Systems and methods for measuring the therapeutic effect of drugs - Patents.com

Abstract

A computer-implemented method, computer program product and computer system (100) for measuring the therapeutic effect of a medical drug (10d) on a disease. A target trial dataset (310) having test covariates (tc) and clinical outcome data (tco) is obtained from a plurality of human patients (300) participating in a target trial having a treatment group (301) and a control group (302). An artificial patient dataset (303) is generated by filtering the artificial patient dataset (303) according to the inclusion / exclusion criteria of the target trial using a distribution of one or more corresponding covariates and their correlations derived from the set of test covariates (tc) or by randomly resampling the test covariates (tc) with replacement, with each data record of the artificial patient dataset (303) storing the covariates of the respective artificial patient. The artificial patient dataset (303) is provided to the disease progression model (200) to generate (1400) a simulated dataset (320) having simulated covariates (sc) and clinical outcome data (sco) for an experimentally untreated artificial patient. The therapeutic effect (10d-te) of the drug is determined by jointly analyzing the test dataset (310) and the simulated dataset (320) using a power prior approach (131) to incorporate the simulated dataset (320) as prior information, and the simulated dataset (320) is given a weight relative to a control group in the test dataset (310), the weight being based on at least the maximum weight value (230-1) received from the user (1).

Description

[Technical field]

[0001] The present invention relates generally to electronic data processing, and more particularly to a computer-implemented method, computer program product, and system for measuring the therapeutic effect of a drug with improved reliability. [Background technology]

[0002] When a drug (medicine) is developed for the medical treatment of a human patient with a certain disease, it is important to measure the therapeutic effect of the drug before applying it to patients on a large scale in order to ensure that an effective treatment is applied to the patient so that the disease can be cured or at least the progression of the disease can be positively influenced. To measure the therapeutic effect of the drug, clinical studies (clinical trials) are carried out in several stages, the last of which usually includes a large number of participants in each clinical trial.

[0003] Clinical targeting trials to measure the therapeutic effect of a drug always include at least one so-called treatment group with human patients who receive the experimental treatment with the drug, and a control group with patients who do not receive the experimental treatment but are instead treated with the standard-of-care (SOC) with a placebo. It may happen that a targeting trial is unbalanced in terms of participants, in that not all relevant characteristics of patients are equally represented in the targeting trial. There may be imbalances in age, sex, the number of participants with certain known pre-existing conditions, etc.

[0004] Such imbalances may lead to reduced reliability of measurements of treatment efficacy based on results from targeted trials.

[0005] Furthermore, it should be noted that participation in targeted trials usually entails a burden for participants that goes beyond the SOC. Patients in such trials usually have to undergo certain tests, receive injections, etc. In particular, patients in the control group of targeted trials do not even receive the experimental treatment, but only a placebo instead of the drug. In other words, patients in the control group may experience additional psychological and physical burdens, even though their health status is not positively affected by their trial participation. Summary of the Invention

[0006] Therefore, there is a need to provide systems and methods for improving the measurement of therapeutic efficacy of medicines (medical drugs) while at the same time providing some relief with respect to patient suffering, particularly in the control group of the respective targeted trial, whereby it would be advantageous to achieve such an improvement, particularly in situations where the number of participants in the targeted trial is less than desired.

[0007] The problem to be solved by the invention is solved by the embodiments (computer implemented method, computer program product and computer system) for measuring the therapeutic effect of a drug according to the independent claims.

[0008] In one embodiment, a computer system is provided for measuring the therapeutic effect of a medical drug on a disease. A medical drug as used herein is a substance used in the diagnosis, treatment, or prevention of a disease, or as a component of a drug. In general, the therapeutic effect of a drug is measured as the difference in the change from baseline of a measured clinical outcome between each treatment group and a control group. The system has one or more interfaces configured to establish communication with other computer systems, such as a remote data storage system, a remote data analysis system, etc. Through each interface, the system obtains a disease progression model of the disease targeted by the experimental drug.

[0009] A disease progression model quantitatively describes the time course of disease progression by one or more corresponding covariates based on historical covariates and clinical outcome data reflecting the disease progression for multiple patients with the disease. A clinical outcome is a measure that refers to the occurrence of disease, symptoms, signs, or laboratory abnormalities that constitute the target outcome of a clinical trial. That is, the term "clinical outcome" refers to a measured variable (e.g., peak oxygen volume, PROMIS fatigue score, etc.) or an event such as death, hospitalization, or disease progression.

[0010] For example, the clinical outcome in an oncology trial may be progression-free survival, defined as the time from starting treatment until disease progression or patient death, or overall survival, defined as the time from starting treatment until patient death. Another example may be a disease affecting the lungs, and the clinical outcome may be the loss of functional lung capacity, measured as the difference in the volume a patient can exhale at the start of the trial and at the end of the trial. See EMA (European Medicines Agency. Clinical efficacy and safety guidelines. https: / / www.ema.europa.eu / en / human-regulatory / research-development / scientific-guidelines / clinical-efficacy-safety-guidelines), or see the US Food & Drug Administration. Clinical Outcome Assessment Compendium. Examples of additional clinical outcomes currently recognized by the FDA (available at https: / / www.fda.gov / drugs / development-resources / clinical-outcome-assessment-compendium) are shown in Table 1 below.

[0011] [Table 1]

[0012] Covariates may include one or more of the following: one or more trends in the development of disease symptoms over time, variability in disease progression among patients, and quantitative descriptions of relationships between patient characteristics, disease characteristics, treatment characteristics, and disease progression dynamics.

[0013] In general, disease progression models are developed using available historical data. Disease progression models are mathematical functions used to quantitatively describe the time course of disease progression (e.g., tumor size over time, progression of disability score over time, evolution of functional markers over time). In the publication Cook, SF, Bies, RR "Disease Progression Modeling: Key Concepts and Recent Developments. Curr Pharmacol Rep 2, 221-230 (2016)", disease modeling techniques are disclosed that include the use of mathematical functions to quantitatively describe the time course of disease progression, and disease progression models can be more or less comprehensive and can describe aspects such as: - Trends in disease progression observed over time (e.g., linear, exponential), - variability in disease progression between patients, - Quantitative description of relationships between patient characteristics (e.g., sex, age, weight, comorbidities, smoking status, ethnicity), Disease characteristics (e.g., disease severity, time since diagnosis), -Treatment characteristics (e.g., drug, dose, schedule, concomitant medications), and -Disease progression dynamics. The features included in the disease progression model are referred to herein as relevant covariates.

[0014] The historical data used to develop such models may be data from previously conducted clinical trials, multiple clinical trials, electronic health records, data registries, or other sources.

