Clinical trial support device, clinical trial support method, and clinical trial support program

Abstract

This invention provides a clinical trial support device that can improve the accuracy of predicting the number of clinical trial candidates. [Solution] The clinical trial support device 10 comprises an acquisition unit 11, an extraction unit 12, an estimation unit 13, a prediction unit 14, and an output unit 15. The acquisition unit 11 acquires data related to the treatment of patients. The extraction unit 12 extracts patients who meet the selection criteria for clinical trial patients at a first time point based on the treatment data, and identifies them as clinical trial candidates. The estimation unit 13 uses a state curve, which is a curve showing the time-series changes in the state of patients suffering from the disease under investigation, to estimate the suitability probability, which is the probability that a clinical trial candidate is suitable for the clinical trial at a second time point. The prediction unit 14 predicts the number of clinical trial candidates at the second time point based on the suitability probability. The output unit 15 outputs information regarding the number of clinical trial candidates at the second time point. With this configuration, the clinical trial support device 10 can support decisions regarding the conduct of clinical trials.

Description

[Technical Field]

[0001] This disclosure relates to clinical trial support devices, etc. [Background technology]

[0002] In clinical trials of pharmaceuticals, the person responsible for selecting patients for the trial may, for example, extract patients who meet the selection criteria by reviewing medical records. For instance, the person determines whether the selection criteria match the information recorded in the medical records. Then, the person extracts patients whose medical records match the selection criteria as candidates for the trial. Furthermore, in order to secure the necessary number of trial patients, the person responsible needs to review the medical records of many patients to find those who meet the selection criteria. For this reason, systems that support the selection of patients for clinical trials are sometimes used.

[0003] The clinical trial support system described in Patent Document 1 screens a database containing medical data based on eligibility and exclusion criteria for clinical trials. Based on the screening results, the clinical trial support system described in Patent Document 1 narrows down the candidates for clinical trials. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] International Publication No. 2023 / 248978 [Overview of the project] [Problems that the invention aims to solve]

[0005] The technology described in Patent Document 1 may make it difficult to accurately predict the number of clinical trial candidates.

[0006] This disclosure aims to provide a clinical trial support device, etc., that can improve the accuracy of predicting the number of clinical trial candidates in order to solve the above-mentioned problems. [Means for solving the problem]

[0007] To solve the above problems, the clinical trial support device of this disclosure comprises: acquisition means for acquiring data on patient treatment; extraction means for extracting patients who meet the selection criteria for clinical trial patients at a first time point based on the treatment data as clinical trial candidates; estimation means for estimating the probability of a clinical trial candidate being suitable for the clinical trial at a second time point later than the first time point, using a state curve which is a curve showing the time-series state changes of patients suffering from the disease under investigation; prediction means for predicting the number of clinical trial candidates at the second time point based on the probability of suitability; and output means for outputting information regarding the number of clinical trial candidates at the second time point.

[0008] The clinical trial support method described herein acquires data on patient treatment, extracts patients who meet the selection criteria for clinical trial patients at a first time point based on the treatment data, estimates the probability of a clinical trial candidate being suitable for the trial at a second time point later than the first time point using a state curve, which is a curve showing the time-series change in the state of patients suffering from the disease under investigation, predicts the number of clinical trial candidates at the second time point based on the probability of suitability, and outputs information regarding the number of clinical trial candidates at the second time point.

[0009] The clinical trial support program described herein causes a computer to perform the following processes: acquiring data on patient treatment; extracting patients who meet the selection criteria for clinical trial patients at a first time point based on the treatment data; estimating the probability of a candidate being suitable for the clinical trial at a second time point later than the first, using a state curve, which is a curve showing the time-series changes in the state of patients suffering from the disease under investigation; predicting the number of candidates at the second time point based on the probability of suitability; and outputting information regarding the number of candidates at the second time point. [Effects of the Invention]

[0010] According to the present disclosure, the accuracy of predicting the number of clinical trial candidates can be improved.

Brief Description of Drawings

[0011] [Figure 1] It is a diagram showing an example of the configuration of a clinical trial support system in the present disclosure. [Figure 2] It is a diagram showing an example of the configuration of a clinical trial support device in the present disclosure. [Figure 3] It is a diagram schematically showing an example of a curve indicating the change in the state of a patient in the present disclosure. [Figure 4] It is a diagram schematically showing an example of a curve indicating the change in the state of a patient in the present disclosure. [Figure 5] It is a diagram showing an example of a display screen for displaying the prediction result of the number of clinical trial candidates in the present disclosure. [Figure 6] It is a diagram showing an example of a display screen for displaying the prediction result of the number of clinical trial candidates in the present disclosure. [Figure 7] It is a diagram showing an example of a display screen for displaying the prediction result of the number of clinical trial candidates in the present disclosure. [Figure 8] It is a diagram showing an example of a screen for setting conditions for extracting clinical trial candidates in the present disclosure. [Figure 9] It is a diagram showing an example of a display screen for displaying the prediction result of the number of clinical trial candidates in the present disclosure. [Figure 10] It is a diagram showing an example of a display screen for displaying the prediction result of the number of clinical trial candidates in the present disclosure. [Figure 11] It is a diagram showing an example of a display screen for displaying the prediction result of the number of clinical trial candidates in the present disclosure. [Figure 12] It is a diagram showing an example of a display screen for displaying details of clinical trial candidates in the present disclosure. [Figure 13] It is a diagram showing an example of the operation flow of a clinical trial support device in the present disclosure. [Figure 14] It is a diagram showing an example of the hardware configuration of a clinical trial support device in the present disclosure.

Modes for Carrying Out the Invention

[0012] Embodiments of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is an example of the configuration of a clinical trial support system. The clinical trial support system includes a clinical trial support device 10, a terminal device 20, and a data management device 30. The clinical trial support device 10 is connected to the terminal device 20 via a network, for example. The clinical trial support device 10 is connected to the data management device 30 via a network, for example. Also, there may be a plurality of terminal devices 20 and data management devices 30, respectively. The numbers of the terminal device 20 and the data management device 30 can be set as appropriate.

[0013] The clinical trial support system is, for example, a system that predicts the number of clinical trial candidates. The clinical trial candidates are, for example, candidates for clinical trial patients. The clinical trial patients are, for example, candidates for patients to be administered the drug in a clinical trial of the drug. The clinical trial patients may include patients in the control group. A pharmaceutical company or an institution commissioned by a pharmaceutical company creates a clinical trial implementation plan, for example, by estimating the number of clinical trial patients at the stage of starting the clinical trial. Then, the pharmaceutical company or the institution commissioned by the pharmaceutical company undergoes a review on the feasibility of implementing the clinical trial based on the created clinical trial implementation plan, for example. When the clinical trial is approved for implementation in the review, the pharmaceutical company or the institution commissioned by the pharmaceutical company secures clinical trial patients, for example, and then conducts the clinical trial based on the clinical trial implementation plan. Since it takes time from the creation of the clinical trial implementation plan to the start of the clinical trial, for example, even a patient who met the selection criteria for clinical trial patients at the time of creating the clinical trial implementation plan may be in a state unsuitable for the clinical trial at the start of the clinical trial. Therefore, in order to conduct the clinical trial as scheduled, it is desirable to accurately predict the number of clinical trial candidates at the start of the clinical trial at the time of creating the clinical trial implementation plan, for example.

[0014] The clinical trial support system, for example, extracts patients who meet the selection criteria for clinical trial patients based on data related to the patient's treatment. The clinical trial support system estimates the probability that the extracted clinical trial candidates will be suitable to be clinical trial patients at the start of the clinical trial as the probability of suitability. Then, based on the estimated probability of suitability, the clinical trial support system predicts the number of clinical trial candidates at the start of the clinical trial.

