Method, device and system for providing process automation solution related to patient customized clinical trials based on multi variable analysis

The method automates patient-customized clinical trials using multivariate analysis to enhance trial precision and safety by classifying patients and setting individualized conditions, addressing the limitations of conventional trials.

KR103044533B1Active Publication Date: 2026-11-06SIMYU CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
KR1020250206258
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2025-12-22
Publication Date
2026-11-06
Estimated Expiration
2045-12-22

AI Technical Summary

Technical Problem

Conventional clinical trials fail to adequately reflect individual patient risks and changes in condition during the trial process, and are limited by the lack of integrated automation solutions that consider multiple patient variables, leading to increased costs, duration, and risks, and manual processes prone to errors.

Method used

A method and system for patient-customized clinical trials using multivariate analysis, involving an AI model to classify patients into groups, set trial conditions based on individual patient data, and manage trial execution, reducing manual intervention and enhancing precision and safety.

Benefits of technology

Enhances the suitability and reliability of clinical trial subject groups, reduces patient risks, minimizes errors, and improves management efficiency by automating trial processes, thus reducing costs and duration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112025145046775-PAT00002_ABST
    Figure 112025145046775-PAT00002_ABST
Patent Text Reader

Abstract

According to one embodiment, a method for providing a process automation solution for a patient-customized clinical trial based on multivariate analysis, performed by a device, comprises: receiving a request to proceed with a clinical trial for a first product from a first person in charge terminal; classifying patients who are eligible to participate in a clinical trial for the first product among a plurality of patients into a clinical trial subject group based on the characteristics of the first product; obtaining first patient information, which is patient information for a first patient who is one of the patients classified into the clinical trial subject group; matching the clinical trial information of the first product with the first patient information to generate first matching information; encoding the first matching information to generate a first input signal; inputting the first input signal into a first artificial intelligence model trained to set conditions for performing a clinical trial for a patient by considering the patient's risk level and an acceptable range when performing the clinical trial; and, when the first artificial intelligence model sets a first condition by analyzing the first input signal, obtaining a first output signal representing the first condition from the first artificial intelligence model. A method for providing a process automation solution for a patient-customized clinical trial based on multivariate analysis is provided, comprising the step of supporting the performance of a clinical trial for the first product in the first patient-customized manner based on the first condition confirmed through the first output signal.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The following examples relate to technology for providing process automation solutions related to patient-customized clinical trials based on multivariate analysis. Background Technology

[0002] Generally, clinical trials to verify the safety and efficacy of new drugs, medical devices, or functional products have been conducted by selecting a subject group that meets certain criteria according to a pre-designed protocol and performing the trial on that group under identical or similar test conditions. However, this conventional clinical trial method has had problems, such as selecting subjects based on only a few limited variables like age, gender, and baseline health status, and failing to adequately reflect individual patients' risks or changes in condition during the trial process.

[0003] In particular, in actual clinical practice, even for clinical trials of the same product, various variables such as medical history, biomarkers, lifestyle habits, concomitant medications, and disease progression stage interact complexly for each patient and can significantly affect the results and safety of the clinical trial; however, there have been limitations in systematically analyzing these multiple variables and reflecting them in the design and execution of clinical trials. As a result, problems have been pointed out, such as unnecessary risks for some patients, increased dropout rates, and excessive increases in the overall duration and cost of the clinical trial.

[0004] In addition, conventional clinical trial processes relied heavily on the experience and manual labor of personnel, which made it difficult to ensure consistency and objectivity in the selection of subject groups based on product characteristics, the setting of trial conditions for individual patients, risk management, and execution support. As the scale or complexity of clinical trials expanded, these manual-based processes increased the management burden and acted as factors that raised the possibility of errors.

[0005] Recently, with the advancement of artificial intelligence and data analysis technologies, there is an increasing demand for automation and intelligence utilizing large amounts of patient data and clinical information in the medical and clinical fields. However, there is a lack of integrated automation solutions that comprehensively consider individual patient risks and acceptable limits for clinical trials to set patient-specific conditions and support the actual clinical trial process.

[0006] Therefore, there is a need for a new type of clinical trial process automation solution that can rationally classify clinical trial subject groups based on product characteristics and multiple patient data, automatically set clinical trial execution conditions by performing multivariate analysis on individual patients, and support the efficient and safe execution of clinical trials tailored to patients according to those conditions. Prior art literature

[0007] Korean Published Patent No. 10-2025-0079904, Korean Published Patent No. 10-2023-0069375, Korean Published Patent No. 10-2021-0084829, Korean Published Patent No. 10-2021-0064751 The problem to be solved

[0008] According to one embodiment, the purpose is to provide a method, apparatus, and system for providing a process automation solution related to patient-customized clinical trials based on multivariate analysis.

[0009] The objectives of the present invention are not limited to those mentioned above, and other unmentioned objectives will be clearly understood from the description below. means of solving the problem

[0010] According to one embodiment, a method for providing a process automation solution for a patient-customized clinical trial based on multivariate analysis, performed by a device, comprises: receiving a request to proceed with a clinical trial for a first product from a first person in charge terminal; classifying patients who are eligible to participate in a clinical trial for the first product among a plurality of patients into a clinical trial subject group based on the characteristics of the first product; obtaining first patient information, which is patient information for a first patient who is one of the patients classified into the clinical trial subject group; matching the clinical trial information of the first product with the first patient information to generate first matching information; encoding the first matching information to generate a first input signal; inputting the first input signal into a first artificial intelligence model trained to set conditions for performing a clinical trial for a patient by considering the patient's risk level and an acceptable range when performing the clinical trial; and, when the first artificial intelligence model sets a first condition by analyzing the first input signal, obtaining a first output signal representing the first condition from the first artificial intelligence model. A method for providing a process automation solution for a patient-customized clinical trial based on multivariate analysis is provided, comprising the step of supporting the performance of a clinical trial for the first product in the first patient-customized manner based on the first condition confirmed through the first output signal.

