CN117854659A - AI interaction method and system for clinical trial - Google Patents
AI interaction method and system for clinical trial Download PDFInfo
- Publication number
- CN117854659A CN117854659A CN202410264726.XA CN202410264726A CN117854659A CN 117854659 A CN117854659 A CN 117854659A CN 202410264726 A CN202410264726 A CN 202410264726A CN 117854659 A CN117854659 A CN 117854659A
- Authority
- CN
- China
- Prior art keywords
- clinical
- target
- patient
- data
- plan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000003993 interaction Effects 0.000 title claims abstract description 43
- 238000012360 testing method Methods 0.000 claims abstract description 48
- 230000036541 health Effects 0.000 claims abstract description 28
- 238000012216 screening Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 48
- 238000011282 treatment Methods 0.000 claims description 37
- 238000003745 diagnosis Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 14
- 201000010099 disease Diseases 0.000 claims description 13
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 13
- 238000010801 machine learning Methods 0.000 claims description 11
- 238000013145 classification model Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 4
- 230000002452 interceptive effect Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000003058 natural language processing Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 208000024891 symptom Diseases 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012552 review Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 9
- 230000002349 favourable effect Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000011269 treatment regimen Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006798 recombination Effects 0.000 description 2
- 238000005215 recombination Methods 0.000 description 2
- 230000007115 recruitment Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Classifications
-
- 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
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to an AI interaction method and system for clinical trial, wherein the method comprises the following steps: acquiring clinical test basic data and constructing an AI interaction platform; screening target patients meeting clinical test standards through an AI interaction platform according to the historical medical records and health data of the patients; acquiring detailed information and medical history of a target patient, and generating a first clinical plan; acquiring a second clinical plan of a doctor on a target patient, and generating a target clinical plan according to the first clinical plan and the second clinical plan; clinical trials were conducted according to the target clinical program. The invention improves the accuracy and efficiency of patient screening by utilizing the AI technology to intelligently analyze and process the patient data and the test plan; meanwhile, by combining the professional judgment and experience of doctors, a more reasonable and feasible clinical test plan is generated.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an AI interaction method and system for clinical trials.
Background
With the continued advancement of medical technology, clinical trials play a critical role in medical research.
However, the traditional clinical test method has a plurality of defects, such as low screening efficiency of patients, unreasonable test plan making and the like. In order to solve the problems and improve the efficiency and the accuracy of clinical tests, the invention provides an AI interaction method and an AI interaction system for clinical tests.
Disclosure of Invention
In order to overcome the technical defects in the prior art, the invention provides an AI interaction method and system for clinical trials, which can effectively solve the problems in the background art.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
the embodiment of the invention discloses an AI interaction method for clinical trials, which is characterized by comprising the following steps of: the method comprises the following steps:
acquiring clinical test basic data and constructing an AI interaction platform;
screening target patients meeting clinical test standards through an AI interaction platform according to the historical medical records and health data of the patients;
acquiring detailed information and medical history of a target patient, and generating a first clinical plan;
acquiring a second clinical plan of a doctor on a target patient, and generating a target clinical plan according to the first clinical plan and the second clinical plan;
clinical trials were conducted according to the target clinical program.
In any of the above aspects, preferably, the acquiring clinical trial base data comprises:
defining a regular expression pattern, and screening character strings conforming to a date format;
sending a request to a target website, receiving webpage content, analyzing the webpage, and acquiring clinical test basic data according to the specific tag and class name of the HTML;
generating a unique hash value according to each piece of data, and storing the unique hash value in a hash table to remove repeated data;
performing Z-score standardization on the data, and adjusting the data to a uniform standard normal distribution;
and calculating the importance of each word by using a TF-IDF algorithm, and classifying the text by using a naive Bayesian algorithm to obtain normal data.