[0015] A clinical trial support system estimates the probability of suitability using, for example, a state curve. A state curve is, for example, a curve showing the time-series changes in the state of a patient suffering from the disease under investigation. A state curve is, for example, a curve showing the probability that a patient suffering from the disease under investigation is in a state that is suitable for the clinical trial. Being suitable for the clinical trial means, for example, being a candidate for administration of the drug under investigation. Being a candidate for administration of the drug under investigation means, for example, that the patient is alive and has not completed treatment. Also, being a candidate for administration of the drug under investigation means, for example, that the patient is alive and has not been administered other drugs with a similar purpose. For example, a Kaplan-Meier curve may be used as a state curve. However, the state curve is not limited to the above.

[0016] For example, if the creation of the clinical trial protocol is considered the first time point and the start of the clinical trial is considered the second time point, the clinical trial support system estimates the probability that a candidate who meets the patient selection criteria at the first time point will be suitable to be a clinical trial patient at the second time point as the probability of suitability. Then, using, for example, a state curve, the clinical trial support system predicts the number of clinical trial candidates at the second time point based on the estimated probability of suitability. The first time point is not limited to the creation of the clinical trial protocol, nor is the second time point limited to the start of the clinical trial. By predicting the number of clinical trial candidates in this way, the clinical trial support system can, for example, improve the accuracy of its prediction of the number of clinical trial candidates.

[0017] Here, a specific example of the configuration of the clinical trial support device 10 will be described. Figure 2 shows an example of the configuration of the clinical trial support device 10. The clinical trial support device 10 has as its basic configuration an acquisition unit 11, an extraction unit 12, an estimation unit 13, a prediction unit 14, and an output unit 15. The clinical trial support device 10 further includes, for example, a storage unit 16.

[0018] The data acquisition unit 11 acquires data related to the treatment of patients. For example, the data acquisition unit 11 acquires data related to the treatment of patients suffering from the disease being investigated. The disease being investigated is, for example, the disease to which the drug being validated in the clinical trial is administered. When multiple drugs are administered sequentially, the data acquisition unit 11 may acquire data related to the treatment of patients who have been administered a drug prior to the drug being investigated. For example, when a clinical trial of an anticancer drug is being conducted, the data acquisition unit 11 may acquire data related to the treatment of patients who are receiving a previous line of treatment. A line refers to, for example, a stage of treatment. In the case of cancer treatment, a line refers to, for example, the sequence of treatments involving the administration of anticancer drugs. A previous line of treatment refers to, for example, treatment with a drug administered in the stage immediately preceding the drug being investigated.

[0019] Treatment-related data may include, for example, records of one or more items from diagnosis, examinations, medication, surgery, follow-up, and the patient's condition. Treatment-related data may also include patient attributes. Patient attributes may include, for example, the patient's condition that does not change with treatment. Patient attributes may include, for example, information on one or more items from age, sex, weight, height, occupation, medical history, family medical history, race, and place of residence. However, patient attributes are not limited to those listed above.

[0020] The patient's condition includes information on one or more items, such as disease information, comorbidity information, biomarkers, disease status, guideline scores, treatment effectiveness, and test results. Treatment effectiveness includes, for example, the effects of treatment, drug administration, and surgery. However, it is not limited to these. Test results include, for example, the results of biopsies, imaging tests, and genomic tests. However, it is not limited to these. In addition, treatment data may include information on the person who performed the medical procedure. Information on the person who performed the medical procedure includes, for example, information indicating the healthcare professional who performed the medical procedure on the patient. Information indicating the healthcare professional who performed the medical procedure on the patient includes, for example, the name or identifier of a physician, nurse, pharmacist, and physical therapist.

[0021] The acquisition unit 11 acquires data from the electronic medical record, for example, as data related to the patient's treatment. The patient's treatment data may also be examination data. If the patient's treatment data is examination data, it may also be image data for diagnostic imaging. Furthermore, the patient's treatment data may also be data recorded on the medical claim form. The treatment data is not limited to the above.

[0022] The acquisition unit 11 may acquire the extraction criteria for clinical trial candidates. The acquisition unit 11 may acquire information on one or more items from among the clinical trial period, medical department, disease name, target region, selection criteria used for extraction, and the standard value of goodness of fit as extraction criteria. The clinical trial period is, for example, information that specifies the period during which the clinical trial will be conducted. The medical department is, for example, information that specifies the medical department that will treat the disease that is the subject of the clinical trial. The target disease name is, for example, information that specifies the disease that will be treated by administering the drug under investigation. The clinical trial region is, for example, information that specifies the region in which the hospital conducting the clinical trial is located. The selection criteria used for extraction is, for example, information that specifies the criteria used for extracting clinical trial candidates from among the criteria included in the selection criteria. The standard value of goodness of fit is, for example, information that indicates the standard value at which a candidate will be extracted as a clinical trial candidate if their goodness of fit is equal to or greater than the standard value. Goodness of fit is, for example, an index that indicates the degree to which the treatment data fits the selection criteria. The extraction criteria are not limited to those described above.

[0023] The extraction unit 12 extracts clinical trial candidates, who are potential patients to be included in the clinical trial, based on treatment data. For example, the extraction unit 12 extracts patients who meet the selection criteria at a first point in time as clinical trial candidates, based on treatment data. The first point in time is, for example, the time when the clinical trial protocol is created. For example, the extraction unit 12 extracts patients from among those for whom treatment data has been obtained, whose treatment data meets the selection criteria, as clinical trial candidates. Meeting the selection criteria means, for example, that the treatment data satisfies each of the conditions included in the selection criteria.

[0024] Furthermore, the extraction unit 12 may, for example, extract patients who meet the selection criteria between the first and second time points based on treatment data as clinical trial candidates. For example, the extraction unit 12 extracts patients who meet the selection criteria between the first and second time points based on treatment data from patients undergoing prior line treatment as clinical trial candidates. The extraction unit 12 may also extract patients who meet the selection criteria between the second time point and the end of the clinical trial period as clinical trial candidates. Furthermore, the extraction unit 12 may extract clinical trial candidates based on extraction conditions acquired by the acquisition unit 11. For example, by extracting clinical trial candidates based on extraction conditions set by the person in charge of selecting clinical trial patients, clinical trial candidates can be extracted under optimized conditions.

[0025] Selection criteria are, for example, the criteria for enrolling patients in a clinical trial. Selection criteria may also be criteria for excluding patients from a clinical trial. Selection criteria may include both enrollment and exclusion criteria. Enrollment criteria are, for example, information indicating the conditions for patients who are eligible to participate in a clinical trial. Enrollment criteria are also called eligibility criteria. The conditions for patients who are eligible to participate in a clinical trial are indicated using data on treatments that make them suitable for clinical trial participation. Exclusion criteria are, on the other hand, information indicating the conditions for excluding patients from participation in a clinical trial. That is, exclusion criteria are, for example, information indicating the conditions for patients who will not be selected as clinical trial participants. Exclusion criteria are indicated using data on treatments for patients who are not suitable to participate in a clinical trial.

[0026] The extraction unit 12 extracts patients who meet the selection criteria, for example, those whose treatment-related data satisfies each of the criteria included in the selection criteria. For example, the extraction unit 12 extracts patients whose treatment-related data falls within the range of the indicators specified for each of the items specified in the selection criteria. Furthermore, if a criterion to be used for extracting clinical trial candidates has been selected from the selection criteria, the extraction unit 12 may, for example, extract clinical trial candidates using the selected criterion from the selection criteria.

[0027] The extraction unit 12 may extract patients based on the degree of fit of the treatment data to the selection criteria. For example, the extraction unit 12 outputs patients whose degree of fit to the selection criteria is equal to or greater than a certain threshold value as patients who meet the selection criteria. The extraction unit 12 may calculate the degree of fit as, for example, the ratio of the number of criteria that the treatment data satisfies to the total number of criteria included in the selection criteria.

