Methods and systems for analyzing healthcare data

A system for determining a diagnosis procedure the system comprising:

• one or more processors at a computing device configured to:
• receive a healthcare dataset, wherein the healthcare data set comprises a plurality of healthcare records for a plurality of patients, wherein the healthcare data set corresponds to at least one of a medical record data, or hospital data, or medical insurance data, and wherein each healthcare record in the plurality of healthcare records comprises one or more physiological markers for a patient in the plurality of patients;
• receive, by one or more processors, an input pertaining to a range of numbers wherein represents a probable number of categories of health conditions for the plurality of patients;
• for each number in the range of numbers:
• estimate one or more first parameters of a distribution associated with a category from the categories of health conditions;
• determine a threshold value based on the one or more first parameters;
• estimate an inverse cumulative distribution of each of one or more n-dimensional variables in the healthcare dataset based on the threshold value and a cumulative distribution of each of the one or more n-dimensional variables, wherein the one or more n-dimensional variables comprise the one or more physiological markers in the healthcare dataset;
• determine one or more latent variables based on the inverse cumulative distribution of each of the one or more n-dimensional variables, wherein the one or more latent variables comprise conditions in the plurality of patients not directly represented in the physiological markers;
• update the one or more first parameters to generate one or more second parameters based on the one or more latent variables, wherein the updating is performed using an expectation-maximization algorithm;
• create a model for each number in the range of numbers based on the one or more second parameters associated with the category from the categories of health conditions;
• and
• determine a score for each model, created for each number in the range of numbers, based on the one or more second parameters, an estimated likelihood value for the one or more second parameters, a first count of one or more free parameters, and a second count of data values corresponding to the one or more n-dimensional variables;
• select a best model from the models created for the range of numbers based on scores corresponding to the models;
• apply the healthcare data set to the best model, wherein the best model categorizes the plurality of patents in one or more of the categories of health conditions based on the one or more physiological markers in the healthcare dataset;
• and
• determine a diagnosis of at least one patient from the plurality of patients based on the categorization of the plurality of patients in the categories of health conditions for providing assistance to a medical practitioner.

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 determining a diagnosis procedure, the computer program code is executable by one or more processors in the computing device to:

• receive a healthcare dataset, wherein the healthcare data set comprises a plurality of healthcare records for a plurality of patients, wherein the healthcare data set corresponds to at least one of a medical record data, or hospital data, or medical insurance data, and wherein each healthcare record in the plurality of healthcare records comprises one or more physiological markers for a patient in the plurality of patients;
• receive an input pertaining to a range of numbers, wherein the range of numbers represents a probable number of categories of health conditions for the plurality of patients;
• for each number in the range of numbers:
• estimate one or more first parameters of a distribution associated with a category from the categories of health conditions;
• determine a threshold value based on the one or more first parameters;
• estimate an inverse cumulative distribution of each of one or more n-dimensional variables in the healthcare dataset based on the threshold value and a cumulative distribution of each of the one or more n-dimensional variables, wherein the one or more n-dimensional variables comprise the one or more physiological markers in the healthcare dataset;
• determine one or more latent variables based on the inverse cumulative distribution of each of the one or more n-dimensional variables, wherein the one or more latent variables comprise conditions in the plurality of patients not directly represented in the physiological markers;
• update the one or more first parameters to generate one or more second parameters based on the one or more latent variables, wherein the updating is performed using an expectation-maximization algorithm;
• create a model for each number in the range of numbers based on the one or more second parameters associated with the category from the categories of health conditions;
• and
• determine a score for each model, created for each number in the range of numbers, based on the one or more second parameters, an estimated likelihood value for the one or more second parameters, a first count of one or more free parameters, and a second count of data values corresponding to the one or more n-dimensional variables;
• select a best model from the models created for the range of numbers based on scores corresponding to the models;
• apply the healthcare data set to the best model, wherein the best model categorizes the plurality of patents in one or more of the categories of health conditions based on the one or more physiological markers in the healthcare dataset;
• and
• determine a diagnosis of at least one patient from the plurality of patients based on the categorization of the plurality of patients in the categories of health conditions for providing assistance to a medical practitioner.