Description:FIELD OF DISCLOSURE
[0001] The present disclosure relates to a system and method of predicting glucose levels among Type 2 Diabetes Mellitus Patients or abbreviated as T2DM here by using the three state Markov Probability Distributions.
BACKGROUND OF DISCLOSURE
[0002] Nowadays due to changes in diet and lifestyle of a lot of people a lot of diseases and health problems have cropped up across the world, out of these health problems diabetes is one of them. Type 2 Diabetes is one of the most common form of diabetes and it affects many young adults. Type 2 Diabetes can also be genetic and passed down from generation to generation so even if the lifestyle choices and diet choices are healthy a person is still in risk of getting type 2 Diabetes. So a lot of precautions and constant prediction of how vulnerable the disease is to a person needs to be tested.
[0003] Type 2 diabetes is a condition where the body does not use insulin properly to regulate the sugar in your blood. This can lead to high or low blood sugar levels, which can cause various health problems. Type 2 diabetes is mainly caused by being overweight, inactive, or having a family history of diabetes. It can be managed by eating well, exercising, and taking medications if needed.
[0004] In the context of glucose level prediction, the three states can represent the different ranges of glucose levels: hypoglycemia (low), normoglycemia (normal), and hyperglycemia (high).
[0005] As mentioned before in the system and method disclosed here, the invention tries to estimate the probability of transitioning from one state to another based on the historical data of glucose levels measured by a continuous glucose monitoring (CGM) device. A CGM device is a device that can measure the glucose levels in the blood continuously and provide real-time feedback to the user and by using the Markov probability distribution, the invention hopes to predict the future glucose levels of T2DM patients and help them manage their condition
[0006] Here, the three state Markov probability distribution to model the glucose dynamics of T2DM patients. A Markov probability distribution is a way of describing how a system changes over time based on some probabilities, and it tries to predict the future glucose levels of the patient accurately. This is called a stochastic process in probability and it is used to accurately predict random system that are display uncertainty and if the future state of the system only depends on its present or current state and not on the preceding or previous events than it can be said that the stochastic process possesses the Markov probability.
[0007] India is the country most affected by diabetes worldwide, with an estimated 77 million Indians (1 in 11) officially diagnosed with the disease. This puts India second only to China. In addition, diabetes, hyperglycemia, renal failure, and other consequences of the disease claimed the lives of 700,000 Indians in 2020. India accounts for one in six (17%) of the global diabetes population. (As of October 2018, India accounted for roughly 17.5% of the world’s population.) The International Diabetes Federation predicts that by 2045, there would be 134 million people with the condition. Worldwide, 537 million adult individuals suffer with diabetes this number is expected to increase to 643 million by 2030 and 783 million by 2045, according to experts. A hidden Markov model, which is a type of statistical model that can deal with missing or uncertain information was used and these probabilities predicted the blood glucose level of a person with diabetes for the next 60 minutes, based on their current glucose storage and state.
SUMMARY OF THE DISCLOSURE
[0008] The following is a summary description of illustrative embodiments of the method for evaluating changing students’ mindset in offline and online classes. It is provided as a preface to assist those skilled in the art to more rapidly assimilate the detailed design discussion which ensues and is not intended in any way to limit the scope of the claims which are appended hereto in order to particularly point out the invention.
[0009] According to the illustrative embodiments the present disclosure relates to a method and system for predicting the future glucose levels of T2DM patients and help them manage their condition better and possibly reduce the effects of the harm caused by the disease to the patient by using the Markov probability distribution.
[0010] By using the Markov probability it has a lot of advantages by capturing the dynamic and stochastic nature of the blood glucose level, which is influenced by many factors, such as food intake, insulin dose, physical activity, stress, etc. It can handle missing or uncertain data, which is common in real-world scenarios, such as sensor errors, data gaps, or measurement noise. It can provide probabilistic estimates of the future states, which can help the patients and the doctors to make informed decisions and take preventive actions. It can be easily updated with new data, which can improve the accuracy and reliability of the predictions over time.
[0011] As mentioned before the data created by the system and method can be used to predict the future glucose levels of T2DM patients and help them manage their condition properly and monitor their blood glucose levels accurately and precisely.
