Abstract: A method (600) of learning and/or optimizing clinical protocols and/or clinical guidelines. Workflow data is received (602) for a plurality of patients. The workflow data includes a plurality of care steps and relations there between for each of the patients. One or more sequences of care steps are identified (604) from the workflow data. The identification includes determining (612) one or more most common sequences of care steps from the workflow data. The identified sequences of care steps include the most common sequences of care steps. One of the identified sequences of care steps is selected (606) and employed (608) as a clinical protocol and/or to generate a clinical guideline.

Abstract: When generating a model of physiological systems in a patient, differential equations representing parameters and variables in the systems are linked together to form one or more sub-models (e.g., one for each physiological system), which in turn are linked together to form the patient model. Simulations of hypothetical clinical situations are then run on the model to solve for the variables, and the solutions are output as decision support data for review by a clinician to facilitate a determination of a treatment of diagnosis for the patient. Additionally, model predictions can be compared to actual measurements, when available, and the model can be refined or optimized as a function of the comparison.

Abstract: When generating a model of physiological systems in a patient, differential equations representing parameters and variables in the systems are linked together to form one or more sub-models (e.g., one for each physiological system), which in turn are linked together to form the patient model. Simulations of hypothetical clinical situations are then run on the model to solve for the variables, and the solutions are output as decision support data for review by a clinician to facilitate a determination of a treatment of diagnosis for the patient. Additionally, model predictions can be compared to actual measurements, when available, and the model can be refined or optimized as a function of the comparison.