Targeting individuals with optimal safe and effective doses by applying complex adaptive systems metrology to functional brain imaging data and other action variable data
Methods and systems are described for a computer-implemented complex adaptive systems metrology (CASM) technique for generating universally and mathematically standardized scores that quantify longitudinal evidence for either temporal-interaction scores or temporal-interaction benefit-and-harm scores to determine a quantitative significance estimate of scores for either standardized temporal-interaction scores or the standardized temporal-interaction benefit-and-harm scores.
1 . A complex adaptive systems metrology (CASM) system for processing functional brain imaging data, the system comprising:
at least one processing device; and
memory storing instructions that when executed cause the at least one processing device to perform operations comprising:
receiving multivariate time-series functional brain imaging data associated with an individual including at least multivariate time-series action variables representing the individual;
pre-processing the multivariate time-series functional brain imaging data;
digitizing each time-series action variable in the pre-processed multivariate time-series functional brain imaging data that has more than two levels to a set of digital time series comprised of zeros and ones to generate analysis parameters;
computing, based on the digitized multivariate time-series functional brain imaging data and the analysis parameters, temporal-interaction scores that quantify evidence for functional or effective connectivity between regions of interest in the brain of the individual;
generating, for a diagnosis or a treatment response for the individual, temporal-interaction phenotypes based on the temporal-interaction scores that account for individual differences, complexity, adaptivity, stochasticity, emergence, and non-linearity in the connectivity between regions of interest in the brain of the individual;
using the generated temporal-interaction phenotypes and the multivariate time-series functional brain imaging data to improve targeting of a drug treatment to the individual, the improvement including evaluating effectiveness and safety of the drug treatment for the individual by monitoring changes in brain connectivity patterns of the individual over time;
targeting the drug treatment to the individual at a determined safe and effective dose according to the evaluating;
generating a recommendation for administering the targeted drug treatment to the individual at the determined safe and effective dose; and
administering the drug treatment to the individual at the targeted safe and effective dose.
2 . The system of claim 1 , further comprising using the temporal-interaction phenotypes to improve diagnoses of chronic disorders by identifying patterns of brain connectivity associated with predefined signs or symptoms of at least one of the chronic disorders.
3 . The system of claim 1 , wherein the temporal-interaction phenotypes are derived from multivariate time series data that includes functional magnetic resonance imaging (fMRI) data or electroencephalography (EEG) data.
4 . The system of claim 1 , wherein the temporal-interaction scores are derived from functional connectivity data obtained through functional magnetic resonance imaging (fMRI) or electroencephalography (EEG).
5 . The system of claim 1 , further comprising using the temporal-interaction phenotypes to identify genetic markers for early detection of neurological or neuropsychiatric diseases based at least in part on analyzing longitudinal fMRI data.
6 . The system of claim 1 , further comprising using the temporal-interaction phenotypes to generate a personalized treatment plan for the individual by identifying treatment options based on one or more patterns associated with the connectivity between regions of interest in the brain of the individual.
7 . The system of claim 1 , further comprising estimating a quantitative significance of the temporal-interaction scores relative to a null hypothesis.
8 . The system of claim 7 , further comprising a user interface configured to display the temporal-interaction phenotypes and the estimated quantitative significance in a format that facilitates clinical decision making.
9 . The system of claim 7 , wherein the system is integrated with an electronic health record (EHR) system to provide clinicians with real-time access to the temporal-interaction phenotypes and associated quantitative significance estimates.
10 . The system of claim 1 , wherein the temporal-interaction phenotypes are generated for a treatment response to a treatment comprising one or more of: the drug, a dietary component, a type of exercise, a task, or a control of environmental exposure.
11 . The system of claim 10 , wherein the control of environmental exposure comprises: a control to one or more allergens or one or more pollutants.
12 . The system of claim 1 , wherein the quantified evidence for functional or effective connectivity between regions of interest in the brain comprises comparing a predefined healthy function versus disordered or diseased function of the individual.
13 . The system of claim 12 , further comprising: using the quantified evidence to diagnose one of: a neuropsychiatric disorder, a chronic disorder, and a mechanism of traumatic brain injury.
14 . The system of claim 1 , further comprising:
predicting, based on the temporal-interaction phenotypes, a treatment response for the individual, the treatment response indicating an up-regulation or down-regulation of one or more mechanisms associated with temporal interactions in the temporal-interaction scores.
