An integrated approach to detecting communicative intent amid hyperkinetic movements in children.

Children with hyperkinetic movement (HKM) often have limited access to traditional augmentative and alternative communication technologies (e.g., mechanical switches). To seek a communication solution for these children, this study explored the possibility that discernable biomechanical patterns, related to preference, exist amid HKM. We deployed a unified approach to analyse a child's movements, fusing caregiver and clinician observations with quantitative data (accelerations of the upper extremities). Two case studies were examined. In both, the accelerometer data identified preference at adjusted accuracies statistically above chance using a linear discriminant classifier. Visually, communicative movement patterns were identified in the first child (κ=0.25-0.27) but not in the second child (κ=0.03-0.11). Implications of this study include possible enhancement in communication and independence for these children.

Physiological and emotional responses of disabled children to therapeutic clowns: a pilot study.

This pilot study examined the effects of Therapeutic Clowning on inpatients in a pediatric rehabilitation hospital. Ten disabled children with varied physical and verbal expressive abilities participated in all or portions of the data collection protocol. Employing a mixed-method, single-subject ABAB study design, measures of physiological arousal, emotion and behavior were obtained from eight children under two conditions-television exposure and therapeutic clown interventions. Four peripheral autonomic nervous system (ANS) signals were recorded as measures of physiological arousal; these signals were analyzed with respect to measures of emotion (verbal self reports of mood) and behavior (facial expressions and vocalizations). Semistructured interviews were completed with verbally expressive children (n = 7) and nurses of participating children (n = 13). Significant differences among children were found in response to the clown intervention relative to television exposure. Physiologically, changes in ANS signals occurred either more frequently or in different patterns. Emotionally, children's (self) and nurses' (observed) reports of mood were elevated positively. Behaviorally, children exhibited more positive and fewer negative facial expressions and vocalizations of emotion during the clown intervention. Content and themes extracted from the interviews corroborated these findings. The results suggest that this popular psychosocial intervention has a direct and positive impact on hospitalized children. This pilot study contributes to the current understanding of the importance of alternative approaches in promoting well-being within healthcare settings.

Revealing personhood through biomusic of individuals without communicative interaction ability.

An increasing number of people are unable to engage in communicative interactions because of their inability to move, speak, and control traditional augmentative and alternative communication devices. According to social interactionist theory, the existence of the human self hinges on successful interaction with others; consequently, those who cannot interact are at risk of not being accorded personhood. This article is a request for research towards the development of technologies that would give caregivers access to the autonomic physiological signals of individuals who are unable to communicate. It explores the hypothesis that meaningful manifestation of signals that change according to mental and emotional states will reveal individual personhood. We hypothesize that music is ideally suited as the basis of interaction with this population, and that physiologically driven musical expression is a form of individual biomusic that can enrich social interaction.

On the use of peripheral autonomic signals for binary control of body-machine interfaces.

In this work, the potential of using peripheral autonomic (PA) responses as control signals for body-machine interfaces that require no physical movement was investigated. Electrodermal activity, skin temperature, heart rate and respiration rate were collected from six participants and hidden Markov models (HMMs) were used to automatically detect when a subject was performing music imagery as opposed to being at rest. Experiments were performed under controlled silent conditions as well as in the presence of continuous and startle (e.g. door slamming) ambient noise. By developing subject-specific HMMs, music imagery was detected under silent conditions with the average sensitivity and specificity of 94.2% and 93.3%, respectively. In the presence of startle noise stimuli, the system sensitivity and specificity levels of 78.8% and 80.2% were attained, respectively. In environments corrupted by continuous ambient and startle noise, the system specificity further decreased to 75.9%. To improve the system robustness against environmental noise, a startle noise detection and compensation strategy were proposed. Once in place, performance levels were shown to be comparable to those observed in silence. The obtained results suggest that PA signals, combined with HMMs, can be useful tools for the development of body-machine interfaces that allow individuals with severe motor impairments to communicate and/or to interact with their environment.

Bedside computer access for an individual with severe and multiple disabilities: a case study.

