Clinical research data analysis method capable of real-time analysis and device therefor

Abstract

Disclosed are a clinical research data analysis method capable of real-time analysis and a device therefor. The clinical research data analysis method according to an embodiment of the present invention may comprise: a data collection step for collecting clinical research data input to an electronic data collection system; a data analysis processing step for generating a data analysis result by performing real-time analysis or statistical analysis by using the collected clinical research data as an input; and a service processing step for converting the data analysis result into a preset report format and providing same to at least one clinical research-related institution.

Description

Method for analyzing clinical research data capable of real-time analysis and device for the same

[0001] The present invention relates to a method for analyzing clinical research data capable of real-time analysis and an apparatus for the same.

[0002] The content described in this section merely provides background information regarding embodiments of the present invention and does not constitute prior art.

[0003] Generally, the procedure for managing clinical research operates as shown in the clinical research management system of Figure 1.

[0004] A pharmaceutical company establishes a research plan for a clinical study and obtains research approval from the Institutional Review Board (IRB).

[0005] Subsequently, each of the multiple medical institutions conducts clinical research, and data on the clinical research is collected through an electronic data collection system.

[0006] Data collected in clinical studies is managed by a data manager through data verification and locking after the completion of the study, and the data is transferred to the statistician after verification is complete.

[0007] Subsequently, the statistician performs statistical analysis on the efficacy and drug safety evaluation items of the clinical study protocol and derives the results. Based on the analyzed results, a results report on the overall outcome of the clinical study is prepared by a Medical Writer (MW). The completed results report is then delivered to the pharmaceutical company and the principal investigators involved in the clinical study.

[0008] However, this procedure for clinical research has the problem of incurring significant time and cost between data collection and result reporting.

[0009] The main objective of the present invention is to provide a method for analyzing clinical research data capable of real-time analysis and an apparatus therefor, which collects clinical research data in conjunction with an electronic data collection system, performs real-time analysis or statistical analysis using the collected clinical research data as input to generate data analysis results, converts the generated data analysis results into a pre-set reporting format, and provides them to at least one clinical research-related institution, such as a pharmaceutical company terminal or a medical institution terminal.

[0010] According to one aspect of the present invention, a method for analyzing clinical research data using a clinical research data analysis device linked with an electronic data collection system for achieving the above objective, wherein the clinical research data analysis method may include: a data collection step of collecting clinical research data inputted into the electronic data collection system; a data analysis processing step of generating a data analysis result by performing real-time analysis or statistical analysis with the collected clinical research data as input; and a service processing step of converting the data analysis result into a pre-set reporting format and providing it to at least one clinical research-related institution.

[0011] In addition, according to another aspect of the present invention, a clinical research data analysis device for achieving the above objective is a clinical research data analysis device linked with an electronic data collection system, wherein the clinical research data analysis device comprises one or more processors; and a memory for storing one or more programs executed by said processors, and when said programs are executed by said processors, said processors may perform a data collection step of collecting clinical research data input into said electronic data collection system; a data analysis processing step of generating a data analysis result by performing real-time analysis or statistical analysis with said collected clinical research data as input; and a service processing step of converting said data analysis result into a pre-set reporting format and providing it to at least one clinical research-related institution.

[0012] As explained above, the present invention enables real-time analysis of data collected in clinical research, thereby having the effect of rapidly detecting problems occurring during the clinical research phase.

[0013] In addition, the present invention has the effect of rapidly deriving evidence of actual use by analyzing data collected in clinical studies in real time.

[0014] In addition, the present invention has the effect of providing progress updates on clinical research at predetermined intervals.

[0015] In addition, the present invention has the effect of increasing the speed and accuracy of decision-making by researchers regarding clinical research, and increasing the overall safety and probability of success of clinical research.

[0016] Figure 1 is a block diagram schematically showing a conventional clinical research management system.

[0017] FIG. 2 is a block diagram schematically showing a clinical research analysis system capable of real-time analysis according to an embodiment of the present invention.

[0018] FIGS. 3 to 5 are block diagrams schematically illustrating a clinical research data analysis device according to an embodiment of the present invention.

[0019] FIG. 6 is a flowchart illustrating a method for analyzing clinical research data according to an embodiment of the present invention.

[0020] FIG. 7 is a diagram illustrating the service processing operation of a clinical research data analysis device according to an embodiment of the present invention.

[0021] FIG. 8 is a diagram illustrating the statistical analysis processing operation of a clinical research data analysis device according to an embodiment of the present invention.

[0022] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In describing the present invention, detailed descriptions of related known configurations or functions are omitted if it is determined that such detailed descriptions may obscure the essence of the present invention. Furthermore, while preferred embodiments of the present invention will be described below, the technical concept of the present invention is not limited or restricted thereto and can be modified and implemented in various ways by those skilled in the art. Hereinafter, a method for analyzing clinical research data capable of real-time analysis and an apparatus for such analysis, as proposed in the present invention, will be described in detail with reference to the drawings.

