Generating Instructions for Physical Experiments Using Whole Body Digital Twin Technology

Abstract

A Digital Twin clinical trial simulator determines one or more trial parameters for a physical experiment to validate a candidate treatment recommendation. For each of one or more variations of the physical experiment, the Digital Twin clinical trial simulator determines an effectiveness of the variation in validating the candidate treatment recommendation. The effectiveness describes a likelihood that the physical experiment will provide insight regarding the effect of the candidate treatment recommendation on a metabolic state. For a variation that satisfies a threshold effectiveness, the Digital Twin clinical trial simulator determines one or more metabolic features shared among a cohort of patients sensitive to the candidate treatment recommendation. The Digital Twin clinical trial simulator generates instructions for a medical professional to perform a physical experiment by adjusting the trial parameters according to the selected variation and enrolling patients sharing at least one of the one or more metabolic features.

What is claimed is: 
     
         1 . A method comprising:
 determining one or more trial parameters for a physical experiment to validate a candidate treatment recommendation, the one or more trial parameters comprising: a duration of the experiment and a number of patients to be enrolled in the experiment;   for each of one or more variations of the physical experiment, determining an effectiveness of the variation in validating the candidate treatment recommendation, the effectiveness describing a likelihood that the physical experiment will provide insight regarding the effect of the candidate treatment recommendation on a metabolic state;   for a selected variation of the physical experiment satisfying a threshold effectiveness, determining one or more metabolic features shared among a cohort of patients sensitive to the candidate treatment recommendation, the sensitivity of a patient representing a likelihood that adjustments to the one or more intervention parameters will affect the metabolic state of the patient; and   generating instructions for a medical professional to perform the selected variation of the physical experiment by adjusting the trial parameters according to the selected variation and enrolling patients sharing at least one of the one or more metabolic features.   
     
     
         2 . The method of  claim 1 , wherein the one or more trial parameters further comprise:
 a number of intervention parameters adjusted in the candidate treatment recommendation;   adjustments to each intervention parameter;   a composition of patients to be enrolled in the experiment; and   a magnitude of the adjustment to each intervention parameter.   
     
     
         3 . The method of  claim 1 , further comprising:
 identifying the candidate treatment recommendation based on the effectiveness of the candidate treatment recommendation, the effectiveness determined by predicting the effect of each candidate treatment recommendation on a cohort of patients.   
     
     
         4 . The method of  claim 1 , further comprising:
 generating a shortlist of candidate treatment recommendations for validation by a physical experiment; and   generating instructions for a medical professional to perform a physical experiment to validate each candidate treatment recommendation of the shortlist.   
     
     
         5 . The method of  claim 1 , further comprising:
 generating the one or more variations of the physical experiment by adjusting the one or more trial parameters, wherein each variation of the physical experiment represents a distinct combination of the one or more trial parameters.   
     
     
         6 . The method of  claim 1 , wherein determining the effectiveness of the variation comprises:
 identifying a target outcome of the candidate treatment recommendation;   determining an acceptable risk of failure backed on past physical experiments designed to validate candidate treatment recommendations with the same target outcome; and   determining a power calculation for the candidate treatment recommendation based on the acceptable risk of failure.   
     
     
         7 . The method of  claim 1 , wherein determining the one or more metabolic features shared among the cohort of patients sensitive to the candidate treatment recommendation comprises:
 identifying a cohort of patients sensitive to intervention parameters adjusted by the candidate treatment recommendation;   identifying one or more metabolic features shared among all patients in the cohort of patients, wherein patients sharing the one or more metabolic features are predicted to experience improvements in metabolic health by adhering to the candidate treatment recommendation; and   generating instructions for a medical professional to enroll patients in the physical experiment with at least one of the one or more identified metabolic features.   
     
     
         8 . The method of  claim 1 , wherein the one or more metabolic features comprise:
 metabolic features associated with binary values; and   metabolic features associated with a range of values.   
     
     
         9 . The method of  claim 1 , wherein determining the one or more metabolic features shared among the cohort of patients sensitive to the candidate treatment recommendation comprises:
 identifying a cohort of patients sensitive to intervention parameters adjusted by the candidate treatment recommendation;   determining a significance that each metabolic feature has on patients in the cohort of patients;   ranking each of the one or more metabolic features based on the determined significance; and   generating instructions for a medical professional to prioritize enrollment of patients sharing higher ranked metabolic features.   
     
     
         10 . A non-transitory computer-readable medium storing instructions encoded thereon that, when executed by a processor, cause the one or more processor to:
 determine one or more trial parameters for a physical experiment to validate a candidate treatment recommendation, the one or more trial parameters comprising: a duration of the experiment and a number of patients to be enrolled in the experiment;   for each of one or more variations of the physical experiment, determine an effectiveness of the variation in validating the candidate treatment recommendation, the effectiveness describing a likelihood that the physical experiment will provide insight regarding the effect of the candidate treatment recommendation on a metabolic state;   for a selected variation of the physical experiment satisfying a threshold effectiveness, determine one or more metabolic features shared among a cohort of patients sensitive to the candidate treatment recommendation, the sensitivity of a patient representing a likelihood that adjustments to the one or more intervention parameters will affect the metabolic state of the patient; and   generate instructions for a medical professional to perform the selected variation of the physical experiment by adjusting the trial parameters according to the selected variation and enrolling patients sharing at least one of the one or more metabolic features.   
     
