CN116364309B - Clinical trial risk assessment method and system based on neural network - Google Patents
Clinical trial risk assessment method and system based on neural network Download PDFInfo
- Publication number
- CN116364309B CN116364309B CN202310313034.5A CN202310313034A CN116364309B CN 116364309 B CN116364309 B CN 116364309B CN 202310313034 A CN202310313034 A CN 202310313034A CN 116364309 B CN116364309 B CN 116364309B
- Authority
- CN
- China
- Prior art keywords
- historical
- risk
- clinical trial
- clinical
- stage
- 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.)
- Active
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 22
- 238000012360 testing method Methods 0.000 claims abstract description 192
- 239000003814 drug Substances 0.000 claims abstract description 33
- 229940079593 drug Drugs 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000015556 catabolic process Effects 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000007726 management method Methods 0.000 description 3
- 238000012827 research and development Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000012550 audit Methods 0.000 description 1
- 239000012472 biological sample Substances 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000002547 new drug Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012552 review Methods 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
- 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
- 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
- G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
-
- 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)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Medicinal Chemistry (AREA)
- Toxicology (AREA)
- Pharmacology & Pharmacy (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioethics (AREA)
- Chemical & Material Sciences (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Automatic Analysis And Handling Materials Therefor (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a clinical trial risk assessment method and system based on a neural network. The method comprises the steps of obtaining a historical clinical test risk record and generating a preset test variable control constraint; formulating a first clinical trial regimen of a first drug, wherein the first clinical trial regimen comprises a first clinical trial stage and a second clinical trial stage; tracking the clinical trial execution overall process and obtaining a first clinical trial record including first record data for the first clinical trial stage; analyzing the first recorded data, calculating to obtain a first safety index, judging whether a preset safety threshold is met, and if so, performing a second clinical test stage; and forming first input information, and obtaining a first clinical trial risk index of the first medicament through an intelligent risk assessment model. Compared with the prior art, the invention can improve the intelligent degree of clinical test risk analysis and improve the comprehensiveness, accuracy and high efficiency of risk assessment.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a clinical trial risk assessment method and system based on a neural network.
Background
In recent years, the average time and cost of successful development and marketing of a new drug have been on the rise. The clinical test of the medicine has long period, large investment and high risk, is a key link and a speed limiting step of medicine research and development, but the clinical test is an important ring of new medicine research and development, and the risk of early termination due to various reasons is also continuously increasing. Furthermore, current clinical trial quality management focuses on traditional audit patterns of single data, which makes pharmaceutical enterprises devoted to a large amount of resources, but it is difficult to timely and effectively discover the systematic and trending problems present in clinical trial data. In general, the existing method has the defects that the risk analysis of the clinical test is not comprehensive enough, the analysis and evaluation accuracy is low, the risk cannot be found in time, and the targeted emergency measures are taken, so that the safety of the clinical risk is poor.
Therefore, how to improve the comprehensiveness and accuracy of clinical test risk analysis by means of computer science and technology provides theoretical guidance for test adjustment, and further improves the effectiveness, reliability and safety of clinical tests, and becomes a problem to be solved urgently.
Disclosure of Invention
The invention mainly aims to provide a clinical trial risk assessment method and system based on a neural network, aiming at improving the assessment efficiency of clinical trial risk and assessing close facts by means of computer technology.
In order to achieve the above purpose, the present invention provides a clinical trial risk assessment method based on a neural network, comprising the following steps:
obtaining a historical clinical test risk record based on big data, and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint;
under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage;
tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage;
analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction;
and obtaining a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine.
In addition, in order to achieve the above object, the present invention also provides a clinical trial risk assessment system based on a neural network, the clinical trial risk assessment system including a memory and a processor, wherein the memory stores a clinical trial risk assessment program, and the clinical trial risk assessment program when executed by the processor implements the steps of:
constraint generation: obtaining a historical clinical test risk record based on big data, and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint;
the scheme making step: under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage;
tracking and recording: tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage;
and a safety analysis step: analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction;
risk assessment step: and obtaining a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine.
