Objective: Pain assessment in children continues to challenge clinicians and researchers, as subjective experiences of pain require inference through observable behaviors, both involuntary and deliberate. The presented approach supplements the subjective self-report-based method by fusing electrodermal activity (EDA) recordings with video facial expressions to develop an objective pain assessment metric. Such an approach is specifically important for assessing pain in children who are not capable of providing accurate self-pain reports, requiring nonverbal pain assessment. We demonstrate the performance of our approach using data recorded from children in post-operative recovery following laparoscopic appendectomy. We examined separately and combined the usefulness of EDA and video facial expression data as predictors of children's self-reports of pain following surgery through recovery. Findings indicate that EDA and facial expression data independently provide above chance sensitivities and specificities, but their fusion for classifying clinically significant pain vs. clinically nonsignificant pain achieved substantial improvement, yielding 90.91% accuracy, with 100% sensitivity and 81.82% specificity. The multimodal measures capitalize upon different features of the complex pain response. Thus, this paper presents both evidence for the utility of a weighted maximum likelihood algorithm as a novel feature selection method for EDA and video facial expression data and an accurate and objective automated classification algorithm capable ofdiscriminating clinically significant pain from clinically nonsignificant pain in children.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that is often accompanied by impaired emotion regulation (ER). There has been increasing emphasis on developing evidence-based approaches to improve ER in ASD. Electroencephalography (EEG) has shown success in reducing ASD symptoms when used in neurofeedback-based interventions. Also, certain EEG components are associated with ER. Our overarching goal is to develop a technology that will use EEG to monitor real-time changes in ER and perform intervention based on these changes. As a first step, an EEG-based brain computer interface that is based on an Affective Posner task was developed to identify patterns associated with ER on a single trial basis, and EEG data collected from 21 individuals with ASD. Accordingly, our aim in this study is to investigate EEG features that could differentiate between distress and non-distress conditions. Specifically, we investigate if the EEG time-locked to the visual feedback presentation could be used to classify between WIN (non-distress) and LOSE (distress) conditions in a game with deception. Results showed that the extracted EEG features could differentiate between WIN and LOSE conditions (average accuracy of 81%), LOSE and rest-EEG conditions (average accuracy 94.8%), and WIN and rest-EEG conditions (average accuracy 94.9%).

Mindfulness has growing empirical support for improving emotion regulation in individuals with Autism Spectrum Disorder (ASD). Mindfulness is cultivated through meditation practices. Assessing the role of mindfulness in improving emotion regulation is challenging given the reliance on self-report tools. Electroencephalography (EEG) has successfully quantified neural responses to emotional arousal and meditation in other populations, making it ideal to objectively measure neural responses before and after mindfulness (MF) practice among individuals with ASD. We performed an EEG-based analysis during a resting state paradigm in 35 youth with ASD. Specifically, we developed a machine learning classifier and a feature and channel selection approach that separates resting states preceding (Pre-MF) and following (Post-MF) a mindfulness meditation exercise within participants. Across individuals, frontal and temporal channels were most informative. Total power in the beta band (16–30 Hz), Total power (4–30 Hz), relative power in alpha band (8–12 Hz) were the most informative EEG features. A classifier using a non-linear combination of selected EEG features from selected channel locations separated Pre-MF and Post-MF resting states with an average accuracy, sensitivity, and specificity of 80.76%, 78.24%, and 82.14% respectively. Finally, we validated that separation between Pre-MF and Post-MF is due to the MF prime rather than linear-temporal drift. This work underscores machine learning as a critical tool for separating distinct resting states within youth with ASD and will enable better classification of underlying neural responses following brief MF meditation.