CASE DIAGNOSIS AS POSITIVE IDENTIFICATION IN PROSTATIC NEOPLASIA

OBJECTIVE: To apply a distance measure and Bayesian belief network-bas ed methodology to the positive identification of case diagnosis in pro static neoplasia. STUDY DESIGN: Eight morphologic and cellular feature s were analyzed in 20 cases of normal prostate, 20 of low grade prosta tic intraepithelial neoplasia (PIN), 20 of high grade PIN, 20 of prost atic adenocarcinoma with a cribriform pattern and 20 of prostatic aden ocarcinoma with an acinar pattern. The diagnostic distance was evaluat ed to measure the ''extent'' to which the feature outcomes of the indi vidual cases differed from the expected profile of outcomes in typical cases of normal prostate, low and high grade PIN, and cribriform and large acinar adenocarcinoma. Belief values were evaluated with a Bayes ian belief network (BBN). RESULTS: A bivariate representation of the c umulative absolute diagnostic distances of all the cases from the prot otypes of normal prostate and cribriform adenocarcinoma was made. Thre e separate groups of cases were observed, corresponding to normal pros tate, low grade PIN and cribriform adenocarcinoma. An additional group was formed by the cases of high grade PIN and acinar adenocarcinoma-i .e. there was complete overlap between the diagnostic distance values of cases belonging to these two categories. However, these cases showe d differences in clue outcomes. To explore the contribution of such ob servations to case identification, a bivariate representation of the d iagnostic distances from high grade PIN and acinar adenocarcinoma was made. The cases then formed five separate groups corresponding to the five diagnostic categories. When the individual cases were considered, their shortest distance was from the prototype of the category into w hich they were originally diagnosed. The BBN gave these diagnostic cat egories the highest belief values. CONCLUSION: The combined evaluation of diagnostic distance and belief represents an identification proced ure. The numeric value of certainty characterizes individual cases acc ording to the level of progression from PIN toward cancer.