[0023] FIG. 2 is a block diagram schematically showing a clinical research analysis system capable of real-time analysis according to an embodiment of the present invention.

[0024] The clinical research analysis system (10) according to the present embodiment includes a pharmaceutical company terminal (20), a medical institution terminal (30), an electronic data collection system (40), and a clinical research data analysis device (50). The clinical research analysis system (10) of FIG. 2 is according to one embodiment, and not all blocks shown in FIG. 2 are essential components, and some blocks included in the clinical research analysis system (10) in other embodiments may be added, changed, or deleted.

[0025] The clinical research analysis system (10) refers to an integrated management system that manages the entire operational process from the planning to the completion of clinical research and provides visualization by analyzing data collected in clinical research in real time.

[0026] The pharmaceutical company terminal (20) may be a terminal carried by a manager at the pharmaceutical company.

[0027] The pharmaceutical company terminal (20) receives the results of the data analysis from the clinical research data analysis device (50).

[0028] A pharmaceutical company terminal (20) can receive a report form, such as a newsletter form, dashboard form, or report form, converted based on data analysis results including real-time analysis results or statistical analysis results from a clinical research data analysis device (50). Here, the pharmaceutical company terminal (20) can receive the converted report form via a web-based URL, but is not necessarily limited thereto.

[0029] The medical institution terminal (30) may be a terminal carried by a manager at the medical institution.

[0030] The medical institution terminal (30) receives the data analysis results from the clinical research data analysis device (50).

[0031] The medical institution terminal (30) can receive a report form, such as a newsletter form, dashboard form, or report form, converted based on data analysis results including real-time analysis results or statistical analysis results from the clinical research data analysis device (50). Here, the medical institution terminal (30) can receive the converted report form via a web-based URL, but is not necessarily limited thereto.

[0032] In a medical institution, clinical research data is transmitted to an electronic data collection system (40) for collection and management. Here, clinical research data refers to real-world clinical data (RWD), meaning data obtained from the actual treatment and health status of patients. Clinical research data includes data collected from hospital records, patient surveys, wearable devices, etc., and refers to data that reflects the patient's experience in the actual clinical environment.

[0033] The electronic data collection system (40) electronically collects and manages clinical research data from at least one medical institution.

[0034] In addition, the electronic data collection system (40) collects and stores clinical research-related information including research objectives, research design, and evaluation items.

[0035] The electronic data collection system (40) transmits stored clinical research data and clinical research-related information to the clinical research data analysis device (50) for the analysis of the clinical research.

[0036] The clinical research data analysis device (50) according to the present embodiment collects clinical research data in conjunction with an electronic data collection system (40), performs real-time analysis or statistical analysis using the collected clinical research data as input to generate data analysis results, converts the generated data analysis results into a pre-set report format, and provides them to at least one clinical research-related institution, such as a pharmaceutical company terminal (20) or a medical institution terminal (30).

[0037] FIGS. 3 to 5 are block diagrams schematically illustrating a clinical research data analysis device according to an embodiment of the present invention.

[0038] FIG. 3 is a block diagram schematically showing a clinical research data analysis device linked with an electronic data collection system according to the present embodiment.

[0039] The clinical research data analysis device (50) according to the present embodiment includes a data collection unit (310), a data analysis processing unit (320), and a service processing unit (330).

[0040] The clinical research data analysis device (50) collects clinical research data in conjunction with the electronic data collection system (40), performs real-time analysis or statistical analysis using the collected clinical research data as input to generate data analysis results, converts the generated data analysis results into a pre-set report format, and provides them to at least one clinical research-related institution, such as a pharmaceutical company terminal (20) or a medical institution terminal (30).

[0041] Below, each component included in the clinical research data analysis device (50) will be described.

[0042] The data collection unit (310) collects clinical research data entered into the electronic data collection system (40). Here, the clinical research data is Real-World Data (RWD), meaning data obtained from the actual treatment and health status of patients. The clinical research data includes data collected from hospital records, patient surveys, wearable devices, etc., and refers to data that reflects the patient's experience in the actual clinical environment.

[0043] The data collection unit (310) collects clinical research data in real time from the electronic data collection system (40). The data collection unit (310) may additionally obtain clinical research-related information, including research objectives, research design, and evaluation items for the clinical research.

[0044] The data analysis processing unit (320) performs real-time analysis or statistical analysis using collected clinical research data as input to generate data analysis results.

[0045] The data analysis processing unit (320) according to the present embodiment includes a real-time analysis processing unit (322) and a statistical analysis processing unit (324).

