Compositions and methods to detect gastrointestinal disease

A method for determining the prognosis of pediatric inflammatory bowel diseases (IBD) in a patient, the method comprising:

• a. fitting a Markov model using a two state transition matrix and propensity values measured among a plurality of subjects, wherein the two state transition matrix comprises a first state and a second state, wherein the first state comprises a non-pediatric inflammatory bowel disease status, wherein the second state comprises a pediatric inflammatory bowel disease status, wherein a propensity value is a function of intestinal Alkaline Phosphatase (iAP) activity values and the amount of iAP found in a stool sample;
• b. using a propensity value of the patient and the fitted Markov model to estimate a probability of transitioning from the first state to the second state, wherein the fitted model indicates that an increased propensity level of the patient significantly increases the probability of transitioning from the first state to the second state;
• c. identifying a propensity value of the infant that is greater than or equal to a threshold value of about 0.5, and treating the patient when the propensity value is greater than or equal to a threshold value of about 0.5.