In addition, to achieve the above object, the present invention also proposes a computer device, including a processor and a memory;
the processor is used for processing and executing the clinical trial risk assessment method based on the neural network;
the memory is coupled to the processor for storing the clinical trial risk assessment program which, when executed by the processor, causes the system to perform the steps of the clinical trial risk assessment method.
Furthermore, to achieve the above object, the present invention also proposes a computer-readable storage medium storing a clinical trial risk assessment program executable by at least one processor to cause the at least one processor to perform the steps of the clinical trial risk assessment method according to any one of the above.
The invention relates to the technical field of artificial intelligence, and discloses a clinical trial risk assessment method and system based on a neural network. According to the method, a historical clinical test risk record is obtained based on big data, and data in the historical clinical test risk record are analyzed to generate a preset test variable control constraint; under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage; tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage; analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction; and obtaining a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine. Compared with the prior art, the invention can improve the intelligent degree of clinical test risk analysis and improve the comprehensiveness, accuracy and high efficiency of risk assessment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the structures shown in these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a neural network-based clinical trial risk assessment method of the present invention;
FIG. 2 is a schematic flow chart of the method for evaluating clinical trial risk based on neural network, wherein the subjective risk factor set is used as the control constraint of the preset trial variable;
FIG. 3 is a schematic flow chart of constructing a risk emergency processing database in a clinical trial risk assessment method based on a neural network according to the present invention;
FIG. 4 is a schematic flow chart of determining the preset safety threshold in a clinical trial risk assessment method based on a neural network according to the present invention;
FIG. 5 is a schematic flow chart of training the intelligent risk assessment model in the neural network-based clinical trial risk assessment method;
FIG. 6 is a schematic diagram of an operating environment of a neural network-based clinical trial risk assessment program according to the present invention;
fig. 7 is a program block diagram of a clinical trial risk assessment program based on a neural network according to the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Description of the drawings:
the system comprises an electronic device 6, a clinical trial risk assessment program 60, a memory 61, a processor 62, a display 63, a constraint generating module 701, a scheme making module 702, a tracking recording module 703, a security analysis module 704 and a risk assessment module 705.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
The invention provides a clinical trial risk assessment method based on a neural network.
Referring to fig. 1, fig. 1 is a schematic flow chart of a clinical trial risk assessment method based on a neural network according to the present invention.
In this embodiment, the method includes:
step S100: obtaining a historical clinical test risk record based on big data, and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint;
as shown in fig. 2, in this embodiment, the method for obtaining a historical clinical test risk record based on big data and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint includes the following steps:
firstly, analyzing the historical clinical test risk record by using an accident tree method to obtain an analysis result;
then, a subjective risk factor set is established based on the analysis result; and
and finally, taking the subjective risk factor set as the control constraint of the preset test variable.
The clinical test has the characteristics of long test period, large drug research and development investment and extremely high risk, and the risk in the clinical test process is evaluated and analyzed based on the risk management method, so that the method has important significance for subsequent test management and control and improvement of test safety and effectiveness.
Firstly, data recorded in each clinical test in history are collected based on big data, and are analyzed, namely, preset test variable control constraint is generated by analyzing the data in the historical clinical test risk record. Specifically, the accident tree method is utilized to analyze each clinical test risk event in the historical clinical test risk record, so that the reasons of problems in each clinical test in history are obtained, the reasons of the problems are summarized and arranged, subjective factors which can influence the safety of the clinical test are obtained, namely, a subjective risk factor set is built, and the subjective risk factor set is used as the control constraint of the preset test variable.
The historical clinical data is analyzed, the risk variable in the clinical test process is obtained, and is further used as a constraint variable to control, so that the reliability of the clinical test is effectively improved, the historical clinical test data and experience are utilized to the maximum extent, and the success probability of the clinical test can be improved.
