the differentiated drugs based on the symptom analysis report by adopting a decision tree algorithm and a probability statistical method to generate drug response evaluation;
the complication pattern recognition module is used for analyzing the medical image of the patient by adopting a convolutional neural network and an image analysis technology based on drug response evaluation, recognizing a target complication pattern and generating a complication pattern recognition result;
the drug interaction prediction module predicts the interaction between drugs by adopting an Apriori association rule mining algorithm based on the drug usage record of the patient, and generates a drug interaction prediction report;
The risk measurement module quantifies the complication risk of the patient by adopting a Bayesian network and a risk assessment model based on the complication pattern recognition result to generate a risk measurement report;
the dynamic disease monitoring module dynamically monitors disease progress and complication risk by adopting a long-short-period memory network and a time sequence analysis technology based on the continuous health record of a patient, and generates a dynamic disease monitoring report;
the personalized treatment scheme module adopts a machine learning algorithm and a clinical decision support system to make a personalized treatment plan based on the risk measurement report and the dynamic disease monitoring report;
the drug side effect tracking module is used for tracking potential side effects of the drug by adopting an anomaly detection algorithm based on the drug interaction prediction report and treatment feedback of the patient, and generating a drug side effect tracking report.
2. The pediatric drug complication monitoring system of claim 1, wherein: the symptom analysis report includes symptom type classification, severity rating, and indication of a concurrent disease, the medication response assessment includes medication response likelihood analysis, potential risk assessment, and safety cues, the complication pattern recognition results include lesion characterization, complication type recognition, and potential disease indications, the medication interaction prediction report includes interaction type decisions, risk rating assessment, and prevention regimens, the risk metric report includes risk probability calculations, severity ratings, and emergency intervention indicators, the dynamic disease monitoring report includes disease progression trend analysis, complication pre-warning signals, and real-time updates of health status, the personalized treatment plan includes treatment regimen customization, medication selection optimization, and treatment effect prediction, and the medication side effect tracking report includes side effect event records, reaction severity assessment, and treatment regimens.
3. The pediatric drug complication monitoring system of claim 1, wherein: the symptom analysis module comprises a text analysis sub-module, a pattern recognition sub-module and a severity evaluation sub-module;
the text analysis submodule adopts a natural language processing technology to analyze the symptom text based on the symptom record of the patient, and performs text mining to generate a symptom text analysis result;
the pattern recognition submodule carries out recognition of a symptom pattern by adopting a pattern recognition algorithm based on a symptom text analysis result and carries out data analysis to generate a symptom pattern recognition result;
the severity evaluation sub-module adopts an evaluation algorithm to evaluate the severity of symptoms based on the symptom pattern recognition result, and carries out algorithm analysis to generate a symptom severity evaluation report;
the natural language processing technology comprises semantic analysis, part-of-speech tagging and entity recognition, the pattern recognition algorithm is specifically a support vector machine, a neural network and cluster analysis, and the evaluation algorithm comprises risk classification, decision analysis and trend prediction.
4. The pediatric drug complication monitoring system of claim 1, wherein: the drug response evaluation module comprises a drug database sub-module, a response prediction sub-module and a drug safety evaluation sub-module;
The medicine database submodule integrates medicine information based on the symptom severity evaluation report by adopting a database matching technology, and performs medicine information retrieval to generate a medicine information comprehensive result;
the reaction prediction submodule predicts the reaction of the medicine based on the medicine information comprehensive result by adopting a decision tree algorithm and a probability statistical method, and performs data analysis to generate a medicine reaction prediction result;
the drug safety evaluation submodule adopts a risk evaluation method to evaluate the safety of the drug based on the drug reaction prediction result, and performs safety analysis to generate a drug safety evaluation report;
the database matching technology comprises data association, a matching algorithm and data fusion, wherein the decision tree algorithm and the probability statistical method are specifically information gain, a base index and Bayesian statistics, and the risk assessment method is specifically risk matrix analysis, sensitivity analysis and influence assessment.
