WO2022251884A1

WO2022251884A1 - Systems and methods for assessment of glucose metabolic health

Info

Publication number: WO2022251884A1
Application number: PCT/US2022/072656
Authority: WO
Inventors: Heyjun PARK; Ahmed Metwally; Michael P. Snyder
Original assignee: The Board Of Trustees Of The Leland Stanford Junior University
Priority date: 2021-05-28
Filing date: 2022-05-31
Publication date: 2022-12-01

Abstract

Systems and methods to assess metabolic health and applications thereof are described. Generally, systems utilize dietary intake data to assess metabolic health such as diabetic diagnostic status, which can be used as a basis to perform interventions and treat individuals.

Description

SYSTEMS AND METHODS FOR ASSESSMENT OF GLUCOSE METABOLIC

HEALTH

CROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Provisional Application Ser. No. 63/194,768, entitled “Systems and Methods for Assessment of Glucose Metabolic Health,” filed May 28, 2021 , which is incorporated herein by reference in its entirety.

FIELD OF TECHNOLOGY

[0002] The disclosure is generally directed to systems and processes to assess glucose metabolism utilizing dietary intake and applications thereof.

BACKGROUND

[0003] One in ten individuals are affected by diabetes, a condition involving abnormal regulation of glycemia (i.e. , the level of sugar or glucose in blood). Standard assessments of glycemia typically utilize single time or average measurements of blood glucose. A few common methods to assess glycemia include measuring fasting plasma glucose (FPG), glycated hemoglobin (HbA1c test), and oral glucose tolerance test (OGTT). In addition, individuals can be tested for their insulin resistance using an insulin suppression test that characterizes the steady-state plasma glucose (SSPG).

[0004] Each glycemia assessment yields different insight. FPG is a measure of glucose levels at a steady state where production of glucose by the liver and kidney needs to match glucose uptake by tissues. Impaired FPG typically results from a mismatch between glucose production and glucose utilization. In contrast, OGTT measures a dynamic response to a glucose load which leads to increased plasma insulin which suppresses hepatic glucose release and stimulates glucose uptake in the peripheral tissues. Impaired pancreatic beta cell function and peripheral insulin resistance, particularly in skeletal muscle, can lead to impaired glucose tolerance (IGT). The ambient glucose concentration determines the rate of formation of HbA1c in erythrocytes which have a lifespan of ~120 days. Accordingly, HbA1c reflects average blood glucose levels over the past 3-4 months. [0005] Insulin resistance is a pathological condition in which cells fail to respond to insulin. Healthy individuals respond to insulin by using the glucose available in the blood stream and inhibit the use of fat for energy, which allows blood glucose to return to the normal range. To perform an insulin suppression test, both glucose and insulin are suppressed from an individual’s bloodstream by intravenous infusion of octreotide. Then, insulin and glucose are infused into the bloodstream at a particular rate and blood glucose concentrations are measured at a number of time checkpoints to determine the ability of the individual to respond to insulin, resulting in a determination of SSPG levels. Subjects with an SSPG of 150 mg/dL or greater are considered insulin-resistant; however, this cutoff can vary depending upon the interpreter.

[0006] Numerous factors impact glucose regulation, including genetics, environmental factors, gut microbiome, and lifestyle. In particular, lifestyle choices such as diet, exercise, and sleep can greatly affect an individual regulation and response to glucose intake. The impact of timing of when these lifestyle choices are made has not been fully assessed, but could be critical to better understanding why some individuals with similar genetics and environmental factors have a higher propensity for developing diabetes.

BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The description and claims will be more fully understood with reference to the following figures and data graphs, which are presented as exemplary embodiments of the invention and should not be construed as a complete recitation of the scope of the invention.

[0008] Fig. 1 provides a process for performing clinical assessments and/or treating an individual based on their dietary intake in accordance with various embodiments. [0009] Fig. 2 provides a flowchart of an exemplary method to construct and train a prediction model such that the model can be utilized to determine an individual’s metabolic health in accordance with various embodiments.

[0010] Fig. 3 provides a flowchart of an exemplary method to indicate an individual’s metabolic health based on the individual’s dietary intake utilizing a constructed and trained prediction model in accordance with various embodiments. [0011] Fig. 4 provides a schematic of a computational processing system in accordance with various embodiments.

[0012] Fig. 5 provides a schematic of the overview of an example to determine metabolic subphenotypes using machine learning models in accordance with various embodiments.

[0013] Fig. 6A provides a table of baseline demographics and lab results of study participants used to build a predictive model in accordance with various embodiments. [0014] Fig. 6B provides glycemia-related test results of study participants in accordance with various embodiments.

[0015] Fig. 7 provides a bar chart showing the percent energy intake of study participants based on intake timing, utilized in accordance with various embodiments. [0016] Figs. 8Ato 8C each provide a data chart depicting principal component analysis results of FlbAIC measurements (Fig. 8A), incretin effect (Fig. 8B), and SSPG (Fig. 8C), generated in accordance with various embodiments.

[0017] Figs. 9A to 9C each provide a bar chart for six meal teams based on individual with normal or pre-diabetes mellitus FlbAIC measurements (Fig. 9A), individuals with normal, intermediate, or dysfunctional incretin effect (Fig. 9B), or individuals that are insulin sensitive or insulin resistant SSPG measurements (Fig. 9C), generated in accordance with various embodiments.

[0018] Fig. 10 provides a table of dietary parameters associated with metabolic health, generated in accordance with various embodiments.

[0019] Figs. 11A to 11 E provide exemplary screen displays and alerts of a dietary intake application in accordance with various embodiments.