PURPOSE: This case study documents the process of designing a custom-tailored bedside computer access solution for a 20-year old individual with quadriplegia and reports the effects of computer access on her participation in life activities. METHOD: We adopted a person-focused approach to match the individual to an access solution. Two months after the access solution's introduction, we measured its impact using a 2-dimensional Fitt's Law test and questionnaire from the ISO 9241-9 standards document, typing tests, a usage log and a semi-structured interview. The Canadian Occupational Performance Measure was also administered pre- and post- access, focusing on the client's perceived ability to use the computer. RESULTS: After 2 months, the individual was spending an average of 8.4 h per day on the computer, engaging in electronic communication, recreational, and educational activities. She learned single-switch typing with a throughput of 1.03 bits/s and targeting accuracy of 87.5%. The questionnaire revealed that the client was thoroughly satisfied with the interface. These results were interpreted as positive gains in the International Classification of Functioning, Disability and Health domains of communication and social interaction. CONCLUSIONS: By addressing individual goals, abilities and relevant environmental factors, a bedside computer access solution can be developed for individuals in long-term care. The introduction of a computer access solution augmented the participant's communication, leisure and educational activities, as well as perceived independence.

A cardiorespiratory classifier of voluntary and involuntary electrodermal activity.

BACKGROUND: Electrodermal reactions (EDRs) can be attributed to many origins, including spontaneous fluctuations of electrodermal activity (EDA) and stimuli such as deep inspirations, voluntary mental activity and startling events. In fields that use EDA as a measure of psychophysiological state, the fact that EDRs may be elicited from many different stimuli is often ignored. This study attempts to classify observed EDRs as voluntary (i.e., generated from intentional respiratory or mental activity) or involuntary (i.e., generated from startling events or spontaneous electrodermal fluctuations). METHODS: Eight able-bodied participants were subjected to conditions that would cause a change in EDA: music imagery, startling noises, and deep inspirations. A user-centered cardiorespiratory classifier consisting of 1) an EDR detector, 2) a respiratory filter and 3) a cardiorespiratory filter was developed to automatically detect a participant's EDRs and to classify the origin of their stimulation as voluntary or involuntary. RESULTS: Detected EDRs were classified with a positive predictive value of 78%, a negative predictive value of 81% and an overall accuracy of 78%. Without the classifier, EDRs could only be correctly attributed as voluntary or involuntary with an accuracy of 50%. CONCLUSIONS: The proposed classifier may enable investigators to form more accurate interpretations of electrodermal activity as a measure of an individual's psychophysiological state.

A review of emerging access technologies for individuals with severe motor impairments.

Research and development in the field of access technologies for individuals with severe motor impairments has accelerated over the past 10 years. Many emergent alternatives to conventional mechanical switches, such as infrared sensing, electromyography, oculography, and computer vision, have been investigated for those retaining some limited volitional motor ability. At the same time, electroencephalography, electrocorticography, intracortical recordings, and electrodermal activity have been explored for those presenting as locked in. The relevant literature is scattered across many disciplines, obfuscating the strength of the clinical evidence in support of the different access technologies currently in development. This article systematically organizes the literature on the aforementioned access technologies, summarizing their underlying operational mechanisms while reviewing the clinical evidence reported between 1996 and 2006. Research evidence within this period is generally found to be at the case study or uncontrolled study level, with very modest sample sizes. Novel mechanical switches and electroencephalography-based access systems dominate the literature, whereas many other movement-based access modalities have emerged with promising early findings. Access methods for those without extant physical movement constitute a critical direction for future and ongoing research efforts.

Assessing the potential of electrodermal activity as an alternative access pathway.