5. The pediatric drug complication monitoring system of claim 1, wherein: the complication pattern recognition module comprises an image processing sub-module, a feature extraction sub-module and a pattern classification sub-module;
The image processing sub-module is used for carrying out preliminary processing on the medical image by adopting an image preprocessing technology based on drug reaction evaluation, and generating a preprocessed medical image;
the feature extraction submodule is used for extracting key features by adopting a feature extraction algorithm based on preprocessing the medical image and generating medical image feature data;
the pattern classification submodule classifies and identifies the complication pattern by adopting a convolutional neural network based on the medical image characteristic data and generates a complication pattern identification result;
the image preprocessing technology comprises self-adaptive histogram equalization, gaussian blur filtering and morphological transformation, the feature extraction algorithm is specifically a local binary mode, a Gabor filter and Hough transformation, and the convolutional neural network comprises a deep learning hierarchical structure, a ReLU activation function and maximum pooling.
6. The pediatric drug complication monitoring system of claim 1, wherein: the medicine interaction prediction module comprises a data mining sub-module, an interaction analysis sub-module and a prediction modeling sub-module;
the data mining sub-module analyzes historical data by adopting a data mining technology based on the drug use record of the patient, mines potential association among drugs and generates drug use association data;
The interaction analysis submodule analyzes interaction among medicines by adopting an Apriori algorithm based on the medicine use association data and generates medicine interaction analysis data;
the prediction modeling submodule predicts and models the drug interaction by adopting a prediction modeling technology based on the drug interaction analysis data and generates a drug interaction prediction report;
the data mining technology comprises time sequence analysis, cluster analysis and anomaly detection, the Apriori algorithm is specifically frequent item set discovery, confidence calculation and promotion degree evaluation, and the predictive modeling technology comprises a support vector machine, a random forest and logistic regression.
7. The pediatric drug complication monitoring system of claim 1, wherein: the risk measurement module comprises a risk assessment sub-module, a probability modeling sub-module and a risk grading sub-module;
the risk assessment submodule carries out preliminary assessment on the risk of the complications of the patient by adopting a risk assessment model based on the identification result of the complications mode and generates preliminary risk assessment data;
the probability modeling sub-module performs probability modeling by adopting a Bayesian network based on the preliminary risk assessment data and generates probability quantification risk data;
The risk classification submodule adopts a risk classification method to carry out risk classification treatment based on probability quantification risk data and generates a risk measurement report;
the risk assessment model comprises quantitative risk assessment, qualitative risk assessment and risk probability analysis, the Bayesian network comprises network parameter learning, evidence reasoning and probability updating, and the risk classification method comprises risk classification, risk heat map analysis and risk priority determination.
8. The pediatric drug complication monitoring system of claim 1, wherein: the dynamic disease monitoring module comprises a time sequence analysis sub-module, a disease progress monitoring sub-module and a risk early warning sub-module;
the time sequence analysis submodule is used for carrying out trend analysis on health data by adopting a time sequence analysis technology based on continuous health records of patients and generating a health data trend analysis result;
the disease progress monitoring submodule adopts a long-short-term memory network to dynamically monitor disease progress based on the health data trend analysis result and generates a disease progress monitoring result;
the risk early-warning submodule adopts a risk early-warning mechanism to early warn the risk of potential complications based on the disease progress monitoring result and generates a dynamic disease monitoring report;
The time sequence analysis technology comprises autocorrelation and partial autocorrelation analysis, trend decomposition and seasonal adjustment, the long-term and short-term memory network comprises a feedback neural network structure, a gating mechanism and state updating, and the risk early warning mechanism comprises dynamic threshold setting, pattern recognition and real-time early warning signal sending.