[0015] Disease progression models are available for several diseases. For example, "Wu K, Gamazon ER, Im HK, Geeleher P, White SR, Solway J, et al. Genome-wide interrogation of longitudinal FEV1 in children with asthma. Am J Respir Crit Care Med. 2014;190(6):619-27" describes a disease progression model for asthma with the clinical outcome "forced vital capacity in 1 second" (FEV1) and the relevant covariates "age" and "height" of the patient. Another example is the melanoma disease progression model described by MS Chatterjee et al. in "Population Pharmacokinetic / Pharmacodynamic Modeling of Tumor Size Dynamics in Pembrolizumab-Treated Advanced Melanoma. CPT Pharmacometrics Syst. Pharmacol. (2017) 6, 29-39" which uses the patient clinical outcome "tumor size" and the associated covariates "number of target lesions" and "ECOG status". Yet another example of a disease progression model for schizophrenia is given by Venkatesh Pilla Reddy et al. in "Pharmacokinetic-pharmacodynamic modeling of antipsychotic drugs in patients with schizophrenia Part I: The use of PANSS total score and clinical utility. Schizophrenia Research, Volume 146, Issues 1-3, 2013, Pages 144-152". The clinical outcome in this example is "PANSS total score" and the relevant covariates are "treatment" and "placebo effect."Yet another example of a disease progression model for predicting tumor size over time (clinical outcome) depending on the treatment a patient received (covariates) is disclosed by Mario Nagase et al. in "Modeling Tumor Growth and Treatment Resistance Dynamics Characterizes DifferResponse to Gefitinib or Chemotherapy in Non-Small Cell Lung Cancer; CPT Pharmacometrics Syst. Pharmacol. (2020) 9, 143-152."

[0016] Further examples of disease progression models are described in the following papers: Lu et al., "Population Analysis of wetAMD Disease Progression and The Therapeutic Effect of Ranibizumab" (presented at the Population Approach Group in Europe (PAGE) 21st Annual Meeting, June 5-8, 2012, Venice, Italy, available at https: / / www.page-meeting.org / pdf_assets / 8526-2012%20PAGE%20 poster_version_FINAL.PDF), describes a disease progression model for wAMD, where the clinical outcome is visual acuity and the covariate is exposure to the drug.

[0017] A disease progression model for CRC in which the clinical outcomes are tumor size and survival and the covariates are exposure to drugs is described by Claret et al. in "Model-based prediction of phase III overall survival in colorectal cancer on the basis of phase II tumor dynamics. J Clin Oncol. 2009 Sep 1;27(25):4103-4108.doi:10.1200 / JCO.2008.21.0807.Epub 2009 Jul 27.PMID:19636014."

[0018] A disease progression model for AMD or DME with visual acuity as the clinical outcome and exposure to medication as a predictive covariate is described by Basile et al. in "Integrating disease progression models, non-clinical pharmacokinetic data and treatment response endpoints to optimize intravitreal dosing regimens. Int J Clin Pharmacol Ther. 2014 Jul;52(7):574-586. doi:10.5414 / CP201998.PMID:24755127."

[0019] Those skilled in the art will be able to identify or develop further models of disease progression in the literature that are suitable in the context of the approaches disclosed herein.

[0020] Additionally, the system has an interface for receiving a target trial dataset (also referred to herein as a trial dataset) with study covariate and clinical outcome data obtained from a plurality of human patients participating in the target trial. The target trial includes one or more treatment arms having human patients receiving the experimental treatment, and a control arm having patients not receiving the experimental treatment.

[0021] Furthermore, the system comprises an artificial patient generator module for creating the artificial patient data set. There are two alternative ways in which the artificial patient generator can create the artificial patient data record.

[0022] In one implementation, the distribution of one or more corresponding covariates is used. The relevant covariates are identified from a disease progression model developed based on historical data (e.g., results from previous studies). Then, a mathematical description of the distribution of the relevant covariates and the correlation between them is constructed based on the target study. For example, if the disease progression model considers height and weight to be covariates related to how the disease progresses over time in a particular population, a mathematical description of the distribution of these two covariates (e.g., mean, median, standard deviation) and their correlation (for the covariates age and height, a positive correlation is most likely to be found, meaning that the taller the patient, the heavier the patient) can be used to generate a dataset describing these covariates. This mathematical description is then used to sample a large artificial patient dataset (e.g., 10,000 patients) with artificial patients that are virtually impossible to distinguish from real patients. Each data record in the generated artificial patient dataset corresponds to a simulated patient. The artificial patient dataset is then filtered according to the inclusion / exclusion criteria of the target study, and data records associated with the artificial patients that do not meet the inclusion / exclusion criteria of the target study are removed from the artificial patient dataset. That is, simulated patients that do not meet the inclusion criteria or meet the exclusion criteria of the target study are then removed from the artificial patient dataset, attempting to reproduce the screening process (e.g., the target study does not recruit patients weighing more than 130 kg, and therefore such artificial patient data records are removed from the artificial patient dataset). Finally, this process generates a dataset in which each data record represents an artificial patient with the characteristics of the patient, the characteristics of the patient's disease, and the treatment the patient is receiving, to the extent that it is considered relevant in the disease progression model used. It should be noted that those skilled in the art will understand the term inclusion / exclusion criteria of the target study as including criteria that qualify a patient to participate in the target study (inclusion criteria) as well as criteria that do not qualify a patient to participate in the target study (exclusion criteria).

[0023] In an alternative implementation, the artificial patient data set is generated by using a bootstrapping approach that includes random sampling with replacement. This sampling with replacement method may be used if the target test data set is large enough. What is unique to this method is that only patients who meet the inclusion / exclusion criteria of the target test are included in the target test data, so only such artificial patients are generated. Therefore, a filtering step as in the first implementation is not necessary here (although it does no harm because data is not filtered from the resampled data set). For example, patients may be randomly sampled from the test data set to obtain paired values ​​of covariates (e.g., age and height) to generate a data set of covariates of the artificial patient. A large data set may be generated (e.g., 10,000 patients). To obtain such a large data set from a smaller set of patients, sampling with replacement is performed (patients may be sampled more than once).

[0024] The artificial patient data set is then provided as input to the disease progression model to generate a simulated data set having simulated covariates and simulated clinical outcome data for the simulated artificial patient not receiving the experimental treatment. In other words, the simulated artificial patient reflects the patient who receives only SOC in the control group of the target trial. That is, such a simulated patient can play the role of the patient in the control group of the target trial to relieve real human patients from the above-mentioned burden of participating in the trial without receiving the experimental treatment.