DETAILED DESCRIPTION

[0020] Turning now to the drawings and data, systems and methods to assess metabolic health based on dietary intake and applications thereof in accordance with various embodiments are described. In some embodiments, the timing and amount of dietary intake of an individual is measured. Dietary intake can be the amount of energy consumed and/or the amount of a nutrient consumed. In some embodiments, dietary intake measurements are used to compute an indication of an individual’s metabolic health and/or dysfunction. Some embodiments utilize an individual’s metabolic health assessment to perform further clinical assessment and/or treat the individual. In some instances, a clinical assessment can include (but is not limited to) a blood test, medical imaging, blood pressure measurements, electrocardiogram, stress test, an angiogram, or any combination thereof. In some instances, a treatment can include (but is not limited to) alteration of timing and/or amount of dietary intake relative to timing, a medication, a dietary supplement and any combination thereof.

[0021] The present disclosure is based on the discovery of the effect and relationship between dietary intake amount and timing measurements with diabetic pathology. This relationship was discovered via a panel of individuals that were assessed for diabetic pathology and had their dietary intake practice monitored over an extended period of time (see Exemplary Data section). This study revealed that dietary intake practice can estimate propensity for metabolic health and/or dysfunction. In particular, it was discovered that the amount of dietary intake at certain times results in a greater propensity for higher HbA1c levels, incretin dysfunction, and insulin resistance. In various embodiments, computational models utilize dietary intake measurements to assess metabolic health and/or dysfunction.

Dietary Intake Indicative of Metabolic Health

[0022] A process for assessing metabolic health using dietary intake measurements, in accordance with various embodiments of the disclosure is provided in Fig. 1. This process results in assessment of metabolic health and/or dysfunction, which can inform of whether further clinical assessment and/or treatments should be performed.

[0023] In some embodiments, dietary intake measurements are to include an amount of energy consumed in accordance with the time of the day. In some embodiments, energy intake amount is recorded during temporal windows across a day and recorded daily. In some embodiments, percent of daily total energy intake amount is determined for each temporal window.

[0024] In some embodiments, clinical data and/or personal data can be additionally used to indicate metabolic health. In some embodiments, clinical data is to include medical patient data such as (for example) weight, height, heart rate, blood pressure, body mass index (BMI), clinical tests and the like. Personal data can include race/ethnicity, age, sex, and behavior data (e.g., smoking).

[0025] Referring back to Fig. 1 , process 100 begins with obtaining 101 dietary intake measurements of an individual. In some embodiments, an amount of dietary intake is measured throughout the day. Dietary intake can be the amount of energy consumed and/or the amount of a nutrient consumed. Dietary intake measurements can be broken into a plurality of temporal windows or measured continuously. Dietary energy intake can be measured in calories or kilocalories, however any appropriate measurement of energy can be utilized.

[0026] In some embodiments, one or more temporal windows utilized are associated with meal times (e.g., breakfast, lunch, dinner, snack, etc.), but can also be associated with other times of the day. In some embodiments, the temporal windows utilized are specific times throughout the day, and the windows can be equivalent or nonequivalent in length. In some embodiments, the ratio (e.g., percent) of dietary intake is determined. In some embodiments, the ratio of dietary intake is the amount of dietary intake at a particular time to the total amount of dietary intake for a day (i.e. , dietary intake of temporal window divided by the total dietary intake of the day). In some embodiments, the amount of dietary intake among multiple days is combined by a statistical or mathematical method (e.g., summation, daily average). In some embodiments, the variability of dietary intake among multiple days is determined.

[0027] Using the dietary intake measurements, process 100 assesses 103 metabolic health and/or dysfunction. It has been found that the ratio of dietary intake at various timepoints in a day is indicative metabolic health status, including (but not limited to) HbA1 c levels, incretin function, and insulin sensitivity. Accordingly, an individual’s diabetic health and/or propensity for diabetes pathology. In some embodiments, the indicated metabolic health provides an indication of nondiabetic, prediabetes, or type II diabetes. In some embodiments, the indicated metabolic health provides an indication of insulin resistance or insulin sensitivity. In some embodiments, the indicated metabolic health provides an indication of incretin effect (e.g., dysfunctional, normal or intermediate). In some embodiments, correlations and/or prediction models can be developed and utilized to indicate metabolic health. [0028] Having determined an individual’s metabolic health, further clinical assessment can optionally be performed and/or the individual can be treated 105. In some instances, a clinical assessment can include (but is not limited to) a blood test, medical imaging, blood pressure measurements, electrocardiogram, stress test, an angiogram, or any combination thereof. In some instances, a treatment can include (but is not limited to) alteration of timing and/or amount of dietary intake, a medication, a dietary supplement, and any combination thereof.

[0029] Several embodiments are directed towards improving dietary intake timing. It has been discovered that dietary energy intake at certain times is associated with better metabolic health (see Exemplary Data). Specifically, it has been found that higher dietary energy intake in the morning and afternoon is associated with better metabolic health whereas higher dietary energy intake in the evening or in the very early morning is associated with worse metabolic health. Accordingly, in some embodiments, an individual is prescribed a dietary plan increasing dietary energy intake in the afternoon. In some embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake in the evening. In some embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake in the early morning. In some embodiments, an individual is prescribed a dietary plan increasing the ratio of dietary energy intake in the afternoon to dietary energy intake in the evening and/or increasing the ratio of dietary energy intake in the morning to dietary energy intake in the evening. In some embodiments, an individual is prescribed a dietary plan decreasing the ratio of dietary energy intake in the evening to dietary energy intake in the afternoon and/or decreasing the ratio of dietary energy intake in the evening to dietary energy intake in the morning. In some particular embodiments, an individual is prescribed a dietary plan increasing dietary energy intake between 12 noon and 5PM and/or increasing dietary energy intake between 8 AM and 11 AM. In some particular embodiments, an individual is prescribed a dietary plan increasing dietary energy intake between 2PM and 5PM. In some particular embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake after 5PM. In some particular embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake between 5PM and 9PM. In some particular embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake between 5AM and 8AM.

