PROGNOSIS MODELING FROM ONE OR MORE SOURCES OF INFORMATION

摘要

A predictor of medical treatment outcome is developed and applied. A prognosis model (14) is developed from literature. The model (14) is determined (204) by reverse engineering the literature reported quantities. A relationship of a given variable to a treatment outcome is derived (204) from the literature. A processor (12, 102) may then use individual patient values for one or more variables to predict outcome. The accuracy may be increased by including a data driven model (16, 18) in combination with the literature driven model.