15 . The system of claim 1 , wherein the temporal-interaction scores further account for:
an importance of individual differences associated with the connectivity between regions of interest in the brain of the individual as compared to another individual;
a stochasticity associated with the connectivity between regions of interest in the brain of the individual;
a plurality of nested time scales associated with activity over time for the connectivity between regions of interest in the brain of the individual; and
an emergence associated with brain-behavior relationships occurring during the activity.
16 . The system of claim 1 , wherein the multivariate time-series functional brain imaging data includes repeated measurement data comprising streaming data.
17 . The system of claim 1 , further comprising:
computing, based on the digitized multivariate time-series functional brain imaging data and the analysis parameters, temporal-interaction benefit-and-harm scores, wherein:
the multivariate time-series functional brain imaging data further includes time-series information about aspects corresponding to an environment associated with the multivariate time-series functional brain imaging data; and
generating the temporal-interaction phenotypes for the diagnosis or the treatment response is further based on the environment associated with the multivariate time-series functional brain imaging data, temporal-interaction phenotypes based on the temporal-interaction scores and on the temporal-interaction benefit-and-harm scores that account for the individual differences, the complexity, the adaptivity, the stochasticity, the emergence, and the non-linearity in the connectivity between regions of interest in the brain of the individual.
18 . The system of claim 17 , further comprising: assessing, based on the time-series information about aspects corresponding to the environment associated with the multivariate time-series functional brain imaging data, a response on brain region activity.
19 . The system of claim 17 , further comprising: assessing, based on the time-series information about aspects corresponding to the environment associated with the multivariate time-series functional brain imaging data, a functional connectivity between one or more portions of a brain of the individual.
20 . The system of claim 17 , wherein the environment associated with the multivariate time-series functional brain imaging data represents administration of the treatment to the individual.
21 . The system of claim 1 , further comprising:
determining a plurality of bidirectional temporal-interaction difference scores of the complex adaptive system;
estimating complex adaptive systems metrology (CASM) causal quantitative significance of the plurality of bidirectional temporal-interaction difference scores;
determining, based on the estimated causal quantitative significance, causal evidence associated with the temporal-interaction phenotypes for time-asymmetry of causation in the complex adaptive system;
monitoring at least one of the temporal-interaction phenotypes corresponding to at least one of the multivariate time-series action variables associated with the multivariate time-series functional brain imaging data;
estimating, based on the monitoring, a quantitative significance of the causal evidence; and
using the estimated quantitative significance of the causal evidence to improve decision making corresponding to a behavior associated with the complex adaptive system.
22 . The system of claim 21 , wherein the behavior is associated with a neuropsychiatric disorder, a chronic disorder, or a brain injury.
23 . The system of claim 21 , wherein estimating the quantitative significance of the causal evidence comprises:
processing a first time-series dataset A and a second time-series dataset B with an operationally defined and transparent CASM scoring protocol to determine a dataset-A-to-dataset-B temporal interaction summary score based at least in part on the plurality of bidirectional temporal-interaction difference scores;
modifying the time-series dataset B to operate as an independent or predictor action variable and modifying the time-series dataset A to operate as a dependent or predicted action variable;
processing the modified time-series dataset B and the modified time-series dataset A to determine a dataset-B-to-dataset-A temporal interaction summary score; and
determining causal evidence for time-asymmetry of causation in the complex adaptive system by differencing the dataset-A-to-dataset-B temporal interaction summary score and the dataset-B-to-dataset-A temporal interaction summary score.
24 . A computer-implemented complex adaptive systems metrology (CASM) method for processing functional brain imaging data, the method being executed by at least one processing device and memory storing instructions that when executed by the at least one processing device cause the at least one processing device to perform operations comprising:
receiving multivariate time-series functional brain imaging data associated with an individual including at least multivariate time-series action variables representing the individual;
pre-processing the multivariate time-series functional brain imaging data;
digitizing each time-series action variable in the pre-processed multivariate time-series functional brain imaging data that has more than two levels to a set of digital time series comprised of zeros and ones to generate analysis parameters;
computing, based on the digitized multivariate time-series functional brain imaging data and the analysis parameters, temporal-interaction scores that quantify evidence for functional or effective connectivity between regions of interest in the brain of the individual;
using the computed temporal-interaction scores and the multivariate time-series action variables to evaluate treatment safety and effectiveness by determining mechanisms of treatment effect, target treatment types, and treatment doses for the individual;
targeting the treatment to the individual at a safe and effective dose according to the evaluation;
generating a recommendation for administering the targeted treatment to the individual at the safe and effective dose; and
administering the treatment to the individual at the targeted safe and effective dose, according to the generated recommendation.
