Methods and systems for predicting health condition of human subjects

A method for classifying one or more human subjects in one or more categories, wherein said one or more categories are indicative of a health condition associated with said one or more human subjects, the method comprising:

• categorizing, by one or more micro-processors, one or more parameters associated with each of said one or more human subjects in one or more data views based on at least a data type of each of said one or more parameters, wherein a data view corresponds to a first data structure storing a set of parameters, categorized in said data view, associated with each of said one or more human subjects;
• transforming, by said one or more micro-processors, said one or more data views to a second data structure, wherein said second data structure is representative of said set of parameters across said one or more data views,
• wherein within the second data structure, correlated information across said one or more data views is preserved, while data view specific information, which is present in a specific data view and is not correlated to information present in other data views, is not preserved in the second data structure,
• wherein transforming said one or more data views includes combining said one or more data views into a collective matrix, and factorizing the collective matrix into the second data structure,
• wherein the second data structure is represented by a matrix with a dimension that is lower than a corresponding dimension of the collective matrix;
• training, by said one or more micro-processors, a classifier based on said second data structure, wherein said classifier classifies said one or more human subjects in said one or more categories;
• and
• sending, by a transceiver, said classification of said one or more human subjects in said one or more categories to a computing device, wherein said classification of said one or more human subjects is displayed on a display device of said computing device through a user-interface.

A computer program product for use with a computing device, the computer program product comprising a non-transitory computer readable medium, the non-transitory computer readable medium stores a computer program code for classifying one or more human subjects in one or more categories, wherein said one or more categories are indicative of a health condition associated with said one or more human subjects, the computer program code is executable by one or more micro-processors in the computing device to:

• categorize one or more parameters associated with each of said one or more human subjects in one or more data views based on at least a data type of each of said one or more parameters, wherein a data view corresponds to a first data structure storing a set of parameters, categorized in said data view, associated with each of said one or more human subjects;
• transform said one or more data views to a second data structure, wherein said second data structure is representative of said set of parameters across said one or more data views,
• wherein within the second data structure, correlated information across said one or more data views is preserved, while data view specific information, which is present in a specific data view and is not correlated to information present in other data views, is not preserved in the second data structure,
• wherein transforming said one or more data views includes combining said one or more data views into a collective matrix, and factorizing the collective matrix into the second data structure,
• wherein the second data structure is represented by a matrix with a dimension that is lower than a corresponding dimension of the collective matrix;
• train a classifier based on said second data structure, wherein said classifier classifies said one or more human subjects in said one or more categories;
• and
• send, by a transceiver, said classification of said one or more human subjects in said one or more categories to a second computing device, wherein said classification of said one or more human subjects is displayed on a display device of said second computing device through a user-interface.