An embedded multiple-case study was conducted with six able-bodied participants to evaluate the potential of electrodermal activity (EDA) as an alternative access pathway to electronic aids to daily living. Electrodermal signals were recorded while participants alternated between rest and three different mental or breathing exercises. In a subsequent experimental session, the exercise exerting the greatest influence on EDA was used to volitionally generate an 'active' state. Two classification algorithms, namely, a probabilistic classifier and a handcrafted rule base were developed and tailored to each individual's physiological patterns to discriminate between participant states. Through cross-validation, participant state was correctly identified to an accuracy exceeding 80% using either classification algorithm. This result demonstrates that consciously controlled EDA could conceivably serve as a binary switch, and encourages further research towards EDA-based alternative access for people who are locked-in.

A radial basis classifier for the automatic detection of aspiration in children with dysphagia.

BACKGROUND: Silent aspiration or the inhalation of foodstuffs without overt physiological signs presents a serious health issue for children with dysphagia. To date, there are no reliable means of detecting aspiration in the home or community. An assistive technology that performs in these environments could inform caregivers of adverse events and potentially reduce the morbidity and anxiety of the feeding experience for the child and caregiver, respectively. This paper proposes a classifier for automatic classification of aspiration and swallow vibration signals non-invasively recorded on the neck of children with dysphagia. METHODS: Vibration signals associated with safe swallows and aspirations, both identified via videofluoroscopy, were collected from over 100 children with neurologically-based dysphagia using a single-axis accelerometer. Five potentially discriminatory mathematical features were extracted from the accelerometry signals. All possible combinations of the five features were investigated in the design of radial basis function classifiers. Performance of different classifiers was compared and the best feature sets were identified. RESULTS: Optimal feature combinations for two, three and four features resulted in statistically comparable adjusted accuracies with a radial basis classifier. In particular, the feature pairing of dispersion ratio and normality achieved an adjusted accuracy of 79.8 +/- 7.3%, a sensitivity of 79.4 +/- 11.7% and specificity of 80.3 +/- 12.8% for aspiration detection. Addition of a third feature, namely energy, increased adjusted accuracy to 81.3 +/- 8.5% but the change was not statistically significant. A closer look at normality and dispersion ratio features suggest leptokurticity and the frequency and magnitude of atypical values as distinguishing characteristics between swallows and aspirations. The achieved accuracies are 30% higher than those reported for bedside cervical auscultation. CONCLUSION: The proposed aspiration classification algorithm provides promising accuracy for aspiration detection in children. The classifier is conducive to hardware implementation as a non-invasive, portable "aspirometer". Future research should focus on further enhancement of accuracy rates by considering other signal features, classifier methods, or an augmented variety of training samples. The present study is an important first step towards the eventual development of wearable intelligent intervention systems for the diagnosis and management of aspiration.

A radial basis function classifier for pediatric aspiration detection.

Silent aspiration presents a serious health issue for children with dysphagia. To date, there is no satisfactory means of detecting aspiration in the home or community. In an effort to design a practical device that could offer reliability, non-invasiveness, portability, and easy usability, radial basis functions based on cervical accelerometry signals were investigated. Vibration signals associated with safe swallows and aspirations, both identified via videofluoroscopy, were collected from over 100 children with neurologically-based dysphagia using a single-axis accelerometer. Three time-domain discriminatory mathematical features were extracted from the accelerometry signals. An exhaustive set of all possible combinations of the features was investigated in the design of radial basis function classifiers. The feature pairing of dispersion ratio and normality achieved an accuracy of 81.03 +/- 5.78%, a false negative rate of 9.06 +/- 4.84%, and a false positive rate of 9.91 +/- 5.03% for aspiration detection. The proposed classifier can be easily implemented in a hand-held device.

Conscious control of electrodermal activity: the potential of mental exercises.

Few practical methods of communicating with people who are locked-in currently exit. This study investigates conscious control of physiological signals, specifically electrodermal activity, to generate two distinguishable and reproducible states. These states can be translated into a binary signal to control a communication device for people who are locked in. Breathing rates, mental arithmetic and mental music were investigated as means of controlling electrodermal activity. Features extracted from the signals included mean, range and number of electrodermal reactions. For these of four subjects, at least one mental technique caused a reproducible, statistically significant the potential of using mental exercises to develop volitional control of electrodermal activity.