[0028] The extraction unit 12 may calculate the goodness of fit for each patient based on the weight of each item in the selection criteria. The extraction unit 12 may also calculate the goodness of fit for each patient based on the difference between the criteria included in the selection criteria and the data related to each patient's treatment, and the weight of each item in the selection criteria. The weight of each item in the selection criteria is set, for example, based on the magnitude of the influence that each item in the selection criteria may have on the results of the clinical trial. For example, if the effectiveness of the drug under investigation is greatly affected by the patient's history of taking other drugs, the weight of each item in the selection criteria may be set so that the weight of the patient's history of taking other drugs is greater than that of the other items.

[0029] The extraction unit 12 may use an extraction model to extract patients who meet the selection criteria. For example, the extraction unit 12 uses an extraction model to extract patients who meet the selection criteria based on data related to the patient's treatment and the selection criteria. The extraction model is, for example, a machine learning model that takes the selection criteria and data related to treatment as input and determines whether or not a patient meets the selection criteria. For example, the extraction unit 12 extracts patients whom the extraction model has determined to meet the selection criteria as clinical trial candidates. For example, the extraction model determines patients whose data related to treatment is similar to the selection criteria as patients who meet the selection criteria. The extraction model is generated, for example, by deep learning using a neural network. The extraction model is generated, for example, in an information processing device outside the clinical trial support device 10. The extraction model may also be generated, for example, in a learning means (not shown) within the clinical trial support device 10.

[0030] The extraction unit 12 may use a language model to extract data related to selection criteria from treatment data. For example, the extraction unit 12 extracts patients who meet the selection criteria based on the data extracted from treatment data using a language model. For example, a large-scale language model may be used as the language model. For example, GPT-2 (Generative Pre-trained Transformer-2), GPT-3, GPT-3.5, or GPT-4 can be used as the language model. Alternatively, Claude3, Claude3.5, T5 (Text-to-Text Transfer Transformer), BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach), or ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) may be used as the language model. The language model used in the process of extracting data related to selection criteria from treatment data is not limited to those listed above.

[0031] The extraction unit 12 may extract patients who meet the selection criteria in multiple stages. For example, the extraction unit 12 may extract patients who meet the selection criteria in two stages. For example, the extraction unit 12 may extract patients based on a first criterion, which is a criterion with high priority among the selection criteria. A criterion with high priority is, for example, a criterion that patients must meet for the purpose of the clinical trial. Then, from the patients extracted based on the first criterion, the extraction unit 12 extracts patients who meet the selection criteria based on a second criterion other than the first criterion. The second criterion is, for example, a criterion that allows patients who meet relaxed conditions to be eligible for the clinical trial. Alternatively, the second criterion may be a criterion that allows patients to be eligible for the clinical trial without determining whether or not they meet the criterion.

[0032] The extraction unit 12 may extract patients as clinical trial candidates who meet criteria that have been modified from the criteria included in the selection criteria for selecting clinical trial candidates. Modifying part of the selection criteria means, for example, relaxing the conditions for some of the criteria among the multiple criteria included in the selection criteria. Relaxing the conditions means, for example, broadening the range of patients indicated by the criterion. For example, if the criterion to be changed is age, relaxing the criterion means changing the condition from 45 to 55 years old to 45 to 60 years old. Modifying part of the selection criteria also means making some of the criteria among the multiple items included in the selection criteria stricter. Modifying part of the selection criteria may include changing one criterion in multiple stages. Making the criteria stricter means, for example, narrowing the range of patients indicated by the criterion. Modifying part of the selection criteria also means deleting some of the criteria among the multiple criteria included in the selection criteria.

[0033] The treatment data may be anonymized data. For example, the extraction unit 12 may extract patients who meet the selection criteria from the anonymized treatment data. Anonymized treatment data is, for example, data from which information that identifies each patient has been removed, but which can still be used to identify each patient by cross-referencing it with other information. Alternatively, the treatment data may be anonymized data. Anonymized treatment data is, for example, data from which information that identifies each patient has been removed, and which cannot be used to identify each patient by cross-referencing it with other information.

[0034] The estimation unit 13 uses a state curve, which is a curve showing the time-series changes in the state of patients suffering from the disease under investigation, to estimate the probability of a candidate being suitable for the clinical trial at a second time point, later than the first time point. The state curve showing the changes in the patient's state is time-series data on the changes in the state of patients who have suffered from the disease in the past and have received treatment for that disease. The state curve is, for example, a Kaplan-Meier curve for the disease under investigation. The estimation unit 13 selects a state curve based, for example, on the disease and the stage of treatment. The state curve to be applied may be specified by the person responsible for selecting the clinical trial candidates.

[0035] The estimation unit 13 estimates the probability that each patient is suitable for the clinical trial at a second time point, starting from the point in time when each patient meets the selection criteria for the clinical trial. The probability of being suitable for the clinical trial decreases with the passage of time since the point in time when the selection criteria were met. For example, when estimating using the same state curve, the probability of being suitable for the clinical trial at the second time point will differ among patients who met the selection criteria at different points in time. For example, the estimation unit 13 estimates the probability of being suitable for the clinical trial at a second time point for each patient, using the same state curve, starting from the point in time when each patient met the selection criteria for the clinical trial.

[0036] Figure 3 is a schematic graph illustrating an example of changes in the condition of each patient estimated using a condition curve. In the example graph in Figure 3, the vertical axis represents the probability of fitting, and the horizontal axis represents time. The example graph in Figure 3 estimates changes in the condition of three patients, Patient A, Patient B, and Patient C, using a condition curve. Patient A, Patient B, and Patient C may refer to individual patients, or to one or more patients with specific attributes.

[0037] For example, suppose at a first time point T1, patients A, B, and C are selected as clinical trial candidates. The first time point is, for example, when the clinical trial protocol is created. In this case, patient A is, for example, at a time point T1 prior to time point T1. ASuppose that the selection criteria are met. At this time, for example, when patient A refers to a patient with a specific attribute, patient A is a population of patients who meet the selection criteria at time point T. A Also, suppose that patient B meets the selection criteria at a time point T before time point T1, for example. Also, suppose that patient C meets the selection criteria at a time point T before time point T1, for example. B At this time, the estimation unit 13 applies a state curve starting from time point T for patient A, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2, which is the second time point. The second time point is, for example, the start time of the clinical trial. Also, the estimation unit 13 applies a state curve starting from time point T for patient B, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2. Also, the estimation unit 13 applies a state curve starting from time point T for patient C, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2. C In this way, the estimation unit 13 applies the same state curve starting from the time point when each patient meets the selection criteria of the clinical trial to estimate the probability of being suitable for a clinical trial patient at the start time of the clinical trial. Also, when patient A, patient B, and patient C are one or more patients with a specific attribute, the number of clinical trial candidates at the start time of the clinical trial can be predicted by calculating the number of the population × the probability of suitability. For example, the number of clinical trial candidates at the start time of the clinical trial in the population of patient A can be predicted by calculating, for example, (the number of people belonging to patient A) × the probability of suitability. A Figure 4 is a graph schematically showing an example of the change in the state of patients who met the selection criteria between the first time point and the second time point in the example of FIG. 3. In the example of the graph of FIG. 4, patient D meets the selection criteria at time point T between time point T1 and time point T2. B The estimation unit 13 applies a state curve starting from time point T for patient D as well, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2. C At this time, the estimation unit 13 applies a state curve starting from time point T for patient A, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2, which is the second time point. The second time point is, for example, the start time of the clinical trial. Also, the estimation unit 13 applies a state curve starting from time point T for patient B, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2. Also, the estimation unit 13 applies a state curve starting from time point T for patient C, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2.

[0038] Figure 4 is a graph schematically showing an example of the change in the state of patients who met the selection criteria between the first time point and the second time point in the example of FIG. 3. In the example of the graph of FIG. 4, patient D meets the selection criteria at time point T between time point T1 and time point T2. D The estimation unit 13 applies a state curve starting from time point T for patient D as well, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2. D At this time, the estimation unit 13 applies a state curve starting from time point T for patient A, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2, which is the second time point. The second time point is, for example, the start time of the clinical trial. Also, the estimation unit 13 applies a state curve starting from time point T for patient B, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2. Also, the estimation unit 13 applies a state curve starting from time point T for patient C, for example, to estimate the probability of being suitable for a clinical trial patient at time point T2.

