Extracting clinical care pathways correlated with outcomes

A method for data analysis, comprising:

• constructing patient traces as a set of medical events for each patient of a patient population, the patient population being segmented based on patient outcomes;
• reducing medical events in one or more of the patient traces to provide processed patient traces;
• clustering the processed patient traces to identify a cluster of patient traces;
• mining a process model, using a processor, representing an aggregation of treatment pathways in the patient traces from the cluster;
• identifying patterns from patient traces that are discriminative of patient outcomes;
• displaying, on a visual interface having a display, at least one of the patterns with respect to the process model to identify treatment pathways that are correlated with the patient outcomes, the plurality of patterns including at least one pattern associated with a positive patient outcome and at least one other pattern associated with a negative patient outcome;
• and
• generating a refined process model of positive outcomes, wherein generating the refined process model includes varying a threshold on a minimum number of observations identified in the process mining and defining a dependence edge between two repeating event nodes according to one or more frequencies of directions of dependencies for the repeating event nodes, and wherein the refined process model is used to provide treatment to a particular patient.