[0025] At this point, the system has 1) actual data for the treatment and control groups of the target study, and 2) simulated data for artificial patients in the control group with characteristics matching those of the patients recruited in the target study, obtained by using a disease progression model created based on historical data. These two sources are now combined into a single analysis. This is performed by the study analyzer module of the system, which determines the therapeutic effect of the drug by analyzing the study data set and the simulated data set together. To do this, the study analyzer incorporates the simulated data set as prior information using a power prior module. For example, the power prior approach described by Ibrahim JG, Chen MH, Gwon Y, Chen F., "The power prior: theory and applications. Stat Med. 2015 Dec 10; 34(28): 3724-49" may be used to incorporate the simulated patient data as prior information. Thereby, the simulated data set is weighted relative to the control group of the study data set to avoid overweighting the impact of the artificial patients on the overall outcome of the analysis. In other words, considering that the number of simulated patients may be disproportionately large (e.g., 10,000 patients) compared to the actual number of patients in the target study (e.g., 300 in the treatment group and 300 in the control group), it is important to select appropriate weights for the simulated data. The weights are based at least on the maximum weight value received by the system from the user. That is, the user of the system provides a limit on the influence of the artificial patient data on the calculation of the therapeutic effect of the drug. The weights can be interpreted as the number of real patients that must be added to the study to provide the same amount of information as the virtual (artificial) patients do.For example, if 10,000 simulated patients are created but only 100 real patients need to be added to the control group, each simulated patient will be considered with only a weight of 1% so that the overall weight of the 10,000 simulated patients corresponds to a total number of 100 patients.

[0026] The maximum weight value received from the user may be based on any of the following: - The number of patients used to develop the disease progression model. This number of (actual) patients in the respective historical test data corresponds to the upper limit of the maximum meaningful weight value provided by the user. Higher weight values ​​would give the appearance of a higher reliability of the disease progression model than the actual reliability achieved based on the historical data, and thus could affect the power prior analysis, which cannot be justified. - Similarity of patients used to develop the disease progression model and patients expected to be enrolled in the target trial, and assumptions made to extrapolate from one population to another. For example, the disease progression model may have been developed using historical data from only adult patients. For example, adult patients are not as valuable for informing pediatric trials as pediatric patients. Correction factors can be applied to account for the assumption that the relationship between a particular combination of covariates and the respective clinical outcome also applies to pediatric patients. For example, the maximum number of patients may be reduced to an appropriate proportion of patients used to develop the disease progression model (e.g., only 50% of these patients). - Sensitivity analysis: The false positive result probability (probability of concluding that the drug works when it does not) is considered as a worst case scenario. For example, the simulated patients may progress faster than the real patients recruited in the trial. As a result, when pooling together the artificial and real patient data, the rate of disease progression in the control patients may be estimated to be faster than the true rate of progression. When comparing the control and treatment groups, this would result in an increased probability of concluding that the drug slows disease progression, when in fact it does not. Under this worst case scenario, a range of weights is evaluated via clinical trial simulation and analysis, using a power prior and a maximum weight. The goal is to keep the probability of a false positive result below a predefined threshold. Typically, a probability of 10% is accepted by regulatory authorities in the pharmaceutical sector. As a result of the sensitivity analysis, the maximum weight of the artificial patients may be further reduced.

[0027] Those skilled in the art will recognize that the maximum weight value received from the users may further be based on the following criteria. - the accuracy of the disease progression model estimates, - Model validation results, and -Size of targeted trials.

[0028] Then, the clinical outcomes for the control group in the target trial are updated using the power prior by considering the maximum weight value for the artificial patient data. By including the simulated patient data, the distribution of the control group becomes narrower and higher than the original distribution of the control group in the target trial. That is, the estimated measure of the treatment effect based on the method disclosed herein (i.e., the difference in the rate of progression of clinical outcomes between the treatment group and the control group) is more reliable than the estimate based solely on the target trial data. It should be noted that this improvement is achieved without additional real patients in the control group, which brings the above-mentioned disadvantages to the humans participating in the control group.

[0029] In one embodiment, the weights are further based on the similarity between the clinical outcome data for the artificial patients not receiving the experimental treatment and the clinical outcome data obtained from the control group of the target trial. This similarity may be obtained by using a dynamic borrowing method, where higher similarity results in higher dynamic borrowing weight values. The weights used for the analysis are the lower of the maximum weight value received and the obtained dynamic borrowing weight value. In other words, in this embodiment, an automatic quantification algorithm is used with the maximum weight value to select the weights that are ultimately used to measure the treatment effect. One example of such an algorithm is the dynamic borrowing for power prior analysis described in Ibrahim JG, Chen MH, Gwon Y, Chen F., "The power prior: theory and applications. Stat Med. 2015 Dec 10; 34(28): 3724-49." This dynamic borrowing algorithm is adapted for treatment effect analysis by implementing a cost function that takes into account the difference between the observed outcomes in patients enrolled in the trial and the simulated outcomes of patients in the simulated patient dataset, and the amount of information borrowed from the simulated dataset. That is, the method uses already available real patient data and leverages additional information from simulated patient data. By doing this, a balance is achieved between the risk of introducing bias into the analysis and improving the accuracy of the estimates.

[0030] Additional aspects of the invention will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as described. [Brief description of the drawings]

[0031] [Figure 1] FIG. 1 is a block diagram of a computer system for measuring the therapeutic effect of a medical drug on a disease, according to one embodiment. [Diagram 2] 1 is a simplified flowchart of a computer-implemented method for measuring the therapeutic effect of a medical drug on a disease, according to one embodiment. [Diagram 3] FIG. 1 shows observed data from a clinical trial used to construct a variance-covariance matrix, and simulated data created by using the variance-covariance matrix. [Figure 4] FIG. 13 shows the probability of a false positive result regarding the therapeutic effect of a drug for different weights given to an artificial patient. [Diagram 5] FIG. 13 illustrates an example behavior of a cost function implemented by dynamic utilization for the power prior algorithm over a range of weights, according to one embodiment. [Figure 6A] FIG. 13 shows an example of the posterior distribution of FEV1 change from baseline estimate with and without an artificial patient. [Figure 6B] FIG. 1 shows an exemplary distribution of treatment effect measures with an artificial patient compared to measures without an artificial patient. [Figure 7] 1 is a table reflecting the characteristics of one example of a particular disease progression model. [Figure 8] FIG. 1 illustrates an example of a general-purpose computing device and a general-purpose mobile computing device that may be used with the techniques described herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] Figure 1 includes a block diagram of a computer system 100 for measuring the therapeutic effect of a medical drug 10d on a disease. Figure 2 is a simplified flow chart of a computer-implemented method 1000 for measuring the therapeutic effect of a medical drug 10d on the disease. The method 1000 can be performed by the system 100. For this reason, Figure 1 will be described in view of Figure 2, and the following description of Figure 1 will also refer to the reference numbers used in Figure 2.