Step S200: under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage;
as shown in fig. 3, in this embodiment, after the first clinical test regimen of the first drug is formulated, the method further includes:
first, analyzing the first clinical trial plan to generate a first work breakdown structure;
secondly, analyzing the first work decomposition structure diagram and constructing a first potential risk set, wherein the first potential risk set comprises P potential risks, and P is a positive integer;
thirdly, sequentially making emergency schemes of the P potential risks, obtaining the P emergency schemes, and building a risk emergency processing database, wherein the P emergency schemes and the P potential risks have corresponding relations.
After the historical clinical test record data are analyzed and the variable constraint of clinical test is determined, a first clinical test scheme of a first medicament is formulated based on the preset test variable control constraint, wherein the first medicament is any medicament which needs to be subjected to clinical test after development, the first clinical test scheme is a test scheme of performing clinical test on the first medicament, and the first clinical test scheme comprises a first clinical test stage and a second clinical test stage. That is, the first clinical trial regimen includes a regimen of each trial phase of a clinical trial on the first drug. Exemplary are, for example, project design control for clinical trial protocols prior to clinical trials, as well as systematic training for researchers, and ethical review of volunteers participating in clinical trials, and the like. And then, carrying out authenticity check on data information recorded in the clinical test after the clinical test, and carrying out scientific and reasonable detection and storage on biological samples. The risk of the later clinical test is reduced by effectively controlling the variables, and the scientific and reasonable clinical test is ensured.
Further, after a first clinical trial regimen of the first drug is formulated based on historical clinical trial experience, the first clinical trial regimen is decomposed using a work decomposition structural tool, corresponding to the first work decomposition structural diagram of the first clinical trial regimen. And then, analyzing the first work decomposition structure diagram, and determining all risks existing in the first clinical test scheme according to an analysis result, namely, constructing the first potential risk set, wherein the first potential risk set comprises P potential risks, and P is a positive integer. Exemplary are brain storms, risk factors for each step of an analytical test protocol, etc., as performed by the relevant professional. Correspondingly, sequentially making emergency schemes of all the potential risks in the P potential risks, and correspondingly obtaining the P emergency schemes. And the P emergency schemes have corresponding relations with the P potential risks. And finally, constructing a risk emergency treatment database based on the P potential risks, the P emergency schemes and the mutual corresponding relations thereof, and storing the risk emergency treatment database in the clinical trial risk assessment system.
By analyzing the first clinical test scheme and correspondingly constructing a risk emergency treatment database of the scheme, once a risk accident occurs in a later clinical test, the corresponding solution can be quickly matched through the risk emergency database, so that the risk treatment speed and effect are improved, and the safety of the clinical test is finally ensured.
Step S300: tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage;
step S400: analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction;
as shown in fig. 4, in this embodiment, before the analyzing the first recorded data and calculating to obtain a first security index, and determining whether the first security index meets a preset security threshold, the method includes:
acquiring a first historical risk event in the historical clinical trial risk record;
analyzing the stage of the first historical risk event in the first historical clinical trial to be set as a first historical risk stage;
judging whether the first historical risk stage is a first stage of the first historical clinical trial;
if yes, calling a preset calculation scheme and calculating to obtain a first preset safety threshold;
acquiring a second historical risk event in the historical clinical test risk record, and calculating a second preset safety threshold according to the second historical risk event;
comparing the first preset safety threshold value with the second preset safety threshold value, and determining the preset safety threshold value.
In this embodiment, the calling the preset calculation scheme and calculating to obtain the first preset security threshold includes:
firstly, according to the preset calculation scheme, first historical record data of the first historical risk stage are obtained;
then, acquiring a preset safety factor index, and traversing in the first historical record data to obtain a first index parameter;
then, calculating according to the first index parameter to obtain a first historical safety index; and
finally, the first preset security threshold is determined based on the first historical security index.
