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 processors said transceiver, a measure of one or more physiological parameters associated with a first human subject, wherein the 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 hemoglobin level, and/or a blood platelet count;

extracting, by the one or more processors, a historical data comprising one or more records, wherein each of the one or more records includes a measure of the 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;

clustering, by the one or more processors, the historical data into a plurality of d-vines by sampling a plurality of latent variables based on a rank transformation of the historical data, wherein the transformed historical data does not include any missing values or categorical data;

estimating, by the one or more processors, one or more latent variables from the plurality of latent variables based on:

a first count indicative of a number of the plurality of d-vines,

a second count indicative of a number of the one or more records,

a first value that is representative of a number of the one or more records clustered into a d-vine from the plurality of d-vines, and

a second value that is representative of a parameter utilizable to predict a third value, wherein the third value corresponds to a probability of clustering the historical data into the d-vine from the plurality of d-vines;

generating, by the one or more processors, the plurality of d-vines based on the estimated one or more latent variables from the plurality of latent variables;

training, by the one or more processors, a classifier based on the generated plurality of d-vines, the classifier configured to sort data into one or more health condition categories, each health condition category corresponding to a health condition, wherein the historical data corresponds to a multivariate dataset from which the health condition is identifiable based on the generated plurality of d-vines;

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

assigning, by the one or more processors, a health condition profile to the first human subject, the profile comprising 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 the display device.

2. The method of claim 1 , wherein the one or more latent variables include one or more parameters associated with each of the plurality of d-vines, a cumulative distribution of each of the one or more physiological parameters, or a distribution of the one or more records into each of the plurality of d-vines.

3. The method of claim 2 , wherein the one or more parameters associated with each of the plurality of d-vines are estimated by utilizing one of a Gibbs sampling technique or an Expectation-Maximization (EM) technique.

4. The method of claim 2 , wherein the one or more parameters associated with each of the plurality of d-vines are estimated based on an inverse Wishart distribution.

5. The method of claim 2 , wherein the one or more parameters comprise at least a covariance matrix associated with the d-vine from the plurality of d-vines.

6. The method of claim 1 , wherein the d-vine from the plurality of d-vines models a dependency between each pair of physiological parameters from the one or more physiological parameters, wherein a first set of physiological parameters from the one or more physiological parameters are continuous and a second set of physiological parameters from the one or more physiological parameters are discrete.

7. The method of claim 1 , wherein the rank transformation corresponds to an extended rank likelihood technique.

8. The method of claim 1 , wherein the health condition corresponds 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.

9. A health condition profiling system comprising a display device and an application server, the application server comprising:

a transceiver configured to receive a measure of one or more physiological parameters associated with a first human subject, wherein the 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 hemoglobin level, and/or a blood platelet count, and one or more processors configured to:

extract a historical data comprising one or more records, wherein each of the one or more records includes a measure of the 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;

cluster the historical data into a plurality of d-vines by sampling a plurality of latent variables based on a rank transformation of the historical data, wherein the transformed historical data does not include any missing values or categorical data;

estimate one or more latent variables from the plurality of latent variables based on:

a first count indicative of a number of the plurality of d-vines,

a second count indicative of a number of the one or more records,

a first value that is representative of a number of the one or more records clustered into a d-vine from the plurality of d-vines, and

a second value that is representative of a parameter utilizable to predict a third value, wherein the third value corresponds to a probability of clustering the historical data into the d-vine from the plurality of d-vines;

generate the plurality of d-vines based on the estimated one or more latent variables from the plurality of latent variables;

train a classifier based on the generated plurality of d-vines, the classifier configured to sort data into one or more health condition categories, each health condition category corresponding to a health condition, wherein the historical data corresponds to a multivariate dataset from which the health condition is identifiable based on the generated plurality of d-vines;

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

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

display the health condition on the display device.

10. The application server of claim 9 , wherein the one or more latent variables include one or more parameters associated with each of the plurality of d-vines, a cumulative distribution of each of the one or more physiological parameters, or a distribution of the one or more records into each of the plurality of d-vines.

11. The application server of claim 10 , wherein the one or more parameters associated with each of the plurality of d-vines are estimated by utilizing one of a Gibbs sampling technique or an Expectation-Maximization (EM) technique.

12. The application server of claim 10 , wherein the one or more parameters associated with each of the plurality of d-vines are estimated based on an inverse Wishart distribution.

13. The application server of claim 10 , wherein the one or more parameters comprise at least a covariance matrix associated with the d-vine from the plurality of d-vines.

14. The application server of claim 9 , wherein the d-vine from the plurality of d-vines models a dependency between each pair of physiological parameters from the one or more physiological parameters, wherein a first set of physiological parameters from the one or more physiological parameters are continuous and a second set of physiological parameters from the one or more physiological parameters are discrete.

15. The application server of claim 9 , wherein the rank transformation corresponds to an extended rank likelihood technique.

16. The application server of claim 9 , wherein the health condition corresponds 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.

17. 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 one or more processors to:

extract a historical data comprising one or more records, wherein each of the one or more records includes a measure of the 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;

cluster the historical data into a plurality of d-vines by sampling a plurality of latent variables based on a rank transformation of the historical data, wherein the transformed historical data does not include any missing values or categorical data;

estimate one or more latent variables from the plurality of latent variables based on:

a first count indicative of a number of the plurality of d-vines,

a second count indicative of a number of the one or more records,

a first value that is representative of a number of the one or more records clustered into a d-vine from the plurality of d-vines, and

a second value that is representative of a parameter utilizable to predict a third value, wherein the third value corresponds to a probability of clustering the historical data into the d-vine from the plurality of d-vines;

generate the plurality of d-vines based on the estimated one or more latent variables from the plurality of latent variables;

train a classifier based on the generated plurality of d-vines, the classifier configured to sort data into one or more health condition categories, each health condition category corresponding to a health condition, wherein the historical data corresponds to a multivariate dataset from which the health condition is identifiable based on the generated plurality of d-vines;

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

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

display the health condition on the display device;

wherein the transceiver is configured to receive the measure of one or more physiological parameters associated with a first human subject, wherein the 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 hemoglobin level, and/or a blood platelet count.