[0011] When the first input signal is input, the first artificial intelligence model checks the first patient information and the clinical trial information of the first product based on the first input signal, checks the first patient's age group, health status score, medical history, and list of medications being taken based on the first patient information, sets the first value within a preset first numerical range to a higher value as the first patient's age group is higher, sets the second value within a preset second numerical range to a higher value as the first patient's health status score is lower, checks the number of diseases experienced by the first patient within a preset analysis target period through the first patient's medical history as the first number of diseases, and sets the third value within a preset third numerical range to a higher value as the first number of diseases is higher, checks the number of medications being taken by the first patient through the list of medications being taken as the first number of medications, and sets the fourth value within a preset fourth numerical range to a higher value as the first number of medications is higher, calculates the risk level of the first patient by summing the first to fourth values, and the clinical trial of the first product Based on the information, the range of permissible daily usage, the range of usage period, and the range of the status check cycle are determined when conducting a clinical trial for the first product; the range of permissible daily usage when conducting a clinical trial for the first product is determined as the first standard range; the higher the risk of the first patient, the lower the value of the first quantity within the first standard range is set; the range of permissible usage period when conducting a clinical trial for the first product is determined as the second standard range; the higher the risk of the first patient, the shorter the value of the first period within the second standard range is set; and the range of permissible status check cycle when conducting a clinical trial for the first product is determined as the third standard range.The higher the risk of the first patient, the shorter the value of the first cycle within the third standard range can be set, and the first condition can be set based on the first quantity, the first period, and the first cycle.

[0012] The step of supporting the performance of a clinical trial for the first product tailored to the first patient comprises: sending a notification message to the first person in charge terminal guiding the progress of the clinical trial for the first patient regarding the first product based on the first quantity, the first period, and the first cycle; confirming the start date of the clinical trial for the first patient regarding the first product as the first date; confirming the date after a preset observation period from the first date as the second date; confirming the health status score of the first patient measured on the second date as the first score; if the first score is confirmed to be lower than a preset first reference score, sending a notification message to the first person in charge terminal guiding the discontinuation of the clinical trial for the first patient regarding the first product; if the first score is confirmed to be not lower than the first reference score but lower than a preset second reference score, calculating a first difference score by subtracting the first score from the second reference score; and calculating a first weight value lower within a preset first weight range as the first difference score increases. The method may include: a step of calculating a second quantity by rounding the decimal point of the value obtained by multiplying the first quantity and the first weight; a step of, if it is confirmed that the first quantity and the second quantity do not match, changing the daily usage of the first product from the first quantity to the second quantity and sending a notification message to the first person in charge terminal guiding the progress of the clinical trial of the first patient; and a step of, if it is confirmed that the first score is not lower than the second reference score, or if it is confirmed that the first quantity and the second quantity match, sending a notification message to the first person in charge terminal guiding the continuation of the clinical trial of the first patient for the first product. Effects of the invention

[0013] According to one embodiment, by comprehensively analyzing product characteristics and various patient information regarding multiple patients using multiple variables, patients eligible to participate in a clinical trial can be selected more rationally and systematically, thereby improving the suitability of the clinical trial subject group and increasing the reliability and reproducibility of the clinical trial.

[0014] In addition, according to one embodiment, by matching clinical trial information of a product with patient information for individual patients and inputting this into an artificial intelligence model to automatically set customized clinical trial execution conditions that consider the patient's risk level and acceptable range for conducting the clinical trial, it becomes possible to conduct a precise clinical trial that reflects the characteristics of each patient, thereby preventing excessive burden or risk to the patient and substantially improving the safety of the clinical trial.

[0015] In addition, according to one embodiment, patient-specific clinical trial execution conditions are automatically calculated and clinical trial execution is supported based thereon, thereby minimizing errors and deviations that may occur in the clinical trial design and management process, which previously relied on the experience or manual work of personnel, thus ensuring consistency and objectivity throughout the clinical trial process and significantly improving management efficiency.

[0016] In addition, according to one embodiment, as a series of processes ranging from the selection of clinical trial subjects to the setting of test conditions for individual patients and support for execution are automated, the time and cost required for the preparation and execution of clinical trials can be reduced, and scalability can be provided to stably respond even if the scale of the clinical trial expands or complexity increases.

[0017] Meanwhile, the effects according to the embodiments are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0018] FIG. 1 is a schematic diagram showing the configuration of a system according to one embodiment. FIG. 2 is a flowchart illustrating the process of providing a process automation solution related to patient-customized clinical trials based on multivariate analysis according to one embodiment. FIGS. 3 and 4 are flowcharts for explaining the process of setting the conditions for performing a clinical trial of a patient according to one embodiment. FIG. 5 is a flowchart illustrating a process to support the performance of a clinical trial for a product tailored to a patient according to one embodiment. FIGS. 6 and 7 are flowcharts for explaining a process to support the performance of a clinical trial when the conditions of the clinical trial are changed according to one embodiment. FIG. 8 is a flowchart illustrating a process to support the performance of a clinical trial by changing the status check cycle according to one embodiment. FIG. 9 is an example diagram of the configuration of a device according to one embodiment. Specific details for implementing the invention

[0019] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0020] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept.

[0021] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0022] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0023] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0024] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0025] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0026] The embodiments can be implemented in various forms of products such as personal computers, laptop computers, tablet computers, smartphones, televisions, smart home appliances, intelligent automobiles, kiosks, and wearable devices.

[0027] In the embodiments, the Artificial Intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, it is a system in which the machine learns and makes judgments on its own. As the AI ​​system improves in recognition rate and becomes capable of understanding sellers' preferences more accurately with use, existing rule-based smart systems are gradually being replaced by deep learning-based AI systems.

[0028] Artificial intelligence technology consists of machine learning and component technologies that utilize machine learning. Machine learning is an algorithmic technology that autonomously classifies and learns the characteristics of input data, while component technologies are technologies that mimic the functions of the human brain, such as cognition and judgment, by utilizing machine learning algorithms like deep learning; these technologies comprise fields such as linguistic understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control.

[0029] The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding refers to the technology of recognizing, applying, and processing human language and text, including natural language processing, machine translation, dialogue systems, question answering, and speech recognition / synthesis. Visual understanding refers to the technology of perceiving and processing objects like human vision, including object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image enhancement. Inference and prediction refers to the technology of logically reasoning and predicting by judging information, including knowledge / probability-based inference, optimization prediction, preference-based planning, and recommendation. Knowledge representation refers to the technology of automatically processing human experiential information into knowledge data, including knowledge construction (data generation / classification) and knowledge management (data utilization). Motion control refers to the technology of controlling autonomous driving of vehicles and the movement of robots, including motion control (navigation, collision, driving) and manipulation control (behavior control).