Modeling Metabolic Health Assessment

[0030] A process for constructing and training a computational prediction model to assess metabolic health in accordance with various embodiments of the disclosure is shown in Fig. 2. Process 200 measures 201 dietary intake over time from each individual of a collection of individuals. Dietary intake can be the amount of energy consumed and/or the amount of a nutrient consumed. Dietary energy intake can be measured in calories or kilocalories, but any appropriate unit of dietary energy intake can be utilized. Dietary intake data can include (but is not limited to) timing of dietary intake, frequency of dietary intake, amount of consumed food and beverage items, and/or a ratio amount of dietary intake (e.g. dietary energy intake of within a certain time or meal, divided by the total dietary energy intake of the day).

[0031] In many embodiments, dietary energy intake is measured for a plurality of temporal windows throughout a day. In some embodiments, one or more temporal windows utilized are associated with meal times (e.g., breakfast, lunch, dinner, snack, etc.), but can also be associated with other times of the day. In some embodiments, the temporal windows utilized are specific times throughout the day, and the window duration can be equivalent or nonequivalent in length.

[0032] In particular examples of temporal windows, in some embodiments, temporal windows are set to have a duration of less than one hour, a duration of about one hour, a duration about of two hours, a duration of about three hours, a duration of about four hours, a duration of about five hours, a duration of about six hours, a duration of about eight hours, a duration of about ten hours, a duration of about 12 hours, a duration of greater than 12 hours but less than 24 hours, or any duration therebetween. In some embodiments, temporal windows are set at higher frequency during the daytime (e.g., between 5AM to 9PM) and set as less frequent at nighttime (e.g., 9PM to 5AM). In some embodiments, temporal windows are set as follows: 5AM to 8AM, 8AM to 11AM, 11AM to 2PM, 2PM to 5PM, 5PM to 9PM, and 9PM to 5AM. [0033] In some embodiments, the ratio (e.g., percent) of dietary intake of the total day is determined for each temporal window (i.e., dietary intake of temporal window divided by the total dietary intake of the day). It should be noted, any acceptable total dietary intake amount can be utilized to calculate a ratio, such as (for example) total in 12 hours, total per 24 hours, total per 48 hours, total per 168 hours, etc. In some embodiments, the amount of dietary intake among multiple days is combined by a statistical or mathematical method (e.g., summation, daily average). In some embodiments, the variability of dietary intake among multiple time periods is determined (e.g., variability in particular temporal window, variability per day, etc.).

[0034] A collection of individuals, in accordance with many embodiments, is a group of individuals that has provided dietary intake data and has undergone various metabolic health assessment such that the data is used to construct and train a prediction model to predict metabolic health assessment from the dietary intake data. The number of individuals in a collection can vary, and in some embodiments, having a greater number of individuals will increase the prediction power of a trained computer model. The precise number and composition of individuals will vary, depending on the model to be constructed and trained.

[0035] In several embodiments, the collection of individuals has provided dietary intake data and has undergone various metabolic health assessment. Metabolic health assessments performed can be any assessment associated with metabolic health, including (but not limited to) fasting glucose levels, fasting insulin levels, HbA1c levels, C- peptide levels, oral glucose tolerance test (OGTT), insulin suppression test, beta cell function assessment, incretin effect assessment, lipid panel assessment, lipoprotein panel assessment, liver function panel assessment, inflammation assessment, vitamins/minerals panel assessment, and/or blood pressure assessment. Associations between dietary intake data and metabolic health assessments can be analyzed to best determine which assessments are most correlated with and/or influenced by dietary intake. Analysis that can be performed include (but is not limited to) correlation analysis, principal component analysis (PCA), linear regression analysis, logistic regression analysis, and/or clustering analysis. [0036] Based on studies performed, it has been found that there is an association between dietary intake and metabolic health. Accordingly, dietary intake data features can be utilized within a prediction model. Dietary energy intake data features can be any data related to dietary energy intake, such as (for example) amount of amount of dietary intake, ratio of dietary intake relative to timings, ratio of dietary intake relative to nutrients, or variability of dietary intake. Other features can be included within a prediction model, such as (for example) patient data, age, sex, ethnicity, BMI, fasting glucose levels, fasting insulin levels, HbA1c levels, diabetic diagnostic status, C-peptide levels, etc. To select features to be utilized, various methods can be utilized, such as (for example) correlation analysis, covariance analysis (e.g., PCA), or a machine learning-based computational model (e.g., a linear regression model, LASSO, a random forest regression model, an elastic net model, etc.). In some embodiments, the features that provide predictive power is utilized. In some embodiments, features with predictive power greater than threshold are utilized. In some embodiments, the top features as ranked by predictive power are utilized.

[0037] A prediction model to indicate an individual’s metabolic health is generated 203 using dietary intake data features and metabolic health assessment data. Various embodiments construct and train a model to determine diabetic diagnostic status, insulin resistance, peripheral insulin resistance, hepatic insulin resistance, adipose tissue insulin resistance, beta cell function, incretin effect, oral glucose tolerance, and/or steady-state plasma glucose. Various prediction models can be utilized, including (but not limited to) regression-based or classification-based models. Regression-based models include (but are not limited to) LASSO regression, ridge regression, K-nearest neighbors, elastic net, least angle regression (LAR), and random forest regression. Classification-based models include (but are not limited to) Support Vector Machine (SVM), hierarchical clustering, k- means clustering, decision trees, and naive Bayes. In some embodiments, a prediction model is regularized.