25 . The method of claim 24 , further comprising:
generating, for a diagnosis or a treatment response, temporal-interaction phenotypes based on the temporal-interaction scores that account for individual differences, complexity, adaptivity, stochasticity, emergence, and non-linearity in the connectivity between regions of interest in the brain of the individual; and
using the temporal-interaction phenotypes to improve diagnoses of chronic disorders by identifying patterns of brain activity associated with predefined signs or symptoms of at least one of the chronic disorders.
26 . The method of claim 25 , wherein the temporal-interaction phenotypes are derived from multivariate time series data that includes functional magnetic resonance imaging (fMRI) data or electroencephalography (EEG) data.
27 . The method of claim 25 , wherein the temporal-interaction scores are derived from functional connectivity data obtained through functional magnetic resonance imaging (fMRI) or electroencephalography (EEG).
28 . The method of claim 25 , further comprising using the temporal-interaction phenotypes to identify genetic markers for early detection of neurological or neuropsychiatric diseases based at least in part on analyzing longitudinal fMRI data.
29 . The method of claim 25 , further comprising using the temporal-interaction phenotypes to generate a personalized treatment plan for the individual by identifying treatment options based on one or more patterns associated with the connectivity between regions of interest in the brain of the individual.
30 . The method of claim 25 , further comprising estimating a quantitative significance of the temporal-interaction scores relative to a null hypothesis.
31 . The method of claim 30 , further comprising a user interface configured to display the temporal-interaction phenotypes and the estimated quantitative significance in a format that facilitates clinical decision making.
32 . The method of claim 30 , wherein the system is integrated with an electronic health record (EHR) system to provide clinicians with real-time access to the temporal-interaction phenotypes and associated quantitative significance estimates.
33 . The method of claim 25 , wherein the temporal-interaction phenotypes are generated for a treatment response to a treatment comprising one or more of: a drug, a dietary component, a type of exercise, a task, or a control of environmental exposure.
34 . The method of claim 33 , wherein the control of environmental exposure comprises: a control to one or more allergens or one or more pollutants.
35 . The method of claim 24 , wherein quantified evidence for functional or effective connectivity between regions of interest in the brain comprises comparing a predefined healthy function versus disordered or diseased function of the individual.
36 . The method of claim 35 , further comprising using the quantified evidence to diagnose one of: a neuropsychiatric disorder, a chronic disorder, and a mechanism of traumatic brain injury.
37 . The method of claim 25 , further comprising:
predicting, based on the temporal-interaction phenotypes, a treatment response for the individual, the treatment response indicating an up-regulation or down-regulation of one or more mechanisms associated with temporal interactions in the temporal-interaction scores.
38 . The method of claim 24 , wherein the temporal-interaction scores further account for:
an importance of individual differences associated with the connectivity between regions of interest in the brain of the individual as compared to another individual;
a stochasticity associated with the connectivity between regions of interest in the brain of the individual;
a plurality of nested time scales associated with activity over time for the connectivity between regions of interest in the brain of the individual; and
an emergence associated with brain-behavior relationships occurring during the activity.
39 . The method of claim 24 , wherein the multivariate time-series functional brain imaging data includes repeated measurement data comprising streaming data.
40 . The method of claim 25 , further comprising:
computing, based on the digitized multivariate time-series functional brain imaging data and the analysis parameters, temporal-interaction benefit-and-harm scores, wherein:
the multivariate time-series functional brain imaging data further includes time-series information about aspects corresponding to an environment associated with the multivariate time-series functional brain imaging data; and
generating the temporal-interaction phenotypes for the diagnosis or the treatment response is further based on the environment associated with the multivariate time-series functional brain imaging data, temporal-interaction phenotypes based on the temporal-interaction scores and on the temporal-interaction benefit-and-harm scores that account for the individual differences, the complexity, the adaptivity, the stochasticity, the emergence, and the non-linearity in the connectivity between regions of interest in the brain of the individual.
41 . The method of claim 40 , further comprising:
assessing, based on the time-series information about aspects corresponding to the environment associated with the multivariate time-series functional brain imaging data, a response on brain region activity.