[0030] Generally, to apply machine learning algorithms to real-world situations, training is performed using a trial-and-error method due to the inherent characteristics of the fundamental methodologies. In particular, deep learning requires hundreds of thousands of iterations. Since it is impossible to execute this in a real physical external environment, training is instead performed through simulations that virtually recreate the actual physical environment on a computer.

[0031] FIG. 1 is a schematic diagram showing the configuration of a system according to one embodiment.

[0032] Referring to FIG. 1, a system according to one embodiment may include a plurality of personnel terminals (100) and devices (200) capable of communicating with each other through a communication network.

[0033] First, the communication network can be configured regardless of the mode of communication, such as wired or wireless, and can be implemented in various forms to enable communication between servers and between servers and terminals.

[0034] Each of the multiple person-in-waiting terminals (100) can be implemented as a computing device equipped with a communication function, for example, a mobile phone, desktop PC, laptop PC, tablet PC, smartphone, etc., but is not limited thereto, and can be implemented as various types of communication devices that can be connected to an external server.

[0035] A plurality of personnel terminals (100) are terminals used by personnel of a company who wish to receive information related to clinical trials, and may include a first personnel terminal (110) used by a first personnel, a second personnel terminal (120) used by a second personnel, etc.

[0036] Each of the multiple personnel terminals (100) may be configured to perform all or part of the computational functions, storage / reference functions, input / output functions, and control functions that a conventional computer has. The multiple personnel terminals (100) may be configured to communicate with the device (200) via wired or wireless means.

[0037] Each of the multiple personnel terminals (100) may be connected to a web page operated by a person or organization providing a service using the device (200), or may have an application developed and distributed by a person or organization providing a service using the device (200) installed. Each of the multiple personnel terminals (100) may be linked with the device (200) through a web page or an application.

[0038] Each of the multiple personnel terminals (100) can access the device (200) through a web page, application, etc. provided by the device (200).

[0039] For convenience of explanation, the operation of the first person in charge terminal (110) is described below, but it is obvious that other person in charge terminals, such as the second person in charge terminal (120), can perform the operation of the first person in charge terminal (110) instead.

[0040] The device (200) may be a private server owned by a person or organization providing a service using the device (200), a cloud server, or a peer-to-peer (P2P) set of distributed nodes. The device (200) may be configured to perform all or part of the computational functions, storage / reference functions, input / output functions, and control functions that a conventional computer possesses. The device (200) may be equipped with at least one artificial intelligence model that performs inference functions.

[0041] The device (200) may be configured to communicate wirelessly or via wired connection with a plurality of personnel terminals (100), control the operation of each of the plurality of personnel terminals (100), and control which information to display on the screen of each of the plurality of personnel terminals (100).

[0042] The device (200) is implemented as a server for providing process automation solutions related to patient-customized clinical trials based on multivariate analysis, and can provide various related services.

[0043] Meanwhile, for convenience of explanation, only the first person-in-command terminal (110) and the second person-in-command terminal (120) among the plurality of person-in-command terminals (100) are shown in FIG. 1, but the number of terminals can vary depending on the embodiment. As long as the processing capacity of the device (200) allows, there is no particular limit to the number of terminals.

[0044] According to one embodiment, the device (200) can set the conditions for a patient's clinical trial by utilizing artificial intelligence to provide a process automation solution related to a patient-customized clinical trial based on multivariate analysis.

[0045] In the present invention, Artificial Intelligence (AI) refers to a technology that imitates human learning ability, reasoning ability, and perceptual ability, and implements them on a computer, and may include concepts such as machine learning and symbolic logic. Machine Learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. AI technology can analyze input data as a machine learning algorithm, learn from the results of the analysis, and make judgments or predictions based on the results of the learning. Furthermore, technologies that mimic the functions of the human brain, such as cognition and judgment, by utilizing machine learning algorithms can also be understood as falling within the category of AI. For example, technological fields such as linguistic understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control may be included.

[0046] Machine learning can refer to the process of training neural network models using experience in processing data. It implies that through machine learning, computer software improves its own data processing capabilities. A neural network model is constructed by modeling the correlations between data, and these correlations can be expressed by multiple parameters. A neural network model extracts and analyzes features from given data to derive correlations between them; machine learning can be defined as the process of optimizing the model's parameters by repeating this process. For example, a neural network model can learn the mapping (correlation) between inputs and outputs for data given as input-output pairs. Alternatively, even when only input data is provided, a neural network model can derive regularities between the given data and learn those relationships.

[0047] An artificial intelligence learning model or neural network model can be designed to implement the structure of the human brain on a computer and may include multiple network nodes that have weights and simulate neurons of a human neural network. The multiple network nodes may have interconnected relationships by simulating the synaptic activity of neurons, where neurons exchange signals through synapses. In an artificial intelligence learning model, multiple network nodes may be located in layers of different depths and exchange data according to convolutional connections. The artificial intelligence learning model may be, for example, an Artificial Neural Network (ANN) or a Convolutional Neural Network (CNN). As an embodiment, the artificial intelligence learning model may be machine learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning may include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, Ada-boost, Perceptron, Genetic Programming, and Clustering.

[0048] Among these, CNNs are a type of multilayer perceptron designed to use minimal preprocessing. CNNs consist of one or more convolutional layers and standard artificial neural network layers stacked on top, additionally utilizing weights and pooling layers. Thanks to this structure, CNNs can fully utilize two-dimensional input data. Compared to other deep learning architectures, CNNs demonstrate good performance in both image and audio fields. CNNs can also be trained using standard backpropagation. CNNs have the advantage of being easier to train than other feedforward artificial neural network techniques and using a small number of parameters.

[0049] Convolutional networks are neural networks comprising sets of nodes with bounded parameters. Many computer vision tasks have been significantly improved, driven by the increased size of available training data and the availability of computational power, combined with algorithmic advancements such as discriminative linear units and dropout training. In the case of massive datasets, such as those available for many tasks today, outfitting is not critical, and increasing the network size improves test accuracy. Optimal utilization of computing resources becomes a limiting factor. To address this, distributed, scalable implementations of deep neural networks can be employed.

[0050] FIG. 2 is a flowchart illustrating the process of providing a process automation solution related to patient-customized clinical trials based on multivariate analysis according to one embodiment.