[0012] In light of the above in another aspect of the present disclosure, the method and system includes a stochastic process of the Markov probability distribution, probability distribution of hypoglycemia, probability distribution of normoglycemia, probability distribution of hyperglycemia, glucose level prediction, methodology and finally the data analysis. All the formulas included in this method and system is given below.
[0013] In one embodiment, a sequence of potential events where the probability of each event depends only on the state obtained in the preceding event is described mathematically as a Markov Chain. The process in question is stochastic and demonstrates the Markov property, which implies that the system’s future state is contingent solely upon its present state and not on the preceding sequence of the events.
[0014] These and other advantages will be apparent from the present application of the embodiments described herein.
[0015] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
[0016] These elements, together with the other aspects of the present disclosure and various features are pointed out with particularity in the claims annexed hereto and form a part of the present disclosure. For a better understanding of the present disclosure, its operating advantages, and the specified object attained by its uses, reference should be made to the accompanying drawings and descriptive matter in which there are illustrated exemplary embodiments of the present disclosure.
BRIEF DESCRIPTION OF THE DRAWINGS
[0017] To describe the technical solutions in the embodiments of the present disclosure or in the prior art more clearly, the following briefly describes the accompanying drawings required for describing the embodiments or the prior art. Apparently, the accompanying drawings in the following description merely show some embodiments of the present disclosure, and a person of ordinary skill in the art can derive other implementations from these accompanying drawings without creative efforts. All of the embodiments or the implementations shall fall within the protection scope of the present disclosure.
[0018] The advantages and features of the present disclosure will become better understood with reference to the following detailed description taken in conjunction with the accompanying drawing, in which:
[0019] FIG.1 illustrates the schematic diagram of the three state Markov model, here Hypo indicates hypoglycemia, Normal indicates normoglycemia and finally Hyper indicates hyperglycemia and it also shows the numerical diagram of the overall data;
[0020] FIG. 2 shows a table showing the initial probability vector and transition probability matrix are given in the following table. It shows the glucose levels at different times of the day and the transition probability matrix;
[0021] FIG.3 shows a table showing a probability distribution which is a mathematical function that describes the likelihood of different possible outcomes for a random experiment or event. It can be continuous or discrete, and it can be based on a set of real numbers, vectors or entities. Probability distributions are depicted using graphs or probability tables. Probability distributions is used here to measure glucose in a patient by comparing the patient’s glucose level to a reference distribution that represents the normal range of glucose levels;
[0022] FIG.4 shows a table with the model behavior of the actual and expected values predicted by derived mathematical form for glucose levels, a graph showing the observed and expected values of different seasons namely – morning season, afternoon season and finally the night season;
[0023] FIG.5 shows a predicted glucose level and the one-day glucose levels are predicted from the given formulae are shown in the table. The graphical representation of the forecasted glucose levels for one day is attached to it, the seasons are namely – morning season, afternoon season, night season.
[0024] Like reference, numerals refer to like parts throughout the description of several views of the drawing.
[0025] The method and system of predicting glucose levels among Type 2 Diabetes Mellitus Patients or abbreviated as T2DM here by using the three state Markov Probability Distributions. This method aims to provide real-time feedback to the user by using the Markov probability distribution It should be noted that the accompanying figure is intended to present illustrations of exemplary embodiments of the present disclosure. This figure is not intended to limit the scope of the present disclosure.
DETAILED DESCRIPTION OF THE DISCLOSURE
[0026] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure.
[0027] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be apparent to one skilled in the art that embodiments of the present disclosure may be practiced without some of these specific details.
[0028] Various terms as used herein are shown below. To the extent a term is used, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0029] The terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items.
[0030] The terms “having”, “comprising”, “including”, and variations thereof signify the presence of a component.
[0031] Referring now to FIG.1. to describe various exemplary embodiment of the present disclosure in FIG.1. illustrates a numerical schematic diagram of the three state Markov model, the figure is about using a mathematical Markov model to study how the blood sugar levels of people with diabetes change over time and across different seasons. The model has three possible states for the blood sugar levels: low, normal, and high. The model also has probabilities for how likely it is to move from one state to another in each season.
