Challenges in predicting community periodontal index from hospital dental care records

Abstract

Many studies have been performed in predicting periodontal diseases based on genetic information, dental images or patients habits but few have yet used dental visits records. This paper proposes a methodology based on Random Forest to classify the periodontal disease condition of patients and a way to assess the most important features that lead to a successful classification. We investigate three problematic issues found in dental care records: noise, class imbalance and concept drift and propose solutions to overcome them by respectively detecting and removing noise, under-sampling and only considering recent data. Experiments performed on records from Finnish public hospitals of two cities had good classification results and feature importance was able to detect dentists with poor performance with respect to diagnosis and treatment application.