Deep learning improves prediction of periodontal therapy effectiveness in Chinese patients

Abstract

Clinical outcomes in periodontal treatment have been confirmed to be influenced by several systemic and local factors such as age, gender, cigarette smoking, and patient compliance, among others. [1][2][3] The combined effects of various factors produce varying states and progression of periodontitis among different individuals which leads to great differences in treatment response. 4 Since the last century, a number of prognostic models and risk assessment tools 2,5-8 based on the abovementioned factors have been developed to calculate the probability of periodontitis progression 9,10 and to predict tooth survival after therapy. 3,5,7,11 However,