9. The pediatric drug complication monitoring system of claim 1, wherein: the personalized treatment scheme module comprises a treatment scheme design sub-module, a personalized adjustment sub-module and an effect prediction sub-module;
the treatment scheme design submodule generates a preliminary treatment scheme by adopting a clinical decision support system based on the risk measurement report and the dynamic disease monitoring report;
the personalized adjustment submodule adopts a personalized adjustment strategy to carry out scheme adjustment based on the primary treatment scheme and generates a personalized treatment scheme;
the effect prediction submodule predicts the treatment effect by adopting a machine learning algorithm based on a personalized treatment scheme and generates a treatment effect prediction report;
the clinical decision support system comprises electronic health record data analysis, drug dose optimization and treatment path selection, the personalized adjustment strategy comprises genome data analysis, drug response prediction and life style factor consideration, and the machine learning algorithm comprises regression analysis, classification algorithm and model verification.
10. The pediatric drug complication monitoring system of claim 1, wherein: the medicine side effect tracking module comprises a side effect monitoring sub-module, an abnormality detection sub-module and a feedback analysis sub-module;
the side effect monitoring sub-module is used for carrying out preliminary tracking of side effects by adopting a drug monitoring technology based on a drug interaction prediction report and treatment feedback of a patient and generating preliminary side effect data;
the abnormality detection submodule adopts an abnormality detection algorithm to deeply analyze potential side effects based on the preliminary side effect data and generates a side effect abnormality detection result;
the feedback analysis submodule carries out comprehensive evaluation and feedback analysis of side effects by adopting a data analysis technology based on the side effect abnormality detection result and generates a drug side effect tracking report;
the drug monitoring technology comprises drug blood concentration analysis, physiological signal monitoring and patient symptom recording, the abnormality detection algorithm comprises multivariate abnormality detection, time sequence abnormality recognition and group behavior analysis, and the data analysis technology comprises causal relationship analysis, side effect trend prediction and treatment effect evaluation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311753319.7A CN117457215B (en) | 2023-12-20 | 2023-12-20 | Pediatric drug complications monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311753319.7A CN117457215B (en) | 2023-12-20 | 2023-12-20 | Pediatric drug complications monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117457215A true CN117457215A (en) | 2024-01-26 |
| CN117457215B CN117457215B (en) | 2024-03-08 |
Family
ID=89595135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311753319.7A Active CN117457215B (en) | 2023-12-20 | 2023-12-20 | Pediatric drug complications monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117457215B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117670378A (en) * | 2024-02-02 | 2024-03-08 | 烟台市食品药品检验检测中心(烟台市药品不良反应监测中心、烟台市粮油质量检测中心) | Food safety monitoring method and system based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018147463A (en) * | 2017-03-02 | 2018-09-20 | 茂樹 扇谷 | System and method for inspecting risk of developing adverse drug reaction, and computer program |
| CN110322944A (en) * | 2019-05-31 | 2019-10-11 | 浙江大学 | Adverse drug reaction intelligent monitoring method, device, system and computer equipment |
| US20210043289A1 (en) * | 2019-08-09 | 2021-02-11 | International Business Machines Corporation | Identifying adverse effects of medications |
| CN113593724A (en) * | 2021-08-25 | 2021-11-02 | 四川省医学科学院·四川省人民医院 | Anticoagulant drug treatment management follow-up system |
| CN114005503A (en) * | 2021-12-31 | 2022-02-01 | 四川省医学科学院·四川省人民医院 | Active monitoring and early warning system for drug-induced diseases |
