Register for free to
view the full innovation profile.
Risk assessments are generated not only based on a current state of a patient case, but also on a patient's history record and all numerical parameters of the model were assessed.
About
Summary The inventors have constructed a Pittsburgh Cervical Cancer Screening Model. The model is a dynamic Bayesian network and consists of 19 variables. The model includes also patient history data, such as history of infections, history of cancer, history of contraception, history of abnormal cytology, menstrual history, and demographics, i.e., age and race. The most recently included variable is HPV vaccine status. The structure of the model, a qualitative part of a modeling problem, is based on existing medical knowledge enhanced with expert opinion and independence tests performed on patient records. The model was quantitatively parametrized by means of the data collected during time period of four years (2005-2008).