When the first medicine is subjected to clinical test based on the first clinical test scheme, the related personnel conduct comprehensive and detailed record on the test process, namely, the whole process is implemented through tracking the clinical test, and a first clinical test record is obtained, wherein the first clinical test record comprises first record data of a first clinical test stage, and the first record data refers to data record corresponding to the first test stage when the clinical test is conducted. And then analyzing the first recorded data and calculating to obtain the comprehensive safety condition of the first medicament in the first test stage, namely obtaining the first safety index. Further, whether the first safety index meets a preset safety threshold is judged, if yes, a system sends out a continuous test instruction, and the second clinical test stage is carried out based on the instruction. Wherein the second clinical trial phase refers to a phase subsequent to the first clinical trial phase.
When calculating the safety index of the first clinical test stage, namely calculating the first safety index, firstly acquiring a preset safety factor index, traversing the preset safety factor index in the first historical record data to obtain a parameter actually corresponding to the preset safety factor index, namely the first index parameter, carrying out normalization processing on the first index parameter, calculating the weight of each factor index through a weight coefficient algorithm, and further carrying out weighted calculation to obtain the first historical safety index. Finally, the first preset security threshold is determined based on the first historical security index. In particular, according to the actual calculated historical safety index, in combination with the historical situation, the clinical trial already has a risk under this safety index, so that the safety threshold should be brought above said first historical safety index. For example, if the first historical security index is 0.75, the corresponding first preset security threshold is (0.75,1). Further, a first historical risk event in the historical clinical test risk record is obtained, and a stage of the first historical risk event in the first historical clinical test is analyzed and is set as a first historical risk stage. Next, it is determined whether the first historical risk stage is a first stage of the first historical clinical trial. When the first historical risk stage is the first stage of the first historical clinical test, the system automatically calls a preset calculation scheme and calculates a first preset safety threshold value, and meanwhile, a second historical risk event in the historical clinical test risk record is acquired, and a second preset safety threshold value is calculated according to the second historical risk event. Finally, comparing the first preset safety threshold value with the second preset safety threshold value, and determining the preset safety threshold value. That is, based on the historical security risk event, the preset security threshold is analyzed and adjusted for multiple times to determine the optimal threshold. For example, if the first historical security index is 0.75, the first preset security threshold is initially set (0.75,1), and if the second historical security index is 0.85, the initially set first preset security threshold is adjusted (0.85,1).
The risk index threshold value of each stage of the clinical test which does not cause the risk event is determined based on historical data mining analysis, so that the quantitative and objective treatment targets of the clinical test risk are realized, and accurate and objective numerical information is provided for identifying the clinical test risk.
As shown in fig. 5, in this embodiment, after determining whether the first historical risk stage is the first stage of the first historical clinical trial, the method further includes:
if not, acquiring second historical record data of a second historical risk stage;
wherein the second historical risk stage refers to a stage previous to the first historical risk stage;
analyzing the second historical record data and calculating to obtain a second historical security index;
acquiring a first historical clinical trial risk index of the first historical clinical trial;
combining the second historical safety index, the first historical safety index and the first historical clinical trial risk index to obtain training data;
and training to obtain the intelligent risk assessment model according to the training data.
When the first historical risk stage is not the first stage of the first historical clinical trial, the system automatically obtains second historical record data for a second historical risk stage. Wherein the second historical risk stage refers to a stage previous to the first historical risk stage. That is, by analyzing the data of the previous trial phase, a risk assessment basis is provided for the clinical trial of the subsequent phase. And then, analyzing the second historical record data and calculating to obtain a second historical safety index, wherein the system is combined with the first historical safety index of the first historical clinical test to be used as input information of model training together at the moment, and further combined with the first historical clinical test risk index to obtain model training data. And finally, training to obtain the intelligent risk assessment model according to the training data. The intelligent risk assessment model is trained to provide a model foundation for clinical trial risk assessment with high efficiency and high intelligent degree.
Step S500: and obtaining a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine.