[0051] Referring to FIG. 2, first, in step S201, the device (200) may receive a request to proceed with a clinical trial for a first product from a first person in charge terminal (110). Here, the first product is a product subject to a clinical trial and may be a pharmaceutical, biopharmaceutical, medical device, digital therapeutic, combination drug, or similar object requiring evaluation of clinical efficacy and safety. It is not limited to a product composed of a single component, but may be a composition containing multiple active ingredients, a combination product combined for a specific use, or a product in the form of a combination of software elements. At this time, the request to proceed with a clinical trial may include first product information, which is product information regarding the first product subject to the clinical trial, and clinical trial information for the first product.

[0052] According to one embodiment, the first product information is information representing the physical and functional characteristics of the first product subject to a clinical trial, and may include various information related to the first product, such as the product name, product type, active ingredient, ingredient composition, formulation, route of administration, expected mechanism of action, indication, manufacturer, development stage, and approval status.

[0053] In addition, the clinical trial information of the first product includes trial design information related to clinical trials planned or currently being conducted for the first product, and may include various information related to the clinical trial of the first product, such as clinical trial phases, clinical trial objectives, target diseases, inclusion and exclusion criteria, daily usage ranges, usage period ranges, status check cycle ranges, evaluation indicators, safety evaluation items, adverse reaction management criteria, trial schedule information, and constraints to be observed during the conduct of the clinical trial.

[0054] In step S202, the device (200) may classify patients eligible to participate in a clinical trial for the first product among a plurality of patients into a clinical trial subject group based on the characteristics of the first product. At this time, the characteristics of the first product may be identified through the first product information and may include various characteristics related to the product, such as active ingredients, mechanism of action, method of administration, expected side effects, applicable diseases, age restrictions, and gender restrictions; the plurality of patients may refer to clinical trial candidate patients registered in a medical institution, a clinical trial database, or a patient management system; and the clinical trial subject group may refer to a set composed of patients who satisfy the inclusion and exclusion criteria set according to the characteristics of the first product.

[0055] In step S203, the device (200) may obtain first patient information, which is patient information for one of the patients classified as a clinical trial subject group. Here, the first patient information may be obtained through the device (200)'s database, an external server, etc. At this time, the first patient information may include, but is not limited to, various information related to the first patient such as the first patient's gender, age group, physical indicators, medical history, a health status score that quantitatively indicates the health status, a list of medications being taken, lifestyle habits, and history of participation in previous clinical trials, and may further include biosignals, genetic information, environmental information, data collected from a wearable device, etc.

[0056] In step S204, the device (200) can generate first matching information by matching clinical trial information of the first product and first patient information. At this time, the first matching information is information representing the correspondence between the conditions for conducting the clinical trial of the first product and the state of the first patient, and may be multidimensional matching information including relationships between multiple variables.

[0057] In step S205, the device (200) can generate a first input signal by encoding the first matching information. At this time, the encoding may include at least one of numerical normalization, vectorization, and numerical conversion of categorical data, and may form clinical trial information and patient information of different formats into an integrated input signal form.

[0058] That is, the device (200) can generate a first input signal by performing normal information processing on the first matching information in order to use the first matching information as an input to the first artificial intelligence model.

[0059] In step S206, the device (200) may input a first input signal to a first artificial intelligence model trained to set conditions for performing a clinical trial of a patient by considering the patient's risk level and an acceptable range for performing the clinical trial. Here, the first artificial intelligence model may be in a state of being trained to set conditions for performing a clinical trial of a patient by considering the patient's risk level and an acceptable range for performing the clinical trial.

[0060] According to one embodiment, the first artificial intelligence model may be an algorithm that receives an input signal generated by encoding matching information that matches product clinical trial information and patient information, analyzes and sets the conditions for performing the clinical trial of the patient by considering the patient's risk level and an acceptable range when performing the clinical trial, and outputs an output value representing the set conditions. A detailed explanation of the process of setting the conditions for performing the clinical trial of the patient in the first artificial intelligence model will be described later with reference to FIGS. 3 and 4.

[0061] In step S207, when the device (200) sets a first condition by analyzing a first input signal in a first artificial intelligence model, it can obtain a first output signal representing the first condition from the first artificial intelligence model. Here, the first condition may include clinical trial performance conditions such as daily usage, usage period, and condition check cycle specific to the first patient.

[0062] That is, the first artificial intelligence model can verify the product's clinical trial information and patient information through an input signal, consider the patient's risk level and the acceptable range for conducting the clinical trial, determine which conditions are suitable for the patient when conducting the product's clinical trial, and output an output signal representing the set conditions. To this end, the first artificial intelligence model may be pre-trained to enable inference regarding which conditions are suitable for a specific patient when conducting a clinical trial for a specific product, based on a large amount of clinical trial information and patient information stored in a database.

[0063] According to one embodiment, the first artificial intelligence model is a model configured to receive patient information and product clinical trial information as input, calculate the patient's risk level, and set corresponding clinical trial execution conditions, and can be implemented with a structure including an input layer, a feature extraction layer, a risk calculation layer, and a condition setting layer.

[0064] The input layer is configured to receive input signals, which may include the patient's age group, health status score, medical history, list of medications being taken, and clinical trial information for the product in an encoded form. In this case, data of different formats may be converted into numerical data, categorical data, or binary data forms before being input.

[0065] The feature extraction layer can be configured to analyze input signals received from the input layer and generate feature vectors that are meaningful for calculating the patient's risk. In this case, the feature extraction layer can be implemented as a fully connected neural network, a tree-based model, an ensemble model, or a combination thereof, and can extract features that reflect the correlation between age group, health status score, medical history, and medication status.

[0066] The risk calculation layer is configured to calculate the patient's risk based on the feature vector generated in the feature extraction layer. In this case, the risk can be expressed as a single numerical value or one of pre-set risk ranges, and can be configured so that a higher value indicates a condition requiring caution during the clinical trial.

[0067] The condition setting hierarchy can determine the acceptable daily usage, usage period, and status check cycle during clinical trials by considering the risk calculation results and the product's clinical trial information together. In this case, the condition setting hierarchy can be configured so that conservative execution conditions are set as the patient's risk level increases, based on the acceptable range included in the product's clinical trial information.

[0068] The learning device in which the first artificial intelligence model is learned may be the same device as the device (200) or may be a separate device. The process of learning the first artificial intelligence model is described below.

