Low Complexity Adaptive Nonlinear Models for the Diagnosis of Periodontal Disease

Abstract

Background / Objective: The paper addresses a specific clinical problem of diagnosis of periodontal disease with an objective to develop and evaluate the performance of low complexity Adaptive Nonlinear Models (ANM) using nonlinear expansion schemes and describes the basic structure and development of ANMs in detail. Methods: Diagnostic data pertaining to periodontal findings of teeth obtained from patients have been used as inputs to train and validate the proposed models. Results: Results obtained from simulations experiments carried out using various nonlinear expansion schemes have been compared in terms of various performance measures such as Mean Absolute Percentage Error (MAPE), matching efficiency, sensitivity, specificity, false positive rate, false negative rate and diagnostic accuracy. Conclusion: The ANM with seven trigonometric expansion scheme demonstrates the best performance in terms of all measures yielding a diagnostic accuracy of 99.11% compared to 94.64% provided by adaptive linear model.