[0046] The real-time analysis processing unit (322) classifies clinical research data collected in real time based on clinical research-related institution identification information and performs real-time analysis on each of the classified data to generate real-time analysis results.

[0047] The real-time analysis processing unit (322) analyzes the drug effect and safety for each classified data in real time. Here, the real-time analysis is performed by grouping the data received from the data collection unit (310) for a certain period of time into one group, and processing the grouped group into one unit to analyze the drug effect and safety. The real-time analysis processing unit (322) aggregates and analyzes data during a pre-set specific time interval.

[0048] The statistical analysis processing unit (324) integrates clinical research-related information and clinical research data collected during a preset time or period to store integrated data and determines variable attributes for the integrated data. Subsequently, the statistical analysis processing unit (324) selects a statistical analysis method based on the determined variable attributes, applies the selected statistical analysis method to perform statistical analysis, and generates a statistical analysis result.

[0049] A detailed description of the statistical analysis processing unit (324) is provided in FIG. 4.

[0050] The data analysis processing unit (320) according to the present embodiment is described as performing real-time analysis and statistical analysis in separate steps, but is not necessarily limited thereto, and real-time analysis and statistical analysis may be performed simultaneously or statistical analysis may be performed at predetermined intervals.

[0051] The service processing unit (330) performs the operation of converting the data analysis results into a pre-set report format and providing it to at least one clinical research-related institution.

[0052] The service processing unit (330) according to the present embodiment includes a management service processing unit (332) and an analysis service processing unit (334).

[0053] The management service processing unit (332) provides management services for the progress of clinical research using the results of data analysis.

[0054] The management service processing unit (332) monitors the real-time analysis results included in the data analysis results and provides the progress status according to the pre-set milestones to at least one clinical research-related institution via a web-based URL. The management service processing unit (332) preferably transmits the web-based URL to a pharmaceutical company among at least one clinical research-related institution, but is not necessarily limited thereto.

[0055] The analysis service processing unit (334) converts the data analysis results into a pre-set report format and provides an analysis service.

[0056] When the analysis service processing unit (334) obtains real-time analysis results from the real-time analysis processing unit (322), it converts the real-time analysis results into at least one format among a report and a newsletter format and provides them to at least one clinical research-related institution.

[0057] Additionally, the analysis service processing unit (334) can convert real-time analysis results into a dashboard format and provide the converted results to at least one clinical research-related institution via a web-based URL. Here, the analysis service processing unit (334) can provide encrypted login information for accessing the URL for each of the at least one clinical research-related institutions.

[0058] The analysis service processing unit (334) filters the data included in the real-time analysis results when the acquired real-time analysis results exceed a preset throughput, and converts the filtered real-time analysis results into at least one format among a report and a newsletter format and provides them to at least one clinical research-related institution. Here, the filtering may be performed based on the order, size, preset identification information, weights, etc. of the data included in the real-time analysis results.

[0059] Meanwhile, the analysis service processing unit (334) may assign different weights to each of the data included in the acquired real-time analysis results and perform filtering on the weighted data. Here, the weights may be calculated using all or part of the conditions among the priority of the clinical research-related institution (priority based on the reliability of previously evaluated research results), the evaluation level of drug effect, the evaluation level of safety, and the manager's setting input values.

[0060] For example, the analysis service processing unit (334) can calculate a first weight for the priority of the clinical research-related institution, a second weight for the evaluation level of the drug effect, a third weight for the evaluation level of safety, and a fourth weight for the manager's setting input value for each of the data included in the real-time analysis result, and can calculate different weights to be assigned to each of the data included in the real-time analysis result by performing calculation processing (e.g., mean, variance) on the first, second, third, and fourth values.

[0061] The analysis service processing unit (334) filters weighted data and extracts real-time analysis results for converting into at least one of a report and a newsletter format.

[0062] The analysis service processing unit (334) performs the operation of recalculating different weights for each of the data included in the real-time analysis result when the amount of data of the real-time analysis result extracted through filtering is less than the preset amount of data.

[0063] When recalculating weights, the analysis service processing unit (334) recalculates weights by combining conditions different from those used in the previous weight calculation. Specifically, the analysis service processing unit (334) may recalculate weights by adding or deleting some conditions from those used in the previous weight calculation, among conditions including the priority of clinical research-related institutions (priority based on the reliability of previously evaluated research results), the evaluation level of drug effect, the evaluation level of safety, and the input value of the manager's settings.

[0064] The analysis service processing unit (334) does not discard the filtered data, but additionally includes it in real-time analysis results obtained within a set period of time at a level below a set throughput, and converts it into at least one of a report and a newsletter format. Here, if there are no real-time analysis results obtained within a set period of time at a level below a set throughput, the filtered data is generated as a separate real-time additional analysis result, and the real-time additional analysis result is converted into at least one of a report and a newsletter format and provided to at least one clinical research-related institution.