In any of the above schemes, preferably, the screening, according to the historical medical records and health data of the patient, of the target patient meeting the clinical test standard through the AI interaction platform includes:
converting the medical records of the patient into a structured data format, and extracting keywords, disease diagnosis and treatment scheme information;
based on the health data of the patient, performing feature extraction and classification using a machine learning algorithm;
constructing a knowledge graph or an expert system, and integrating clinical test standards and medical knowledge;
and (3) recommending a target clinical test for a target patient according to the medical record and the health data of the patient by using a recommendation algorithm.
In any of the above embodiments, preferably, the converting the medical record of the patient into a structured data format, and extracting the keyword, the disease diagnosis, and the treatment plan information includes:
the method comprises the steps of performing text cleaning on medical records of patients, performing word segmentation processing, and dividing the texts into words or phrases;
applying a named entity recognition algorithm to recognize entity information in the medical record;
performing part-of-speech tagging on each word by using a part-of-speech tagging algorithm;
calculating the importance of each word by using a TF-IDF algorithm, and selecting the word ranked at the top as a keyword;
a sample of medical records containing known disease diagnosis and treatment protocols is constructed and the medical records are classified using a machine learning algorithm to determine the categories of diagnosis and treatment protocols.
In any of the above aspects, preferably, the feature extraction and classification based on the health data of the patient using a machine learning algorithm includes:
extracting physiological parameters, genome data and biochemical indexes according to health data of a patient to obtain health characteristics, and preprocessing each characteristic;
selecting target features from the preprocessed features by using a feature selection algorithm;
according to the feature data and the known labels, carrying out node division on the target features, and constructing a decision tree model; selecting the nearest features on each node for division, and classifying according to the feature values;
and constructing a classification model, inputting new patient characteristic data into the classification model, carrying out classification prediction according to the characteristic values, and judging the category to which the patient belongs.
In any of the above aspects, preferably, the acquiring detailed information and medical history of the target patient generates a first clinical schedule, including:
acquiring personal information, symptom descriptions, medical history and family medical history data of a patient;
preprocessing a data text, identifying key entities in medical history by using a named entity identification algorithm, and extracting key information in the medical history;
generating a first clinical plan based on the key entity and the key information;
the generated first clinical plan is submitted to a medical professional for review, and optimization and modification of the clinical plan is performed based on their opinion and advice.
In any of the above aspects, preferably, acquiring a second clinical plan of the target patient by the doctor, and generating the target clinical plan according to the first clinical plan and the second clinical plan, includes:
a doctor makes a second clinical plan according to the illness state and treatment progress of the target patient;
text matching and similarity calculation are carried out on the first clinical schedule and the second clinical schedule through a natural language processing algorithm, and the difference and the overlapped part between the two schedules are determined according to the matching result and the similarity evaluation;
and merging and adjusting the difference parts of the first clinical schedule and the second clinical schedule according to medical knowledge and rules to form a final target clinical schedule.
In a second aspect, an AI interactive system for clinical trials, comprising:
the acquisition module is used for acquiring basic data of clinical tests and constructing an AI interaction platform;
the screening module is used for screening target patients meeting clinical test standards through the AI interaction platform according to the historical medical records and the health data of the patients;
the generation module is used for acquiring detailed information and medical history of the target patient and generating a first clinical plan;
the planning module is used for acquiring a second clinical plan of a doctor on a target patient and generating a target clinical plan according to the first clinical plan and the second clinical plan;
and the test module is used for carrying out clinical tests according to the target clinical plans.
In a third aspect, a computing device includes:
one or more processors;
and a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the above-described methods.
In a fourth aspect, a computer readable storage medium stores a program that when executed by a processor implements the above method.
Compared with the prior art, the invention has the beneficial effects that:
the invention improves the accuracy and efficiency of patient screening by utilizing the AI technology to intelligently analyze and process the patient data and the test plan; meanwhile, by combining the professional judgment and experience of doctors, a more reasonable and feasible clinical test plan is generated.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification.
FIG. 1 is a schematic flow chart of the AI interaction method for clinical trials of the invention;
fig. 2 is a block diagram of an AI interactive system for clinical trials of 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.
It will be understood that when an element is referred to as being "mounted" or "disposed" on another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element.