[0038] Models and sets of features used to train a model can be evaluated for their ability to assess metabolic health. By evaluating models, predictive abilities of features can be confirmed. In some embodiments, a portion of the cohort data is withheld to test the model to determine its efficiency and accuracy. A number of accuracy evaluations can be performed, including (but not limited to) area under the receiver operating characteristics (AUROC), R-square error analysis, root mean square error analysis, and hyperplane in dimensional space analysis. In some embodiments, the contribution of each feature to the ability to predict outcome is determined. In some embodiments, top contributing features are utilized to construct the model. Accordingly, an optimized model can be identified.

[0039] Process 200 also outputs 205 the parameters of a prediction model indicative of metabolic health. Prediction models can be used to assess metabolic health, diabetic status, inform disease risk, and inform potential treatment strategies, as will be described in detail below.

[0040] While specific examples of processes for constructing and training a prediction model to assess an individual’s metabolic health are described above, one of ordinary skill in the art can appreciate that various steps of the process can be performed in different orders and that certain steps may be optional according to some embodiments of the invention. As such, it should be clear that the various steps of the process could be used as appropriate to the requirements of specific applications. Furthermore, any of a variety of processes for constructing and training a prediction model appropriate to the requirements of a given application can be utilized in accordance with various embodiments of the disclosure.

[0041] A constructed and trained prediction model can be used to compute an assessment of an individual’s metabolic health and/or dysfunction. As shown in Fig. 3, a method to assess an individual’s metabolic health using a trained prediction model is provided in accordance with various embodiments of the disclosure. Process 300 obtains 301 dietary intake measurements from an individual.

[0042] In several embodiments, dietary intake is determined based on the eating habits of the individual being assessed. Dietary intake can be the amount of energy consumed and/or the amount of a nutrient consumed. Dietary energy intake can be measured in calories or kilocalories, but any appropriate unit of dietary energy can be utilized. Dietary intake data can include (but is not limited to) timing of energy intake, frequency of dietary intake, amount of dietary intake, and/or ratio amount of dietary intake (e.g. dietary intake within a certain time or meal, divided by the total dietary intake of the day).

[0043] In many embodiments, an individual’s dietary energy is measured for a plurality of temporal windows throughout a day. In some embodiments, one or more temporal windows utilized are associated with meal times (e.g., breakfast, lunch, dinner, snack, etc.), but can also be associated with other times of the day. In some embodiments, the temporal windows utilized are specific times throughout the day, and the window duration can be equivalent or nonequivalent in length. An individual’s dietary intake measurements will need to be compatible with the prediction model utilized and thus should have some similarity to the type of data features utilized to train the model. As stated herein, dietary intake data features can be any data related to dietary intake, such as (for example) : amount of amount of dietary intake, ratio of dietary intake relative to timings, ratio of dietary intake relative to nutrients, or variability of dietary intake. Other features can be included within a prediction model, such as (for example) patient data, diabetic diagnostic status, age, sex, ethnicity, BMI, fasting glucose levels, fasting insulin levels, HbA1c levels, C-peptide levels, etc.

[0044] In some embodiments, an individual has been diagnosed as being normoglycemic, prediabetic, or diabetic. Embodiments are also directed to an individual being one that has not been diagnosed, especially in situations in which the individual is unaware of their metabolic dysregulation.

[0045] Process 300 also obtains 303 a trained computational prediction model that indicates an individual’s metabolic health from dietary intake data. Any prediction model that can compute an indicator of an individual’s metabolic health from dietary intake data can be used. In some embodiments, the prediction model is constructed and trained as described in Fig. 2. The prediction model, in accordance with various embodiments, has been optimized to accurately and efficiently estimate metabolic health.

[0046] A number of prediction models can be used in accordance with various embodiments, including (but not limited to) regression-based or classification-based models. Regression-based models include (but are not limited to) LASSO regression, ridge regression, K-nearest neighbors, elastic net, least angle regression (LAR), and random forest regression. Classification-based models include (but are not limited to) Support Vector Machine (SVM), hierarchical clustering, k-means clustering, decision trees, and naive Bayes. In some embodiments, a prediction model is regularized.

[0047] Process 300 also enters 305 an individual’s dietary intake data into the prediction model to indicate the individual’s metabolic health. In various embodiments, the prediction model to determines the individual’s diabetic diagnostic status, insulin resistance, peripheral insulin resistance, hepatic insulin resistance, adipose tissue insulin resistance, beta cell function, incretin effect, oral glucose tolerance, and/or steady-state plasma glucose.

[0048] Process 300 also outputs 307 a report containing an individual’s metabolic health result and/or diagnosis. Furthermore, based on an individual’s indicated metabolic health, the individual is optionally further examined and/or treated 309 to further assess and/or ameliorate a symptom related to the result and/or diagnosis. In several embodiments, an individual is provided with a personalized treatment plan. Further discussion of treatments that can be utilized in accordance with this embodiment are described in detail below, which may include various dietary adjustments, medications, and dietary supplements.

[0049] While specific examples of processes for determining an individual’s metabolic health are described above, one of ordinary skill in the art can appreciate that various steps of the process can be performed in different orders and that certain steps may be optional according to some embodiments of the disclosure. As such, it should be clear that the various steps of the process could be used as appropriate to the requirements of specific applications. Furthermore, any of a variety of processes for predicting an individual’s metabolic health as appropriate to the requirements of a given application can be utilized in accordance with various embodiments of the disclosure.

Feature Selection

[0050] As explained in the previous sections, dietary intake measurements are used as features to construct a computational prediction model that is then used to indicate an individual’s metabolic health. Further, any other data features appropriate to the computational prediction model can be utilized as well. Features used to train the model can be selected by a number of ways. In some embodiments, features are determined by which features provide strong correlation with metabolic health. In various embodiments, features are determined using a computational model, such as Bayesian network, which can determine which features influence or are influenced by an individual’s metabolic health. LASSO models can be used to select which features are most strongly associated with the outcome (e.g., metabolic health). Embodiments also consider practical factors, such as (for example) the ease and/or cost of obtaining the feature data, patient comfort when obtaining the feature data, and current clinical protocols are also considered when selecting features.