[0065] Meanwhile, when the analysis service processing unit (334) obtains statistical analysis results from the statistical analysis processing unit (324), it converts the statistical analysis results into a dashboard form and a report form, and provides the converted results to at least one clinical research-related institution via a web-based URL. Here, the analysis service processing unit (334) may provide encrypted login information for accessing the URL for each of the at least one clinical research-related institutions.

[0066] FIG. 4 is a block diagram schematically showing the statistical analysis processing unit of a clinical research data analysis device according to the present embodiment.

[0067] The statistical analysis processing unit (324) of the clinical research data analysis device (50) according to the present embodiment includes a data integration unit (410), a variable attribute determination unit (420), a statistical analysis method selection unit (430), and a statistical analysis result generation unit (440).

[0068] The data integration unit (410) integrates clinical research-related information and clinical research data collected during a preset time or period and stores the integrated data.

[0069] The data integration unit (410) groups clinical research data that matches the research purpose, research design, and evaluation items included in the clinical research-related information and stores the integrated data.

[0070] The variable attribute determination unit (420) determines the variable attributes of the integrated data.

[0071] The variable attribute judgment unit (420) determines the variable attributes for categorical or continuous types by dividing the integrated data into a research objective variable (ARM: Planned Arm), an evaluation item variable (PARAM: Parameter), and an evaluation result variable (AVAL: Analysis Value).

[0072] The statistical analysis method selection unit (430) selects a statistical analysis method based on the determined variable attributes.

[0073] The statistical analysis method selection unit (430) determines the relationship between the two variables based on whether the two variables included in the integrated data are continuous (relationship determination step). Afterward, the statistical analysis method selection unit (430) analyzes the independent variable and the dependent variable based on the result of determining the relationship between the two variables and selects a statistical analysis method (analysis step).

[0074] The statistical analysis method selection unit (430) selects simple regression analysis or correlation analysis as the statistical analysis method based on the result of judging the relationship between two variables, if the relationship between two variables is continuous.

[0075] Meanwhile, the statistical analysis method selection unit (430) additionally determines whether the independent variable is categorical and the dependent variable is continuous based on the result of judging the relationship between the two variables, if the relationship between the two variables is discontinuous.

[0076] The statistical analysis method selection unit (430) selects a statistical analysis method based on the number of independent samples when the independent variable is categorical and the dependent variable is continuous, and if there are two or more groups, one-way ANOVA (one-way analysis of variance), otherwise, a t-test (independent t-test or paired t-test).

[0077] Meanwhile, the statistical analysis method selection unit (430) selects the Chi-square test or McNemar test as the statistical analysis method when the independent variable is categorical and the dependent variable is categorical.

[0078] The statistical analysis method selection unit (430) selects a log-rank test as a statistical analysis method for analyzing survival data when the independent variable or dependent variable includes survival data.

[0079] Meanwhile, the statistical analysis method selection unit (430) selects the statistical analysis method based on the type of independent variable when the relationship between the two variables is not determined in the relationship judgment stage.

[0080] When the statistical analysis method selection unit (430) confirms that the type of independent variable is continuous, it selects multiple linear regression or a mixed model as the statistical analysis method depending on the number of dependent variables and whether they are repeated.

[0081] When the statistical analysis method selection unit (430) confirms that the type of independent variable is categorical, it selects one of the following as a statistical analysis method based on the number of categories of the dependent variable: Binary logistic regression, Cumulative logit model, and Multinomial logit model.

[0082] The statistical analysis method selection unit (430) does not determine the relationship between two variables in the relationship judgment stage, and if survival data is included in the independent variable or dependent variable, it selects the Cox's regression model as the statistical analysis method.

[0083] The statistical analysis result generation unit (440) performs statistical analysis by applying a statistical analysis method and generates statistical analysis results for clinical research.

[0084] The statistical analysis result generation unit (440) transmits the generated statistical analysis result to the service processing unit (330).

[0085] FIG. 5 is a block diagram schematically showing the hardware configuration of a clinical research data analysis device according to an embodiment of the present invention.

[0086] FIG. 5 is a block diagram showing the hardware configuration of a clinical research data analysis device (50) to illustrate and explain a computing environment including a computing device suitable for use in preferred embodiments of the present invention.

[0087] The clinical research data analysis device (50) can be implemented as a computing device and may be a smartphone, personal computer (PC), tablet PC, personal digital assistant (PDA), laptop, etc., but is not necessarily limited thereto.

[0088] The clinical research data analysis device (50) may include a processor and a memory that stores a program executed by the processor, and may generate instructions for operations such as data collection, data analysis processing, and service processing in the processor, and provide information for data collection, data analysis processing, and service processing using the generated instructions.