[0069] The first artificial intelligence model can be trained based on previously collected clinical trial data and patient data. In this case, the training data may include patient characteristic information from past clinical trials, actual clinical trial conditions applied, whether adverse reactions occurred, whether patients dropped out of the clinical trial, and clinical trial result information.

[0070] During the learning process, the first artificial intelligence model can learn how risk changes for specific combinations of patient characteristics by learning the relationship between patient characteristics, clinical trial conditions, and clinical trial results. For example, it can be trained to calculate a relatively high risk when a patient is older, has a low health status score, and has a history of multiple diseases and polypharmacy.

[0071] In addition, the first artificial intelligence model can learn rules for setting appropriate daily dosages, usage periods, and status check cycles based on risk levels by learning the conditions and results of clinical trials applied to high-risk patients. In this process, conditions where safety was compromised or adverse events occurred can be reflected as negative training data, while conditions where the clinical trial was conducted stably can be reflected as positive training data.

[0072] The training of the first artificial intelligence model may be performed through at least one of supervised learning, semi-supervised learning, or reinforcement learning methods, and may be periodically retrained or its parameters updated as new clinical trial results or patient data are accumulated. Through this, the first artificial intelligence model can be improved to enable more precise risk calculation and condition setting by reflecting patient characteristics and the clinical trial environment that change over time.

[0073] In addition to the learning method described above, the first artificial intelligence model may also be trained through various learning methods of the known artificial intelligence model.

[0074] In step S208, the device (200) can support the performance of a clinical trial for the first product tailored to the first patient based on the first condition identified through the first output signal. At this time, the device (200) may provide information including at least one of a clinical trial schedule, performance conditions, or monitoring information. Here, the support may go beyond simple information provision and include substantial performance control, including changing, suspending, and resuming the performance conditions of the clinical trial.

[0075] The device (200) can send a notification message guiding the progress of the clinical trial to the first person in charge terminal (110) to support the performance of a clinical trial for the first product tailored to the first patient, and a detailed explanation related thereto will be described later with reference to FIG. 5.

[0076] As described above, by automatically classifying the clinical trial subject group based on product characteristics and clinical trial information, and by analyzing the patient information of individual patients included in the subject group using multiple variables to set customized clinical trial execution conditions for each patient, automation and precision of the entire clinical trial process can be achieved. Furthermore, by enabling the application of conditions that consider the risk level of each patient and the acceptable range for clinical trial execution, patient safety can be improved and the likelihood of adverse reactions reduced. Additionally, through matching and condition setting using artificial intelligence models, clinical trial dropouts can be reduced, and both the success rate and operational efficiency of the clinical trial can be improved.

[0077] FIGS. 3 and 4 are flowcharts for explaining the process of setting the conditions for performing a clinical trial of a patient according to one embodiment.

[0078] Referring to FIGS. 3 and 4, first, in step S301, when a first input signal is input, the first artificial intelligence model can verify the first patient information and the clinical trial information of the first product based on the first input signal.

[0079] In step S302, the first artificial intelligence model can verify the first patient's age group, health status score, medical history, and list of medications being taken based on the first patient's information. Here, the age group may be information classified according to a pre-set age range, the health status score may be an indicator that quantitatively represents the patient's health status, the medical history is information regarding past disease history, and the list of medications being taken may include information regarding medications currently or during a recent period.

[0080] According to one embodiment, the health status score may refer to an indicator calculated to quantitatively represent the overall health status of a patient, and may be calculated based on at least one of the patient's physical indicators, biosignals, clinical test results, presence of chronic disease, functional evaluation results, and lifestyle information, and is not limited to a score determined by a single indicator, and may be calculated based on at least one of clinical evaluation results generated by a medical institution, automatically measured biosignals, and patient-reported results.

[0081] For example, the health status score may be calculated by quantifying at least one of blood pressure, heart rate, body mass index, blood glucose levels, blood test results, and organ function indicators; the values ​​may be normalized or weighted to be calculated in the form of a composite score; or it may be calculated based on clinical evaluation scores generated by a medical institution, patient-reported results, or automatically measured biosignals.

[0082] The health status score can be defined such that a lower value indicates a relatively poor health status of the patient, and a higher value indicates a relatively good health status of the patient.

[0083] In step S303, the first artificial intelligence model may set the first value within the first numerical range to a higher value as the age of the first patient increases. Here, the first numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 100.

[0084] For example, if the first artificial intelligence model confirms that the first patient's age group is in the teens, the first value can be set to 10, and if the first patient's age group is confirmed to be in the 20s, the first value can be set to 20.

[0085] In step S304, the first artificial intelligence model may set the second value within the second numerical range to a higher value as the health status score of the first patient decreases. Here, the second numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 100.

[0086] For example, if the first artificial intelligence model confirms that the first patient's health status score is 90 points, it can set the second value to 10, and if the first patient's health status score is 80 points, it can set the second value to 20.

[0087] In step S305, the first artificial intelligence model can identify the number of diseases experienced by the first patient within the analysis period as the number of first diseases through the first patient's medical history. Here, the analysis period may be set differently depending on the embodiment, for example, within the last 5 years.

[0088] In step S306, the first artificial intelligence model may set the third value within the third numerical range to a higher value as the number of first diseases increases. Here, the third numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 100.

[0089] For example, if the first artificial intelligence model confirms that the number of first diseases is 1, the third value can be set to 10, and if the number of first diseases is confirmed to be 2, the third value can be set to 20.

[0090] In step S307, the first artificial intelligence model can determine the number of drugs the first patient is taking as the number of drugs the first patient is taking through the list of drugs the first patient is taking.

[0091] In step S308, the first artificial intelligence model can set the fourth value within the fourth numerical range to a higher value as the number of first drugs increases. Here, the fourth numerical range may be set differently depending on the embodiment, for example, to a range of 0 to 100.

[0092] For example, if the first artificial intelligence model confirms that the first number of drugs is 1, the fourth value can be set to 10, and if the first number of drugs is confirmed to be 2, the fourth value can be set to 20.

[0093] In step S309, the first artificial intelligence model may calculate the risk level of the first patient by summing the first through fourth values. In this case, the risk level may refer to an indicator that comprehensively represents the likelihood of adverse reactions, the likelihood of dropping out of the clinical trial, or the likelihood of reduced safety during the course of the clinical trial for a specific product, and may be defined such that a higher value indicates a state requiring greater caution during the conduct of the clinical trial.