42 . The method of claim 40 , further comprising:
assessing, based on the time-series information about aspects corresponding to the environment associated with the multivariate time-series functional brain imaging data, a functional connectivity between one or more portions of a brain of the individual.
43 . The method of claim 40 , wherein the environment associated with the imaging data represents administration of the treatment individual.
44 . The method of claim 25 , further comprising:
determining a plurality of bidirectional temporal-interaction difference scores of the complex adaptive system;
estimating complex adaptive systems metrology (CASM) causal quantitative significance of the plurality of bidirectional temporal-interaction difference scores;
determining, based on the estimated causal quantitative significance, causal evidence associated with the temporal-interaction phenotypes for time-asymmetry of causation in the complex adaptive system;
monitoring at least one of the temporal-interaction phenotypes corresponding to at least one of the multivariate time-series action variables associated with the multivariate time-series functional brain imaging data;
estimating, based on the monitoring, a quantitative significance of the causal evidence; and
using the estimated quantitative significance of the causal evidence to improve decision making corresponding to a behavior associated with the complex adaptive system.
45 . The method of claim 44 , wherein the behavior is associated with a neuropsychiatric disorder, a chronic disorder, or a brain injury.
46 . The method of claim 44 , wherein estimating the quantitative significance of the causal evidence comprises:
processing a first time-series dataset A and a second time-series dataset B with an operationally defined and transparent CASM scoring protocol to determine a dataset-A-to-dataset-B temporal interaction summary score based at least in part on the plurality of bidirectional temporal-interaction difference scores;
modifying the time-series dataset B to operate as an independent or predictor action variable and modifying the time-series dataset A to operate as a dependent or predicted action variable;
processing the modified time-series dataset B and the modified time-series dataset A to determine a dataset-B-to-dataset-A temporal interaction summary score; and
determining causal evidence for time-asymmetry of causation in the complex adaptive system by differencing the dataset-A-to-dataset-B temporal interaction summary score and the dataset-B-to-dataset-A temporal interaction summary score.
47 . A non-transitory computer-readable medium for a complex adaptive systems metrology (CASM) for processing functional brain imaging data, comprising:
at least one processor; and
a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving multivariate time-series functional brain imaging data associated with an individual undergoing a drug treatment, the multivariate time-series functional brain imaging data including at least multivariate time-series action variables representing the individual and time-series information about aspects corresponding to an environment associated with the multivariate time-series functional brain imaging data;
pre-processing the multivariate time-series functional brain imaging data;
digitizing each time-series action variable in the pre-processed multivariate time-series functional brain imaging data that has more than two levels to a set of digital time series comprised of zeros and ones to generate analysis parameters;
computing, based on the digitized multivariate time-series functional brain imaging data and the analysis parameters, temporal-interaction scores that quantify evidence for functional or effective connectivity between regions of interest in the brain of the individual;
generating, for a diagnosis or a treatment response for the individual and based on the environment associated with the multivariate time-series functional brain imaging data, temporal-interaction phenotypes based on the temporal-interaction scores that account for individual differences, complexity, adaptivity, stochasticity, emergence, and non-linearity in the connectivity between regions of interest in the brain of the individual;
using the generated temporal-interaction phenotypes and the multivariate time-series functional brain imaging data to evaluate effectiveness and safety of a drug treatment for the individual by monitoring changes in brain connectivity patterns of the individual over time;
targeting the drug treatment to the individual at a determined safe and effective dose according to the evaluating; and
administering the drug treatment to the individual at the targeted safe and effective dose.
48 . The non-transitory computer-readable medium of claim 47 , further comprising using the temporal-interaction phenotypes to improve diagnoses of chronic disorders by identifying patterns of connectivity associated with predefined signs or symptoms of at least one of the chronic disorders.
49 . The non-transitory computer-readable medium of claim 47 , wherein the temporal-interaction phenotypes are derived from multivariate time series data that includes functional magnetic resonance imaging (fMRI) data or electroencephalography (EEG) data.
50 . The non-transitory computer-readable medium of claim 47 , wherein the temporal-interaction scores are derived from functional connectivity data obtained through functional magnetic resonance imaging (fMRI) or electroencephalography (EEG).
51 . The non-transitory computer-readable medium of claim 47 , further comprising using the temporal-interaction phenotypes to identify genetic markers for early detection of neurological diseases based at least in part on analyzing longitudinal fMRI data.