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, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In order to better understand the above technical scheme, the following detailed description of the technical scheme of the present invention will be given with reference to the accompanying drawings of the specification and the specific embodiments.
The invention provides an AI interaction method for clinical trials, which comprises the following steps:
step 1, acquiring clinical test basic data and constructing an AI interaction platform;
step 2, screening target patients meeting clinical test standards through an AI interaction platform according to the historical medical records and health data of the patients;
step 3, acquiring detailed information and medical history of a target patient, and generating a first clinical plan;
step 4, obtaining a second clinical plan of the doctor to the target patient, and generating a target clinical plan according to the first clinical plan and the second clinical plan;
and 5, performing clinical tests according to the target clinical plans.
In the AI interaction method for clinical trial, which is provided by the embodiment of the invention, the centralized management and the efficient processing of the clinical trial data are realized by acquiring the clinical trial basic data and constructing the AI interaction platform. Therefore, the accessibility and analysis efficiency of data can be improved, better support is provided for the design, execution and analysis of clinical trials, and the accuracy and screening efficiency of target patients can be improved by utilizing the AI interaction platform to screen the target patients. This helps to expedite the recruitment of clinical trials, ensure that target patients meet trial criteria, improve the reliability and effectiveness of clinical trials, and provide more comprehensive and accurate patient information to the medical team by acquiring detailed information and medical history of the target patients and generating a first clinical plan. The method is favorable for making a personalized treatment scheme, improves the individuation degree and treatment effect of a clinical test, and can realize the integration and optimization of a clinical plan by acquiring a second clinical plan of a doctor on a target patient and generating the target clinical plan by combining the first clinical plan. This helps to improve the consistency and individuality of the treatment regimen of the clinical trial, ensures the scientificity and feasibility of the treatment regimen, performs the clinical trial according to the target clinical schedule, and can ensure the consistency and individuality of the treatment regimen of the clinical trial. This helps to improve the therapeutic effect and data reliability of clinical trials, providing better support for medical research and treatment.
Optionally, the step 1, obtaining clinical test basic data includes:
step 11, defining a regular expression pattern, and screening character strings conforming to a date format;
step 12, sending a request to a target website, receiving webpage content, analyzing the webpage, and acquiring clinical test basic data according to the specific tag and class name of the HTML;
step 13, generating a unique hash value according to each piece of data, and storing the unique hash value in a hash table to remove repeated data;
step 14, performing Z-score standardization on the data, and adjusting the data to a uniform standard normal distribution;
and step 15, calculating the importance of each word by using a TF-IDF algorithm, and classifying the text by using a naive Bayesian algorithm to obtain normal data.
In the AI interaction method for clinical trials, which is disclosed by the embodiment of the invention, the character strings conforming to the date format can be effectively screened out by defining the regular expression pattern. The method is favorable for extracting date information in clinical test data, ensures the accuracy and consistency of the data, and can acquire clinical test basic data by sending a request to a target website and analyzing a webpage. This helps to gather information about clinical trials, such as study purpose, sample size, treatment regimen, etc. The required data can be accurately extracted by analyzing the specific tag and class name of the webpage, the acquisition efficiency and accuracy of the data are improved, and the repeated clinical test data can be removed by generating and storing the unique hash value in the hash table. The method is helpful for ensuring the uniqueness of the data, avoiding the interference of repeated data on analysis and decision, improving the quality and accuracy of the data, and converting the data into uniform standard normal distribution by performing Z-score standardization on the data. The method is helpful for eliminating dimension differences among different data, so that the data has comparability and interpretability, the accuracy and the reliability of data analysis are improved, and normal data can be obtained by calculating the importance of each word by using a TF-IDF algorithm and carrying out text classification by combining a naive Bayesian algorithm. The method is favorable for carrying out text analysis and classification on clinical test basic data, identifying normal data and improving the accuracy and reliability of the data.