[0039] The prediction unit 14 predicts the number of clinical trial candidates at a second time point based on the probability of fit. For example, the prediction unit 14 predicts the number of patients whose probability of fit is equal to or greater than a certain threshold at a predetermined time point as the number of clinical trial candidates at that time point. The threshold value for the probability of fit is set, for example, to be a value that can be expected to be a clinical trial candidate at a predetermined time point if the probability of fit is equal to or greater than that threshold value.

[0040] The prediction unit 14 may calculate the sum of the patient fit probabilities at a second time point and predict the calculated sum as the number of clinical trial candidates at the second time point. Alternatively, the prediction unit 14 may weight the patient fit probabilities at a predetermined time point, calculate the sum, and predict the calculated sum as the number of clinical trial candidates at the second time point.

[0041] The prediction unit 14 may predict the number of clinical trial candidates at the second time point for each hospital where the clinical trial is being conducted. The prediction unit 14 predicts the number of clinical trial candidates at the second time point for each hospital where the clinical trial is being conducted, for example, by predicting the number of clinical trial candidates at the second time point for each hospital.

[0042] The prediction unit 14 predicts, for example, combinations of hospitals in which the total number of clinical trial candidates is sufficient to meet the number required to conduct the clinical trial. The prediction unit 14 predicts combinations of hospitals in which the number of clinical trial candidates required to conduct the clinical trial can be secured by, for example, weighting each hospital based on predetermined criteria.

[0043] The prescribed criteria are set based on one or more of the following items: the presence or absence of a principal investigator, the number of physicians, the size of the hospital, the clinical trial track record, and the type of hospital establishment. For example, if the prescribed criteria are based on the presence or absence of a principal investigator, the criteria are set so that hospitals with a principal investigator on staff are given greater weight. Also, for example, if the prescribed criteria are based on the size of the hospital, the criteria are set so that larger hospitals are given greater weight. The size of the hospital is, for example, at least one of the number of physicians in the department that oversees the disease being investigated and the number of inpatient beds. The size of the hospital is not limited to the above. Also, for example, if the prescribed criteria are based on the clinical trial track record, the criteria are set so that hospitals with a large track record in clinical trials are given greater weight. Also, for example, if the prescribed criteria are based on the type of establishment, the criteria are set so that hospitals with a high level of specialization in advanced medical care, such as university hospitals, are given greater weight. The way in which the prescribed criteria are set is not limited to the above.

[0044] The prediction unit 14 may also predict the number of patients who will meet the selection criteria from the second time point onward as the number of additional patients. For example, the prediction unit 14 predicts the number of patients who will meet the selection criteria from the start of the clinical trial onward as the number of additional patients. If the number of additional patients is predicted, the prediction unit 14 predicts the number of clinical trial candidates from the second time point onward based on, for example, the number of patients who are clinical trial candidates at the second time point and the number of additional patients.

[0045] The prediction unit 14 may also predict the number of clinical trial candidates referred from hospitals other than those targeted for prediction as the number of referred patients. When predicting the number of referred patients, the prediction unit 14 predicts the number of clinical trial candidates at the second time point, for example, based on the number of patients who are clinical trial candidates at the first time point and are clinical trial candidates at the second time point, the number of additional patients, and the number of referred patients.

[0046] The prediction unit 14 may predict the number of clinical trial candidates at a second time point based on information about competing companies conducting clinical trials. For example, if a competing company plans to conduct a clinical trial of a similar drug, the prediction unit 14 predicts the number of clinical trial candidates at a second time point by multiplying the number of clinical trial candidates predicted based on the probability of fit by a predetermined coefficient. The predetermined coefficient is set, for example, based on the prediction results and the number of clinical trial patients actually obtained in past clinical trials when a competing company was present. The prediction unit 14 may also predict the number of clinical trial candidates at a second time point by subtracting a predetermined number from the number of clinical trial candidates predicted based on the probability of fit. The predetermined number is set, for example, based on the difference between the prediction results and the number of clinical trial patients actually obtained in past clinical trials when a competing company was present. The predetermined coefficient and predetermined number may be set based on at least one of the following: the size of the competing company, the clinical trial record of the hospitals where the competing company conducts clinical trials, and the nationality of the competing company. The predetermined coefficient and predetermined number may be set as appropriate.

[0047] The output unit 15 outputs information regarding the number of clinical trial candidates at a second point in time. For example, the output unit 15 outputs information regarding the number of clinical trial candidates at the start of the clinical trial. The output unit 15 may also output the number of clinical trial candidates for each hospital. The output unit 15 may also output combinations of hospitals where the number of clinical trial candidates satisfies the number of patients required for the clinical trial.

[0048] The output unit 15 may output the expected increase in the number of clinical trial candidates at a second point in time. For example, the output unit 15 may output the expected increase in the number of clinical trial candidates after the start of the clinical trial for each hospital. The output unit 15 may output the expected increase in the number of clinical trial candidates from the start of the clinical trial to the end of the clinical trial for each hospital. For example, the output unit 15 may output the number of patients who have completed treatment in the previous line and are eligible for the clinical trial after the start of the clinical trial as the expected increase in the number of clinical trial candidates. The output unit 15 may also output information indicating when clinical trial candidates who meet the selection criteria after the second point in time will meet the selection criteria. The output unit 15 may also output the expected increase in the number of clinical trial candidates due to referrals from other hospitals.

[0049] The output unit 15 may output the change in the number of clinical trial candidates for each changed condition when the conditions included in the selection criteria are changed. For example, the output unit 15 may output the increase in the number of clinical trial candidates for each relaxed condition when the conditions included in the selection criteria are relaxed.

[0050] The output unit 15 may output a display screen for inputting setting values ​​related to the prediction process of the number of clinical trial candidates. For example, the output unit 15 may output a display screen for inputting extraction conditions for clinical trial candidates as a display screen for inputting setting values ​​related to the prediction process of the number of clinical trial candidates. The output unit 15 may output a display screen that includes input for inputting information on one or more items from among the clinical trial period, medical department, disease name, target region, selection criteria, and criteria values ​​for goodness of fit. The output unit 15 may output a display screen for inputting setting values ​​related to the prediction process of the number of clinical trial candidates to the terminal device 20.

[0051] The output unit 15 may output a display screen that overlays the number of clinical trial candidates onto a map based on the predicted number of clinical trial candidates. The output unit 15 may also display a screen for making inquiries about clinical trial candidates to the hospitals where the clinical trial candidates are receiving treatment. The output unit 15 may output a display screen that shows a list of clinical trial candidates receiving treatment at each hospital. The output unit 15 may also output a display screen that shows a list of clinical trial candidates receiving treatment at the selected hospital when a hospital is selected on the display screen showing the number of clinical trial candidates at each hospital. The output unit 15 may output a display screen that shows at least one of the clinical trial candidate's status and treatment data when a clinical trial candidate is selected from the list of clinical trial candidates. The output unit 15 may also output a display screen that shows the clinical trial candidate's treatment history when a clinical trial candidate is selected from the list of clinical trial candidates. The output unit 15 may also output a display screen that shows the extraction conditions used to extract the selected clinical trial candidate. Furthermore, the output unit 15 may output a display screen that shows information indicating the criteria used to extract the selected clinical trial candidates from among the selection criteria.

[0052] Figure 5 shows an example of a display screen showing the predicted number of clinical trial candidates. In the example screen in Figure 5, the predicted number of clinical trial candidates is displayed in a list format for each hospital. In the example screen in Figure 5, hospitals are displayed in order of the number of clinical trial candidates. For example, when conducting a clinical trial, if you can identify hospitals that can secure as many candidate patients as possible, you can reduce the number of hospitals you need to contact. Therefore, by displaying hospitals in order of the number of clinical trial candidates, you can improve the efficiency of tasks related to conducting clinical trials. Furthermore, the criteria for the order in which the number of clinical trial candidates for each hospital is displayed can be set as appropriate.