52 . The non-transitory computer-readable medium of claim 47 , further comprising using the temporal-interaction phenotypes to generate a personalized treatment plan for the individual by identifying treatment options based on one or more patterns associated with the connectivity between regions of interest in the brain of the individual.
53 . The non-transitory computer-readable medium of claim 47 , further comprising estimating a quantitative significance of the temporal-interaction scores relative to a null hypothesis.
54 . The non-transitory computer-readable medium of claim 53 , further comprising a user interface configured to display the temporal-interaction phenotypes and quantitative significance estimates in a format that facilitates clinical decision making.
55 . The non-transitory computer-readable medium of claim 53 , wherein the system is integrated with an electronic health record (EHR) system to provide clinicians with real-time access to the temporal-interaction phenotypes and associated quantitative significance estimates.
56 . The non-transitory computer-readable medium of claim 47 , wherein the temporal-interaction phenotypes are generated for a treatment response to a treatment comprising one or more of: a drug, a dietary component, a type of exercise, a task, or a control of environmental exposure.
57 . The non-transitory computer-readable medium of claim 56 , wherein the control of environmental exposure comprises: a control to one or more allergens or one or more pollutants.
58 . The non-transitory computer-readable medium of claim 47 , wherein the quantified evidence for functional or effective connectivity between regions of interest in the brain comprises comparing a predefined healthy function versus disordered or diseased function of the individual.
59 . The non-transitory computer-readable medium of claim 58 , further comprising using the quantified evidence to diagnose one of: a neuropsychiatric disorder, a chronic disorder, and a mechanism of traumatic brain injury.
60 . The non-transitory computer-readable medium of claim 47 , further comprising:
predicting, based on the temporal-interaction phenotypes, a treatment response for the individual, the treatment response indicating an up-regulation or down-regulation of one or more mechanisms associated with temporal interactions in the temporal-interaction scores.
61 . The non-transitory computer-readable medium of claim 47 , wherein the temporal-interaction scores further account for:
an importance of individual differences associated with the connectivity between regions of interest in the brain of the individual as compared to another individual;
a stochasticity associated with the connectivity between regions of interest in the brain of the individual;
a plurality of nested time scales associated with activity over time for the connectivity between regions of interest in the brain of the individual; and
an emergence associated with brain-behavior relationships occurring during the activity.
62 . The non-transitory computer-readable medium of claim 47 , wherein the multivariate time-series functional brain imaging data includes repeated measurement data comprising streaming data.
63 . The non-transitory computer-readable medium of claim 47 , wherein the environment associated with the imaging data represents administration of the treatment to the individual.
64 . The non-transitory computer-readable medium of claim 47 , further comprising:
determining a plurality of bidirectional temporal-interaction difference scores of the complex adaptive system;
estimating complex adaptive systems metrology (CASM) causal quantitative significance of the plurality of bidirectional temporal-interaction difference scores;
determining, based on the estimated causal quantitative significance, causal evidence associated with the temporal-interaction phenotypes for time-asymmetry of causation in the complex adaptive system;
monitoring at least one of the temporal-interaction phenotypes corresponding to at least one of the multivariate time-series action variables associated with the multivariate time-series functional brain imaging data;
estimating, based on the monitoring, a quantitative significance of the causal evidence; and
using the estimated quantitative significance of the causal evidence to improve decision making corresponding to a behavior associated with the complex adaptive system.
65 . The non-transitory computer-readable medium of claim 64 , wherein the behavior or treatment is associated with a neuropsychiatric disorder, a chronic disorder, or a brain injury.
66 . The non-transitory computer-readable medium of claim 64 , wherein estimating the causal quantitative significance of the causal evidence comprises:
processing a first time-series dataset A and a second time-series dataset B with an operationally defined and transparent CASM scoring protocol to determine a dataset-A-to-dataset-B temporal interaction summary score based at least in part on the plurality of bidirectional temporal-interaction difference scores;
modifying the time-series dataset B to operate as an independent or predictor action variable and modifying the time-series dataset A to operate as a dependent or predicted action variable;
processing the modified time-series dataset B and the modified time-series dataset A to determine a dataset-B-to-dataset-A temporal interaction summary score; and
determining causal evidence for time-asymmetry of causation in the complex adaptive system by differencing the dataset-A-to-dataset-B temporal interaction summary score and the dataset-B-to-dataset-A temporal interaction summary score.