Optionally, step 2, screening, according to the historical medical records and the health data of the patient, the target patient meeting the clinical test standard through the AI interaction platform, including:
step 21, converting the medical records of the patient into a structured data format, and extracting keywords, disease diagnosis and treatment scheme information;
step 22, performing feature extraction and classification by using a machine learning algorithm based on the health data of the patient;
step 23, constructing a knowledge graph or expert system, and integrating clinical test standards and medical knowledge;
step 24, applying a recommendation algorithm to recommend a target clinical trial for a target patient meeting clinical trial criteria based on the patient's medical records and health data.
In the AI interaction method for clinical trials, which is disclosed by the embodiment of the invention, the medical records of patients are converted into the structured data format, so that the processibility and the analyzability of the data can be improved. The medical professional can be helped to better understand the illness state and treatment history of the patient by extracting the key words and the information of the illness diagnosis and treatment scheme, a basis is provided for the subsequent clinical test screening, and the useful characteristics can be extracted from the health data of the patient and classified and judged by a machine learning algorithm. The method is favorable for identifying the target patients meeting the clinical test standard, improves the screening accuracy and efficiency, and can provide more comprehensive and accurate reference for screening the target patients by constructing a knowledge graph or an expert system and integrating the clinical test standard and medical knowledge. This helps to ensure that the screening process meets the requirements of clinical trials and improves the scientificity and reliability of the screening, and by applying a recommendation algorithm, appropriate clinical trials can be recommended for target patients meeting clinical trial criteria based on the patient's medical records and health data. This helps to increase the recruitment efficiency and accuracy of clinical trials, providing more personalized and appropriate treatment opportunities for the target patient.
Optionally, the step 21 converts the medical record of the patient into a structured data format, and extracts keywords, disease diagnosis and treatment plan information, including:
step 211, performing text cleaning on the medical record of the patient, performing word segmentation processing, and dividing the text into words or phrases;
step 212, applying a named entity recognition algorithm to recognize entity information in the medical record;
step 213, marking the parts of speech of each word by using a part of speech marking algorithm;
step 214, calculating the importance of each word by using TF-IDF algorithm, and selecting the word with the top ranking as the key word;
at step 215, a medical record sample is constructed containing known disease diagnosis and treatment protocols, and the medical records are classified using a machine learning algorithm to determine the categories of diagnosis and treatment protocols.
In the AI interaction method for clinical trial according to the embodiment of the invention, irrelevant characters and punctuation marks can be removed through text cleaning and word segmentation processing, and texts are divided into meaningful words or phrases. This helps to improve the accuracy and efficiency of subsequent text processing and analysis, and through named entity recognition algorithms, entity information in medical records, such as disease names, drug names, surgical names, etc., can be identified. The method is helpful for extracting key entities, provides a basis for subsequent information extraction and analysis, and can label the parts of speech of each word, such as nouns, verbs, adjectives and the like, through a part of speech labeling algorithm. This helps understand the grammatical and semantic features of the words, provides a more accurate basis for subsequent information extraction and analysis, and by means of the TF-IDF algorithm, the importance of each word in the text can be calculated. The words with the most representative and important words in the text can be extracted by selecting the words with the highest rank as key words, so that important clues are provided for subsequent information extraction and analysis, and the automatic classification and diagnosis of medical records can be realized by constructing medical record samples containing known disease diagnosis and treatment schemes and classifying by using a machine learning algorithm. This helps to quickly determine the diagnosis and treatment plan in the medical record, improving the accuracy of the diagnosis and the degree of individuation of the treatment plan.
Optionally, the step 22 uses a machine learning algorithm to perform feature extraction and classification based on the health data of the patient, including:
step 221, extracting physiological parameters, genome data and biochemical indexes according to the health data of the patient to obtain health characteristics, and preprocessing each characteristic;
step 222, selecting target features from the preprocessed features by using a feature selection algorithm;
step 223, according to the feature data and the known label, node division is carried out on the target feature, and a decision tree model is constructed; selecting the nearest features on each node for division, and classifying according to the feature values;
and 224, constructing a classification model, inputting new patient characteristic data into the classification model, and carrying out classification prediction according to the characteristic values to judge the category to which the patient belongs.