[0089] The clinical research data analysis device (50) may include a database. A database refers to a data storage form in which data can be freely searched, extracted, deleted, edited, added, etc. The database may be implemented to suit the purpose of this embodiment using Oracle, Informix, Sybase, a Relational Data Base Management System (RDBMS), Gemston, Orion, an Object Oriented Database Management System (OODBMS), a distributed database, a cloud, etc.

[0090] In the embodiment illustrated in FIG. 5, each component may have different functions and capabilities in addition to those described below, and may include additional components in addition to those not described below.

[0091] The illustrated computing environment includes a clinical research data analysis device (50). In one embodiment, the clinical research data analysis device (50) may be any type of computing device that transmits and receives signals to and from other terminals.

[0092] The clinical research data analysis device (50) includes at least one processor (13), a computer-readable storage module (16), and a communication bus. The processor (13) can enable the clinical research data analysis device (50) to operate according to the exemplary embodiment described above. For example, the processor (13) can execute one or more programs stored in the computer-readable storage module (16). The one or more programs may include one or more computer-executable instructions, and the computer-executable instructions may be configured to enable the clinical research data analysis device (50) to perform operations according to the exemplary embodiment when executed by the processor (13).

[0093] The processor (13) may work in conjunction with the neural network module (14) to process operations such as data collection, data analysis processing, and service processing. Meanwhile, although the processor (13) and the neural network module (14) are described as being different modules, they are not necessarily limited to this and may be implemented as a single module to perform their respective operations.

[0094] The neural network module (14) performs neural network processing related to operations such as data collection, data analysis processing, and service processing based on artificial intelligence (AI). The neural network module (14) has input nodes, intermediate nodes, and output nodes, and has a structure specified by decision weights that have been pre-learned through training data as connection weights connecting each node. The output value of the neural network module (14) may be the coordinate value of an expanded area or the coordinate value of a unit block area, and may be implemented in the form of a feature value matrix for the expanded area or the unit block area.

[0095] A computer-readable storage module (16) is configured to store computer-executable instructions or program code, program data and / or other suitable forms of information. A program stored in a computer-readable storage module (16) includes a set of instructions executable by a processor (13). In one embodiment, the computer-readable storage module (16) may be memory (volatile memory such as random access memory, non-volatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash memory devices, or other forms of storage media that can be accessed by a clinical research data analysis device (50) and store desired information, or a suitable combination thereof.

[0096] The communication bus interconnects various other components of the clinical research data analysis device (50), including the processor (13) and the computer-readable storage module (16).

[0097] The clinical research data analysis device (50) may also include one or more input modules (11) and output modules (12) and one or more communication interfaces that provide interfaces for one or more input / output devices (not shown). The input modules (11) and output modules (12) and the communication interfaces are connected to a communication bus. The input / output devices (not shown) may be connected to other components of the clinical research data analysis device (50) through the input modules (11) and output modules (12). Exemplary input / output devices may include input devices such as a pointing device (mouse or trackpad, etc.), a keyboard, a touch input device (touchpad or touchscreen, etc.), a voice or sound input device, various types of sensor devices and / or imaging devices, and / or output devices such as a display device, a printer, a speaker and / or a network card. An exemplary input / output device (not shown) may be included inside the clinical research data analysis device (50) as a component constituting the clinical research data analysis device (50), or it may be connected to a computing device as a separate device distinct from the clinical research data analysis device (50).

[0098] FIG. 6 is a flowchart illustrating a method for analyzing clinical research data according to an embodiment of the present invention.

[0099] The clinical research data analysis device (50) collects clinical research data from the electronic data collection system (40) (S610).

[0100] When the clinical research data analysis device (50) performs real-time analysis in step S620, it separates the collected clinical research data by medical institution (S630).

[0101] The clinical research data analysis device (50) performs real-time analysis of the drug effect, safety analysis, etc. of the clinical research data (S632) and generates real-time analysis results (S634).

[0102] The clinical research data analysis device (50) provides real-time analysis results to at least one clinical research-related institution, such as a pharmaceutical company terminal (20) or a medical institution terminal (30) (S640). Here, the clinical research data analysis device (50) can convert the real-time analysis results into a format such as a report or a newsletter and provide them.

[0103] Meanwhile, when the clinical research data analysis device (50) performs an integrated analysis in step S620, it integrates clinical research data collected from multiple sources and stores the integrated data (S650). Here, the integrated data may include clinical research-related information, such as the research purpose, research design, and evaluation items for the clinical research.

[0104] The clinical research data analysis device (50) determines the variable attributes of the integrated data (S652) and selects a statistical analysis method based on the variable attributes (S654).

[0105] The clinical research data analysis device (50) performs an evaluation of validity based on a selected statistical analysis method and generates a statistical analysis result (S656).

