Classification of respiratory disturbances in Rett Syndrome patients using Restricted Boltzmann Machine

Rett syndrome (RTT) is a severe neurodevelopmental disorder that can cause pervasive wakeful respiratory disturbances that include tachypnea, breath-holding, and central apnea. Quantitative analysis of these respiratory disturbances in RTT is considered a promising outcome measure for clinical trials. Currently, machine learning methodologies have not been employed to automate the classification of RTT respiratory disturbances. In this paper, we propose using temporal, flow, and autocorrelation features taken from the respiratory inductance plethsymography chest signal. We tested the performance of six classifiers including: Support Vector Machine, Restricted-Boltzmann-Machine, Back-propagation, Levenberg-Marquardt, and Decision-Fusion. We evaluate this classification in two modalities: (1) a subject-independent modality (leave-one-subject-out) obtaining the best F1 score in 93.67%, and (2) a trial-independent modality (leave-one-trial-out per subject) obtaining the best F1 score in 78.21%.