[0032] The figure shows how the model is fitted to some data that was collected from people with diabetes. The data includes the blood sugar levels measured at different times of the day and in different seasons. The figure also shows how the model is used to make predictions about the future blood sugar levels based on the data, it also uses some statistical methods to evaluate how well the model fits the data and to compare different models. Some of the methods are Chi-Square goodness fit test is a test that checks if the observed data matches the expected data based on the model. If the test result is small, it means the model fits the data well. If the test result is large, it means the model does not fit the data well. AIC and BIC values: These are measures that balance the complexity and the accuracy of the model. The lower the values, the better the model. AIC stands for Akaike Information Criterion and BIC stands for Bayesian Information Criterion. One day glucose levels prediction: This is a way of using the model to estimate the blood sugar levels for a whole day (96 observations) based on the previous data. This can help people with diabetes to plan their diet and medication.
[0033] The given Markov matrices are used to model how things change from one state to another over time. In this case, the Markov matrices are used to study how the blood sugar levels of people with diabetes change from low to normal to high over different seasons and times of the day. Blood sugar levels are important to monitor because they affect the health and well-being of people with diabetes.
[0034] Referring now to FIG.2 the table shows the initial probability vector and transition probability matrix are given in the following table. It shows the glucose levels at different times of the day and the transition probability matrix. The initial probability vector tells us the starting distribution of the blood sugar levels. For example, the vector [0.026, 0.3646, 0.6094] for the morning session means that at the beginning of the morning, 2.6% of the people have low blood sugar, 36.46% have normal blood sugar, and 60.94% have high blood sugar. The transition probability matrix tells the chances of moving from one blood sugar level to another over a period of time. For example, the matrix for the morning session means that: If the patient has a low blood sugar in the morning, the patient has a 30% chance of having normal blood sugar by the end of the morning, and a 70% chance of staying low. If the patient has a normal blood sugar in the morning, he has a 10.79% chance of having high blood sugar by the end of the morning, and 87% chance of staying normal. If the patient has a high blood sugar in the morning, the patient has a 6% chance of having normal blood sugar by the end of the morning, and a 94% chance of staying high. And for example, the matrix for the afternoon session means that if the patient has a low blood sugar in the afternoon, he has a 100% chance of having normal blood sugar by the end of the afternoon. If the patient has a normal blood sugar in the afternoon, he has a 1% chance of having low blood sugar, an 80% chance of staying normal, and a 19% chance of having high blood sugar by the end of the afternoon. If the patient has high blood sugar in the afternoon, he has a 0% chance of having low blood sugar, a 5% chance of having normal blood sugar, and a 95% chance of staying high by the end of the afternoon. The matrix for the night session shows how the blood sugar levels change from low to normal to high in the night time. For example, the matrix for the night session means that: If the patient has low blood sugar in the night, he has a 44.44% chance of having normal blood sugar by the end of the night, and a 55.56% chance of staying low. If the patient has normal blood sugar in the night, he has a 2.69% chance of having low blood sugar, a 91.4% chance of staying normal, and a 5.91% chance of having high blood sugar by the end of the night. If the patient has high blood sugar in the night, he has a 0% chance of having low blood sugar, a 5.32% chance of having normal blood sugar, and a 94.68% chance of staying high by the end of the night.
[0035] Referring now to FIG.3 to describe various exemplary embodiment of the present disclosure, FIG.3 shows a probability distribution which is a mathematical function that describes the likelihood of different possible outcomes for a random experiment or event Here, Hypoglycemia is a condition where the blood glucose level is too low, usually below 70 mg/dL. Normoglycemia is a normal range of blood glucose level, usually between 70 and 130 mg/dL. Hyperglycemia is a condition where the blood glucose level is too high, usually above 130 mg/dL. The probability distribution of hypoglycemia, normoglycemia, and hyperglycemia in different sessions, we can compare the mean, standard deviation, and coefficient of variation of each condition across the sessions. The possible outcomes are Hypoglycemia has the lowest mean probability in the afternoon (0.0026), followed by the evening (0.0234) and the morning (0.0261). This means hypoglycemia is very unlikely to happen in the afternoon, and slightly more likely to happen in the evening and the morning. Hypoglycemia has the lowest standard deviation in the afternoon (0.0509), followed by the evening (0.1514) and the morning (0.1594). This means the probabilities of hypoglycemia are more consistent in the afternoon, and more variable in the evening and the morning.
