Methods and systems for predicting a health condition of a human subject

1. A method of operating a health condition profiling system,

the method comprising:

receiving, by a transceiver, a measure of one or more physiological parameters associated with a first human subject, wherein said one or more physiological parameters comprise at least one of an age, a cholesterol level, a heart rate, a blood pressure, a breath carbon-dioxide concentration, a breath oxygen concentration, a stroke score, a blood creatinine level, a blood albumin level, a blood sodium level, a total blood count, a blood glucose/sugar level, a blood haemoglobin level, and a blood platelet count;

extracting, by one or more processors, a historical data comprising a measure of said one or more physiological parameters associated with each of one or more second human subjects, wherein the historical data is missing values, comprises categorical data, or both;

determining, by said one or more processors, a first distribution associated with a first physiological parameter, from said one or more physiological parameters, based on a marginal cumulative distribution of a transformed historical data, wherein said transformed historical data is determined by ranking of said historical data, and does not include any missing values or categorical data;

determining, by said one or more processors, a second distribution associated with a second physiological parameter, from said one or more physiological parameters, based on said first distribution and a first conditional cumulative distribution of said transformed historical data, wherein said first conditional cumulative distribution is deterministic of at least an association between said first physiological parameter and said second physiological parameter;

determining, by said one or more processors, a latent variable based at least on said first distribution and said second distribution;

estimating, by said one or more processors, one or more parameters of at least one bivariate distribution based on said latent variable, wherein said at least one bivariate distribution corresponds to a D-vine copula, wherein said D-vine copula is deterministic of one or more health conditions associated with each of said one or more second human subjects in said historical data, each health condition corresponding to a health condition category and to at least one of a disease risk, a disease symptom, an onset of a disease, a recovery from a disease, or an effect of medications for a disease, and said historical data corresponds to a multivariate dataset from which said one or more health conditions are identifiable based on said bivariate distribution;

training, by said one or more processors, a classifier based on said D-vine copula;

sorting, by said one or more processors, said received measure of said one or more physiological parameters associated with said first human subject into one or more of the health condition categories using the trained classifier;

assigning, by said one or more processors, a health condition profile to the first human subject, the profile comprising the one or more health conditions corresponding to the one or more categories into which the measure is sorted; and

displaying the health condition profile on a display device.

2. The method of claim 1 further comprising determining, by said one or more processors, a third distribution associated with a third physiological parameter, from said one or more physiological parameters, based on said second distribution and a second conditional cumulative distribution of said transformed historical data, wherein said second conditional cumulative distribution is deterministic of at least an association between said third physiological parameter and one or more of said first physiological parameter or said second physiological parameter.

3. The method of claim 2 , wherein said determination of said latent variable is further based on said third distribution.

4. The method of claim 1 , wherein said one or more parameters are estimated by utilizing one of a Gibbs sampling technique or an Expectation-Maximization (EM) technique.

5. The method of claim 1 , wherein said estimation of said one or more parameters is further based on an inverse Wishart distribution, parameterized using said latent variable.

6. The method of claim 1 , wherein each of said first distribution and said second distribution is truncated based on a respective lower bound and a respective upper bound of said latent variable for each of said first physiological parameter and said second physiological parameter.

7. The method of claim 1 , wherein said D-vine copula models a dependency between each pair of physiological parameters from said one or more physiological parameters.

8. The method of claim 1 , wherein said bivariate distribution corresponds to a bivariate copula distribution including one or more of a T-student copula distribution, a Clayton copula distribution, a Gumbel copula distribution, or a Gaussian copula distribution.

9. The method of claim 1 , wherein said one or more parameters comprise at least a covariance matrix associated with said at least one bivariate distribution.

10. The method of claim 1 , wherein said ranking of said historical data corresponds to an extended rank likelihood.

11. A health condition profiling system, the system comprising:

a transceiver configured to receive a measure of one or more physiological parameters associated with said first human subject, wherein said one or more physiological parameters comprise at least one of an age, a cholesterol level, a heart rate, a blood pressure, a breath carbon-dioxide concentration, a breath oxygen concentration, a stroke score, a blood creatinine level, a blood albumin level, a blood sodium level, a total blood count, a blood glucose/sugar level, a blood haemoglobin level, and a blood platelet count;

a display device; and

one or more processors configured to:

extract a historical data comprising a measure of said one or more physiological parameters associated with each of one or more second human subjects, wherein the historical data is missing values, comprises categorical data, or both;

determine a first distribution associated with a first physiological parameter, from said one or more physiological parameters, based on a marginal cumulative distribution of a transformed historical data, wherein said transformed historical data is determined by ranking of said historical data, and does not include any missing values or categorical data;