[0053] In the example display screen in Figure 5, "Hospital Name," "Location," and "Number of Suitable Patients" are displayed in association with each other. "Hospital Name" is, for example, the name of the hospital. "Location" is, for example, the location where the hospital is located. In the example display screen in Figure 5, "Location" is displayed on a prefecture-by-prefecture basis. The display of "Location" is not limited to prefectures. "Number of Suitable Patients" is, for example, the number of clinical trial candidates. In addition, "Location" may be displayed in order of hospitals closest to the location information of the terminal device 20. In addition, "Location" may be displayed by grouping hospitals that are located close to each other. For example, if hospitals A, C, and D are located close to each other, and hospitals B, E, and F are located close to each other, the list may be displayed from top to bottom as follows: hospital A, hospital C, and hospital D group, hospital B, hospital E, and hospital F. For example, a company conducting a clinical trial may dispatch personnel to hospitals to carry out tasks related to the implementation of the clinical trial. Therefore, by knowing which hospitals are located close to each other, it is possible to improve the efficiency of tasks related to the implementation of the clinical trial.

[0054] Figure 6 is an example of a display screen showing the predicted number of clinical trial candidates, including those that will increase after the start of the clinical trial. In the example display screen in Figure 6, the predicted number of clinical trial candidates at the start of the clinical trial and the predicted number of candidates after the start of the clinical trial are displayed in the form of a list of the number of people for each hospital. In the example display screen in Figure 6, hospitals are displayed in order from the number of clinical trial candidates to the number of people with the most candidates. In the example display screen in Figure 6, "Hospital Name," "Location," "Number of Suitable Patients," and "Expected Increase After the Start of the Clinical Trial" are associated with each hospital. "Expected Increase After the Start of the Clinical Trial" is, for example, the number of patients who will meet the selection criteria after the start of the clinical trial.

[0055] Figure 7 shows an example of a display screen showing the predicted number of clinical trial candidates when the selection criteria are relaxed. In the example display screen in Figure 7, the predicted number of clinical trial candidates who meet the selection criteria and the predicted number of candidates who would become clinical trial candidates if the selection criteria are relaxed are displayed in the form of a list of numbers for each hospital. In the example display screen in Figure 7, hospitals are displayed in order from the number of clinical trial candidates to the number of candidates. In the example display screen in Figure 7, "Hospital Name," "Location," "Number of Suitable Patients," and "Increase in Number of Patients When Conditions are Relaxed" are associated with each hospital. "Increase in Number of Patients When Conditions are Relaxed" is, for example, the number of patients who would newly meet the selection criteria if some of the criteria included in the selection criteria were relaxed.

[0056] Figure 8 shows an example of a display screen for setting the extraction criteria for selecting clinical trial candidates. In the example display screen of Figure 8, the setting items are displayed as "Trial Period," "Department," "Target Disease Name," "Trial Region," "Selection Criteria," and "Fitness." In the example display screen of Figure 8, "Trial Period" is, for example, the field for setting the duration of the clinical trial. In the example display screen of Figure 8, the setting field for "Trial Period" displays a "Start" field for entering the first day of the period and a "End" field for entering the last day of the period. In the example display screen of Figure 8, "Department" is, for example, the field for selecting the department that is responsible for the disease in which the drug under investigation will be administered. Multiple departments may be selected. In the example display screen of Figure 8, "Target Disease Name" is, for example, the field for entering the disease in which the drug under investigation will be administered.

[0057] In the example screen shown in Figure 8, "Clinical Trial Region" is, for example, a field for selecting the region to be included in the clinical trial. In the example screen shown in Figure 8, a button for selecting the region in which the clinical trial will be conducted is displayed in the "Clinical Trial Region" field. In the example screen shown in Figure 8, "Clinical Trial Region" can be selected, for example, at the regional level. "Clinical Trial Region" may also be selected, for example, at the prefectural level.

[0058] In the example screen shown in Figure 8, "Selection Criteria" is a field where you select the criteria used to extract clinical trial candidates from among the selection criteria. In the example screen shown in Figure 8, black squares indicate selected criteria. In the example screen shown in Figure 8, white squares indicate criteria that have not been selected. In the example screen shown in Figure 8, "Fit" is used as a criterion for extracting a clinical trial candidate, for example, when the degree of suitability for the treatment relative to the selection criteria exceeds a set value. In the example screen shown in Figure 8, "Fit" is set by moving a slider. "Fit" may also be set by entering a numerical value. In addition, in the example screen shown in Figure 8, an "Extract" button is displayed at the bottom. The "Extract" button is a button that instructs the execution of the clinical trial candidate extraction process using the extraction conditions.

[0059] The output unit 15 outputs a display screen of the extraction conditions, as shown in Figure 8, to the terminal device 20, for example. The acquisition unit 11 then acquires the extraction conditions from the terminal device 20, for example, which are entered by the operator on the display screen displayed by the terminal device 20. The operator is, for example, a person who creates a clinical trial protocol using the predicted number of clinical trial candidates. The operator is not limited to the above. When the operator presses the "Extract" button on the display screen, the acquisition unit 11 acquires information indicating that the "Extract" button has been pressed. When information indicating that the "Extract" button has been pressed is acquired, the extraction unit 12 extracts clinical trial candidates using the extraction conditions set at the time the button was pressed, for example.

[0060] Figure 9 shows an example of a display screen showing the predicted number of clinical trial candidates. In the example display screen of Figure 9, "Extraction Criteria," "Clinical Trial Region," and "Hospital List" are displayed. In the example display screen of Figure 9, "Extraction Criteria" is the field that displays the conditions used to extract clinical trial candidates. In the example display screen of Figure 9, "Extraction Criteria" is, for example, the conditions entered in a display screen like Figure 8. In the example display screen of Figure 9, "Clinical Trial Region" is, for example, the region where the target hospitals from which clinical trial candidates were extracted are located. In addition, in the example display screen of Figure 9, the number of clinical trial candidates is superimposed on the map in the "Clinical Trial Region" section. In addition, in the example display screen of Figure 9, the "Hospital List" shows the predicted number of clinical trial candidates for each hospital. In the example display screen of Figure 9, "Hospital Name," "Location," and "Number of Suitable Patients" are displayed together. "Hospital Name" is, for example, the name of the hospital. "Location" is, for example, the place where the hospital is located. In the example display screen of Figure 9, "Location" is displayed on a prefecture basis. The "Location" display is not limited to prefectures. "Number of Suitable Patients" is, for example, the number of clinical trial candidates. In the example display screen in Figure 9, an "Inquiry" button is displayed for each hospital. When the "Inquiry" button is pressed in the example display screen in Figure 9, the output unit 15 outputs, for example, a screen for contacting the selected hospital.

[0061] In the example display screen shown in Figure 9, a "Secure Patient" button may also be displayed. The output unit 15 outputs a display screen to the terminal device 20, for example, that shows the display screen as shown in Figure 9, with the "Secure Patient" button also displayed. The acquisition unit 11 then acquires information from the terminal device 20, for example, indicating that the "Secure Patient" button was pressed by the person in charge on the display screen shown by the terminal device 20. Once information indicating that the "Secure Patient" button has been pressed is acquired, the output unit 15 outputs a message to the hospitals listed in the list, for example, requesting them to secure clinical trial candidates. The message requesting the securing of clinical trial candidates may be selectable for each hospital.