[0036] Hypoglycemia has the highest coefficient of variation in the afternoon (19.58%), followed by the evening (6.47%) and the morning (6.11%). This means the relative variability of hypoglycemia is very high in the afternoon, and moderate in the evening and the morning. Normoglycemia has the highest mean probability in the evening (0.4819), followed by the morning (0.3642) and the afternoon (0.2423). This means normoglycemia is more likely to happen in the evening, and less likely to happen in the morning and the afternoon. Normoglycemia has the highest standard deviation in the evening (0.4997), followed by the morning (0.4812) and the afternoon (0.4285). This means the probabilities of normoglycemia are more variable in the evening, and less variable in the morning and the afternoon. Normoglycemia has the highest coefficient of variation in the afternoon (1.7684%), followed by the morning (1.3213%) and the evening (1.0368%). This means the relative variability of normoglycemia is high in the afternoon, and moderate in the morning and the evening. Hyperglycemia has the highest mean probability in the afternoon (0.7551), followed by the morning (0.6097) and the evening (0.4947). This means hyperglycemia is very likely to happen in the afternoon, and moderately likely to happen in the morning and the evening. Hyperglycemia has the lowest standard deviation in the afternoon (0.4300), followed by the morning (0.4878) and the evening (0.4999). This means the probabilities of hyperglycemia are more consistent in the afternoon, and more variable in the morning and the evening. Hyperglycemia has the lowest coefficient of variation in the afternoon (0.5695%), followed by the morning (0.8001%) and the evening (1.0107%). This means the relative variability of hyperglycemia is low in the afternoon, and moderate in the morning and the evening. So from this we can see that, hypoglycemia is very unlikely in the afternoon, but more likely in the morning and evening. Hyperglycemia is very likely in the afternoon, but less likely in the morning and evening. Normoglycemia is more likely in the evening, but less likely in the morning and afternoon. The information also shows how much the probabilities deviate from their average values, and how much relative variability there is in each session. This can help you understand the risk and uncertainty of each condition in different times of the day.
[0037] Referring now to FIG.4 to describe various exemplary embodiment of the present disclosure, FIG.4 shows a table with the model behavior of the actual and expected values predicted by derived mathematical form for glucose levels, a graph showing the observed and expected values of different seasons namely – morning season, afternoon season and finally the night season. The figure shows a model that predicts the glucose levels of a person based on some mathematical formula. The model makes predictions for three different times of the day: morning, afternoon, and night. The text compares the predictions with the actual glucose levels measured by a device such as MAE: Mean absolute error. This is the average of how much the predictions differ from the actual values in absolute terms. For example, if the prediction is 120 and the actual value is 130, the absolute error is 10. The lower the MAE, the better the model. RMSE: Root mean squared error. This is similar to MAE, but it squares the errors before averaging them and then takes the square root. This gives more weight to larger errors. For example, if the prediction is 120 and the actual value is 130, the squared error is 100. The lower the RMSE, the better the model. AIC: Akaike information criterion. This is a measure that balances the goodness-of-fit of the model with its complexity.
[0038] The complexity is related to the number of parameters in the model. The lower the AIC, the better the model. BIC: Bayesian information criterion. This is similar to AIC, but it penalizes complex models more. The lower the BIC, the better the model. P-value: This is a measure of how likely it is to observe a result as extreme or more extreme than the one we obtained, assuming that the null hypothesis is true. The null hypothesis is a statement that there is no relationship or difference between the variables. For example, if the null hypothesis is that the model predictions and the actual values are not different, and the p-value is 0.05, it means that there is a 5% chance of observing such a difference or more by chance. The lower the p-value, the more likely the null hypothesis is false and the alternative hypothesis is true The alternative hypothesis is the opposite of the null hypothesis, i.e., that there is a relationship or difference between the variables. The values of these measures for each time of the day and concludes that: The model performs reasonably well in the morning and afternoon, but has larger errors in the night, the model does not show a statistically significant difference from the actual values, according to the chi-square test and the p-values, the model has the lowest AIC and BIC values in the afternoon, which means that it is the best model among the three.