[0051] Correlation analysis utilizes statistical methods to determine the strength of relationships between two measurements. Accordingly, a strength of relationship between a feature and metabolic health can be determined. Many statistical methods are known to determine correlation strength (e.g., correlation coefficient), including linear association (Pearson correlation coefficient), Kendall rank correlation coefficient, and Spearman rank correlation coefficient. Data measurements that correlate strongly with metabolic health can then be used as features to construct a prediction model to assess an individual’s metabolic health.

[0052] In a number of embodiments, data features are identified by a computational model, including (but not limited to) a Bayesian network model, LASSO, random forest and elastic net. In some embodiments, the contribution of a feature to the predictive ability of the model is determined and features are selected based on their contribution. In some embodiments, the top contributing features are utilized. The precise number of contributing features will depend on the results of the model and each feature’s contribution. Various embodiments utilize an appropriate computational model that results in a number of features that is manageable. For instance, constructing predictive models from hundreds to thousands of analyte measurement features may have overfitting issues. On the other hand, too few features can result in less prediction power.

Computational Processing System

[0053] A computational processing system to evaluate immunity in accordance with various embodiments of the disclosure typically utilizes a processing system including one or more of a CPU, GPU and/or other processing engine. In some embodiments, the computational processing system is housed within a computing device. In certain embodiments, the computational processing system is implemented as a software application on a computing device such as (but not limited to) mobile phone, a tablet computer, and/or portable computer.

[0054] A computational processing system in accordance with various embodiments of the disclosure is illustrated in Fig. 4. The computational processing system 400 includes a processor system 402, an I/O interface 404, and a memory system 406. As can readily be appreciated, the processor system 402, I/O interface 404, and memory system 406 can be implemented using any of a variety of components appropriate to the requirements of specific applications including (but not limited to) CPUs, GPUs, ISPs, DSPs, wireless modems (e.g., WiFi, cellular, Bluetooth modems), serial interfaces, volatile memory (e.g., DRAM) and/or non-volatile memory (e.g., SRAM, and/or NAND Flash). In the illustrated embodiment, the memory system is capable of storing various applications and computational models, each of which or optional and/or combinable in any fashion. Applications include metabolic health assessment application 408 and dietary plan application 410. Metabolic health assessment application 408 can predict the metabolic health of an individual based on the dietary intake measurements collected, which can be entered via the I/O interface or gathered via a connection (e.g., WiFi, cellular Bluetooth). Dietary plan application 410 can provide a dietary intake plan based on dietary intake. The dietary plan application can also provide alerts of when dietary intake timing is less than optimal. Computational models include regression models 412 and classifier models 414, such as (for example) as discussed in reference to Figs. 2 and 3. Regression models 412 and classier models 414 can optionally be used in metabolic health assessment application 408 or dietary plan application 410. The various model applications can be downloaded and/or stored in non-volatile memory. Dietary intake data 416 can optionally be stored in non-volatile memory, which can be utilized in any of the applications and/or models or used to keep a data log. When executed the various applications and models are each capable of configuring the processing system to implement computational processes including (but not limited to) the computational processes described above and/or combinations and/or modified versions of the computational processes described above. [0055] While specific computational processing systems are described above with reference to Fig. 4, it should be readily appreciated that computational processes and/or other processes utilized in the provision of dietary intake and metabolic health evaluation in accordance with various embodiments of the disclosure can be implemented on any of a variety of processing devices including combinations of processing devices. Accordingly, computational devices in accordance with embodiments of the disclosure should be understood as not limited to specific computational processing systems. Computational devices can be implemented using any of the combinations of systems described herein and/or modified versions of the systems described herein to perform the processes, combinations of processes, and/or modified versions of the processes described herein.

Applications and Treatments Related to Metabolic Health Assessment [0056] Various embodiments are directed to performing further clinical assessment and/or treatments based on an assessment of metabolic health. As described herein, an individual’s metabolic and/or likelihood of developing a metabolic condition is determined by various methods (e.g., computational methods, dietary energy/nutrient intake assessment). Based on one’s metabolic health and/or likelihood of developing a metabolic condition, an individual can be subjected to further clinical assessment and/or treated with various medications, dietary supplements, dietary alterations (including prescribing a dietary intake meal plan) and/or physical exercise.

Medications and Supplements

[0057] Several embodiments are directed to the use of medications and/or dietary supplements to treat an individual based on their metabolic health assessment. In some embodiments, medications and/or dietary supplements are administered in a therapeutically effective amount as part of a course of treatment. As used in this context, to "treat" means to ameliorate at least one symptom of the disorder to be treated or to provide a beneficial physiological effect. For example, one such amelioration of a symptom could be improvement of HbA1c levels or improvement of insulin sensitivity. Assessment of metabolic health can be performed in many ways, including (but not limited to) performing an assessment based upon dietary intake data.

[0058] A therapeutically effective amount can be an amount sufficient to prevent reduce, ameliorate or eliminate the symptoms of diseases or pathological conditions susceptible to such treatment, such as, for example, diabetes, heart disease, or other diseases that are affected by elevated glycemia. In some embodiments, a therapeutically effective amount is an amount sufficient to reduce an individual’s HbA1c and/or improve an individual’s insulin sensitivity and/or improve incretin effect and/or improve beta cell function.