[0094] Following step S309, in step S401, the first artificial intelligence model can determine the acceptable range of daily usage, usage period, and status check cycle for conducting a clinical trial of the first product, based on the clinical trial information of the first product. Here, each range represents a condition range acceptable in the clinical trial design and can be applied as a limit range when setting patient-specific conditions.

[0095] According to one embodiment, the status check cycle may refer to a time interval during which a status check is performed to verify the patient's physical condition, health status, or whether there is an adverse reaction during the performance of a clinical trial, and may be set in at least one of daily, weekly, or specific event occurrence criteria, and may be set differently depending on the characteristics of the clinical trial and the patient's risk level.

[0096] In step S402, the first artificial intelligence model can determine the range of acceptable daily usage for conducting clinical trials of the first product as the first standard range.

[0097] For example, if the first artificial intelligence model determines that the range of acceptable daily usage for the first product is from 1 to 10 when conducting a clinical trial, it can determine that 1 to 10 is the first standard range.

[0098] In step S403, the first artificial intelligence model can set the first quantity to a smaller value within the first standard range as the risk level of the first patient increases.

[0099] For example, if the first artificial intelligence model confirms that the risk level of the first patient is 40, the first quantity can be set to 9, and if the risk level of the first patient is confirmed to be 80, the first quantity can be set to 8.

[0100] In step S404, the first artificial intelligence model can determine the range of acceptable usage periods for the first product when conducting clinical trials as the second standard range.

[0101] For example, if the first artificial intelligence model determines that the acceptable usage period range for conducting a clinical trial for the first product is from one month to ten months, it can determine that one month to ten months is the second standard range.

[0102] In step S405, the first artificial intelligence model can set the first period to a shorter value within the second standard range as the risk level of the first patient increases.

[0103] For example, if the first artificial intelligence model confirms that the risk level of the first patient is 40, the first period can be set to 9 months, and if the risk level of the first patient is confirmed to be 80, the first period can be set to 8 months.

[0104] In step S406, the first artificial intelligence model can determine the range of acceptable status check cycles for conducting clinical trials on the first product as the third standard range.

[0105] For example, if the first artificial intelligence model determines that the range of acceptable condition check cycles for performing a clinical trial for the first product is from 1 to 10, it can determine that 1 to 10 is the first standard range.

[0106] In step S407, the first artificial intelligence model can set the first cycle to a shorter value within the third criterion range as the risk level of the first patient increases.

[0107] For example, if the first artificial intelligence model confirms that the risk level of the first patient is 40, the first cycle can be set to 9 days, and if the risk level of the first patient is confirmed to be 80, the first cycle can be set to 8 days.

[0108] In step S408, the first artificial intelligence model can set a first condition based on a first quantity, a first period, and a first cycle.

[0109] As described above, by establishing customized clinical trial conditions that reflect the patient's risk level and health status, the safety and reliability of the clinical trial can be improved. Furthermore, by flexibly adjusting the daily usage amount, usage period, and status check cycle according to the risk level, the likelihood of adverse reactions and dropout can be reduced, the efficiency of clinical trial operations can be increased, and the management burden can be alleviated.

[0110] FIG. 5 is a flowchart illustrating a process to support the performance of a clinical trial for a product tailored to a patient according to one embodiment.

[0111] Referring to FIG. 5, first, in step S501, the device (200) may send a notification message to the first person in charge terminal (110) to guide the progress of the clinical trial of the first patient for the first product based on the first quantity, the first period, and the first cycle. At this time, the notification message may include information regarding the daily usage, usage period, and status check cycle that reflect the clinical trial performance conditions applied to the first patient.

[0112] In step S502, the device (200) can confirm the start date of the clinical trial for the first patient for the first product as the first date. To do this, the device (200) can check in advance when the clinical trial for the first patient for the first product started through the first person in charge terminal (110).

[0113] In step S503, the device (200) can identify a date after the observation period from the first date as the second date. Here, the observation period may be set differently depending on the embodiment, for example, it may be set to one week.

[0114] In step S504, the device (200) can identify the health status score of the first patient measured on the second day as the first score. To this end, the health status score of the first patient may be measured on the second day based on the first patient's vital signs, clinical test results, patient report information, or a combination thereof, and when the health status score of the first patient measured on the second day is stored in a database, the device (200) can identify that the health status score of the first patient measured on the second day is the first score.

[0115] In step S505, the device (200) can check whether the first score is lower than the first reference score. Here, the first reference score may be set differently depending on the embodiment.

[0116] If it is confirmed in step S505 that the first score is lower than the first reference score, in step S506, the device (200) can send a notification message to the first person in charge terminal (110) instructing the discontinuation of the clinical trial of the first patient for the first product.

[0117] If it is confirmed in step S505 that the first score is not lower than the first reference score, in step S507, the device (200) can check whether the first score is lower than the second reference score. Here, the second reference score can be set to a score higher than the first reference score.

[0118] If it is confirmed in step S507 that the first score is lower than the second reference score, in step S508, the device (200) can calculate the first difference score by subtracting the first score from the second reference score.

[0119] In step S509, the device (200) can calculate a lower value for the first weight within the first weight range as the first difference score increases. Here, the first weight range may be set differently depending on the embodiment, for example, to a range of 0 to 1.

[0120] For example, the device (200) can set the first weight to 0.9 when the first difference score is confirmed to be 10 points, and can set the first weight to 0.8 when the first difference score is confirmed to be 20 points.

[0121] In step S510, the device (200) can calculate a second quantity by rounding the decimal point of the value obtained by multiplying the first quantity and the first weight. At this time, the second quantity may represent a daily usage amount adjusted to reflect the current health condition of the first patient, and may be calculated as a value less than or equal to the first quantity.

[0122] In step S511, the device (200) can check whether the first quantity and the second quantity match.

[0123] If it is confirmed in step S511 that the first quantity and the second quantity do not match, in step S512, the device (200) can change the daily usage of the first product from the first quantity to the second quantity and send a notification message to the first person in charge terminal (110) to guide the progress of the clinical trial of the first patient.

[0124] If it is confirmed in step S507 that the first score is not lower than the second reference score, or if it is confirmed in step S511 that the first quantity and the second quantity match, then in step S513, the device (200) can send a notification message to the first person in charge terminal (110) guiding the continuation of the clinical trial of the first patient for the first product.