[0033] The system 100 has one or more interfaces 140 for communicating with other computer systems (e.g., simulation systems, data storage systems, etc.) for data acquisition, and further with a human user 1 of the system. Through the interfaces 140, the system 100 obtains (1100) a disease progression model 200 of the disease. The obtained disease progression model 200 is based on historical covariates and clinical outcome data reflecting the disease progression for a number of patients affected by the disease. The disease progression model quantitatively describes the time evolution 210 of the disease progression by one or more corresponding covariates. In the examples described herein, a disease progression model is used that characterizes the lung function changes over time in asthma patients. In this example, the disease progression is monitored by the "forced vital capacity in 1 second" (FEV1), which increases with age and decreases in asthma patients. Thereby, the loss of lung functional capacity is measured as the difference in the volume that the human patient can exhale at the beginning and end of the test. This model describes how this marker evolves over time in patients receiving standard treatment and how covariates affect this. In this example, the relevant covariates are age and height (as described in the above cited paper by Wu et al.). It should be noted that those skilled in the art may also use other / further covariates when monitoring the progression of FEV1. It should also be noted that those skilled in the art may apply the approach disclosed herein to other diseases using other suitable disease progression models. With regard to the example of FEV1, "Equation 3" in Wu's paper states that the best prediction by the disease progression model for FEV1 was achieved by the following exponential function of age and height: FEV1 = exp(theta1 x age + theta2 x height - theta3) + theta drugeffect where theta1 and theta2 are the rates of change in FEV1 with respect to age and height, respectively. Theta3 refers to the baseline level of FEV1 (i.e., the FEV1 level at birth assuming the model is applicable to that age range). Figure 7 reproduces Table 2 of Wu's paper as table 700 showing parameter estimates from the final model reflected by "Equation 3".

[0034] Using this model, the system 100 can predict how a patient with a particular set of covariates (age and height) is expected to progress in terms of FEV1 over time, taking into account inter-patient variability and FEV1 measurement noise. Note that in the examples described herein, theta3 is not considered as a relevant covariate in the disease progression model. This has the effect that when using the disease progression model to simulate artificial patient data, the simulation is relative to a reference patient (not related to a particular ethnic group). Inter-patient variability (inter-individual variability) is described in Equation 1 by Wu et al. "Interindividual variability for FEV1 was assessed using an additive error model. P ij =P TVj +η ij (1) In the formula, P ij is the true value of the jth parameter for the ith subject. P TVj is the population typical value (TV) of the jth parameter, and η ij is a between-individual random effect, and P TVj From P ij It quantifies the deviation of and is assumed to be normally distributed with mean 0 and variance ω2j".

[0035] FEV1 measurement noise (intra-individual variability or residual variability) is described by Equation 2 of Wu et al. "Intra-individual variability was assessed using a combination of proportional and additive error models as follows: FEV 1obs =FEV 1pred(1+ε1)+ε2(2) In the formula, FEV 1obs is the observed value, and FEV 1pred are the corresponding model predictions. ε1 and ε2 are independent normally distributed random variables with mean 0 and variances σ21 and σ22, respectively, explaining the remaining unexplained variability. The final models were assessed by non-parametric bootstrap and visual prediction checks to evaluate their predictive performance and robustness."

[0036] The system 100 further receives (1200) a test dataset 310 having test covariates tc and clinical outcome data tco obtained from a plurality of human patients 300 participating in the target test. The target test includes at least one treatment group 301 (indicated by black heads in FIG. 1) with human patients 11t receiving the experimental treatment, and a control group 302 (indicated by white heads in FIG. 1) with patients 11nt not receiving the experimental treatment. Patients in the control group 302 receive a placebo 10p instead of the experimental drug 10d. The target test and clinical outcome discussion for this example includes a one-year observation period, in which enrolled patients are randomly assigned to a treatment group or a control group, and then receive the corresponding treatment (experimental drug or standard treatment 10p) for one year. It was intended to enroll 300 patients per group. Before randomization, patients were screened and their baseline FEV1 was measured. After a one-year follow-up period, the patients' FEV1 was measured again. The change in FEV1 (change in FEV1 from baseline) over this period is the clinical outcome. As children grow, FEV1 is expected to increase. Thus, the change from baseline for patients not receiving the drug is expected to increase. The change from baseline for patients receiving the experimental drug is expected to be larger if the drug actually works as intended.

[0037] The artificial patient generator module 110 (APG) of the system 100 generates 1300 an artificial patient data set 303 based on data obtained from a target study. In a first implementation, the APG 110 simulates the artificial patient data based on a variance-covariance matrix using the distributions of one or more corresponding covariates (e.g., age and height) and their correlations derived from a set of study covariates tc. This can be done by using the variance-covariance matrix of the covariates of interest obtained from the data of real patients of the target study. In this example, the variance-covariance matrix for age and height had the form shown in Table 2 below.

[0038] [Table 2]

[0039] This variance-covariance matrix is ​​then used to simulate a new cohort of artificial patient datasets 303. In this implementation, the APG 110 has a filtering module APF 120 that filters the artificial patient dataset 303 according to the inclusion-exclusion criteria of the target study, such that data records associated with artificial patients that do not meet the inclusion criteria of the target study or that meet the exclusion criteria of the target study are removed from the artificial patient dataset 303. Inclusion criteria are characteristics that are necessary for a target study participant to be included in the clinical trial. Exclusion criteria are characteristics that make a potential participant ineligible from inclusion in the clinical trial. In the target study, an exclusion criterion was that patients over 18 years of age did not participate in the target study. Thus, the artificial patients 303-1 and 303-2 that fell under such exclusion criteria (i.e., over 18 years of age) were filtered and removed from the artificial patient dataset 303. Figure 3 shows the correlation of the covariates "age" and "height" (considered to be relevant to the disease progression model) to the observed data 3100 used to build the variance-covariance matrix, and to the simulated dataset 3200 created by using the variance-covariance matrix. The output of the APG 110 is a dataset with simulated covariates sc′ for the artificial patients of the artificial patient dataset 303 .

[0040] In an alternative implementation, bootstrap is used, where patients are randomly sampled from the target test dataset to obtain paired values ​​of age and height to generate simulated covariates sc' for the artificial patients. A large dataset can be generated (e.g., 10,000 patients). To obtain such a large dataset from a smaller set of real patients in the target study, sampling with replacement may be performed (meaning that a patient may be sampled more than once). In other words, by random sampling, the test covariates tc APG110 generates an artificial patient data record for each patient in the artificial patient dataset 303 and stores the simulated covariates sc' for each artificial patient with the data record. No further filtering is required in this implementation of the APG110, since sampling patients from the target study automatically results in an artificial patient dataset that meets the exclusion / inclusion criteria of the target study.

[0041] The generated artificial patient data set 303 with simulated covariates sc' is now provided as input to the disease progression model 200. Using this input, the disease progression model 200 generates (1400) a simulated data set 320 with simulated covariates sc and simulated clinical outcome data sco for artificial patients not receiving experimental treatment. That is, the disease progression model simulates covariates and clinical outcomes only for artificial patients who receive standard treatment and therefore belong to the control group of the targeted trial. It is clear that the simulated patient data cannot be associated with the treatment group of the trial, since it is not possible to simulate the therapeutic effect of a drug. Measuring such a therapeutic effect is precisely the goal of the targeted trial. In this example, the clinical outcomes of 10,000 artificial control patients were simulated. That is, the simulated data set 320 now contains information on how each of the 10,000 artificial patients evolves over time in terms of FEV1 progression.