[0039] Referring now to FIG.5 to describe various exemplary embodiment of the present disclosure, FIG.5 shows a predicted glucose level and the one-day glucose levels are predicted from the given formulae are shown in the table. Here the glucose levels for one day are given, the given results in the table are the predicted levels of the glucose levels of a patient at morning, afternoon and night time, this prediction can be useful to the patient for regulating his or her food intake and taking control of glucose spikes and fall in the body. This method aims to provide real-time feedback to the user by using the Markov probability distribution and it hopes to predict the future glucose levels of T2DM patients and help them manage their condition better and possibly reduce the effects of the harm caused by the disease to the patient. In one embodiment, a sequence of potential events where the probability of each event depends only on the state obtained in the preceding event is described mathematically as a Markov Chain. The process in question is stochastic and demonstrates the Markov property, which implies that the system’s future state is contingent solely upon its present state and not on the preceding sequence of the events.
[0040] In light of the above in another aspect of the present disclosure, in order to understand the model behavior, there is need of formulating the probability mass function for different states under study. Statistical characteristics can be derived when the PMF of the relevant state’s distribution is available. Probability distributions are mathematical models that describe how likely it is for a random variable to take on different values, Statistical characteristics are numerical values that summarize some aspects of a probability distribution, such as the mean, the variance, the standard deviation, etc. A probability mass function (PMF) is a specific type of probability distribution that applies to discrete random variables.
[0041] In one embodiment, the Probability Mass Function of Hypoglycemia a PMF of hypoglycemia can be used to model the probability of having hypoglycemia given some variables, such as the time of day, the type of food eaten, or the level of physical activity. A PMF of hypoglycemia can help us understand the risk factors and the frequency of this condition, as well as design preventive measures and treatments. The is function is as shown:

[0042] In one embodiment, the rth order origin moments of hypoglycemia are the expected values of the rth power of the indicator variable for hypoglycemia. The rth order origin moments of hypoglycemia can help us understand the frequency and variability of this condition, as well as compare different groups or populations that may have different risk factors or treatments.

[0043] In one embodiment, the 2nd,3rd,4th Central Moments of Normoglycemia. The second central moment is the variance of the blood glucose level, which measures how much it varies from the mean, the third central moment is the skewness of the blood glucose level, which measures how asymmetric the distribution is, the fourth central moment is the kurtosis of the blood glucose level, which measures how peaked or flat the distribution is.

[0044] In one embodiment, the Skewness and Kurtosis of Normoglycemia are two measures of the shape of the distribution of the blood glucose level when it is within the normal range. The skewness and kurtosis of normoglycemia can help us understand the characteristics and patterns of the blood glucose level, as well as identify potential risks or complications of abnormal glucose levels.

[0045] In one embodiment, the Coefficient of Variation of Hyperglycemia, the coefficient of variation (CV) of hyperglycemia is a measure of how much the blood glucose levels vary over time. It is calculated by dividing the standard deviation (SD) of the blood glucose by the average blood glucose and multiplying by 100 to get a percentage. A lower CV means less glucose variability, which is desirable for people with diabetes. A higher CV means more glucose variability, which can increase the risk of complications and hypoglycemia.

[0046] In light of the above in another aspect of the present disclosure for Glucose Levels Predictions, the mathematical formula for predicting blood glucose levels of the patients over a time period needs to be calculated.
[0047] In one embodiment, the Variance of Glucose Storage in the blood is a measure of how much the amount of glucose stored in the blood varies over time. It is related to the glycemic variability, which is the fluctuation of blood glucose levels. The higher the variance, the more unstable the blood glucose is, which can increase the risk of complications and hypoglycemia. The mathematical formula is:

[0048] In one embodiment, Prediction of glucose level is the task of estimating the future blood glucose levels of a person with diabetes, based on their past and current measurements. This can help the person to manage their diabetes better, avoid complications, and improve their quality of life. In this method and system in the given PGL formula three combinations are used for variance of glucose storage and expected glucose levels at particular time.


[0049] In one embodiment, Model Validation-Goodness of Fit, the effectiveness of the constructed model has been evaluated using the Chi-Square Test, which determines whether there is a significant difference between the observed (actual) and expected (predicted) glucose levels. The standard formula used to calculate the Chi-Square test is:

[0050] In one embodiment, Statistical measurements called AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion) are employed in the process of selecting models, especially when it comes to statistical modeling methodologies. By using these criteria, one can compare many models and choose the one that most effectively strikes a compromise between model complexity and goodness of fit.

