Using ordinal logistic regression to estimate the likelihood of colorectal neoplasia.

The utility of ordinal logistic regression in the prediction of colorectal neoplasia was demonstrated in a group of 461 consecutive patients undergoing colonoscopy in a community practice. One hundred twenty-nine patients had adenomatous polyps and 34 had colorectal adenocarcinoma. An ordinal logistic regression model developed in a random subset (292 patients) identified five predictors of colorectal neoplasia.

Studies of gastric ulcer disease by community-based gastroenterologists.

A community-based group of gastroenterologists examined 623 patients (541 prospectively and 82 retrospectively) with endoscopically diagnosed gastric ulcer disease during a 12-month period. Patients averaged 60 years of age; the majority were women (62%). Women were less likely to smoke, abuse alcohol, and were more likely to present with abdominal pain (p less than 0.