[0062] Figure 10 is an example of a display screen that shows a list of clinical trial candidates at a selected hospital when a hospital is selected in the example display screen of Figure 9. In the example display screen of Figure 10, "Extraction Conditions," "Clinical Trial Region," and "Hospital List" are displayed. In the example display screen of Figure 10, the "Hospital List" shows a list of clinical trial candidates at "A University Hospital." For example, when any hospital is selected in the "Hospital List" of the example display screen of Figure 9 displayed on the display device of the terminal device 20, the acquisition unit 11 acquires the hospital selection result from the terminal device 20. Then, the output unit 15 outputs a list of clinical trial candidates at the selected hospital based on the selection result.

[0063] Figure 11 is an example of a display screen that shows at least a portion of the treatment data for a selected clinical trial candidate when a clinical trial candidate is selected from the list of clinical trial candidates, as shown in the example of the display screen in Figure 10. For example, when any clinical trial candidate is selected in the list of clinical trial candidates in the example of the display screen in Figure 10, the output unit 15 outputs at least a portion of the treatment data for the selected clinical trial candidate. In the example of the display screen in Figure 11, the treatment data for patient P1, selected in the example of the display screen in Figure 10, is displayed in a pop-up format. For example, when the cursor is moved to the location of any hospital in the list of clinical trial candidates shown on the display device of the terminal device 20 and a clinical trial candidate is selected, the acquisition unit 11 acquires the selection result of the clinical trial candidate from the terminal device 20. Then, the output unit 15 outputs to the terminal device 20, for example, a display screen that shows the treatment data for the selected clinical trial candidate in a pop-up format based on the selection result.

[0064] Figure 12 is an example of a display screen that shows detailed information of a clinical trial candidate selected from the list of clinical trial candidates, as shown in the example of the display screen in Figure 10. In the example of the display screen in Figure 12, the "Patient Name," "Treatment History," and "Suitability to Selection Criteria" of the selected clinical trial candidate are displayed. In the example of the display screen in Figure 10, "Patient Name" is the patient's name or identifier. In the example of the display screen in Figure 10, "Treatment History" is information showing the progress of treatment given to the patient. In the example of the display screen in Figure 10, "Suitability to Selection Criteria" is information showing whether the treatment data is suitable for each of the criteria included in the selection criteria. In the example of the display screen in Figure 10, "○" indicates that the treatment data meets the criteria. In the example of the display screen in Figure 10, "×" indicates that the treatment data does not meet the criteria. In the example of the display screen in Figure 10, white squares indicate criteria that have not been selected as criteria used to extract clinical trial candidates. For example, if any clinical trial candidate is selected in the patient list shown in the example display screen of Figure 10 on the display device of the terminal device 20, the acquisition unit 11 acquires the selection result of the clinical trial candidate from the terminal device 20. Then, the output unit 15 outputs a display screen to the terminal device 20, for example, that displays detailed information of the selected clinical trial candidate based on the selection result.

[0065] The memory unit 16 stores, for example, data related to the prediction of the number of clinical trial candidates. The memory unit 16 stores, for example, data related to patient treatment. The memory unit 16 stores, for example, selection criteria. The memory unit 16 stores, for example, the extraction conditions for clinical trial candidates. The memory unit 16 stores, for example, the identification information of extracted clinical trial candidates in association with data related to the treatment of the clinical trial candidates. The memory unit 16 stores, for example, the estimated results of the fit probability of clinical trial candidates at a second time point. The memory unit 16 stores the prediction results of the number of clinical trial candidates at a second time point. The memory unit 16 also stores, for example, the extraction model. The extraction model may be stored in a storage means other than the memory unit 16.

[0066] The terminal device 20 may be, for example, an information processing device used to access the clinical trial support device 10 and extract clinical trial candidates. The terminal device 20 is, for example, a terminal device used by a person in charge at a medical institution or a person in charge at an institution that has been contracted by a medical institution to handle clinical trial matters. An institution that a hospital has contracted to handle clinical trials may be, for example, an SMO (Site Management Organization). A person in charge at an institution that has been contracted by a medical institution to handle clinical trial matters may be, for example, a CRC (Clinical Research Coordinator). The terminal device 20 may also be a terminal device used by a person in charge of conducting clinical trials at a pharmaceutical company or a person in charge at an institution that has been contracted by a pharmaceutical company to conduct clinical trials of a drug. An institution that has been contracted by a pharmaceutical company to conduct clinical trials may be, for example, a CRO (Contract Research Organization). A person in charge at an institution that has been contracted by a pharmaceutical company to conduct clinical trials may be, for example, a CRA (Clinical Research Associate).

[0067] The terminal device 20 may be an information processing device used by healthcare professionals to keep track of the number of clinical trial candidates. Healthcare professionals include, for example, doctors, nurses, pharmacists, clinical laboratory technicians, physical therapists, counselors, hospital administrative staff, or hospital counselors. Healthcare professionals are not limited to those listed above.

[0068] The terminal device 20 obtains information regarding the number of clinical trial candidates from, for example, the output unit 15 of the clinical trial support device 10. The terminal device 20 then outputs information regarding the number of clinical trial candidates to, for example, a display device (not shown). For example, the terminal device 20 obtains a display screen showing the number of clinical trial candidates for each hospital from the output unit 15 of the clinical trial support device 10 as information regarding the number of clinical trial candidates. The terminal device 20 then outputs a display screen showing the number of clinical trial candidates for each hospital to, for example, a display device (not shown).

[0069] When a hospital is selected on the display screen showing the number of clinical trial candidates for each hospital, the terminal device 20 outputs information indicating the selected hospital to, for example, the acquisition unit 11 of the clinical trial support device 10. The terminal device 20 also obtains, for example, a display screen showing a list of clinical trial candidates for the hospital corresponding to the selection result from the output unit 15 of the clinical trial support device 10. The terminal device 20 then outputs the display screen showing the list of clinical trial candidates to, for example, a display device (not shown).

[0070] When a clinical trial candidate is selected on the display screen showing a list of clinical trial candidates, the terminal device 20 outputs information indicating the clinical trial candidate to, for example, the acquisition unit 11 of the clinical trial support device 10. The terminal device 20 also obtains, for example, a display screen from the output unit 15 of the clinical trial support device 10 that displays detailed information about the clinical trial candidate corresponding to the selection result. The terminal device 20 then outputs the display screen showing the detailed information of the clinical trial candidate to, for example, a display device (not shown).

[0071] The terminal device 20 acquires, for example, a display screen for setting the clinical trial candidate extraction criteria from the output unit 15 of the clinical trial support device 10. The terminal device 20 then outputs the display screen for setting the clinical trial candidate extraction criteria to, for example, a display device (not shown). The terminal device 20 also outputs the clinical trial candidate extraction criteria, which are entered by the operator on the display screen for setting the clinical trial candidate extraction criteria, to the acquisition unit 11 of the clinical trial support device 10.

[0072] The terminal device 20 can be, for example, a personal computer, a tablet computer, a smartphone, or a smartwatch. The information processing device used in the terminal device 20 is not limited to those mentioned above.

[0073] The data management device 30 stores, for example, data related to the patient's treatment. The data management device 30 stores, for example, electronic medical record data as data related to the patient's treatment. The data related to the patient's treatment may also be examination data. If the data related to the patient's treatment is examination data, the data related to the patient's treatment may also be image data for diagnostic imaging. Alternatively, the data related to the patient's treatment may also be data recorded on the medical claim form. The data related to treatment may also be, for example, the patient's perception of their medical condition. The data management device 30 outputs the data related to treatment to, for example, the acquisition unit 11 of the clinical trial support device 10.

[0074] The data management device 30 stores, for example, data on patient treatment at each hospital accepting the clinical trial. The data management device 30 may be installed at each hospital and store patient treatment data at the hospital where it is installed. Alternatively, the data management device 30 may be installed for each group of hospitals and store patient treatment data at the hospitals belonging to the group. How the data management device 30 stores treatment data can be configured as appropriate.