[0059] A number of medications are available to treat elevated glycemia, such as those used to treat type II Diabetes. Medications include (but are not limited to) insulin, alpha-glucosidase inhibitors (e.g., acarbose, miglitol, voglibose), biguanides (e.g., metformin), dopamine agonists (e.g., bromocriptine), DPP-4 inhibitors (e.g., alogliptin, linagliptin, saxagliptin, sitagliptin, vildagliptin, gemigliptin, anagliptin, teneligliptin, trelagliptin, omarigliptin, evogliptin, gosogliptin, dutogliptin, berberine), GLP-1 receptor agonists (e.g., glucagon-like peptide 1 , gastric inhibitory peptide, albiglutide, dulaglutide, exenatide, liraglutide, lixisenatide, semaglutide), meglitinides (e.g., nateglinide, repaglinide), sodium glucose transporter 2 inhibitors (e.g., dapagliflozin, canagliflozin, empagliflozin, ertugliflozin, ipragliflozin, luseogliflozin, sotagliflozin, tofogliflozin), sulfonylureas (e.g., glimepiride, gliclazide, glyburide, chlorpropamide, tolazamide, tolbutamide, acetohexamide, carbutamide, metahexamide, glycyclamide, glibornuride, glipizide, gliquidone, glisoxepide, glyclopyramide), and thiazolidinediones (e.g., rosiglitazone, pioglitazone, lobeglitazone). Accordingly, an individual may be treated, in accordance with various embodiments, by a single medication or a combination of medications described herein. Furthermore, several embodiments of treatments further incorporate heart disease medications (e.g., aspirin, cholesterol and high blood pressure medications), dietary supplements, dietary alterations, physical exercise, sleep alteration, or a combination thereof.

[0060] Numerous dietary supplements may also help to treat elevated glycemia. Various dietary supplements, such as alpha-lipoic acid, chromium, coenzyme Q10, garlic, hydroxychalcone (cinnamon), magnesium, omega-3 fatty acids, soluble and insoluble fibers, vitamin C, vitamin D, and selenium have been shown to have beneficial effects on individuals having diabetes and cardiac conditions. Thus, embodiments are directed to the use of dietary supplements, included those listed herein, to be used to treat an individual based on one’s metabolic health assessment. A number of embodiments are also directed to combining dietary supplements with medications, dietary alterations, and physical exercise to improve metabolic health.

Diet and Exercise

[0061] Numerous embodiments are directed to dietary alteration and exercise treatments. Altering one’s lifestyle, including diet, physical activity, and sleep, has been shown to improve glycemic regulation. Accordingly, in a number of embodiments, an individual is treated by altering their diet, increasing physical activity, improving sleep in response to a metabolic assessment.

[0062] Several embodiments are directed towards improving dietary energy intake timing. It has been discovered that dietary energy intake at certain times is associated with better metabolic health (see Exemplary Data). Specifically, it has been found that higher dietary energy intake in the morning and afternoon is associated with better metabolic health whereas higher dietary energy intake in the evening is associated with worse metabolic health. Accordingly, in some embodiments, an individual is prescribed a dietary plan increasing dietary energy intake in the morning and afternoon. In some embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake in the evening. In some embodiments, an individual is prescribed a dietary plan increasing the ratio of dietary energy intake in the morning and afternoon to dietary energy intake in the evening. In some embodiments, an individual is prescribed a dietary plan decreasing the ratio of dietary energy intake in the evening to dietary energy intake in the morning and afternoon. In some particular embodiments, an individual is prescribed a dietary plan increasing dietary energy intake between 8 AM and 11 AM or 12 noon and 5PM. In some particular embodiments, an individual is prescribed a dietary plan decreasing dietary energy intake after 5PM. [0063] There are various substantive diets that will help different individuals in improving metabolic health. A number of embodiments are directed to treatments to reduce weight, which has been considered by some to be the best approach to control one’s glycemia. There are many programs based on the seminal study for a low-fat diet to prevent diabetes (see Diabetes Prevention Program (DPP) Research Group. Diabetes Care. 2002 25:2165-71 , the disclosure of which is herein incorporated by reference). For others, a diet low in refined carbohydrates and sugars will work better. Numerous embodiments take a more personalized approach such that one can utilize continuous glucose monitoring (CGM) results to determine which foods cause glycemic spikes for an individual and devise a diet to limit these particular foods while maintaining appropriate nutrient intake. Numerous embodiments are directed to treating an individual by substituting saturated fats with monounsaturated and unsaturated fats to help lower the risk for cardiovascular disease, which would be beneficial for many individuals struggling to control their glycemia. Also, embodiments are directed to increasing amounts of fiber in the diet, which would be highly recommended to both help with glycemic regulation and also balance serum lipid levels (cholesterol and triglycerides).

[0064] Various embodiments are directed towards assisting an individual improve their dietary habits. In some embodiments, an individual can utilize a food tracking application (e.g., on their mobile phone) to track the amount of dietary energy and nutrient intake being performed at various times. In some embodiments, a dietary plan based on dietary energy and nutrient intake timing can be utilized to inform an individual when and the amount of food to intake. In some embodiments, a food tracking application will provide a dietary plan that increases the ratio of dietary consumption in the afternoon or morning to evening. In some embodiments, a food tracking application will alarm an individual when their consumption at a certain time is too high or too low, which can be detected by variety of means (e.g., continuous glucose monitor, or motion detecting sensors indicating dietary consumption). In some embodiments, a machine-learning algorithm can estimate an individual’s typical daily energy intake based on the food logged data over time, and then inform the user in a prospective way that the ideal distribution of energy intake across different meal timings (e.g., 30% energy intake from 8:00 am - 11 :00 am, 30% from 11 :00 am - 2:00 pm, 20% from 2:00 pm - 5:00 pm, 20% from 5:00 pm - 8:00 pm). In some embodiments, a food tracking application can monitor the day-to-day variations in dietary intake timing and inform an individual when the variation in timing is harmful to metabolic health.

[0065] Exercise has a large impact on metabolic health. In several embodiments, a treatment entails a minimum of some minutes of active exercise per week. In some embodiments, treatments would include a minimum of 150 minutes of exercise a week, however, the precise duration of exercise may be dependent on the individual to be treated and their cardiovascular health. It is further noted that cardiovascular exercise is important for the immediate glycemic control and weight training will have a long-term effect by increasing muscle mass, affecting glucose utilization during rest. To plan accurate treatment or prevention, exercise needs to be monitored along with dietary intake.