[0106] The clinical research data analysis device (50) provides the results of the statistical analysis to at least one clinical research-related institution, such as a pharmaceutical company terminal (20) or a medical institution terminal (30) (S660). Here, the clinical research data analysis device (50) can convert the results of the statistical analysis into a visualization, dashboard, report, etc. format and provide them.

[0107] Although FIG. 6 describes each step as being executed sequentially, it is not necessarily limited to this. In other words, FIG. 6 is not limited to a chronological order, as it may be applicable to execute the steps described in FIG. 6 by modifying them or to execute one or more steps in parallel.

[0108] The clinical research data analysis method according to the present embodiment described in FIG. 6 may be implemented as an application (or program) and recorded on a recording medium readable by a terminal device (or computer). The recording medium on which the application (or program) for implementing the clinical research data analysis method according to the present embodiment is recorded and which is readable by a terminal device (or computer) includes all types of recording devices or media in which data that can be read by a computing system is stored.

[0109] FIG. 7 is a diagram illustrating the service processing operation of a clinical research data analysis device according to an embodiment of the present invention.

[0110] The clinical research data analysis device (50) classifies clinical research data collected from the electronic data collection system (40) by the IDs of medical institutions and performs real-time analysis or statistical analysis.

[0111] The clinical research data analysis device (50) converts the analysis results into a dashboard and report format and transmits the results in real time to pharmaceutical companies, medical institutions, etc.

[0112] The clinical research data analysis device (50) transmits the analysis results in the form of a URL, and the results can be checked anytime and anywhere without device restrictions through the URL transmission. Here, the clinical research data analysis device (50) can provide results in a report format to pharmaceutical companies and results in a newsletter format to each medical institution.

[0113] The clinical research data analysis device (50) can control the authority of pharmaceutical companies and each medical institution through role-based access control. In other words, pharmaceutical companies can check the integrated results and the results of each medical institution in real time, and each medical institution can check the results of that institution in real time.

[0114] FIG. 8 is a diagram illustrating the statistical analysis processing operation of a clinical research data analysis device according to an embodiment of the present invention.

[0115] The clinical research data analysis device (50) according to the present embodiment selects a statistical analysis method by applying a statistical analysis algorithm based on the variable attributes of the clinical research data.

[0116] The clinical research data analysis device (50) determines the relationship between the two variables based on whether the two variables included in the integrated data are continuous.

[0117] The clinical research data analysis device (50) selects simple regression analysis or correlation analysis as a statistical analysis method based on the result of determining the relationship between two variables, if the relationship between the two variables is continuous.

[0118] Meanwhile, the clinical research data analysis device (50) further determines whether the independent variable is categorical and the dependent variable is continuous based on the result of determining the relationship between the two variables, if the relationship between the two variables is discontinuous.

[0119] When the independent variable is categorical and the dependent variable is continuous, the clinical research data analysis device (50) selects a statistical analysis method based on the number of independent samples: if there are two or more groups, a one-way ANOVA (one-way analysis of variance); otherwise, a t-test (independent t-test or paired t-test).

[0120] Meanwhile, the clinical research data analysis device (50) selects the Chi-square test or McNemar test as the statistical analysis method when the independent variable is categorical and the dependent variable is categorical.

[0121] The clinical research data analysis device (50) selects a log-rank test as a statistical analysis method for analyzing survival data when the independent variable or dependent variable includes survival data.

[0122] Meanwhile, if the clinical research data analysis device (50) does not determine the relationship between two variables in the relationship determination stage, it selects the statistical analysis method based on the type of independent variable.

[0123] When the clinical research data analysis device (50) confirms that the type of independent variable is continuous, it selects multiple linear regression or a mixed model as a statistical analysis method depending on the number of dependent variables and whether they are repeated.

[0124] When the clinical research data analysis device (50) confirms that the type of independent variable is categorical, it selects one of binary logistic regression, cumulative logit model, and multiminomial logit model as a statistical analysis method depending on the number of categories of the dependent variable.

[0125] The clinical research data analysis device (50) does not determine the relationship between two variables in the relationship determination step, and if survival data is included in the independent variable or dependent variable, it selects the Cox's regression model as the statistical analysis method.

[0126] Below, we will describe the specific operation of selecting a statistical analysis method in the statistical analysis processing unit (324) of the clinical research data analysis device (50).

[0127] The statistical analysis processing unit (324) determines whether to investigate the relationship between two variables to determine whether the two variables included in the integrated data are continuous (Association between two variables?).

[0128] The statistical analysis processing unit (324) investigates the relationship between the two variables to determine whether the two variables are continuous and determines whether both variables are continuous (Two variables continuous?).

[0129] The statistical analysis processing unit (324) selects simple linear regression or correlation analysis as the statistical analysis method if both variables are continuous.