[0075] The data management device 30 may, for example, store treatment-related data as anonymized or pseudonymized information. Anonymized information is, for example, information that has been processed so that an individual cannot be identified even when cross-referenced with other information. Pseudonymized information is, for example, information that cannot identify an individual on its own, but can identify an individual when cross-referenced with other information. The data management device 30 may also perform anonymization or pseudonymization when outputting treatment-related data to the acquisition unit 11 of the clinical trial support device 10 before outputting the treatment-related data.

[0076] The process by which the clinical trial support device 10 predicts the number of clinical trial candidates at the second time point will be described. Figure 13 shows an example of the operation flow in the process by which the clinical trial support device 10 predicts the number of clinical trial candidates at the second time point.

[0077] The acquisition unit 11 acquires data related to the patient's treatment (step S11). The acquisition unit 11 acquires data related to the patient's treatment from, for example, the data management device 30.

[0078] Once data regarding the patient's treatment is obtained, the extraction unit 12 extracts patients who meet the selection criteria for clinical trial patients at the first point in time, based on the treatment data, as clinical trial candidates (step S12).

[0079] Once clinical trial candidates are selected, the estimation unit 13 uses a state curve to estimate the probability of suitability, which is the probability that a clinical trial candidate is suitable for the trial at a second time point later than the first time point (step S13). The state curve is a curve that shows the time-series changes in the state of a patient suffering from the disease being investigated.

[0080] Once the probability of matching is estimated, the prediction unit 14 predicts the number of clinical trial candidates at the second time point based on the probability of matching (step S14).

[0081] Once the number of clinical trial candidates at the second time point is predicted, the output unit 15 outputs information regarding the number of clinical trial candidates at the second time point (step S15). The output unit 15 outputs information regarding the number of clinical trial candidates at the second time point to, for example, the terminal device 20.

[0082] Each process in the clinical trial support device 10 may be distributed and executed across multiple information processing devices connected via a network. For example, the processing in the extraction unit 12 and the processing in the estimation unit 13 and prediction unit 14 may be performed on separate information processing devices. The information processing devices on which each process in the clinical trial support device 10 is performed can be set as appropriate.

[0083] The clinical trial support device 10 extracts patients who meet the selection criteria for clinical trial patients at a first time point, based on treatment data, as clinical trial candidates. The clinical trial support device 10 uses a state curve, which is a curve showing the time-series changes in the state of patients suffering from the disease under investigation, to estimate the probability of suitability, which is the probability that a clinical trial candidate is suitable for the clinical trial at a second time point, after the first time point. The clinical trial support device 10 then outputs information regarding the number of clinical trial candidates at the second time point. By predicting the number of clinical trial candidates in this way, the clinical trial support device 10 can improve the accuracy of its prediction of the number of clinical trial candidates.

[0084] For example, if the first time point is defined as the creation of the clinical trial protocol and the second time point as the start of the clinical trial, the clinical trial support device 10 can accurately predict the number of clinical trial candidates at the start of the clinical trial based on the treatment data at the time of creating the clinical trial protocol. Furthermore, by predicting the number of clinical trial candidates at each hospital, for example, the person in charge of selecting clinical trial patients can accurately determine which hospitals to negotiate with in order to secure clinical trial patients. Therefore, the clinical trial support device 10 can, for example, support decision-making in the selection of clinical trial patients.

[0085] Furthermore, by predicting the number of clinical trial candidates at the second time point, including patients who meet the criteria for clinical trial candidates between the first and second time points, the clinical trial support device 10 can, for example, facilitate the securing of clinical trial patients. Additionally, by further predicting the number of patients who meet the criteria for clinical trial candidates after the second time point, the clinical trial support device 10 can, for example, make it even easier to secure clinical trial patients. Furthermore, by predicting the increase or decrease in the number of clinical trial candidates when the selection criteria are changed, the clinical trial support device 10 can, for example, increase the likelihood of securing clinical trial patients even when there are not enough clinical trial candidates who meet the selection criteria.

[0086] Each process in the clinical trial support device 10 can be realized by executing a computer program on a computer. Figure 14 shows an example of the configuration of a computer 100 that executes the computer programs that perform each process in the clinical trial support device 10. The computer 100 includes a CPU (Central Processing Unit) 101, memory 102, storage device 103, input / output interface 104, and communication interface 105.

[0087] The CPU 101 reads and executes computer programs that perform various processing tasks from the storage device 103. The CPU 101 may be composed of a combination of multiple CPUs. Alternatively, the CPU 101 may be composed of a combination of a CPU and another type of processor. For example, the CPU 101 may be composed of a combination of a CPU and a GPU (Graphics Processing Unit). The memory 102 is composed of DRAM (Dynamic Random Access Memory) or the like, and temporarily stores computer programs executed by the CPU 101 and data being processed. The storage device 103 stores computer programs executed by the CPU 101. The storage device 103 is composed of, for example, a non-volatile semiconductor storage device. Other storage devices such as hard disk drives may be used for the storage device 103. The input / output interface 104 is an interface that receives input from the operator and outputs display screens, etc. The communication interface 105 is an interface that sends and receives data between the terminal device 20, the data management device 30, and other information processing devices. The terminal device 20 and the data management device 30 can also be configured similarly to the computer 100.

[0088] The computer programs used to execute each process can also be stored and distributed on a computer-readable recording medium that non-temporarily stores data. Examples of recording media include magnetic tapes for data recording and magnetic disks such as hard disks. Optical discs such as CD-ROMs (Compact Disc Read Only Memory) can also be used as recording media. Non-volatile semiconductor memory devices may also be used as recording media.

[0089] Some or all of the above embodiments may also be described as follows, but are not limited to the following:

[0090] [Note 1] A means of acquiring data related to patient treatment, Based on the data relating to the aforementioned treatment, an extraction means for selecting patients who meet the selection criteria for clinical trial patients at a first point in time as clinical trial candidates, An estimation means for estimating the probability of a candidate being suitable for the clinical trial at a second time point later than the first time point, using a state curve, which is a curve showing the time-series changes in the state of a patient suffering from the disease under investigation; A prediction means for predicting the number of clinical trial candidates at the second time point based on the aforementioned probability of suitability, Output means for outputting information regarding the number of clinical trial candidates at the second time point in time, A clinical trial support device equipped with the following features.

[0091] [Note 2] The prediction means predicts the number of clinical trial candidates at the second time point for each hospital where the clinical trial is to be conducted. The clinical trial support device described in Appendix 1.

[0092] [Note 3] The prediction means predicts combinations of hospitals where the total number of clinical trial candidates is sufficient to meet the number required to conduct the clinical trial. The clinical trial support device described in Appendix 2.

[0093] [Note 4] The prediction means assigns weights to each hospital based on predetermined criteria to predict combinations of hospitals that can secure the number of clinical trial candidates necessary for conducting the clinical trial. Clinical trial support device as described in Appendix 3.

[0094] [Note 5] The prediction means predicts the number of patients who will meet the selection criteria from the second time point onward as the number of additional patients, and predicts the number of clinical trial candidates from the second time point onward based on the number of patients who are clinical trial candidates at the second time point and the number of additional patients. A clinical trial support device as described in any of the appendices 1 to 4.

[0095] [Note 6] The extraction means extracts patients who meet the criteria obtained by relaxing the conditions included in the selection criteria as clinical trial candidates. A clinical trial support device as described in any of the appendices 1 to 5.

[0096] [Note 7] The prediction means predicts the number of clinical trial candidates referred from hospitals other than the target hospital for which the number of clinical trial candidates is predicted, and predicts the number of clinical trial candidates from the second time point onward based on the number of patients who are clinical trial candidates at the second time point out of the first time point, the number of additional patients, and the number of referred patients. Clinical trial support device as described in Appendix 5.

[0097] [Note 8] The prediction means predicts the number of clinical trial candidates at the second time point based on information about competing companies in conducting the clinical trial. A clinical trial support device as described in any of the appendices 1 through 7.

[0098] [Note 9] The output means outputs information indicating the time when a clinical trial candidate who will meet the selection criteria from the second time point onward will meet the selection criteria. Clinical trial support device as described in Appendix 5.