[0066] In many embodiments, a treatment to improve metabolic health is to increase sleep duration and quality because an adequate amount of sleep with a good quality is related to better glycemic control. Therefore, increasing sleep quantity and quality are the ways to improve metabolic health. To plan accurate treatment or prevention, sleep needs to be monitored along with dietary intake.

[0067] In many embodiments, a treatment to improve metabolic health is stress management, as stress increases blood glucose levels. Some proven ways to help control stress include meditation, social support, adequate sleep, journaling, and therapy.

EXEMPLARY DATA

[0068] Bioinformatic and biological data support the methods and systems of assessing metabolic health and applications thereof. In the description below, exemplary data and exemplary applications related to metabolic health and dietary intake are provided.

Meal Timing-Based Dietary Patterns Are Associated With Glucose Regulation, Insulin Resistance, and Incretin Effect in Individuals at Risk for Type 2 Diabetes [0069] A study was performed to assess dietary patterns and risks of dietary intake associated with glucose regulation, insulin resistance and incretin effect (Fig. 5). Thirty- five study participants (prediabetes n=19 and normoglycemia n=16) tracked their food intake and timing by a food-logging mobile app for at least two weeks. The demographics of the participants are provided in Fig. 6A. Several glucose metabolic tests were performed to quantify insulin resistance, beta-cell function, and incretin effects, including oral glucose tolerance test (OGTT), insulin suppression test (1ST), isoglycemic intravenous glucose infusion (IIGI), incretin response (GLP-1 , GIP), HbA1c levels, fasting blood glucose levels, and fasting insulin levels (Figs. 6A and 6B).

[0070] A total of 2307 meals and 625 days of food logs were collected from the study participants (Fig. 7). When determining the energy contribution of six meal timings to the total daily energy intake, considerable heterogeneity in meal timing-related energy composition was found within and between persons.

[0071] Principal component analysis (PCA) was performed based on meal timing features. PCA plots for FlbAlc levels (Fig. 8A), incretin effect (Fig. 8B), and SSPG (Fig. 8C) separated into two clusters, showing a clear distinction of individuals based dietary intake timing. Machine learning regression models further showed that people with prediabetes had lower Meal_4 (2pm-5pm) energy contribution (p=0.0212), higher MeaM (5am-8am) energy contribution, and higher Meal_5 (5pm-9pm) energy contribution than normal group even after adjustment for age, sex, ethnicity, and BMI (Figs. 9A, 9B, & 9C; asterisks indicate a statistical significance (^** P < 0.01 ; ^* P < 0.05)). The data provides that meal timing-based dietary patterns can be used to predict different types of glucose metabolic dysregulation such as prolonged high blood glucose, incretin dysfunction, and insulin resistance.

[0072] Among thirty diet parameters, most of the models showed that energy proportion from a particular time of the day is associated with glucose outcomes (Fig. 10). Specifically, higher energy proportion of the meal between 14:00 and 17:00 to the total daily energy intake were associated with better glucose outcomes (FPG, CGM, incretin function). Higher energy proportion of the meal between 8:00 and 11 :00 were also associated with better glucose outcomes (CGM). On the other hand, energy contribution from the meal between 17:00 and 21 :00 were negatively associated with beta cell function. Computational application for assessing energy and nutrient intake [0073] In this example, a computational application is utilized to track, monitor, and provide recommendations to improve energy and nutrient intake. The computational application can be downloaded and utilized on any computational device, such as those described herein, and especially on a device that is portable such as a phone, tablet, or watch. The application can be configured to receive dietary intake data. A user of the application can input what they ate and the timing of the meal. The application can utilize this information to determine dietary nutrient and energy intake, including (but not limited to) calories, protein, carbohydrates, fat, fiber, vitamins and minerals. The application can compute the ratio of energy intake for each meal, which can be displayed for an individual day or a computed average over several days (e.g., 2 days, 3 days, 7 days, 28 days, 365 days, cumulative average) (Figs. 11A and 11 B). Based on the energy or nutrient intake and the timing of the intake, the app can utilize a trained computational model to determine the individual’s metabolic health. In some embodiments, the trained computational model utilizes a ratio of energy intake to determine the individual’s metabolic health.

[0074] The application can further provide diagnostics and/or recommendations (Figs. 11 C, 11 D, & 11 E). The diagnostics and recommendations can be based on one or more of the following: the determined metabolic health, the energy or nutrient intake thus far of the day, a prescribed dietary plan, and/or general health recommendations. For instance, Fig. 11 C provides an alert to the user that it is time to eat their third meal. Fig. 11 D provides a recommendation/prescription to keep a late meal light and finished before 8PM. Fig. 11 E provides an alert of that a specific meal was consumed at an unusual time.

DOCTRINE OF EQUIVALENTS

[0075] In particular, as can be inferred from the above discussion, the above- mentioned concepts can be implemented in a variety of arrangements in accordance with embodiments of the invention. Accordingly, although the present invention has been described in certain specific aspects, many additional modifications and variations would be apparent to those skilled in the art. It is therefore to be understood that the present invention may be practiced otherwise than specifically described. Thus, embodiments of the present invention should be considered in all respects as illustrative and not restrictive.

Claims

WHAT IS CLAIMED IS:

1 . A method for assessing metabolic health of an individual, the method comprising: obtain dietary intake measurements of an individual, wherein the dietary intake measurements are associated with a time of intake; entering the dietary intake measurements as a feature into a prediction model that indicates the individual’s metabolic health from the dietary intake measurements; and determining an assessment of the individual’s metabolic health based upon a result of entering the dietary intake measurements into the prediction model.