In this embodiment, the obtaining the first historical clinical trial risk index of the first historical clinical trial includes:
a first step, the first historical clinical trial having a first final goal;
step two, combining the first historical record data to obtain a first target realization risk index; and
and thirdly, taking the first target realization risk index as a first historical clinical trial risk index.
After the intelligent risk assessment model is obtained through training, the system takes the relevant data of the first clinical test scheme, namely the second safety index and the first safety index of the second clinical test stage, as first input information of the intelligent risk assessment model, and obtains a corresponding first output result through the intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine. The first historical clinical test risk index refers to a comprehensive risk index of the first clinical test scheme, specifically, the first historical clinical test has a first final target, so that a first target implementation risk index is obtained by combining the first historical record data, and then the first target implementation risk index is used as a first historical clinical test risk index.
The invention relates to the technical field of artificial intelligence, and discloses a clinical trial risk assessment method and system based on a neural network. According to the method, a historical clinical test risk record is obtained based on big data, and data in the historical clinical test risk record are analyzed to generate a preset test variable control constraint; under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage; tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage; analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction; and obtaining a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine. Compared with the prior art, the invention can improve the intelligent degree of clinical test risk analysis and improve the comprehensiveness, accuracy and high efficiency of risk assessment.
The invention provides a clinical trial risk assessment program based on a neural network.
Referring to FIG. 6, a schematic diagram of the operating environment of a clinical trial risk assessment program 60 according to the present invention is shown.
In the present embodiment, the clinical trial risk assessment program 60 is installed and run in the electronic device 6. The electronic device 6 may be a computing device such as a desktop computer, a notebook computer, a palm top computer, a server, etc. The electronic device 6 may include, but is not limited to, a memory 61, a processor 62, and a display 63. Fig. 6 shows only the electronic device 6 with components 11-13, but it is understood that not all shown components are required to be implemented, and that more or fewer components may alternatively be implemented.
The memory 61 may in some embodiments be an internal storage unit of the electronic device 6, such as a hard disk or a memory of the electronic device 6. The memory 61 may also be an external storage device of the electronic apparatus 6 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic apparatus 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the electronic apparatus 6. The memory 61 is used for storing application software installed on the electronic device 6 and various data, such as program codes of the clinical trial risk assessment program 60. The memory 61 may also be used to temporarily store data that has been output or is to be output.
The processor 62 may in some embodiments be a central processing unit (Central Processing Unit, CPU), microprocessor or other data processing chip for executing program code or processing data stored in the memory 61, such as executing the clinical trial risk assessment program 60 or the like.
The display 63 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like in some embodiments. The display 63 is used for displaying information processed in the electronic device 6 and for displaying a visualized user interface. The components 11-13 of the electronic device 6 communicate with each other via a program bus.
Referring to FIG. 7, a block diagram of a clinical trial risk assessment program 60 according to the present invention is shown.
In this embodiment, the clinical trial risk assessment program 60 may be divided into one or more modules, which are stored in the memory 61 and executed by one or more processors (the processor 62 in this embodiment) to complete the present invention. For example, in fig. 7, the clinical trial risk assessment program 60 may be partitioned into a constraint generation module 701, a solution formulation module 702, a tracking record module 703, a security analysis module 704, a risk assessment module 705. The modules of the present invention refer to a series of computer program instruction segments capable of performing a specific function, more suitable than the program for describing the execution of the clinical trial risk assessment program 60 in the electronic device 6, wherein:
constraint generation module 701: obtaining a historical clinical test risk record based on big data, and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint;
scheme formulation module 702: under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage;
trace recording module 703: tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage;
the security analysis module 704: analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction;
risk assessment module 705: and obtaining a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine.
The application also provides an electronic device, which comprises a processor and a memory;
the processor configured to process the step of performing the clinical trial risk assessment method according to any one of the above embodiments;
the memory is coupled to the processor for storing a program that, when executed by the processor, causes the system to perform the steps of any of the clinical trial risk assessment methods described above.