In the AI interaction method for clinical trial of the embodiment of the invention, abundant characteristic information can be obtained by extracting health data such as physiological parameters, genome data, biochemical indexes and the like of patients. Features with different scales can be converted into a comparable form through preprocessing such as normalization and standardization, the interpretability and analysis effect of the features are improved, and the most relevant features can be selected from the preprocessed features through a feature selection algorithm. The method is beneficial to eliminating irrelevant features, improving the accuracy and generalization capability of the classification model, reducing feature dimension, improving the efficiency and the interpretation of the model, and realizing the classification of target features by constructing a decision tree model and carrying out node division according to feature data and known labels. In the construction process of the decision tree model, the nearest features are selected for division, classification is carried out according to the feature values, the accuracy and the interpretation of the classification model are improved, and new patient feature data can be input into the model by constructing the classification model, and classification prediction is carried out according to the feature values. This helps to determine the category to which the patient belongs, such as disease type, risk level, etc. Through application of the classification model, support can be provided for medical decision making, and personalized treatment scheme and prediction can be realized.
Optionally, step 3, obtaining detailed information and medical history of the target patient, and generating a first clinical schedule includes:
step 31, personal information, symptom descriptions, medical history and family medical history data of the patient are obtained;
step 32, preprocessing the data text, identifying key entities in the medical history by using a named entity identification algorithm, and extracting key information in the medical history;
step 33, generating a first clinical plan based on the key entity and the key information;
step 34, submitting the generated first clinical plan to a medical professional for review, packaging, and optimizing and modifying the clinical plan based on their opinion and advice.
In the AI interaction method for clinical trial provided by the embodiment of the invention, the illness state and medical background of the patient can be comprehensively known by acquiring the personal information, symptom description, medical history and family medical history data of the patient. The method is beneficial to the medical team to make personalized treatment schemes, improves the accuracy and the personalized degree of medical decision making, and can extract key entities and key information in medical history by preprocessing data texts and applying a named entity recognition algorithm. The method is favorable for quickly identifying key entities such as disease names, drug names, operation names and the like, extracting key information in medical history, providing a basis for generating subsequent clinical plans, and converting the illness state and treatment requirements of patients into specific treatment schemes by generating a first clinical plan based on the key entities and the key information. This helps the medical team in developing a treatment plan to improve the individuality and scientificity of the treatment plan in consideration of the patient's special situation and needs, and by generating a first clinical plan based on the key entities and key information, the patient's condition and treatment needs can be converted into a specific treatment plan. This helps the medical team to increase the individuation and scientificity of the treatment plan in consideration of the patient's special situation and needs when making the treatment plan.
Optionally, step 4, obtaining a second clinical schedule of the doctor for the target patient, and generating the target clinical schedule according to the first clinical schedule and the second clinical schedule, includes:
step 41, a doctor makes a second clinical plan according to the illness state and treatment progress of the target patient;
step 42, performing text matching and similarity calculation on the first clinical schedule and the second clinical schedule through a natural language processing algorithm, and determining differences and overlapping parts between the two schedules according to matching results and similarity evaluation;
and 43, merging and adjusting the difference parts of the first clinical schedule and the second clinical schedule according to medical knowledge and rules to form a final target clinical schedule.
In the AI interaction method for clinical trial provided by the embodiment of the invention, the doctor can make a second clinical plan according to the illness state and treatment progress of the target patient, and can perform personalized adjustment and optimization according to the actual condition of the patient. The method is favorable for improving the accuracy and individuation degree of the treatment scheme so as to better meet the treatment requirement of the patient, and the similarity and the difference of the two plans can be quickly compared by carrying out text matching and similarity calculation on the first clinical plan and the second clinical plan through a natural language processing algorithm. This helps to determine the overlap and difference between the two schedules, providing a basis for subsequent merging and adjustment, by merging and adjusting the difference between the first and second clinical schedules according to medical knowledge and rules, the final target clinical schedule can be formed. This helps to combine the advantages of both schedules, improving the scientificity and feasibility of the treatment regimen, and providing better medical services to the patient.
