| It is crucial to objectively assess orthodontic treatment outcome for patients, orthodontists, and healthcare providers. Current occlusal indices suffer from several limitations including a crisp decision making criterion that sometimes contradicts human intuition. We develop an expert system based on fuzzy reasoning that assesses orthodontic treatment outcome close to human perception. We examine its reliability by comparing the results with the opinion of a panel of expert orthodontists. Our index shows a great consistency with practitioners' clinical judgments.; It is also important for orthodontists to predict the treatment outcome prior to establishing a treatment plan. We develop two artificial neural network models to assess the treatment success by estimating the value of the Peer Assessment Rating (PAR) index from initial orthodontic measurements. Our models outperform previous linear regression predictive models. |