Further, the present invention also proposes a computer-readable storage medium storing a clinical trial risk assessment program executable by at least one processor to cause the at least one processor to perform the clinical trial risk assessment method of any of the above embodiments.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structural changes made by the description of the present invention and the accompanying drawings or direct/indirect application in other related technical fields are included in the scope of the invention.
Claims (7)
1. A neural network-based clinical trial risk assessment method, comprising:
obtaining a historical clinical test risk record based on big data, and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint;
under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage;
tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage;
acquiring a first historical risk event in the historical clinical trial risk record;
analyzing the stage of the first historical risk event in the first historical clinical trial to be set as a first historical risk stage;
judging whether the first historical risk stage is a first stage of the first historical clinical trial;
if yes, calling a preset calculation scheme and calculating to obtain a first preset safety threshold;
acquiring a second historical risk event in the historical clinical test risk record, and calculating a second preset safety threshold according to the second historical risk event;
comparing the first preset safety threshold value with the second preset safety threshold value, and determining a preset safety threshold value;
analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction;
acquiring a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine;
the calling the preset calculation scheme and calculating to obtain a first preset safety threshold value comprises the following steps:
acquiring first historical record data of the first historical risk stage according to the preset calculation scheme;
acquiring a preset safety factor index, and traversing in the first historical record data to obtain a first index parameter;
calculating according to the first index parameter to obtain a first historical safety index; and
determining the first preset safety threshold based on the first historical safety index;
the method for obtaining the historical clinical test risk record based on the big data and analyzing the data in the historical clinical test risk record to generate a preset test variable control constraint comprises the following steps:
analyzing the historical clinical test risk record by using an accident tree method to obtain an analysis result;
establishing a subjective risk factor set based on the analysis result; and
and taking the subjective risk factor set as the control constraint of the preset test variable.
2. The method of claim 1, further comprising, after the formulating the first clinical trial regimen of the first drug:
analyzing the first clinical trial plan to generate a first work breakdown structure;
analyzing the first work decomposition structure diagram and constructing a first potential risk set, wherein the first potential risk set comprises P potential risks, and P is a positive integer;
and sequentially making the emergency schemes of the P potential risks, obtaining the P emergency schemes, and building a risk emergency processing database, wherein the P emergency schemes and the P potential risks have corresponding relations.
3. The method of claim 1, further comprising, after said determining whether said first historical risk stage is a first stage of said first historical clinical trial:
if not, acquiring second historical record data of a second historical risk stage;
wherein the second historical risk stage refers to a stage previous to the first historical risk stage;
analyzing the second historical record data and calculating to obtain a second historical security index;
acquiring a first historical clinical trial risk index of the first historical clinical trial;
combining the second historical safety index, the first historical safety index and the first historical clinical trial risk index to obtain training data;
and training to obtain the intelligent risk assessment model according to the training data.
4. A method of clinical trial risk assessment according to claim 3, wherein the obtaining a first historical clinical trial risk index for the first historical clinical trial comprises:
the first historical clinical trial has a first final goal;
combining the first historical record data to obtain a first target realization risk index; and
and taking the first target achievement risk index as a first historical clinical trial risk index.