The invention also provides an AI interaction system for clinical trials, comprising:
the acquisition module is used for acquiring basic data of clinical tests and constructing an AI interaction platform;
the screening module is used for screening target patients meeting clinical test standards through the AI interaction platform according to the historical medical records and the health data of the patients;
the generation module is used for acquiring detailed information and medical history of the target patient and generating a first clinical plan;
the planning module is used for acquiring a second clinical plan of a doctor on a target patient and generating a target clinical plan according to the first clinical plan and the second clinical plan;
and the test module is used for carrying out clinical tests according to the target clinical plans.
It should be noted that the apparatus is an apparatus corresponding to the above method, and all implementation manners in the above method embodiment are applicable to this embodiment, so that the same technical effects can be achieved.
Embodiments of the present invention also provide a computing device comprising: a processor, a memory storing a computer program which, when executed by the processor, performs the method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a method as described above. All the implementation manners in the method embodiment are applicable to the embodiment, and the same technical effect can be achieved.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk, etc.
Furthermore, it should be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. Also, the steps of performing the series of processes described above may naturally be performed in chronological order in the order of description, but are not necessarily performed in chronological order, and some steps may be performed in parallel or independently of each other. It will be appreciated by those of ordinary skill in the art that all or any of the steps or components of the methods and apparatus of the present invention may be implemented in hardware, firmware, software, or a combination thereof in any computing device (including processors, storage media, etc.) or network of computing devices, as would be apparent to one of ordinary skill in the art after reading this description of the invention.
The object of the invention can thus also be achieved by running a program or a set of programs on any computing device. The computing device may be a well-known general purpose device. The object of the invention can thus also be achieved by merely providing a program product containing program code for implementing said method or apparatus. That is, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. It is apparent that the storage medium may be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is apparent that the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present invention. The steps of executing the series of processes may naturally be executed in chronological order in the order described, but are not necessarily executed in chronological order. Some steps may be performed in parallel or independently of each other.
The above is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that the present invention is described in detail with reference to the foregoing embodiments, and modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An AI interaction method for clinical trials is characterized in that: the method comprises the following steps:
acquiring clinical test basic data and constructing an AI interaction platform;
screening target patients meeting clinical test standards through an AI interaction platform according to the historical medical records and health data of the patients;
acquiring detailed information and medical history of a target patient, and generating a first clinical plan;
acquiring a second clinical plan of a doctor on a target patient, and generating a target clinical plan according to the first clinical plan and the second clinical plan;
clinical trials were conducted according to the target clinical program.
2. The AI interaction method for clinical trials of claim 1, wherein: the acquisition of clinical trial basic data comprises the following steps:
defining a regular expression pattern, and screening character strings conforming to a date format;
sending a request to a target website, receiving webpage content, analyzing the webpage, and acquiring clinical test basic data according to the specific tag and class name of the HTML;
generating a unique hash value according to each piece of data, and storing the unique hash value in a hash table to remove repeated data;
performing Z-score standardization on the data, and adjusting the data to a uniform standard normal distribution;
and calculating the importance of each word by using a TF-IDF algorithm, and classifying the text by using a naive Bayesian algorithm to obtain normal data.
3. The AI interaction method for clinical trials according to claim 2, wherein: screening target patients meeting clinical test standards through an AI interaction platform according to the historical medical records and health data of the patients, wherein the method comprises the following steps:
converting the medical records of the patient into a structured data format, and extracting keywords, disease diagnosis and treatment scheme information;
based on the health data of the patient, performing feature extraction and classification using a machine learning algorithm;
constructing a knowledge graph or an expert system, and integrating clinical test standards and medical knowledge;
and (3) recommending a target clinical test for a target patient according to the medical record and the health data of the patient by using a recommendation algorithm.