[0130] Meanwhile, the statistical analysis processing unit (324) determines whether the independent variable is categorical and the dependent variable is continuous if both variables are not continuous.

[0131] The statistical analysis processing unit (324) selects a one-way ANOVA as the statistical analysis method when the independent variable is categorical and the dependent variable is continuous, depending on the number of independent samples, if there are two or more groups. If there are two or fewer groups, the statistical analysis processing unit (324) selects a t-test (independent t-test or paired t-test) as the statistical analysis method.

[0132] Meanwhile, the statistical analysis processing unit (324) selects the Chi-square test or McNemar test as the statistical analysis method when the independent variable is categorical and the dependent variable is categorical.

[0133] The statistical analysis processing unit (324) selects a log-rank test as a statistical analysis method to analyze survival data when the independent variable is not categorical and the independent variable or dependent variable is survival data.

[0134] Meanwhile, the statistical analysis processing unit (324) determines whether to investigate the relationship between two variables regarding whether the two variables included in the integrated data are continuous (Association between two variables?). If the relationship between two variables regarding whether the two variables are continuous is not investigated, the relationship between the two variables is not investigated, and if the type of independent variable is confirmed to be continuous (Type of Independent variables: Continuous), multiple linear regression or a mixed model is selected as the statistical analysis method depending on the number of dependent variables and whether there is repetition. Specifically, the statistical analysis processing unit (324) selects multiple linear regression as the statistical analysis method when there is one dependent variable, and selects a mixed model as the statistical analysis method when there are multiple dependent variables or repeated measurements.

[0135] The statistical analysis processing unit (324) does not investigate the relationship between the two variables, and if it is confirmed that the type of independent variable is categorical (Type of Independent variables: Categorical), it selects a statistical analysis method based on the number of categories of the dependent variable. Here, the statistical analysis processing unit (324) selects Binary Logistic Regression as the statistical analysis method when the dependent variable is binary (two categories). The statistical analysis processing unit (324) selects Cumulative Logistic Regression as the statistical analysis method when the dependent variable is multinomial (three or more categories) and the dependent variable is ordinal data. Additionally, the statistical analysis processing unit (324) selects Multinomial Logistic Regression as the statistical analysis method when the dependent variable is multinomial (three or more categories) and the dependent variable is non-ordinal multinomial data.

[0136] Meanwhile, the statistical analysis processing unit (324) does not investigate the relationship between the two variables, and if survival data is included in the independent variable or dependent variable, it selects a Cox's regression model for analyzing survival data as a statistical analysis method.

[0137] The foregoing description is merely an illustrative explanation of the technical concept of the embodiments of the present invention, and those skilled in the art to which the embodiments of the present invention pertain will be able to make various modifications and variations within the scope that does not deviate from the essential characteristics of the embodiments of the present invention. Accordingly, the embodiments of the present invention are intended to explain, not limit, the technical concept of the embodiments of the present invention, and the scope of the technical concept of the embodiments of the present invention is not limited by these embodiments. The scope of protection of the embodiments of the present invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the embodiments of the present invention.

[0138]

[0139] [Explanation of the symbol]

[0140] 10: Clinical Research Analysis System

[0141] 20: Pharmaceutical company terminal

[0142] 30: Medical institution terminal

[0143] 40: Electronic data collection system

[0144] 50: Clinical research data analysis device

[0145] 310: Data Collection Unit

[0146] 320: Data Analysis Processing Unit

[0147] 330: Service Processing Unit /

Claims

1. A method for a clinical research data analysis device linked with an electronic data collection system to analyze clinical research data, wherein A data collection step for collecting clinical research data entered into the above electronic data collection system; A data analysis processing step that generates data analysis results by performing real-time analysis or statistical analysis using the collected clinical research data as input; and A service processing step of converting the above data analysis results into a pre-set reporting format and providing them to at least one clinical research-related institution. A clinical research data analysis method characterized by including 2. In Paragraph 1, The above data collection step is, The clinical research data is collected in real time from the above electronic data collection system, A method for analyzing clinical research data characterized by additionally obtaining clinical research-related information, including research objectives, research design, and evaluation items for the clinical research.

3. In Paragraph 2, The above data analysis processing step is, A method for analyzing clinical research data characterized by classifying the above-mentioned clinical research data collected in real time based on identification information of clinical research-related institutions, and performing real-time analysis on each of the classified data to generate real-time analysis results.

4. In Paragraph 3, The above data analysis processing step is, A clinical research data analysis method characterized by real-time analysis of drug efficacy and safety for each of the above-described data.

5. In Paragraph 3, The above service processing step is, A method for analyzing clinical research data characterized by converting the above real-time analysis results into at least one of a report and a newsletter format and providing them to at least one clinical research-related institution.