[0125] As described above, by automatically determining whether to proceed with, discontinue, or change conditions of a clinical trial based on the patient's health status and providing notifications accordingly, the entire clinical trial process can be precisely controlled in a patient-customized manner. Furthermore, by rapidly deciding whether to discontinue the clinical trial by comparing the health status score after the observation period with a reference score, or by dynamically adjusting the daily usage by applying weights based on the degree of change in health status, patient safety can be improved and the likelihood of adverse reactions can be effectively reduced.

[0126] FIGS. 6 and 7 are flowcharts for explaining a process to support the performance of a clinical trial when the conditions of the clinical trial are changed according to one embodiment.

[0127] According to one embodiment, each step illustrated in FIGS. 6 to 7 can be performed after step S512.

[0128] Referring to FIGS. 6 and 7, first, in step S601, the device (200) can identify a date after the observation period from the second date as the third date.

[0129] In step S602, the device (200) can verify the health status score of the first patient measured on the third day as the second score. To this end, the health status score of the first patient may be measured on the third day based on the first patient's vital signs, clinical test results, patient report information, or a combination thereof, and when the health status score of the first patient measured on the third day is stored in a database, the device (200) can verify that the health status score of the first patient measured on the third day is the second score.

[0130] In step S603, the device (200) can check whether the second score is lower than the first reference score.

[0131] If it is confirmed in step S603 that the second score is lower than the first reference score, in step S604, the device (200) can send a notification message to the first person in charge terminal (110) instructing the discontinuation of the clinical trial of the first patient for the first product.

[0132] If it is confirmed in step S603 that the second score is not lower than the first reference score, in step S701, the device (200) can check whether the second score is lower than the second reference score.

[0133] If it is confirmed in step S701 that the second score is lower than the second reference score, in step S702, the device (200) can calculate the first increase / decrease rate by subtracting the first score from the second score and dividing by the first score. Here, the first increase / decrease rate can be used as an indicator to quantitatively show whether the health condition of the first patient has improved or worsened compared to the previous observation point.

[0134] In step S703, the device (200) can calculate a first ratio by adding 100% and a first increase / decrease rate. At this time, the first ratio can be calculated within the range of 0% to 200%.

[0135] In step S704, the device (200) can calculate a third score by rounding the decimal point of the value obtained by multiplying the second score by the first ratio.

[0136] In step S705, the device (200) can calculate a second difference score by subtracting a third score from a second reference score.

[0137] In step S706, the device (200) may calculate a second weight at a lower value within the second weight range as the second difference score increases. Here, the second weight range may be set differently depending on the embodiment, for example, to a range of 0 to 2.

[0138] For example, the device (200) can set the second weight to 1.1 if the second difference score is confirmed to be -10 points, the second weight to 1 if the second difference score is confirmed to be 0 points, and the second weight to 0.9 if the second difference score is confirmed to be 10 points.

[0139] In step S707, the device (200) may calculate a third quantity by rounding the decimal point of the value obtained by multiplying the second quantity by the second weight. At this time, the third quantity may represent a daily usage adjusted to reflect the current health condition of the first patient, and if the third quantity is calculated to be greater than the first quantity, the third quantity may be adjusted to be equal to the first quantity.

[0140] In step S708, the device (200) can check whether the second quantity and the third quantity match.

[0141] If it is confirmed in step S708 that the second quantity and the third quantity match, in step S709, the device (200) can maintain the daily usage of the first product at the second quantity and send a notification message to the first person in charge terminal (110) to guide the progress of the clinical trial of the first patient.

[0142] If it is confirmed in step S708 that the second quantity and the third quantity do not match, in step S710, the device (200) can change the daily usage of the first product from the second quantity to the third quantity and send a notification message to the first person in charge terminal (110) to guide the progress of the clinical trial of the first patient.

[0143] If it is confirmed in step S701 that the second score is not lower than the second reference score, in step S711, the device (200) can change the daily usage of the first product from the second quantity to the first quantity and send a notification message to the first person in charge terminal (110) to guide the progress of the clinical trial of the first patient.

[0144] As described above, even after the initial usage adjustment, an additional observation period can be established to continuously evaluate changes in the patient's health status, and based on the results, the discontinuation, maintenance, further adjustment, or return to initial conditions of the clinical trial can be automatically determined. Furthermore, by quantitatively considering the direction and extent of changes in the patient's condition through a correction score reflecting the rate of increase or decrease in the health status score and weight-based usage recalculation, the conditions for conducting the clinical trial can be precisely controlled stepwise.

[0145] FIG. 8 is a flowchart illustrating a process to support the performance of a clinical trial by changing the status check cycle according to one embodiment.

[0146] According to one embodiment, each step illustrated in FIG. 8 may be performed after step S512 or step S513.

[0147] Referring to FIG. 8, in step S801, the device (200) can identify a date after the observation period from the second date as the third date.

[0148] In step S802, the device (200) can verify the health status score of the first patient measured on the third day as the second score.

[0149] In step S803, the device (200) can determine the date after the observation period from the third date as the fourth date.

[0150] In step S804, the device (200) can check the health status score of the first patient measured on the fourth day as the fourth score.

[0151] In step S805, the device (200) can calculate a second increase / decrease rate by subtracting the first score from the fourth score and dividing by the first score, and calculate a third increase / decrease rate by subtracting the second score from the fourth score and dividing by the second score. Here, the second increase / decrease rate can be used as an indicator representing the degree of change in the current health condition compared to the initial observation point, and the third increase / decrease rate can be used as an indicator representing the degree of change in the current health condition compared to the previous observation point.

[0152] In step S806, the device (200) can calculate the average of the second and third increase / decrease rates as the fourth increase / decrease rate. Here, the fourth increase / decrease rate can be used as a representative indicator that comprehensively reflects the trend of changes in the first patient's health condition.

[0153] In step S807, the device (200) can calculate a second ratio by adding 100% and a fourth increase / decrease rate. Here, the second ratio can be used as a correction factor to adjust the status check cycle, and can be reflected so that the status check cycle becomes relatively longer when the first patient's health condition improves, and becomes relatively shorter when the first patient's health condition deteriorates.

[0154] In step S808, the device (200) can determine the number of days of the first cycle as the first day.

[0155] In step S809, the device (200) can calculate a second number of days by rounding the decimal point of the value obtained by multiplying the first number of days by the second ratio. Here, the second number of days may represent the length of a status check cycle adjusted to reflect the trend of recent changes in the first patient's health status.