4. The AI interaction method for clinical trials according to claim 3, wherein: the method for converting the medical records of the patient into a structured data format and extracting keywords, disease diagnosis and treatment scheme information comprises the following steps:
the method comprises the steps of performing text cleaning on medical records of patients, performing word segmentation processing, and dividing the texts into words or phrases;
applying a named entity recognition algorithm to recognize entity information in the medical record;
performing part-of-speech tagging on each word by using a part-of-speech tagging algorithm;
calculating the importance of each word by using a TF-IDF algorithm, and selecting the word ranked at the top as a keyword;
a sample of medical records containing known disease diagnosis and treatment protocols is constructed and the medical records are classified using a machine learning algorithm to determine the categories of diagnosis and treatment protocols.
5. The AI interaction method for clinical trials of claim 4, wherein: the patient-based health data feature extraction and classification using a machine learning algorithm, comprising:
extracting physiological parameters, genome data and biochemical indexes according to health data of a patient to obtain health characteristics, and preprocessing each characteristic;
selecting target features from the preprocessed features by using a feature selection algorithm;
according to the feature data and the known labels, carrying out node division on the target features, and constructing a decision tree model; selecting the nearest features on each node for division, and classifying according to the feature values;
and constructing a classification model, inputting new patient characteristic data into the classification model, carrying out classification prediction according to the characteristic values, and judging the category to which the patient belongs.
6. The AI interactive method for clinical trials according to claim 5, wherein: the obtaining of the detailed information and medical history of the target patient generates a first clinical schedule comprising:
acquiring personal information, symptom descriptions, medical history and family medical history data of a patient;
preprocessing a data text, identifying key entities in medical history by using a named entity identification algorithm, and extracting key information in the medical history;
generating a first clinical plan based on the key entity and the key information;
the generated first clinical plan is submitted to a medical professional for review, and optimization and modification of the clinical plan is performed based on their opinion and advice.
7. The AI interaction method for clinical trials of claim 6, wherein: the obtaining a second clinical schedule of the doctor for the target patient, and generating a target clinical schedule according to the first clinical schedule and the second clinical schedule, includes:
a doctor makes a second clinical plan according to the illness state and treatment progress of the target patient;
text matching and similarity calculation are carried out on the first clinical schedule and the second clinical schedule through a natural language processing algorithm, and the difference and the overlapped part between the two schedules are determined according to the matching result and the similarity evaluation;
and merging and adjusting the difference parts of the first clinical schedule and the second clinical schedule according to medical knowledge and rules to form a final target clinical schedule.
8. An AI interactive system for clinical trials, comprising:
the acquisition module is used for acquiring basic data of clinical tests and constructing an AI interaction platform;
the screening module is used for screening target patients meeting clinical test standards through the AI interaction platform according to the historical medical records and the health data of the patients;
the generation module is used for acquiring detailed information and medical history of the target patient and generating a first clinical plan;
the planning module is used for acquiring a second clinical plan of a doctor on a target patient and generating a target clinical plan according to the first clinical plan and the second clinical plan;
and the test module is used for carrying out clinical tests according to the target clinical plans.