[0099] [Note 10] The output means outputs the amount of increase in the number of clinical trial candidates for each relaxed condition when the conditions included in the selection criteria are relaxed. Clinical trial support device as described in Appendix 6.

[0100] [Note 11] The aforementioned state curve is a Kaplan-Meier curve for the disease being investigated. A clinical trial support device as described in any of the appendices 1 through 10.

[0101] [Note 12] The aforementioned selection criteria include criteria for inclusion in the clinical trial and criteria for exclusion from the clinical trial. A clinical trial support device as described in any of the appendices 1 through 11.

[0102] [Note 13] The extraction means, for example, uses a machine learning model that takes the selection criteria and treatment-related data as input to determine whether or not the candidate meets the selection criteria, and extracts candidates as clinical trial candidates. A clinical trial support device as described in any of the appendices 1 through 12.

[0103] [Note 14] The output means outputs a display screen to the terminal device showing the selection criteria to be used for extracting the clinical trial candidates from among the selection criteria. The acquisition means acquires the criteria selected on the display screen displayed by the terminal device from the terminal device, The extraction means extracts patients who meet the selected criteria as clinical trial candidates. A clinical trial support device as described in any of the appendices 1 through 13.

[0104] [Note 15] The output means outputs a display screen to the terminal device that sets a standard value for the degree of suitability indicating the extent to which the treatment data satisfies the selection criteria. The acquisition means acquires a reference value set on the display screen displayed on the terminal device from the terminal device. The extraction means extracts patients whose fitness level is equal to or above the set standard value as clinical trial candidates. A clinical trial support device as described in any of the appendices 1 through 14.

[0105] [Note 16] The output means outputs a display screen to the terminal device showing the number of clinical trial candidates for each hospital. The acquisition means acquires the hospital selected on the display screen shown on the terminal device from the terminal device, The output means outputs to the terminal device a list of the clinical trial candidates at the selected hospital. A clinical trial support device as described in any of the appendices 1 through 15.

[0106] [Note 17] The acquisition means acquires from the terminal device the clinical trial candidate selected on the display screen of the list of clinical trial candidates displayed on the terminal device, The output means outputs at least a portion of the data relating to the treatment of the selected clinical trial candidate to the terminal device. Clinical trial support device as described in Appendix 16.

[0107] [Note 18] The output means outputs to the terminal device information indicating whether the data relating to the treatment of the selected clinical trial candidate satisfies each of the selection criteria. The clinical trial support device described in Appendix 17.

[0108] [Note 19] We obtain data on patient treatment, Based on the data regarding the aforementioned treatment, patients who meet the selection criteria for clinical trial patients at the first time point are selected as clinical trial candidates. Using a state curve, which is a curve showing the time-series changes in the state of a patient suffering from the disease under investigation, the probability of suitability, which is the probability that the clinical trial candidate is suitable for the clinical trial at a second time point later than the first time point, is estimated. Based on the aforementioned probability of suitability, the number of clinical trial candidates at the second time point is predicted. The system outputs information regarding the number of clinical trial candidates at the second point in time. Methods for supporting clinical trials.

[0109] [Note 20] The process of acquiring data related to patient treatment, Based on the data relating to the aforementioned treatment, a process is performed to extract patients who meet the selection criteria for clinical trial patients at a first point in time as clinical trial candidates, A process for estimating the probability of suitability, which is the probability that the clinical trial candidate is suitable for the clinical trial at a second time point later than the first time point, using a state curve, which is a curve showing the time-series change in the state of a patient suffering from the disease under investigation; A process to predict the number of clinical trial candidates at the second time point based on the aforementioned probability of suitability, A process to output information regarding the number of clinical trial candidates at the second time point. A clinical trial support program that has a computer execute commands.

[0110] Furthermore, some or all of the configurations described in Appendices 2 to 18, which are dependent on Appendice 1 above, may also be dependent on Appendices 19 and 20 in the same way as Appendices 2 to 18. Moreover, not limited to Appendices 1, 19, and 20, some or all of the configurations described as appendices may also be dependent on various hardware, software, various recording means for recording software, or systems, without departing from the embodiments described above.

[0111] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure can be made as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate. [Explanation of symbols]

[0112] 10 Clinical trial support devices 11 Acquisition Department 12 Extraction part 13 Estimation part 14 Prediction Section 15 Output section 16 Memory section 20 Terminal devices 30 Data Management Devices 100 Computers 101 CPU 102 memory 103 Storage device 104 Input / Output Interfaces 105 Communication I / F

Claims

1. A means of acquiring data related to patient treatment, Based on the data relating to the aforementioned treatment, an extraction means for selecting patients who meet the selection criteria for clinical trial patients at a first point in time as clinical trial candidates, An estimation means for estimating the probability of suitability, which is the probability that the clinical trial candidate is suitable for the clinical trial at a second time point later than the first time point, using a state curve, which is a curve showing the time-series change in the state of a patient suffering from the disease under investigation; A prediction means for predicting the number of clinical trial candidates at the second time point based on the aforementioned suitability probability, Output means for outputting information regarding the number of clinical trial candidates at the second time point in time, A clinical trial support device equipped with the following features.

2. The prediction means predicts the number of clinical trial candidates at the second time point for each hospital where the clinical trial is to be conducted. The clinical trial support device according to claim 1.

3. The prediction means predicts combinations of hospitals where the total number of clinical trial candidates is sufficient to meet the number required to conduct the clinical trial. The clinical trial support device according to claim 2.

4. The prediction means assigns weights to each hospital based on predetermined criteria to predict combinations of hospitals that can secure the number of clinical trial candidates necessary for conducting the clinical trial. The clinical trial support device according to claim 3.

5. The prediction means predicts the number of patients who will meet the selection criteria from the second time point onward as the number of additional patients, and predicts the number of clinical trial candidates from the second time point onward based on the number of patients who are clinical trial candidates at the second time point and the number of additional patients. A clinical trial support device according to any one of claims 1 to 4.

6. The extraction means extracts patients who meet the criteria obtained by relaxing the conditions included in the selection criteria as clinical trial candidates. A clinical trial support device according to any one of claims 1 to 4.

7. The prediction means predicts the number of clinical trial candidates referred from hospitals other than the target hospital for which the number of clinical trial candidates is predicted, and predicts the number of clinical trial candidates from the second time point onward based on the number of patients who are clinical trial candidates at the second time point out of the first time point, the number of additional patients, and the number of referred patients. The clinical trial support device according to claim 5.

8. The prediction means predicts the number of clinical trial candidates at the second time point based on information about competing companies in conducting the clinical trial. A clinical trial support device according to any one of claims 1 to 4.

9. We obtain data on patient treatment, Based on the data regarding the aforementioned treatment, patients who meet the selection criteria for clinical trial patients at the first time point are selected as clinical trial candidates. Using a state curve, which is a curve showing the time-series changes in the state of a patient suffering from the disease being investigated, the probability of suitability, which is the probability that the clinical trial candidate is suitable for the clinical trial at a second time point later than the first time point, is estimated. Based on the aforementioned probability of suitability, the number of clinical trial candidates at the second time point is predicted. The system outputs information regarding the number of clinical trial candidates at the second point in time. Methods for supporting clinical trials.

10. The process of acquiring data related to patient treatment, Based on the data relating to the aforementioned treatment, a process is performed to extract patients who meet the selection criteria for clinical trial patients at a first point in time as clinical trial candidates, A process for estimating the probability of suitability, which is the probability that the clinical trial candidate is suitable for the clinical trial at a second time point later than the first time point, using a state curve, which is a curve showing the time-series change in the state of a patient suffering from the disease being investigated, A process to predict the number of clinical trial candidates at the second time point based on the aforementioned probability of suitability, A process to output information regarding the number of clinical trial candidates at the second time point. A clinical trial support program that has a computer execute commands.

Images