6. In Paragraph 3, The above service processing step is, The above real-time analysis results are converted into a dashboard format, and the converted results are provided to at least one clinical research-related institution via a web-based URL, A method for analyzing clinical research data characterized by providing encrypted login information for accessing the URL for each of the above at least one clinical research-related institutions.

7. In Paragraph 2, The above data analysis processing step is, A data integration step for storing integrated data by integrating the clinical study-related information and clinical study data collected during a preset time or period; A variable attribute determination step for determining variable attributes for the above integrated data; A statistical analysis method selection step for selecting a statistical analysis method based on the determined variable attributes; and A step for generating statistical analysis results by applying the above statistical analysis method to perform the above statistical analysis and generating statistical analysis results. A clinical research data analysis method characterized by including 8. In Paragraph 7, The above data integration step is, A method for analyzing clinical research data characterized by grouping clinical research data that matches the research purpose, research design, and evaluation items included in the clinical research-related information and storing the integrated data.

9. In Paragraph 7, The above variable attribute determination step is, A clinical research analysis method characterized by classifying the above integrated data into a research objective variable (ARM: Planned Arm), an evaluation item variable (PARAM: Parameter), and an evaluation result variable (AVAL: Analysis Value), and determining the attributes of the said variables for categorical or continuous types.

10. In Paragraph 9, The above statistical analysis method selection step is, A relationship determination step for determining the relationship between the two variables based on whether the two variables included in the integrated data are continuous; and Analysis step of selecting the statistical analysis method by analyzing the independent and dependent variables based on the result of determining the relationship between the two variables mentioned above. A clinical research data analysis method characterized by including 11. In Paragraph 10, The above analysis step is, A method for analyzing clinical research data characterized by selecting simple regression analysis or correlation analysis as a statistical analysis method based on the result of determining the relationship between the two variables, if the relationship between the two variables is continuous.

12. In Paragraph 11, The above analysis step is, Based on the result of determining the relationship between the two variables above, if the relationship between the two variables is discontinuous, it is additionally determined whether the independent variable is categorical and the dependent variable is continuous, and If the above independent variable is categorical and the above dependent variable is continuous, depending on the number of independent samples, if there are two or more groups, One-way ANOVA is selected as the statistical analysis method, otherwise, a t-test (Independent t-test or Paired t-test) is selected, and If the above independent variable is categorical and the above dependent variable is categorical, the Chi-square test or McNemar test shall be selected as the statistical analysis method, A method for analyzing clinical research data characterized by selecting a log-rank test as a statistical analysis method for analyzing survival data when the above independent variable or the above dependent variable includes survival data.

13. In Paragraph 7, The above analysis step is, If the relationship between the two variables mentioned above has not been determined, the statistical analysis method mentioned above shall be selected based on the type of independent variable, If the type of the above independent variable is confirmed to be continuous, multiple linear regression or a mixed model is selected as the statistical analysis method depending on the number of dependent variables and whether repetition is required. If the type of the above independent variable is confirmed to be categorical, one of Binary Logistic Regression, Cumulative Logistic Regression, or Multinomial Logistic Regression shall be selected as the statistical analysis method depending on the number of categories of the dependent variable, A method for analyzing clinical research data characterized by selecting a Cox's regression model as a statistical analysis method when survival data is included in the independent variable or the dependent variable, without determining the relationship between the two variables mentioned above.

14. In Paragraph 7, The above service processing step is, A management service processing step that provides a management service for the progress of a clinical study using the above data analysis results; and Analysis service processing step that converts the above data analysis results into a pre-set report format to provide an analysis service A clinical research data analysis method characterized by including 15. In Paragraph 14, The above management service processing step is, A clinical research data analysis method characterized by monitoring real-time analysis results included in the above data analysis results and providing the above progress status according to a preset milestone to at least one clinical research-related institution via a web-based URL.

16. In Paragraph 14, The above analysis service processing step is, The above statistical analysis results are converted into a dashboard format and a report format, and the converted results are provided to at least one clinical research-related institution via a web-based URL, A method for analyzing clinical research data characterized by providing encrypted login information for accessing the URL for each of the above at least one clinical research-related institutions.

17. A clinical research data analysis device linked with an electronic data collection system, wherein the clinical research data analysis device comprises: One or more processors; and It includes memory for storing one or more programs executed by the above processor, and when the programs are executed by one or more processors, in the one or more processors, A data collection step for collecting clinical research data entered into the above electronic data collection system; A data analysis processing step that generates data analysis results by performing real-time analysis or statistical analysis using the collected clinical research data as input; and A service processing step of converting the above data analysis results into a pre-set reporting format and providing them to at least one clinical research-related institution. A clinical research data analysis device characterized by performing

Images