     
         11 . The non-transitory computer readable storage medium of  claim 10 , further comprising instructions that cause the processor to:
 identify the candidate treatment recommendation based on the effectiveness of the candidate treatment recommendation, the effectiveness determined by predicting the effect of each candidate treatment recommendation on a cohort of patients.   
     
     
         12 . The non-transitory computer readable storage medium of  claim 10 , further comprising instructions that cause the processor to:
 generate a shortlist of candidate treatment recommendations for validation by a physical experiment; and   generate instructions for a medical professional to perform a physical experiment to validate each candidate treatment recommendation of the shortlist.   
     
     
         13 . The non-transitory computer readable storage medium of  claim 10 , further comprising instructions that cause the processor to:
 generate the one or more variations of the physical experiment by adjusting the one or more trial parameters, wherein each variation of the physical experiment represents a distinct combination of the one or more trial parameters.   
     
     
         14 . The non-transitory computer readable storage medium of  claim 10 , wherein instructions for determining the effectiveness of the variation further comprise instructions that cause the processor to:
 identify a target outcome of the candidate treatment recommendation;   determine an acceptable risk of failure backed on past physical experiments designed to validate candidate treatment recommendations with the same target outcome; and   determine a power calculation for the candidate treatment recommendation based on the acceptable risk of failure.   
     
     
         15 . The non-transitory computer readable storage medium of  claim 10 , wherein instructions for determining the one or more metabolic features shared among the cohort of patients sensitive to the candidate treatment recommendation further comprise instructions that cause the processor to:
 identify a cohort of patients sensitive to intervention parameters adjusted by the candidate treatment recommendation;   identify one or more metabolic features shared among all patients in the cohort of patients, wherein patients sharing the one or more metabolic features are predicted to experience improvements in metabolic health by adhering to the candidate treatment recommendation; and   generate instructions for a medical professional to enroll patients in the physical experiment with at least one of the one or more identified metabolic features.   
     
     
         16 . The non-transitory computer readable storage medium of  claim 10 , wherein instructions for determining the one or more metabolic features shared among the cohort of patients sensitive to the candidate treatment recommendation further comprise instructions that cause the processor to:
 identify a cohort of patients sensitive to intervention parameters adjusted by the candidate treatment recommendation;   determine a significance that each metabolic feature has on patients in the cohort of patients;   rank each of the one or more metabolic features based on the determined significance; and   generate instructions for a medical professional to prioritize enrollment of patients sharing higher ranked metabolic features.   
     
     
         17 . A system comprising:
 one or more processors; and   a non-transitory computer readable medium storing instructions encoded thereon that, when executed by the one or more processors, cause the one or more processors to:
 determine one or more trial parameters for a physical experiment to validate a candidate treatment recommendation, the one or more trial parameters comprising: a duration of the experiment and a number of patients to be enrolled in the experiment; 
 for each of one or more variations of the physical experiment, determine an effectiveness of the variation in validating the candidate treatment recommendation, the effectiveness describing a likelihood that the physical experiment will provide insight regarding the effect of the candidate treatment recommendation on a metabolic state; 
 for a selected variation of the physical experiment satisfying a threshold effectiveness, determine one or more metabolic features shared among a cohort of patients sensitive to the candidate treatment recommendation, the sensitivity of a patient representing a likelihood that adjustments to the one or more intervention parameters will affect the metabolic state of the patient; and 
 generate instructions for a medical professional to perform the selected variation of the physical experiment by adjusting the trial parameters according to the selected variation and enrolling patients sharing at least one of the one or more metabolic features. 
   
     
     
         18 . The system of  claim 17 , further comprising instructions that cause the processor to:
 identify the candidate treatment recommendation based on the effectiveness of the candidate treatment recommendation, the effectiveness determined by predicting the effect of each candidate treatment recommendation on a cohort of patients.   
     
     
         19 . The system of  claim 17 , further comprising instructions that cause the processor to:
 generate the one or more variations of the physical experiment by adjusting the one or more trial parameters, wherein each variation of the physical experiment represents a distinct combination of the one or more trial parameters.   
     
     
         20 . The system of  claim 17 , wherein instructions for determining the effectiveness of the variation further comprise instructions that cause the processor to:
 identify a target outcome of the candidate treatment recommendation;   determine an acceptable risk of failure backed on past physical experiments designed to validate candidate treatment recommendations with the same target outcome; and   determine a power calculation for the candidate treatment recommendation based on the acceptable risk of failure.   
     
     
         21 . The system of  claim 17 , wherein instructions for determining the one or more metabolic features shared among the cohort of patients sensitive to the candidate treatment recommendation further comprise instructions that cause the processor to:
 identify a cohort of patients sensitive to intervention parameters adjusted by the candidate treatment recommendation;   identify one or more metabolic features shared among all patients in the cohort of patients, wherein patients sharing the one or more metabolic features are predicted to experience improvements in metabolic health by adhering to the candidate treatment recommendation; and   generate instructions for a medical professional to enroll patients in the physical experiment with at least one of the one or more identified metabolic features.   
     
     
         22 . The system of  claim 17 , wherein instructions for determining the one or more metabolic features shared among the cohort of patients sensitive to the candidate treatment recommendation further comprise instructions that cause the processor to:
 identify a cohort of patients sensitive to intervention parameters adjusted by the candidate treatment recommendation;   determine a significance that each metabolic feature has on patients in the cohort of patients;   rank each of the one or more metabolic features based on the determined significance; and   generate instructions for a medical professional to prioritize enrollment of patients sharing higher ranked metabolic features.