Probabilities for a probabilistic network: A case-study in Oesophageal Carcinoma

Abstract

With the help of two experts in gastrointestinal oncology from the Netherlands Can­ cer Institute, Antoni van Leeuwenhoekhuis, a decision­support system is being devel­ oped for patient­specific therapy selection for oesophageal carcinoma. The kernel of the system is a probabilistic network that describes the characteristics of oesophageal carcinoma and the pathophysiological processes of invasion and metastasis. While the construction of the graphical structure of the network was relatively straightfor­ ward, probability elicitation with existing methods proved to be a major obstacle. We designed a new method for eliciting probabilities from experts that combines the ideas of transcribing probabilities as fragments of text and of using a scale with both numerical and verbal anchors for marking assessments. The method allowed us to elicit the many probabilities required for our network in little time. Using data from 185 patients, we conducted an evaluation study to assess the quality of the proba­ bilities obtained. We found that for 85% of the patients, our probabilistic network yielded the correct outcome.