5. A clinical trial risk assessment system based on a neural network, the clinical trial risk assessment system comprising a memory and a processor, wherein the memory has stored thereon a clinical trial risk assessment program which when executed by the processor performs the steps of:
constraint generation: obtaining a historical clinical test risk record based on big data, and analyzing data in the historical clinical test risk record to generate a preset test variable control constraint;
the scheme making step: under the control constraint of the preset test variables, a first clinical test scheme of the first medicine is formulated, wherein the first clinical test scheme comprises a first clinical test stage and a second clinical test stage;
tracking and recording: tracking the clinical trial implementation overall process and obtaining a first clinical trial record, wherein the first clinical trial record comprises first record data of the first clinical trial stage;
acquiring a first historical risk event in the historical clinical trial risk record;
analyzing the stage of the first historical risk event in the first historical clinical trial to be set as a first historical risk stage;
judging whether the first historical risk stage is a first stage of the first historical clinical trial;
if yes, calling a preset calculation scheme and calculating to obtain a first preset safety threshold;
acquiring a second historical risk event in the historical clinical test risk record, and calculating a second preset safety threshold according to the second historical risk event;
comparing the first preset safety threshold value with the second preset safety threshold value, and determining a preset safety threshold value;
and a safety analysis step: analyzing the first recorded data, calculating to obtain a first safety index, judging whether the first safety index meets a preset safety threshold, if so, sending out a continuous test instruction, and carrying out the second clinical test stage based on the instruction;
risk assessment step: acquiring a second safety index of the second clinical test stage, combining the first safety index to form first input information, and obtaining a first output result through an intelligent risk assessment model, wherein the first output result comprises a first clinical test risk index of the first medicine;
the calling the preset calculation scheme and calculating to obtain a first preset safety threshold value comprises the following steps:
acquiring first historical record data of the first historical risk stage according to the preset calculation scheme;
acquiring a preset safety factor index, and traversing in the first historical record data to obtain a first index parameter;
calculating according to the first index parameter to obtain a first historical safety index; and
determining the first preset safety threshold based on the first historical safety index;
the method for obtaining the historical clinical test risk record based on the big data and analyzing the data in the historical clinical test risk record to generate a preset test variable control constraint comprises the following steps:
analyzing the historical clinical test risk record by using an accident tree method to obtain an analysis result;
establishing a subjective risk factor set based on the analysis result; and
and taking the subjective risk factor set as the control constraint of the preset test variable.
6. A computer device comprising a processor and a memory;
the processor for processing to perform the method of any of claims 1-4;
the memory being coupled to the processor for storing a program which, when executed by the processor, causes the system to perform the steps of the method of any of claims 1-4.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a clinical trial risk assessment program executable by at least one processor to cause the at least one processor to perform the steps of the clinical trial risk assessment method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310313034.5A CN116364309B (en) | 2023-03-28 | 2023-03-28 | Clinical trial risk assessment method and system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310313034.5A CN116364309B (en) | 2023-03-28 | 2023-03-28 | Clinical trial risk assessment method and system based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116364309A CN116364309A (en) | 2023-06-30 |
| CN116364309B true CN116364309B (en) | 2024-02-02 |
Family
ID=86936078
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310313034.5A Active CN116364309B (en) | 2023-03-28 | 2023-03-28 | Clinical trial risk assessment method and system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116364309B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133300A (en) * | 2016-11-30 | 2018-06-08 | 北京经纬传奇医药科技有限公司 | A kind of clinical test quality evaluation system and its method |
| CN111080159A (en) * | 2019-12-27 | 2020-04-28 | 嘉兴太美医疗科技有限公司 | Risk monitoring method and system for quality supervision of clinical trial research center |