[0042] The test analyzer module (TA) 130 of the system 100 finally determines (1500) the treatment effect 10d-te of the drug 10d. In a conventional treatment effect analysis, only the test data set 310 (tc / tco) would have been used for such an analysis. However, the method disclosed herein analyzes the test data set 310 and the simulated data set 320 together using the power prior module 131 to incorporate the simulated data set 320 as prior information. Thereby, the simulated data set 320 is weighted compared to the control group of the test data set 310. The weight for the simulated data set allows to recognize that the information gain obtained from the artificial patients is smaller than the information obtained from the real patients of the trail control group 302. In other words, the weight is interpreted as the number of real patients that need to be added to the test control group to provide the same amount of information as the simulated patients can contribute. The weight is a constraint (for the TA 130 and its power prior function 131) limited to a maximum weight value 230-1 by the user 1 via a corresponding input to the TA 130. User 1 sets this maximum weighting value used by the efficacy analysis algorithm based on medical considerations that take into account their respective statistics.

[0043] For example, the maximum weight value 230-1 may be the number of patients used to develop the disease progression model 200. This reflects that the reliability of the disease progression model prediction is limited by the number of input data sets (of real patients) that were available for model development. It would not make sense to give a higher weight in the analysis to all outcomes of the simulated patients than is justified by the model used to generate the simulated clinical outcome 320. In that sense, the number of patients used to develop the disease progression model provides an upper limit for the maximum weight value input 230-1. For example, if the disease progression model 200 was developed using a data set of 660 real patients, the maximum weight value 230-1 received in this implementation (corresponding to an objectively meaningful upper limit for the weight) is 660. That is, 10,000 simulated patients are only given weight in the analysis corresponding to 660 patients in the control group.

[0044] In another implementation, the maximum weight value 230-1 may be based on the similarity of the patients used to develop the disease progression model 200 to the target test patients 300 and the assumptions made to extrapolate from one population to another. In the FEV1 example, the disease progression model 200 was developed using data from adult test patients. A multidisciplinary team of FEV1 experts reached the consensus that 660 adult patients are not as valuable for informing a pediatric study as pediatric patients. Therefore, a correction factor of 0.5 is applied to account for the assumption that the relationship between age, height and FEV1 applies to pediatric patients, and therefore the maximum number of patients may be set to 50% of the patients used to develop the model. This results in a maximum weight value of 330 patients. A reduction in the maximum weight value always results in a treatment effect 10d-te estimate that approaches the treatment effect measured based only on the test dataset 310. That is, the risk of introducing errors from the simulation is reduced, but at the same time, the reliability of the measured treatment effect is reduced, as further shown below.

[0045] In a third implementation, user 1 may use the sensitivity analysis (SA) tool 230 to determine the maximum weighting value that reduces the probability of concluding that the drug 10d works when it does not. In other words, the worst case scenario is considered to be a too high "false positive result probability" (i.e., the probability of concluding that the drug works when it does not). In the FEV1 example, the simulated data set 320 shows a lower FEV1 change from baseline than the patients 300 recruited in the study. When the simulated data 320 of the artificial patient 303 and the actual data 310 of the actual patient 300 are pooled together, the FEV1 change from baseline in the control patient may be estimated to be lower than the true FEV1 change from baseline. As a result, when comparing the control group with the treatment group, it would be more likely to conclude that the drug increases the FEV1 change from baseline when in fact it does not.

[0046] Under this worst case scenario, the range of weights is evaluated through clinical trial simulations and analyzed using a power prior. Figure 4 shows an example with six weight values ​​in the range of 0-150 (units equivalent to the number of patients) used for the FEV1 example. In this example, the user has determined a 10% threshold for the probability of a false positive. That is, the maximum weight value used as an input for TA130 should keep the probability of a false positive result (Type I error rate) below 10%. By interpolation using linear regression, a weight of 60 was identified as the weight value corresponding to a Type I error rate of 10% (0.1). In this case, the maximum weight value was set to 60 patients. As a result, in this example, the artificial patients cannot have a higher weight in the analysis than the 60 real patients.

[0047] Other factors that may affect the selection of the appropriate maximum weight value input are the accuracy of the disease progression model estimate, the results of model validation, and the size of the target test. Those skilled in the art will know how to evaluate these factors before inputting the maximum weight value as an input to TA130. In general, higher weights are desirable when there is a good match between the observed and simulated control patients, and lower weights are desirable when there is a mismatch to prevent biased analysis.

[0048] If the received maximum weight value 230-1 is the only consideration for setting the weight in the treatment effect analysis, it will automatically become the predetermined weight used by the TA 130 in the analysis of the treatment effect 10d-te for this drug. In one embodiment, an automatic quantification algorithm is used with this maximum weight value to select the weight to be used in the analysis. In this embodiment, the weight used is further based on the similarity between the clinical outcome data sco for the artificial patient not receiving the experimental treatment and the clinical outcome data tco obtained from the control group of the target trial. The similarity is obtained by using a dynamic utilization method with a higher similarity, resulting in a higher dynamic utilization weight value. The weight value finally used is the lower of the received maximum weight value and the obtained dynamic utilization weight value.

[0049] An example of an algorithm implementing such a dynamic utilization method is the dynamic utilization for power prior analysis described in Ibrahim JG, Chen MH, Gwon Y, Chen F. "The power prior: theory and applications. Stat Med. 2015 Dec 10;34(28):3724-49." The algorithm implements a cost function that takes into account the difference between the clinical outcomes observed for patients enrolled in the study and the clinical outcomes of patients in the external dataset. In the method described herein, a simulated dataset is used instead of the external dataset. Furthermore, the algorithm uses the amount of information utilized from the simulated dataset. This allows a balance to be struck between the risk of introducing bias into the treatment effect analysis and improving the accuracy of the estimation. Following Ibrahim et al. 2015, section 2, the cost function takes the following form:

[0050]

number

[0051] FIG. 5 shows the relationship of this cost function 500 over a range of weights. In the example of FEV1, the minimum MIN was found at weight 58 (patient). Because this weight was less than the maximum weight value received from the user, the weight value determined by the dynamic utilization is now used as the weight of the simulated patient in the clinical trial analysis when using the power prior function PP131 of TA 130. If the dynamic utilization indicated weights of more than 60 patients and the maximum weight value was determined based on the third implementation as described in FIG. 4, the maximum weight value would have been used as the weight value given to the simulated patient for PP131 since TA 130 always uses the lower weight value in this embodiment.

[0052] Returning to FIG. 1, it should be noted that the reliability of the determined treatment effect 10d-te is improved by incorporating simulated patient clinical outcomes with appropriate weights using the PP131 function of TA130, compared to a traditional clinical trial analysis based only on real patient data 310 from clinical trials 300. This improvement effect is illustrated in FIG. 6A, FIG. 6B as an example for the FEV1 scenario.

[0053] Once the weights are applied to the artificial patient data, the FEV1 change from baseline for the control group in the study is updated using the power prior 131 and the simulated FEV1 change from baseline. Figure 6A shows the posterior distribution of the FEV1 change from baseline estimate for the control group (solid line) and the treatment group (dashed line). The fact that the distribution of the treatment group differs from that of the control group already indicates that there is a treatment effect associated with the medical drug. In the left chart 610, the distributions obtained with a conventional treatment effect analysis without artificial patients are shown. The distribution of the control group 611 is slightly lower and wider than the distribution of the treatment group 612. In the right chart 620, the distributions 621, 622 are obtained with simulated patient data using PP 131 with a given weight value of 58. That is, the control group is augmented by 58 simulated patients, resulting in a higher number of patients in the control group than in the treatment group. The control group distribution 621 is higher and narrower than the treatment group distribution 622 (which of course remains unchanged relative to distribution 612). That is, the control group distribution 621 using the artificial patient with weight 58 results in better accuracy of the FEV1 change estimate.

[0054] FIG. 6B shows a chart 630 with distributions 631, 632 of treatment effects derived from the charts 610 and 620 of FIG. 6A. The distributions of treatment effects are calculated as the difference in FEV1 change from baseline between the respective treatment group and the control group. Distribution 631 is derived from chart 620 (including 58 artificial patients). Distribution 631 is derived from chart 610 without artificial patients. FIG. 6B clearly demonstrates how the estimate of treatment effect is improved by the approach disclosed herein, using artificial patients in the control group. The distribution 631 of treatment effect measured by including artificial patients has a narrower and higher peak than the distribution 632 showing the distribution of treatment effect derived from real patient data from the clinical trial alone, in short providing a more accurate estimate of the treatment effect. Thus, the proposed method not only improves the measurement of the treatment effect of a drug based on clinical trials, but also makes it possible to achieve this improved result without adding additional patients to the control group. This avoids unnecessary burden on patients who would receive only a placebo and would not even be able to benefit from the therapeutic effects of the drug.

[0055] FIG. 8 illustrates an example of a general-purpose computing device 900 and a general-purpose mobile computing device 950 that may be used with the techniques described herein. The computing device 900 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The general-purpose computing device 900 may correspond to the computer system 100 of FIG. 1. The computing device 950 is intended to represent various forms of mobile devices, such as personal digital assistants, mobile phones, smartphones, and other similar computing devices. For example, the computing device 950 may be used as a GUI front end for a user to input a maximum weight value into the computing device 900 and then receive a predicted therapeutic effect of a drug from the computing device 9900. The components, their connections and relationships, and their functions shown herein are merely exemplary and are not intended to limit the implementation of the invention described and / or claimed herein.

[0056] The computing device 900 includes a processor 902, a memory 904, a storage device 906, a high-speed interface 908 that connects to the memory 904 and a high-speed expansion port 910, and a low-speed interface 912 that connects to a low-speed bus 914 and the storage device 906. Each of the components 902, 904, 906, 908, 910, and 912 are interconnected using various buses and may be mounted on a common motherboard or otherwise as needed. The processor 902 can process instructions for execution within the computing device 900, including instructions stored in the memory 904 or the storage device 906, to display graphical information for a GUI on an external input / output device, such as a display 916 coupled to the high-speed interface 908. In other implementations, multiple processing units and / or multiple buses may be used, along with multiple memories and multiple types of memories, as needed. Multiple computing devices 900 may also be connected, with each device providing a portion of the required operations (e.g., as a server bank, a group of blade servers, or a processing device).

[0057] The memory 904 stores information within the computing device 900. In one implementation, the memory 904 is one or more volatile memory units. In another implementation, the memory 904 is one or more non-volatile memory units. The memory 904 may be another form of computer-readable medium, such as a magnetic disk or an optical disk.

[0058] The storage device 906 can provide mass storage for the computing device 900. In one implementation, the storage device 906 can be or include a computer-readable medium such as a floppy disk device, a hard disk device, an optical disk device, or a tape device, a flash memory or other similar solid-state memory device, or an array of devices including devices in a storage area network or other configuration. The computer program product can be tangibly embodied in an information carrier. The computer program product can also include instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer-readable or machine-readable medium, such as the memory 904, the storage device 906, or a memory on the processor 902.

[0059] The high-speed controller 908 manages bandwidth-intensive operations for the computing device 900, while the low-speed controller 912 manages lower bandwidth-intensive operations. Such an allocation of functions is merely exemplary. In one implementation, the high-speed controller 908 is coupled to the memory 904, a display 916 (e.g., via a graphics processor or accelerator), and a high-speed expansion port 910 that can accept various expansion cards (not shown). In this implementation, the low-speed controller 912 is coupled to the storage device 906 and the low-speed expansion port 914. The low-speed expansion port, which may include various communication ports (e.g., USB, Bluetooth, Ethernet, wireless Ethernet), may be coupled to one or more input / output devices, such as a keyboard, pointing device, scanner, or a networking device, such as a switch or router, for example, via a network adapter.

[0060] Computing device 900 may be implemented in a number of different forms, as shown. For example, it may be implemented as a standard server 920, or multiple times in a cluster of such servers. It may also be implemented as part of a rack server system 924. It may also be implemented in a personal computer, such as a laptop computer 922. Alternatively, components from computing device 900 may be combined with other components in a mobile device (not shown), such as device 950. Each such device may include one or more of computing devices 900, 950, and the entire system may be composed of multiple computing devices 900, 950 in communication with each other.

[0061] Computing device 950 includes, among other components, a processor 952, memory 964, input / output devices such as a display 954, a communication interface 966, and a transceiver 968. Device 950 may also include a storage device, such as a microdrive or other device, to provide additional storage. Each of the components 950, 952, 964, 954, 966, and 968 are interconnected using various buses, and some of the components may be mounted on a common motherboard or in other manners as desired.

[0062] The processor 952 may execute instructions within the computing device 950, including instructions stored in the memory 964. The processor may be implemented as a chipset of chips including separate analog and digital processing units. The processor may coordinate other components of the device 950, such as, for example, the user interface, applications run by the device 950, and control of wireless communications by the device 950.

[0063] The processor 952 may communicate with a user via a control interface 958 and a display interface 956 coupled to a display 954. The display 954 may be, for example, a Thin-Film-Transistor Liquid Crystal Display (TFT LCD) or an Organic Light Emitting Diode (OLED) display, or other suitable display technology. The display interface 956 may comprise appropriate circuitry for driving the display 954 to present graphical and other information to the user. The control interface 958 may receive commands from the user and convert them for sending to the processor 952. Additionally, an external interface 962 may be provided in communication with the processor 952 to enable short-range communication of the device 950 with other devices. The external interface 962 may, for example, be provided for wired communication in some implementations and wireless communication in other implementations, and multiple interfaces may be used.

[0064] The memory 964 stores information within the computing device 950. The memory 964 may be implemented as one or more of one or more computer readable media, one or more volatile memory units, or one or more non-volatile memory units. An expansion memory 984 may also be provided and connected to the device 950 via an expansion interface 982, which may include, for example, a Single In Line Memory Module (SIMM) card interface. Such expansion memory 984 may provide additional storage space for the device 950 or may also store applications or other information for the device 950. In particular, the expansion memory 984 may include instructions for performing or supplementing the processes described above, and may also include secure information. Thus, for example, the expansion memory 984 may function as a security module for the device 950 and may be programmed with instructions that enable secure use of the device 950. Furthermore, secure applications may be provided via a SIMM card along with additional information, such as placing identifying information on the SIMM card in an unhackable manner.

[0065] The memory may include, for example, flash memory and / or NVRAM memory, as described below. In one implementation, a computer program product is tangibly embodied in an information carrier. The computer program product includes instructions that, when executed, perform one or more methods, such as those described above. The information carrier is a computer-readable or machine-readable medium, such as memory 964, expansion memory 984, or memory on processor 952, and may be received, for example, via transceiver 968 or external interface 962.

[0066] Device 950 may communicate wirelessly via communication interface 966, which may include digital signal processing circuitry, as needed. Communication interface 966 may provide communications under various modes or protocols, such as GSM voice calls, SMS, EMS, or MMS messaging, CDMA, TDMA, PDC, WCDMA, CDMA2000, or GPRS, among others. Such communications may occur, for example, via radio frequency transceiver 968. In addition, short-range communications may occur using, for example, Bluetooth, WiFi, or other such transceivers (not shown). In addition, a Global Positioning System (GPS) receiver module 980 may provide additional navigation- and location-related wireless data to device 950, which may be used as appropriate by applications executing on device 950.

[0067] Device 950 may also communicate audibly using audio codec 960, which may receive spoken information from a user and convert it into usable digital information. Audio codec 960 may also generate audible sounds for the user, such as through a speaker in a handset of device 950. Such sounds may include sounds from a voice call, may include recorded sounds (e.g., voice messages, music files, etc.), and may include sounds generated by applications running on device 950.

[0068] The computing device 950 may be implemented in a number of different forms, as shown in the figure. For example, it may be implemented as a cellular telephone 980. It may also be implemented as part of a smartphone 982, personal digital assistant, or other similar mobile device.

[0069] Various implementations of the systems and techniques described herein may be realized in digital electronic circuitry, integrated circuits, specially designed application specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs executable and / or interpretable on a programmable system including at least one programmable processor, which may be special purpose or general purpose, coupled to receive data and instructions from and transmit data and instructions to a storage system, at least one input device, and at least one output device.

[0070] These computer programs (also known as programs, software, software applications or codes) include machine instructions for a programmable processor and may be implemented in high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus and / or device used to provide machine instructions and / or data to a programmable processor (e.g., magnetic disks, optical disks, memories, Programmable Logic Devices (PLDs)), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0071] To provide for interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to a user, and a keyboard and pointing device (e.g., a mouse or trackball) by which the user can provide input to the computer. Other types of devices may be used to provide interaction with a user. For example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user may be received in any form, including acoustic, speech, or tactile input.

[0072] The systems and techniques described herein can be implemented in a computing device that includes a back-end component (e.g., as a data server), or includes a middleware component (e.g., an application server), or includes a front-end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or includes any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0073] Computing devices may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0074] Although several embodiments have been described, it will be understood that various modifications may be made without departing from the spirit and scope of the invention.

[0075] Additionally, the logic flows depicted in the figures do not require the particular order shown, or sequential order, to achieve desired results. Additionally, other steps may be provided or steps may be eliminated from the described flows, and other components may be added to or removed from the described systems. Accordingly, other embodiments are within the scope of the following claims.

Claims

1. A computer-implemented method (1000) for measuring the therapeutic effect of a medical drug (10d) against a disease, comprising: Obtaining (1100) a disease progression model (200) for the disease, the disease progression model (200) being based on historical covariates and clinical outcome data reflecting the progression of the disease for a plurality of patients affected by the disease, the disease progression model quantitatively describing the time course (210) of disease progression in terms of one or more corresponding covariates; receiving (1200) a target trial dataset (310) having trial covariates (tc) and clinical outcome data (tco) obtained from a plurality of human patients (300) participating in a targeted trial, the targeted trial including at least one treatment group (301) in which the human patients are receiving an experimental treatment (11t) and a control group (302) in which the patients are not receiving the experimental treatment (11nt); Generating (1300) an artificial patient dataset (303), comprising: by filtering the artificial patient dataset (303) according to the inclusion / exclusion criteria of the target study using the distribution of one or more corresponding covariates and their correlations derived from the set of study covariates (tc) such that data records associated with artificial patients (303-1, 303-2) that do not meet the inclusion criteria of the target study or that meet the exclusion criteria of the target study are removed from the artificial patient dataset (303); or by randomly sampling the test covariates (tc) with replacement, with each data record of the artificial patient data set (303) storing the covariates of a respective artificial patient; generating an artificial patient dataset; using said artificial patient dataset (303) as input for said disease progression model (200) to generate (1400) a simulated dataset (320) having simulated covariates (sc) and simulated clinical outcome data (sco) for an experimentally untreated artificial patient; determining (1500) the therapeutic effect (10d-te) of the drug (10d) by jointly analyzing the test dataset (310) and the simulated dataset (320) using a power prior approach (131) to incorporate the simulated dataset (310) as prior information, wherein the simulated dataset (320) is weighted relative to the control group of the test dataset (310), the weight being based at least on a maximum weight value (230-1) received from a user (1); A method comprising:

2. 2. The method of claim 1, wherein the given weight is further based on a similarity between the simulated clinical outcome data (sco) for an artificial patient not receiving an experimental treatment and the clinical outcome data (tco) obtained from the control group of the target trial, the similarity being obtained by using a dynamic utilization method with higher similarity resulting in a higher dynamic utilization weight value, and the given weight is the lower of the maximum weight value received and the obtained dynamic utilization weight value.

3. The maximum weight value is the number of patients used to develop said disease progression model; Similarity of patients used to develop the disease progression model and target study patients, and assumptions made to extrapolate from one population to another; a predetermined risk of concluding that a drug is working when it is not working, obtained by using a sensitivity analysis performed on the disease progression model based on the historical data; the accuracy of the estimates of said disease progression model; As a result of model validation, the scale of said targeted test; The method according to claim 1 or 2, based on any one of the following:

4. The method according to any one of claims 1 to 3, wherein the clinical outcome is a measure referring to the occurrence of a disease, symptom, sign or laboratory abnormality that constitutes the target outcome of the clinical trial.

5. The clinical outcome for a particular patient is the time from when the study begins until the disease progresses or the patient dies; loss of functional lung capacity measured as the difference in the volume the patient can exhale at the beginning of the study and at the end of the study; clinical remission at week X for a duration of X weeks, 12 weeks induction, and 52 weeks remission assessed by Mayo component subscore; clinical remission at week X for a duration of X weeks, 12 weeks induction, and 52 weeks remission; or enhanced endoscopic response at week X for a duration of X weeks, 12 weeks induction, and 52 weeks remission; annualized rate of decline in forced vital capacity over X weeks for up to 52 weeks after initiation of treatment in patients with SSc-ILD; 5. The method of claim 4, wherein the effect of drug Y compared to placebo for achieving NASH resolution on liver histology in patients with non-cirrhotic NASH at baseline and 52 week measurement periods; change from baseline to week 40 in best corrected visual acuity score at the mean of weeks 36 and 40 as assessed using the Early Treatment Diabetic Retinopathy Study visual acuity chart at a starting distance of 4 meters; or survival or progression-free survival for a period of Z years.

6. One or more corresponding covariates one or more trends in the development of disease symptoms over time; variability in disease progression among patients; Quantitative description of the relationships between patient, disease, treatment characteristics and disease progression dynamics; The method according to any one of claims 1 to 5, comprising one or more of the following:

7. 7. The method of any one of claims 1 to 6, wherein the distribution of treatment effects (10d-te) is calculated as the difference in change from baseline in the measured clinical outcome between each treatment group and a control group.

8. A computer program product for measuring the therapeutic effect of a medical drug (10d) on a disease, the computer program product, when loaded into a memory of a computing device and executed by at least one processor of the computing device, causes the at least one processor to perform the steps of the computer-implemented method according to any one of claims 1 to 7.

9. A computer system (100) for measuring the therapeutic effect of a drug (10d) on a disease, comprising: one or more interfaces (140) configured to obtain a disease progression model (200) for the disease, the disease progression model (200) being based on historical covariates and clinical outcome data reflecting the progression of the disease for a plurality of patients affected by the disease, the disease progression model quantitatively describing a time course of disease progression (210) by one or more corresponding covariates, the one or more interfaces further configured to receive a target trial dataset (310) having test covariates (tc) and clinical outcome data (tco) obtained from a plurality of human patients (300) participating in a targeted trial, the target trial including at least one treatment group (301) in which human patients are receiving an experimental treatment (11t) and a control group (302) in which patients are not receiving the experimental treatment (11nt); An artificial patient generator module (110) configured to create an artificial patient data set (303), comprising: by filtering the artificial patient dataset (303) according to the inclusion / exclusion criteria of the target study using the distribution of the one or more corresponding covariates and their correlations derived from the set of study covariates (tc) such that data records associated with artificial patients (303-1, 303-2) that do not meet the inclusion criteria of the target study or that meet the exclusion criteria of the target study are removed from the artificial patient dataset (303); or by randomly sampling the test covariates (tc) with replacement, with each data record of the artificial patient data set (303) storing the covariates of a respective artificial patient; an artificial patient generator module configured to create an artificial patient generator module for generating an artificial patient; said disease progression model (200) configured to use said artificial patient dataset (303) as input to generate a simulated dataset (320) having simulated covariates (sc) and simulated clinical outcome data (sco) for an experimentally untreated artificial patient; a test analyzer module (130) configured to determine the therapeutic effect (10d-te) of the drug (10d) by analyzing the test data set (310) and the simulated data set (320) together using a power prior module (131) to incorporate the simulated data set (310) as prior information, wherein the simulated data set (320) is weighted relative to the control group of the test data set (310), the weighting being based on at least a maximum weighting value (230-1) received from a user (1); 2. A computer system comprising:

10. 10. The computer system of claim 9, wherein the given weight is further based on a similarity between the simulated clinical outcome data (sco) for an artificial patient not receiving an experimental treatment and the clinical outcome data (tco) obtained from the control group of the target trial, the similarity being obtained by using a dynamic utilization method with higher similarity resulting in a higher dynamic utilization weight value, and the given weight is the lower of the maximum weight value received and the obtained dynamic utilization weight value.

11. The maximum weight value is the number of patients used to develop said disease progression model; a predetermined risk of concluding that a drug is working when it is not working, obtained by using a sensitivity analysis performed on the disease progression model based on the historical data; Similarity of patients used to develop the disease progression model and target study patients, and assumptions made to extrapolate from one population to another; the accuracy of the estimates of said disease progression model; As a result of model validation, the size of the targeted trial; 11. The computer system according to claim 9 or 10,

12. The computer system according to any one of claims 9 to 11, wherein the clinical outcome is a measure referring to the occurrence of a disease, symptom, sign or laboratory abnormality that constitutes the target outcome of the clinical trial.

13. The clinical outcome for a particular human patient is the time from when the study begins until the disease progresses or the human patient dies; loss of functional lung capacity measured as the difference in the volume the human patient can exhale at the beginning of the study and at the end of the study; clinical remission at week X for a duration of X weeks, 12 weeks induction phase, and 52 weeks remission, as assessed by Mayo component subscores; clinical remission at week X for a duration of X weeks, 12 weeks induction phase, and 52 weeks remission; or enhanced endoscopic response at week X for a duration of X weeks, 12 weeks induction phase, and 52 weeks remission; or effortful pulmonary function over X weeks for up to 52 weeks after initiation of dosing in patients with SSc-ILD.

13. The computer system of claim 12, wherein the computer system is associated with one of the following: annualized rate of decline in physical activity; improvement of at least one stage of fibrosis without worsening of NASH using the NASH Clinical Research Network scoring system over an 18-month period; effect of drug Y compared to placebo in achieving NASH resolution on liver histology in patients with non-cirrhotic NASH at baseline and 52-week measurement periods; change from baseline to week 40 in best corrected visual acuity score averaged at weeks 36 and 40 as assessed using the Early Treatment Diabetic Retinopathy Study Visual Acuity Chart at a starting distance of 4 meters; survival or progression-free survival over a period of Z years.

14. One or more corresponding covariates one or more trends in the development of disease symptoms over time; variability in disease progression among patients; Quantitative description of the relationships between patient, disease, treatment characteristics and disease progression dynamics; A computer system according to any one of claims 9 to 13, comprising one or more of the following:

15. 15. The computer system of claim 9, wherein the distribution of treatment effects (10d-te) is calculated as the difference in change from baseline in the measured clinical outcome between each treatment group and a control group.

Images