[0051] In light of the above in another aspect of the present disclosure, a methodology and analysis of the method and system is disclosed therein, the methodology focused on one person’s data, which had 1196 measurements of blood sugar levels taken every 15 minutes for 11 days, 22 hours, and 30 minutes. The study divided the data into three parts based on the time of the day: morning (6:00 to 14:00), afternoon (14:00 to 22:00), and night (22:00 to 6:00). Each part had 384 measurements. And the analysis includes how to analyze the data from a three-state Markov model. A three-state Markov model is a way of describing how the blood sugar levels of a person with diabetes change over time, depending on the state they are in. The states are low, normal, and high blood sugar levels. The model uses probabilities to show how likely it is to move from one state to another, and how likely it is to observe a certain blood sugar level from each state.
[0052] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it will be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0053] The foregoing descriptions of specific embodiments of the present disclosure have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed, and many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described to best explain the principles of the present disclosure and its practical application, and to thereby enable others skilled in the art to best utilize the present disclosure and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but such omissions and substitutions are intended to cover the application or implementation without departing from the scope of the present disclosure.
[0054] Disjunctive language such as the phrase “at least one of X, Y, Z,” unless specifically stated otherwise, is otherwise understood with the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.
[0055] In a case that no conflict occurs, the embodiments in the present disclosure and the features in the embodiments may be mutually combined. The foregoing descriptions are merely specific implementations of the present disclosure, but are not intended to limit the protection scope of the present disclosure. Any variation or replacement readily figured out by a person skilled in the art within the technical scope disclosed in the present disclosure shall fall within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
, Claims:I/WE CLAIM:
1. A method (100) for predicting glucose levels among Type 2 Diabetes Mellitus Patients, the method (100) comprising:
using a Markov function to show the advantages of capturing the dynamic and stochastic nature of the blood glucose level;
using a Probability Mass Function of Hypoglycemia a PMF of hypoglycemia to model the probability of having hypoglycemia given some variables;
using a Skewness and Kurtosis of normoglycemia to understand the characteristics and patterns of the blood glucose level, as well as identify potential risks or complications of abnormal glucose levels;
using a Coefficient of Variation of Hyperglycemia, the coefficient of variation (CV) of hyperglycemia is a measure showing the blood glucose levels .
using Variance of Glucose Storage formula in the blood to measure of how much the amount of glucose stored in the blood varies over time;
using a Prediction of glucose level to estimate the future blood glucose levels of a person with diabetes, based on their past and current measurements;
using the Chi-Square Test, which determines whether there is a significant difference between actual and predicted difference; and
comparing many models and choosing the one that is most effective and strikes a compromise between model complexity and goodness of fit using AIC and BIC.
2. The method (100) as claimed in claim 1, wherein the Probability Mass Function of Hypoglycemia a PMF of hypoglycemia the rth order origin moments of hypoglycemia are the expected values of the rth power of the indicator variable for hypoglycemia.
3. The method (100) as claimed in claim 1, wherein a second central moment is the variance of the blood glucose level, which measures how much it varies from the mean, a third central moment is the skewness of the blood glucose level, which measures how asymmetric the distribution is, the fourth central moment is the kurtosis of the blood glucose level.
4. The method (100) as claimed in claim 3 wherein the Skewness and Kurtosis of Normoglycemia are two measures of the shape of the distribution of the blood glucose level when it is within the normal range.
5. The method (100) as claimed in claim 1 wherein the Coefficient of Variation of Hyperglycemia, the coefficient of variation (CV) of hyperglycemia is used to measure of how much the blood glucose levels vary over time.
6. The method (100) as claimed in claim 1 wherein the Variance of Glucose Storage in the blood is a measure shows much the amount of glucose stored in the blood varies over time.
7. The method (100) as claimed in claim 6, wherein a PGL formula or Prediction of Glucose is utilised to predict the amount of glucose stored in the blood in a given period of time.
8. The method (100) as claimed in claim 1, wherein the Model Validation-Goodness of Fit, the effectiveness of the constructed model is calculated using the Chi-Square Test.