| CN111695836A (en) * | 2020-06-23 | 2020-09-22 | 上海用正医药科技有限公司 | Clinical trial online operation management and control integrated system |
| CN111695835A (en) * | 2020-06-23 | 2020-09-22 | 上海用正医药科技有限公司 | Method for assessing risk of clinical trials |
| CN112801488A (en) * | 2020-06-23 | 2021-05-14 | 上海用正医药科技有限公司 | Clinical trial quality real-time management and control optimization method and system |
| CN113393946A (en) * | 2021-08-17 | 2021-09-14 | 奥罗科技(天津)有限公司 | Medical clinical test auxiliary system and method based on virtual reality technology |
| CN113871026A (en) * | 2021-10-14 | 2021-12-31 | 曹庆恒 | Medical risk assessment system and method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016073776A1 (en) * | 2014-11-05 | 2016-05-12 | Healthcare Business Intelligence Solutions Inc. | System for management of health resources |
| US11526953B2 (en) * | 2019-06-25 | 2022-12-13 | Iqvia Inc. | Machine learning techniques for automatic evaluation of clinical trial data |
-
2023
- 2023-03-28 CN CN202310313034.5A patent/CN116364309B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133300A (en) * | 2016-11-30 | 2018-06-08 | 北京经纬传奇医药科技有限公司 | A kind of clinical test quality evaluation system and its method |
| CN111080159A (en) * | 2019-12-27 | 2020-04-28 | 嘉兴太美医疗科技有限公司 | Risk monitoring method and system for quality supervision of clinical trial research center |
| CN111695836A (en) * | 2020-06-23 | 2020-09-22 | 上海用正医药科技有限公司 | Clinical trial online operation management and control integrated system |
| CN111695835A (en) * | 2020-06-23 | 2020-09-22 | 上海用正医药科技有限公司 | Method for assessing risk of clinical trials |
| CN112801488A (en) * | 2020-06-23 | 2021-05-14 | 上海用正医药科技有限公司 | Clinical trial quality real-time management and control optimization method and system |
| CN113159502A (en) * | 2020-06-23 | 2021-07-23 | 上海用正医药科技有限公司 | Method for assessing risk of clinical trials |
| CN113393946A (en) * | 2021-08-17 | 2021-09-14 | 奥罗科技(天津)有限公司 | Medical clinical test auxiliary system and method based on virtual reality technology |
| CN113871026A (en) * | 2021-10-14 | 2021-12-31 | 曹庆恒 | Medical risk assessment system and method |
Non-Patent Citations (1)
| Title |
|---|
| 药物临床试验机构生物等效性试验实施阶段质量风险管理研究;李江帆;李可欣;武志昂;;中国新药杂志(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116364309A (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114723287A (en) | Quantitative statistical method for risk formation based on enterprise characteristics and operation behaviors | |
| CN113656805B (en) | Event map automatic construction method and system for multi-source vulnerability information | |
| CN114448657B (en) | Distribution communication network security situation awareness and abnormal intrusion detection method | |
| CN114220536A (en) | Disease analysis method, device, equipment and storage medium based on machine learning | |
| CN116662839A (en) | Associated big data cluster analysis method and device based on multidimensional intelligent acquisition | |
| CN114220541A (en) | Disease prediction method, disease prediction device, electronic device, and storage medium | |
| CN117155771B (en) | Equipment cluster fault tracing method and device based on industrial Internet of things | |
| CN116012019B (en) | Financial wind control management system based on big data analysis | |
| CN113642672A (en) | Feature processing method and device of medical insurance data, computer equipment and storage medium | |
| CN116364309B (en) | Clinical trial risk assessment method and system based on neural network | |
| CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network | |
| CN116525053A (en) | Patient report generation method, device, electronic equipment and medium | |
| US20230126567A1 (en) | Operation system, operation method and recording medium having recorded thereon operation program | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| CN114841165B (en) | User data analysis and display method and device, electronic equipment and storage medium | |
| CN114113487B (en) | Volatile organic compound online monitoring system and method | |
| CN115775635A (en) | Medicine risk identification method and device based on deep learning model and terminal equipment | |
| CN114201328A (en) | Fault processing method and device based on artificial intelligence, electronic equipment and medium | |
| CN111221704B (en) | Method and system for determining running state of office management application system | |
| CN115881257A (en) | User privacy protection method and system applied to big data | |
| CN117390933B (en) | Process data tracing method and system for lubricating oil preparation | |
| CN113689246B (en) | Website monitoring method and device based on artificial intelligence, electronic equipment and medium | |
| CN115779445B (en) | Game data abnormity early warning system, method, computer equipment and storage medium | |
| CN116364223B (en) | Feature processing method, device, computer equipment and storage medium | |
| CN114662623B (en) | XGboost-based blood sample classification method and system in blood coagulation detection |
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 |