Accuracy and consistency of radiographic interpretation among clinical instructors in conjunction with a training program

Abstract

There are inaccuracies and inconsistencies of radiographic interpretation among clinical instructors. The purpose of this investigation was to determine if a training program could improve the accuracy and consistency of instructors' ratings of bone loss. A total of thirty-five clinical instructors consisting of periodontal faculty (periodontists and general dentists), dental hygiene faculty, and periodontal graduate students viewed projected digitized radiographic images and quantified bone loss for twenty-five teeth into four descriptive categories. Ratings of bone loss were made immediately before (pretest) and after (post-test 1) initiation of the training program and then again three months later (post-test 2). Ratings were compared to the correct choice categories as determined by direct measurement using the Schei ruler. Overall agreement with the correct choice improved over time (from 64.5 percent to 85.2 percent) with the greatest change from pretest (64.5 percent) to post-test 1 (76.5 percent). Mean and absolute differences improved in three of the four categories, but worsened in one from pretest to post-test 1. This category returned to its original high value at post-test 2. The greatest improvement in consistency among instructors' ratings was seen in one of the four categories, which was "none" (no bone loss). Extension of the training program may further enhance the accuracy and consistency of instructors' radiographic interpretation.