9. A computing device, comprising: one or more processors; one or more processors; storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a program which, when executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410264726.XA CN117854659A (en) | 2024-03-08 | 2024-03-08 | AI interaction method and system for clinical trial |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410264726.XA CN117854659A (en) | 2024-03-08 | 2024-03-08 | AI interaction method and system for clinical trial |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117854659A true CN117854659A (en) | 2024-04-09 |
Family
ID=90533117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410264726.XA Pending CN117854659A (en) | 2024-03-08 | 2024-03-08 | AI interaction method and system for clinical trial |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117854659A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070156459A1 (en) * | 2002-11-27 | 2007-07-05 | George Medica Pty. Ltd. | System for conducting clinical trials |
| CN108364692A (en) * | 2018-02-27 | 2018-08-03 | 北京盛诺家医院管理咨询有限公司 | Clinical test matching process and system |
| CN112489774A (en) * | 2020-11-30 | 2021-03-12 | 中国人民解放军陆军军医大学第二附属医院 | Clinical trial subject recruitment system |
| CN113314192A (en) * | 2021-06-17 | 2021-08-27 | 医渡云（北京）技术有限公司 | Clinical trial data processing system, method, device and storage medium |
| CN113626696A (en) * | 2021-08-06 | 2021-11-09 | 湖南慧泽生物医药科技有限公司 | Project recommendation method of clinical recruitment project recommendation platform |
| CN113724807A (en) * | 2021-08-30 | 2021-11-30 | 浙江海心智惠科技有限公司 | Rapid screening method of clinical test for patient diagnosis and treatment suggestion |
| CN116959650A (en) * | 2023-08-08 | 2023-10-27 | 丁雨周 | Clinical trial research nurse operation auxiliary system |
-
2024
- 2024-03-08 CN CN202410264726.XA patent/CN117854659A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070156459A1 (en) * | 2002-11-27 | 2007-07-05 | George Medica Pty. Ltd. | System for conducting clinical trials |
| CN108364692A (en) * | 2018-02-27 | 2018-08-03 | 北京盛诺家医院管理咨询有限公司 | Clinical test matching process and system |
| CN112489774A (en) * | 2020-11-30 | 2021-03-12 | 中国人民解放军陆军军医大学第二附属医院 | Clinical trial subject recruitment system |
| CN113314192A (en) * | 2021-06-17 | 2021-08-27 | 医渡云（北京）技术有限公司 | Clinical trial data processing system, method, device and storage medium |
| CN113626696A (en) * | 2021-08-06 | 2021-11-09 | 湖南慧泽生物医药科技有限公司 | Project recommendation method of clinical recruitment project recommendation platform |
| CN113724807A (en) * | 2021-08-30 | 2021-11-30 | 浙江海心智惠科技有限公司 | Rapid screening method of clinical test for patient diagnosis and treatment suggestion |
| CN116959650A (en) * | 2023-08-08 | 2023-10-27 | 丁雨周 | Clinical trial research nurse operation auxiliary system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Stanfill et al. | Health information management: implications of artificial intelligence on healthcare data and information management | |
| US10818397B2 (en) | Clinical content analytics engine | |
| US20220044812A1 (en) | Automated generation of structured patient data record | |
| CN109213870A (en) | Document process | |
| US20060136259A1 (en) | Multi-dimensional analysis of medical data | |
| US20110093293A1 (en) | Method and system for performing clinical data mining | |
| US8600772B2 (en) | Systems and methods for interfacing with healthcare organization coding system | |
| CN113243033A (en) | Integrated diagnostic system and method | |
| CN112635011A (en) | Disease diagnosis method, disease diagnosis system, and readable storage medium | |
| CN112037910A (en) | Health information management method, device, equipment and storage medium | |
| CN114664463A (en) | General practitioner diagnoses auxiliary system | |
| CN111597789A (en) | Electronic medical record text evaluation method and equipment | |
| Liu et al. | A large-scale multi-label 12-lead electrocardiogram database with standardized diagnostic statements | |
| CN112071431B (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| CN116721730B (en) | Whole-course patient management system based on digital therapy | |
| WO2023217737A1 (en) | Health data enrichment for improved medical diagnostics | |
| US20220293253A1 (en) | Systems and methods using natural language processing to improve computer-assisted coding | |
| Diomaiuta et al. | A novel system for the automatic extraction of a patient problem summary | |
| CN113643825B (en) | Medical case knowledge base construction method and system based on clinical key feature information | |
| CN117854659A (en) | AI interaction method and system for clinical trial | |
| Bajaj et al. | Non-Invasive Mental Health Prediction using Machine Learning: An Exploration of Algorithms and Accuracy | |
| Sánchez-de-Madariaga et al. | Semi-supervised incremental learning with few examples for discovering medical association rules | |
| EP3937105A1 (en) | Methods and systems for user data processing | |
| CN113191141A (en) | Method, device and equipment for generating inquiry regular expression and storage medium | |
| US20190198141A1 (en) | Systems and methods for generating subsets of electronic healthcare-related documents |
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 |