[0156] In step S810, the device (200) can set a second cycle to a second number of days. Here, the second cycle can be used as a new cycle applied to the condition check of the first patient when performing a clinical trial thereafter.

[0157] In step S811, the device (200) can check whether the first cycle and the second cycle match.

[0158] If it is confirmed in step S811 that the first cycle and the second cycle do not match, in step S812, the device (200) can change the status check cycle of the first product from the first cycle to the second cycle and send a notification message to the first person in charge terminal (110) to guide the progress of the clinical trial of the first patient.

[0159] As described above, by calculating the rate of increase and decrease and the average rate of increase and decrease from the patient's health status score measured at multiple observation points and reflecting this in the status check cycle, it is possible to adjust the monitoring cycle by quantitatively considering the trend of changes in the patient's condition. Furthermore, while preventing excessive cycle changes due to short-term fluctuations, the frequency of status checks can be automatically adjusted according to the improvement or deterioration of the health condition, thereby improving patient safety and the reliability of clinical trial management.

[0160] FIG. 9 is an example diagram of the configuration of a device according to one embodiment.

[0161] A device (200) according to one embodiment includes a processor (210) and a memory (220). The processor (210) may include at least one device described with reference to FIGS. 1 through 8 or may perform at least one method described with reference to FIGS. 1 through 8. A person or organization using the device (200) may provide services related to some or all of the methods described with reference to FIGS. 1 through 8.

[0162] The memory (220) may store information related to the methods described above or store a program in which the methods described below are implemented. The memory (220) may be volatile memory or non-volatile memory.

[0163] The processor (210) can execute a program and control the device (200). The code of the program executed by the processor (210) can be stored in memory (220). The device (200) is connected to an external device (e.g., a personal computer or a network) through an input / output device (not shown in the drawing) and can exchange data through wired or wireless communication.

[0164] The device (200) can be used to train an artificial intelligence model or to use a trained artificial intelligence model. The memory (220) may contain an artificial intelligence model that is being trained or has been trained. The processor (210) can train or execute an artificial intelligence model algorithm stored in the memory (220). The training device for training the artificial intelligence model and the device (200) for using the trained artificial intelligence model may be the same or separate.

[0165] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0166] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0167] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0168] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0169] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 A method for providing a process automation solution for a patient-customized clinical trial based on multivariate analysis, performed by a device, comprising: receiving a request to proceed with a clinical trial for a first product from a first person in charge terminal; classifying patients who are eligible to participate in a clinical trial for the first product among a plurality of patients into a clinical trial subject group based on the characteristics of the first product; obtaining first patient information, which is patient information for a first patient who is one of the patients classified into the clinical trial subject group; matching clinical trial information of the first product with the first patient information to generate first matching information; encoding the first matching information to generate a first input signal; inputting the first input signal to a first artificial intelligence model trained to set conditions for performing a clinical trial for a patient by considering the patient's risk level and the range of daily usage, usage period, and status check cycle that are permissible when performing a clinical trial included in the clinical trial information of the first product; and, if the first artificial intelligence model analyzes the first input signal and sets a first condition representing the conditions for performing a clinical trial for the first patient, obtaining a first output signal representing the first condition from the first artificial intelligence model. The method includes a step of supporting the performance of a clinical trial for the first product tailored to the first patient based on the first condition confirmed through the first output signal, wherein when the first input signal is input, the first artificial intelligence model checks the first patient information and the clinical trial information of the first product based on the first input signal, checks the age group, health status score, medical history, and list of medications being taken of the first patient based on the first patient information, and sets the first value to a higher value within a preset first value range as the age group of the first patient increases.The lower the health status score of the first patient, the higher the second value is set within a preset second value range; through the medical history of the first patient, the number of diseases experienced by the first patient within a preset analysis period is identified as the first number of diseases; the higher the first number of diseases, the higher the third value is set within a preset third value range; through the list of medications the first patient is taking, the number of medications the first patient is taking is identified as the first number of medications; the higher the first number of medications, the higher the fourth value is set within a preset fourth value range; the first to fourth values ​​are summed to calculate the risk level of the first patient; based on the clinical trial information of the first product, the range of acceptable daily usage, the range of usage period, and the range of status check cycles for conducting a clinical trial of the first product are identified; the range of acceptable daily usage for conducting a clinical trial of the first product is identified as the first standard range; the higher the risk level of the first patient, the lower the first quantity is set within the first standard range; and the acceptable usage for conducting a clinical trial of the first product The step of confirming the range of the period as a second standard range, setting the first period to a shorter value within the second standard range as the risk level of the first patient increases, confirming the range of the acceptable status check cycle for conducting a clinical trial for the first product as a third standard range, setting the first cycle to a shorter value within the third standard range as the risk level of the first patient increases, setting the first condition based on the first quantity, the first period, and the first cycle, and supporting the performance of a clinical trial for the first product tailored to the first patient, is based on the first quantity, the first period, and the first cycle.A step of transmitting a notification message to the first person in charge terminal guiding the progress of the clinical trial of the first patient for the first product; a step of confirming the start date of the clinical trial of the first patient for the first product as the first date; a step of confirming a date after a preset observation period from the first date as the second date; a step of confirming the health status score of the first patient measured on the second date as the first score; a step of transmitting a notification message to the first person in charge terminal guiding the discontinuation of the clinical trial of the first patient for the first product if it is confirmed that the first score is lower than a preset first reference score; a step of calculating a first difference score by subtracting the first score from the second reference score if it is confirmed that the first score is not lower than the first reference score but lower than a preset second reference score; a step of calculating a first weight to a lower value within a preset first weight range as the first difference score increases; a step of calculating a second quantity by rounding the decimal point of the value obtained by multiplying the first quantity and the first weight; and a step in which the first quantity and the second quantity A method for providing a process automation solution for a patient-customized clinical trial based on multivariate analysis, comprising: a step of sending a notification message to a first person in charge terminal guiding the progress of the clinical trial of the first patient by changing the daily usage of the first product from the first quantity to the second quantity if it is confirmed that there is no match; and a step of sending a notification message to a first person in charge terminal guiding the continuation of the clinical trial of the first patient for the first product if it is confirmed that the first score is not lower than the second reference score or if it is confirmed that the first quantity and the second quantity match. Claim 2 delete Claim 3 delete

Citation Information

Patent Citations

  • Integrated clinical risk assessment system

    US20090070138A1