determine a second distribution associated with a second physiological parameter, from said one or more physiological parameters, based on said first distribution and a first conditional cumulative distribution of said transformed historical data, wherein said first conditional cumulative distribution is deterministic of at least an association between said first physiological parameter and said second physiological parameter;

determine a latent variable based at least on said first distribution and said second distribution;

estimate one or more parameters of at least one bivariate distribution based on said latent variable, wherein said at least one bivariate distribution corresponds to a D-vine copula, wherein said D-vine copula is deterministic of one or more health conditions associated with each of said one or more second human subjects in said historical data, each health condition corresponding to a health condition category and to at least one of a disease risk, a disease symptom, an onset of a disease, a recovery from a disease, or an effect of medications for a disease, and said historical data corresponds to a multivariate dataset from which said one or more health conditions are identifiable based on said bivariate distribution;

train a classifier based on said D-vine copula;

sort said received measure of said one or more physiological parameters associated with said first human subject into one or more of the health condition categories using the trained classifier;

assign, by said one or more processors, a health condition profile to the first human subject, the profile comprising the one or more health conditions corresponding to the one or more categories into which the measure is sorted; and

display the health condition profile on the display device.

12. The system of claim 11 , wherein said one or more processors are further configured to determine a third distribution associated with a third physiological parameter, from said one or more physiological parameters, based on said second distribution and a second conditional cumulative distribution of said transformed historical data, wherein said second conditional cumulative distribution is deterministic of at least an association between said third physiological parameter and one or more of said first physiological parameter or said second physiological parameter.

13. The system of claim 12 , wherein said determination of said latent variable is further based on said third distribution.

14. The system of claim 11 , wherein said D-vine copula models a dependency between each pair of physiological parameters from said one or more physiological parameters.

15. The system of claim 11 , wherein said bivariate distribution corresponds to a bivariate copula distribution including one or more of a T-student copula distribution, a Clayton copula distribution, a Gumbel copula distribution, or a Gaussian copula distribution.

16. The system of claim 11 , wherein the system further comprises one or more biosensors and a human subject-computing device, the human subject-computing device comprises said one or more processors, the transceiver, and the display device, and the measure of one or more physiological parameters associated with the first human subject is received from the one or more biosensors.

17. The system of claim 11 , wherein the system further comprises a database server and an application server, the application server comprises said one or more processors and the transceiver, and the measure of one or more physiological parameters associated with the first human subject is received from the database server.

18. A computer program product for use with a health condition profiling system comprising one or more processors, a transceiver, and a display, the computer program product comprising a non-transitory computer readable medium, wherein the non-transitory computer readable medium stores a computer program code for assigning a health condition profile to a first human subject, wherein the computer program code is executable by the one or more processors to:

extract a historical data comprising a measure of said one or more physiological parameters associated with each of one or more second human subjects, wherein the historical data is missing values, comprises categorical data, or both;

determine a first distribution associated with a first physiological parameter, from said one or more physiological parameters, based on a marginal cumulative distribution of a transformed historical data, wherein said transformed historical data is determined by ranking of said historical data, and does not include any missing values or categorical data;

determine a second distribution associated with a second physiological parameter, from said one or more physiological parameters, based on said first distribution and a first conditional cumulative distribution of said transformed historical data, wherein said first conditional cumulative distribution is deterministic of at least an association between said first physiological parameter and said second physiological parameter;

determine a latent variable based at least on said first distribution and said second distribution;

estimate one or more parameters of at least one bivariate distribution based on said latent variable, wherein said at least one bivariate distribution corresponds to a D-vine copula, wherein said D-vine copula is deterministic of one or more health conditions associated with each of said one or more second human subjects in said historical data, each health condition corresponding to a health condition category and to at least one of a disease risk, a disease symptom, an onset of a disease, a recovery from a disease, or an effect of medications for a disease, and said historical data corresponds to a multivariate dataset from which said one or more health conditions are identifiable based on said bivariate distribution;

train a classifier based on said D-vine copula;

sort said received measure of said one or more physiological parameters associated with said first human subject into one or more of the health condition categories using the trained classifier;

assign, by said one or more processors, a health condition profile to the first human subject, the profile comprising the one or more health conditions corresponding to the one or more categories into which the measure is sorted; and

display the health condition profile on the display device,

wherein the measure of one or more physiological parameters associated with said first human subject is received by the transceiver, and said one or more physiological parameters comprise at least one of an age, a cholesterol level, a heart rate, a blood pressure, a breath carbon-dioxide concentration, a breath oxygen concentration, a stroke score, a blood creatinine level, a blood albumin level, a blood sodium level, a total blood count, a blood glucose/sugar level, a blood haemoglobin level, and a blood platelet count.