| CN117253614A (en) * | 2023-11-14 | 2023-12-19 | 天津医科大学朱宪彝纪念医院(天津医科大学代谢病医院、天津代谢病防治中心) | Diabetes risk early warning method based on big data analysis |
-
2023
- 2023-12-20 CN CN202311753319.7A patent/CN117457215B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018147463A (en) * | 2017-03-02 | 2018-09-20 | 茂樹 扇谷 | System and method for inspecting risk of developing adverse drug reaction, and computer program |
| CN110322944A (en) * | 2019-05-31 | 2019-10-11 | 浙江大学 | Adverse drug reaction intelligent monitoring method, device, system and computer equipment |
| US20210043289A1 (en) * | 2019-08-09 | 2021-02-11 | International Business Machines Corporation | Identifying adverse effects of medications |
| CN113593724A (en) * | 2021-08-25 | 2021-11-02 | 四川省医学科学院·四川省人民医院 | Anticoagulant drug treatment management follow-up system |
| CN114005503A (en) * | 2021-12-31 | 2022-02-01 | 四川省医学科学院·四川省人民医院 | Active monitoring and early warning system for drug-induced diseases |
| CN117253614A (en) * | 2023-11-14 | 2023-12-19 | 天津医科大学朱宪彝纪念医院(天津医科大学代谢病医院、天津代谢病防治中心) | Diabetes risk early warning method based on big data analysis |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117670378A (en) * | 2024-02-02 | 2024-03-08 | 烟台市食品药品检验检测中心(烟台市药品不良反应监测中心、烟台市粮油质量检测中心) | Food safety monitoring method and system based on big data |
| CN117670378B (en) * | 2024-02-02 | 2024-04-30 | 烟台市食品药品检验检测中心(烟台市药品不良反应监测中心、烟台市粮油质量检测中心) | Food safety monitoring method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117457215B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11404145B2 (en) | Medical machine time-series event data processor | |
| Alaa et al. | Learning from clinical judgments: Semi-markov-modulated marked hawkes processes for risk prognosis | |
| CN117457215B (en) | Pediatric drug complications monitoring system | |
| US9959390B2 (en) | Modeling techniques for predicting mortality in intensive care units | |
| CN117457147B (en) | Personalized nursing planning method and system for rehabilitation patient | |
| CN117457217B (en) | Risk assessment method and system for diabetic nephropathy | |
| CN117649941A (en) | Dynamic early warning system for hemorrhagic shock after orthopedics trauma | |
| CN117390499A (en) | Be applied to multiple sample detecting system that food pesticide remained and detected | |
| Rout et al. | Prediction of diabetes risk based on machine learning techniques | |
| Reyes-Garcia et al. | Evaluation of the impact of data uncertainty on the prediction of physiological patient deterioration | |
| Pan et al. | Liver disease detection: evaluation of machine learning algorithms performances with optimal thresholds | |
| CN114255878A (en) | Training method, system, device and storage medium of disease typing model | |
| CN117473241B (en) | Clinical trial progress statistics and analysis tool based on big data | |
| CN118136270B (en) | Data analysis based health monitoring and early warning system and method for chronic diseases | |
| Pradhan et al. | Wearable device based on IoT in the healthcare system for disease detection and symptom recognition | |
| CN118053541A (en) | Intelligent identification and prevention system for adverse drug reaction | |
| CN118039165B (en) | Cardiovascular and cerebrovascular rehabilitation intelligent auxiliary system | |
| Rajput et al. | Detection Of Diseases And Predictive Analytic | |
| Sobhana et al. | Enhancement of patient's health prediction system in a graphical representation using digital twin technology | |
| CN117457153A (en) | Intelligent recommendation system and method for nursing in psychiatric house | |
| Fadillah et al. | Diabetes Diagnosis and Prediction using Data Mining and Machine Learning Techniques | |
| Bhatnagar et al. | An Efficient Techniques For Disease Prediction From Medical Data Using Data Mining And Machine Learning | |
| Ishaq et al. | Exploring Sleep Paralysis Phenomenon Through Machine Learning: An Analytical Study | |
| Natarajan et al. | An Exploration of the Performance using Ensemble Methods Utilizing Random Forest Classifier for Diabetes Detection | |
| Kumar et al. | 3 Efficientfor TechniquesPrediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |