# US 12,002,553 B2 · Systems and methods for designing clinical trials > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,553 B2 - Document ID: US12002553B2 - Status: Granted - Kind: B2 - Application number: 17/493,506 - Filed: 2021-10-04 - Published: 2022-05-05 - Granted: 2024-06-04 - Earliest claimed: 2018-10-02 - Assignees: Origent Data Sciences, Inc. - Applicants: Origent Data Sciences, Inc. - Inventors: David L. Ennist; Albert A. Taylor; Danielle E. Beaulieu; Michael A. Keymer - Web page: https://patentgrep.com/patent/US12002553B2 ## CPC - G16H 10/20: for electronic clinical trials or questionnaires - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 50/30: for calculating health indices; for individual health risk assessment - G16H 50/50: for simulation or modelling of medical disorders - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A method for enrolling patient candidates in a clinical trial includes generating first prediction data indicating predicted progression of a condition for a first group of patients that participated in a first clinical trial using a predictive model and clinical data associated with the first group of patients; grouping clinical trial data into subsets based on the first prediction data; analyzing each subset of clinical trial data to generate a measure of efficacy of the treatment; establishing screening criteria for a second clinical trial by identifying at least one subset that has a measure of efficacy that is higher than a measure of efficacy of the treatment for the full first group of patients; receiving clinical data of a candidate for the second clinical trial; generating second prediction data for the candidate; and enrolling the candidate in the second clinical trial when the second prediction data satisfies the screening criteria. ## Claims ### Claim 1 A method for determining a treatment for a condition, the method comprising, at a computing system: computing, for a first group of patients that participated in a clinical trial for the treatment for the condition, predictions for at least one condition progress metric that indicate predicted progression of the condition for the first group of patients, wherein the predictions for the at least one condition progress metric are computed via a machine learning predictive model and clinical data associated with the first group of patients, wherein the machine learning predictive model was trained on clinical data associated with a second group of patients having the condition; grouping clinical trial data associated with the first group of patients into a plurality of subsets of clinical trial data based on the predictions for the at least one condition progress metric, wherein each subset of clinical trial data is associated with a corresponding subgroup of the first group of patients; for each subset of clinical trial data, computing a measure of efficacy of the treatment for a subgroup of patients corresponding to the respective subset; identifying at least one subset of the plurality of subsets that has a measure of efficacy that is higher than a measure of efficacy of the treatment for the full first group of patients; and determining a treatment for the condition based on a range of values for the predictions for the at least one condition progress metric that is associated with the identified at least one subset of the plurality of subsets that has a measure of efficacy that is higher than a measure of efficacy of the treatment for the full first group of patients. ### Claim 2 (depends on 1) The method of claim 1, comprising selecting the machine learning predictive model from a plurality of different machine learning predictive models based on a goal for the treatment. ### Claim 3 (depends on 2) The method of claim 2, comprising training the machine learning predictive model and standardizing the clinical data for the second group of patients prior to training the machine learning predictive model. ### Claim 4 (depends on 1) The method of claim 1, wherein the clinical data associated with the second group of patients comprises historical data for the at least one condition progress metric. ### Claim 5 (depends on 1) The method of claim 1, wherein the clinical data associated with the first group of patients is clinical data generated prior to the clinical trial. ### Claim 6 (depends on 1) The method of claim 1, wherein a number of patients associated with one subset of the plurality of subsets is equal to a number of patients associated with at least one other subset of the plurality of subsets. ### Claim 7 (depends on 1) The method of claim 1, wherein a number of patients associated with one subset of the plurality of subsets is different than a number of patients associated with at least one other subset of the plurality of subsets. ### Claim 8 (depends on 1) The method of claim 1, wherein the measure of efficacy of the treatment is based on the at least one condition progress metric. ### Claim 9 (depends on 1) The method of claim 1, wherein a measure of efficacy of the treatment for the full first group of patients indicates no statistically significant difference in treatment outcome between a control group and a treatment group. ### Claim 10 (depends on 1) The method of claim 1, wherein the measure of efficacy is generated by comparing treatment outcomes for control patients to treatment outcomes for treated patients. ### Claim 11 (depends on 1) The method of claim 1, wherein identifying at least one subset of the plurality of subsets comprises identifying at least one subset that has a measure of efficacy that meets a threshold test. ### Claim 12 (depends on 11) The method of claim 11, wherein the threshold test is a p-value that is no greater than 0.05. ### Claim 13 (depends on 1) The method of claim 1, wherein identifying at least one subset of the plurality of subsets comprises plotting a representation of the measure of efficacy as a function of subgroup size and the predictions for the at least one condition progress metric. ### Claim 14 (depends on 13) The method of claim 13, wherein plotting the representation of the measure of efficacy comprises generating a heat map, wherein a variation in appearance in the heat map indicates a variation in the measure of efficacy. ### Claim 15 (depends on 14) The method of claim 14, wherein the heat map comprises a representation of the measure of efficacy of the treatment for the full group of patients. ### Claim 16 (depends on 14) The method of claim 14, wherein identifying at least one subset of the plurality of subsets comprises identifying a location on the heat map that is surrounded by locations having the same appearance. ### Claim 17 (depends on 1) The method of claim 1, wherein the at least one prediction progress metric comprises predicted patient regression or predicted time to an event. ### Claim 18 (depends on 1) The method of claim 1, wherein the patients are human and the condition is a disease. ### Claim 19 (depends on 18) The method of claim 18, wherein the disease is a neurodegenerative disease or a cancer. ### Claim 20 (depends on 1) The method of claim 1, wherein the first clinical trial is configured to determine at least one of an efficacy of a drug, an efficacy of a different dosage of a drug, or an efficacy of a different combination of drugs. ### Claim 21 (depends on 1) The method of claim 1, comprising treating a patient with the treatment based on a prediction for a condition progress metric for the patient being within the range of values for the predictions for the at least one condition progress metric that is associated with the identified at least one subset of the plurality of subsets that has a measure of efficacy that is higher than a measure of efficacy of the treatment for the full first group of patients. ### Claim 22 (depends on 1) The method of claim 1, wherein determining a treatment comprises determining a dose level. ### Claim 23 A system for enrolling candidates in a clinical trial for a treatment, the system comprising one or more processors, memory, and one or more programs stored in the memory and executable by the one or more processors, the one or more programs including instructions for: computing, for a first group of patients that participated in a clinical trial for the treatment for the condition, predictions for at least one condition progress metric that indicate predicted progression of the condition for the first group of patients, wherein the predictions for the at least one condition progress metric are computed via a machine learning predictive model and clinical data associated with the first group of patients, wherein the machine learning predictive model was trained on clinical data associated with a second group of patients having the condition; grouping clinical trial data associated with the first group of patients into a plurality of subsets of clinical trial data based on the predictions for the at least one condition progress metric, wherein each subset of clinical trial data is associated with a corresponding subgroup of the first group of patients; for each subset of clinical trial data, computing a measure of efficacy of the treatment for a subgroup of patients corresponding to the respective subset; identifying at least one subset of the plurality of subsets that has a measure of efficacy that is higher than a measure of efficacy of the treatment for the full first group of patients; and determining a treatment for the condition based on a range of values for the predictions for the at least one condition progress metric that is associated with the identified at least one subset of the plurality of subsets that has a measure of efficacy that is higher than a measure of efficacy of the treatment for the full first group of patients. ### Claim 24 (depends on 23) The system of claim 23, wherein the one or more programs include instructions for receiving a selection of the machine learning predictive model from a plurality of different machine learning predictive models based on a goal for the treatment. ### Claim 25 (depends on 24) The system of claim 24, wherein the one or more programs include instructions for training the machine learning predictive model and standardizing the clinical data for the second group of patients prior to training the machine learning predictive model. ### Claim 26 (depends on 23) The system of claim 23, wherein the clinical data associated with the second group of patients comprises historical data for the at least one condition progress metric. ### Claim 27 (depends on 23) The system of claim 23, wherein the clinical data associated with the first group of patients is clinical data generated prior to the clinical trial. ### Claim 28 (depends on 23) The system of claim 23, wherein a number of patients associated with one subset of the plurality of subsets is equal to a number of patients associated with at least one other subset of the plurality of subsets. ### Claim 29 (depends on 23) The system of claim 23, wherein a number of patients associated with one subset of the plurality of subsets is different than a number of patients associated with at least one other subset of the plurality of subsets. ### Claim 30 (depends on 23) The system of claim 23, wherein the measure of efficacy of the treatment is based on the at least one condition progress metric. ### Claim 31 (depends on 23) The system of claim 23, wherein a measure of efficacy of the treatment for the full first group of patients indicates no statistically significant difference in treatment outcome between a control group and a treatment group. ### Claim 32 (depends on 23) The system of claim 23, wherein the measure of efficacy is generated by comparing treatment outcomes for control patients to treatment outcomes for treated patients. ### Claim 33 (depends on 23) The system of claim 23, wherein identifying at least one subset of the plurality of subsets comprises identifying at least one subset that has a measure of efficacy that meets a threshold test. ### Claim 34 (depends on 33) The system of claim 33, wherein the threshold test is a p-value that is no greater than 0.05. ### Claim 35 (depends on 23) The system of claim 23, wherein identifying at least one subset of the plurality of subsets comprises plotting a representation of the measure of efficacy as a function of subgroup size and the predictions for the at least one condition progress metric. ### Claim 36 (depends on 35) The system of claim 35, wherein plotting the representation of the measure of efficacy comprises generating a heat map, wherein a variation in appearance in the heat map indicates a variation in the measure of efficacy. ### Claim 37 (depends on 36) The system of claim 36, wherein the heat map comprises a representation of the measure of efficacy of the treatment for the full group of patients. ### Claim 38 (depends on 36) The system of claim 36, wherein identifying at least one subset of the plurality of subsets comprises identifying a location on the heat map that is surrounded by locations having the same appearance. ### Claim 39 (depends on 23) The system of claim 23, wherein the at least one prediction progress metric comprises predicted patient regression or predicted time to an event. ### Claim 40 (depends on 23) The system of claim 23, wherein the patients are human and the condition is a disease. ### Claim 41 (depends on 40) The system of claim 40, wherein the disease is a neurodegenerative disease or a cancer. ### Claim 42 (depends on 23) The system of claim 23, wherein the first clinical trial is configured to determine at least one of an efficacy of a drug, an efficacy of a different dosage of a drug, or an efficacy of a different combination of drugs. ### Claim 43 (depends on 23) The system of claim 23, wherein determining a treatment comprises determining a dose level.