2. The method of claim 1 , wherein the dietary intake measurements comprise at least one of the following: an amount energy consumed of a dietary intake, an amount of a nutrient of a dietary intake, a ratio of an amount of energy consumed, a ratio of an amount of a nutrient consumed, or a variability of the dietary intake measurements.

3. The method of claim 1 , wherein at least one additional feature is utilized within the prediction model to determine the assessment of the individual’s metabolic health, wherein the at least one additional feature is: diabetic diagnostic status, age, sex, ethnicity, BMI, fasting glucose levels, fasting insulin levels, HbA1c levels, or C-peptide levels.

4. The method of claim 1 , wherein the individual has not been diagnosed with metabolic dysregulation.

5. The method of claim 1 , wherein the prediction model is a regression-based model.

6. The method of claim 5, wherein the regression-based model comprises LASSO regression, ridge regression, K-nearest neighbors, elastic net, least angle regression (LAR), or random forest regression.

7. The method of claim 1 , wherein the prediction model is a classification-based model.

8. The method of claim 7, wherein the classification-based model comprises support vector machine (SVM), hierarchical clustering, k-means clustering, decision trees, or naive Bayes.

9. The method of claim 1 , wherein the assessment of the individual’s metabolic health comprises a determination of at least one of: a diabetic diagnostic status, an insulin resistance, a peripheral insulin resistance, a hepatic insulin resistance, an adipose tissue insulin resistance, a beta cell function, an incretin effect, an oral glucose tolerance, or a steady-state plasma glucose.

10. The method of claim 1 further comprising treating the individual with a dietary adjustment, a medication, or a dietary supplement.

11. A computational processing system, comprising: a processor system; an I/O interface; a memory system; and a metabolic health assessment application stored within the memory system; wherein the metabolic health assessment application can configure the processor to perform the following: receive dietary intake measurements of an individual, wherein the dietary intake measurements are associated with a time of dietary intake; utilizing the dietary intake measurements as a feature in a prediction model that indicates the individual’s metabolic health from the dietary intake measurements; and determining an assessment of the individual’s metabolic health based upon a result of entering the dietary intake measurements into the prediction model.

12. The computational processing system of claim 11, wherein the dietary intake measurements comprise at least one of the following: an amount energy consumed of a dietary intake, an amount of a nutrient of a dietary intake, a ratio of an amount of energy consumed, a ratio of an amount of a nutrient consumed, or a variability of the dietary intake measurements.

13. The computational processing system of claim 11 , wherein at least one additional feature is utilized within the prediction model to determine the assessment of the individual’s metabolic health, wherein the at least one additional feature is: diabetic diagnostic status, age, sex, ethnicity, BMI, fasting glucose levels, fasting insulin levels, HbA1c levels, or C-peptide levels.

14. The computational processing system of claim 11, wherein the individual has not been diagnosed with metabolic dysregulation.

15. The computational processing system of claim 11 , wherein the prediction model is a regression-based model.

16. The computational processing system of claim 15, wherein the regression-based model comprises LASSO regression, ridge regression, K-nearest neighbors, elastic net, least angle regression (LAR), or random forest regression.

17. The computational processing system of claim 11 , wherein the prediction model is a classification-based model.

18. The computational processing system of claim 17, wherein the classification- based model comprises support vector machine (SVM), hierarchical clustering, k-means clustering, decision trees, or naive Bayes.

19. The computational processing system of claim 11 , wherein the assessment of the individual’s metabolic health comprises a determination of at least one of: a diabetic diagnostic status, an insulin resistance, a peripheral insulin resistance, a hepatic insulin resistance, an adipose tissue insulin resistance, a beta cell function, an incretin effect, an oral glucose tolerance, or a steady-state plasma glucose.

20. The computational processing system of claim 11 further comprising displaying the assessment of the individual’s metabolic health via the I/O interface.

21 . A method for improving an individual’s metabolic health, comprising: determining that an individual has an undesirable ratio of dietary intake at a particular time; and prescribing to the individual a dietary intake plan that improves the undesirable ratio of dietary intake.

22. The method of claim 21 , wherein the undesirable ratio is a ratio of afternoon dietary energy intake to evening dietary energy intake.

23. The method of claim 22, wherein the individual is prescribed a dietary plan that increases the amount of afternoon dietary energy intake to the amount of evening dietary energy intake.

24. The method of claim 21 , wherein the undesirable ratio is a ratio of morning dietary energy intake to evening dietary energy intake.

25. The method of claim 24, wherein the individual is prescribed a dietary plan that increases the amount of afternoon dietary energy intake to the amount of evening dietary energy intake.

26. A computational processing system, comprising: a processor system; an I/O interface; a memory system; and a dietary intake assessment application stored within the memory system; wherein the dietary intake assessment application can configure the processor to perform the following: determine that an individual has an undesirable ratio of dietary intake at a particular time; and prescribe to the individual a dietary intake plan that improves the undesirable ratio of dietary intake.

27. The computational processing system of claim 26, wherein the undesirable ratio is a ratio of afternoon dietary energy intake to evening dietary energy intake.

28. The computational processing system of claim 27, wherein the individual is prescribed a dietary plan that increases the amount of afternoon dietary energy intake to the amount of evening dietary energy intake.

29. The computational processing system of claim 28, wherein the dietary intake assessment application provides an alert to the individual when to or how much energy to consume in the afternoon or in the evening.

30. The computational processing system of claim 26, wherein the undesirable ratio is a ratio of morning dietary energy intake to evening dietary energy intake.

31. The computational processing system of claim 30, wherein the individual is prescribed a dietary plan that increases the amount of afternoon dietary energy intake to the amount of evening dietary energy intake.

32. The computational processing system of claim 31, wherein the dietary intake assessment application provides an alert to the individual when to or how much energy to consume in the morning or in the evening.