Learning health systems and methods

A personalized healthcare system, implemented as machine executable instructions stored on a set of at least one non-transitory computer readable medium, each operatively connected to an associated processor, the system comprising:

• a knowledge base comprising a record for each of a population of patients, a given record comprising a time series of values of a plurality of biochemical parameters taken from biochemical assays performed at scheduled intervals, a plurality of genetic markers, and a plurality of clinical parameters associated with the patient, the population of patients including, for each of a plurality of conditions of interest, a set of patients having the condition and a set of patients not having the condition;
• a baseline calculation component configured to calculate, for a given patient, an expected time series for each of a plural subset of the biochemical parameters from at least the clinical parameters and the genomic parameters associated with the patient;
• an analytics and modeling component configured to determine a deviation of the time series of values from the calculated expected time series and apply the deviation as an input to a predictive model associated with one of the plurality of conditions, the predictive model being derived from data associated with each of the set of patients having the condition and the set of patients not having the condition and configured to determine the likelihood of that the patient has the condition from at least one parameter derived from the deviation;
• and
• a user interface configured to provide the determined likelihood that the patient has the condition to a user.

A method for providing personalized healthcare for a patient comprising:

• conducting biochemical assays at scheduled intervals on blood samples taken from an patient to provide, for each of a plurality of biochemical parameters, a time series of values representing the patient;
• extracting a plurality of clinical parameters associated with the patient from a knowledge base;
• determining a plurality of genomic parameters for the patient;
• extracting a plurality of cohort parameters from respective series of biochemical assays representing individuals who are associated with the patient;
• calculating an expected time series for each of a plural subset of the plurality of biochemical parameters from at least the clinical parameters, the cohort parameters, and the genomic parameters;
• determining a deviation of the time series of values from the calculated expected time series;
• applying the deviation as an input to a predictive model associated with a condition, the predictive model being configured to determine the likelihood of the condition from at least one parameter derived from the deviation;
• and
• providing the user with a healthcare treatment course of action, based on the likelihood of the conditions.