Combining Cardiovascular and Pupil Features Using k-Nearest Neighbor Classifiers to Assess Task Demand, Social Context, and Sentence Accuracy During Listening.

In daily life, both acoustic factors and social context can affect listening effort investment. In laboratory settings, information about listening effort has been deduced from pupil and cardiovascular responses independently. The extent to which these measures can jointly predict listening-related factors is unknown. Here we combined pupil and cardiovascular features to predict acoustic and contextual aspects of speech perception. Data were collected from 29 adults (mean  =  64.6 years, SD  =  9.2) with hearing loss. Participants performed a speech perception task at two individualized signal-to-noise ratios (corresponding to 50% and 80% of sentences correct) and in two social contexts (the presence and absence of two observers). Seven features were extracted per trial: baseline pupil size, peak pupil dilation, mean pupil dilation, interbeat interval, blood volume pulse amplitude, pre-ejection period and pulse arrival time. These features were used to train k-nearest neighbor classifiers to predict task demand, social context and sentence accuracy. The k-fold cross validation on the group-level data revealed above-chance classification accuracies: task demand, 64.4%; social context, 78.3%; and sentence accuracy, 55.1%. However, classification accuracies diminished when the classifiers were trained and tested on data from different participants. Individually trained classifiers (one per participant) performed better than group-level classifiers: 71.7% (SD  =  10.2) for task demand, 88.0% (SD  =  7.5) for social context, and 60.0% (SD  =  13.1) for sentence accuracy. We demonstrated that classifiers trained on group-level physiological data to predict aspects of speech perception generalized poorly to novel participants. Individually calibrated classifiers hold more promise for future applications.

Activity Tracking Using Ear-Level Accelerometers.

Introduction: By means of adding more sensor technology, modern hearing aids (HAs) strive to become better, more personalized, and self-adaptive devices that can handle environmental changes and cope with the day-to-day fitness of the users. The latest HA technology available in the market already combines sound analysis with motion activity classification based on accelerometers to adjust settings. While there is a lot of research in activity tracking using accelerometers in sports applications and consumer electronics, there is not yet much in hearing research. Objective: This study investigates the feasibility of activity tracking with ear-level accelerometers and how it compares to waist-mounted accelerometers, which is a more common measurement location. Method: The activity classification methods in this study are based on supervised learning. The experimental set up consisted of 21 subjects, equipped with two XSens MTw Awinda at ear-level and one at waist-level, performing nine different activities. Results: The highest accuracy on our experimental data as obtained with the combination of Bagging and Classification tree techniques. The total accuracy over all activities and users was 84% (ear-level), 90% (waist-level), and 91% (ear-level + waist-level). Most prominently, the classes, namely, standing, jogging, laying (on one side), laying (face-down), and walking all have an accuracy of above 90%. Furthermore, estimated ear-level step-detection accuracy was 95% in walking and 90% in jogging. Conclusion: It is demonstrated that several activities can be classified, using ear-level accelerometers, with an accuracy that is on par with waist-level. It is indicated that step-detection accuracy is comparable to a high-performance wrist device. These findings are encouraging for the development of activity applications in hearing healthcare.

Social observation increases the cardiovascular response of hearing-impaired listeners during a speech reception task.

Certain cardiovascular measures allow for distinction between sympathetic and parasympathetic nervous system activity. Applied during listening, these measures may provide a novel and complementary insight into listening effort. To date, few studies have implemented cardiovascular measures of listening effort and seldom have these included hearing-impaired participants. These studies have generally measured changes in cardiovascular parameters while manipulating environmental factors, such as listening difficulty. Yet, listening effort is also known to be moderated by individual factors, including the importance of performing successfully. In this study, we aimed to manipulate success importance by adding observers to the traditional laboratory set-up. Twenty-nine hearing-impaired participants performed a speech reception task both alone and in the presence of two observers. Auditory stimuli consisted of Danish Hearing in Noise Test (HINT) sentences masked by four-talker babble. Sentences were delivered at two individually adapted signal-to-noise ratios, corresponding to 50 and 80% of sentences correct. We measured change scores, relative to baseline, of pre-ejection period, two indices of heart rate variability, heart rate and blood pressure (systolic, diastolic, and mean arterial pressure). After each condition, participants rated their effort investment, stress, tendency to give up and preference to change the situation to improve audibility. A multivariate analysis revealed that cardiovascular reactivity increased in the presence of the observers, compared to when the task was performed alone. More specifically, systolic, diastolic, and mean arterial blood pressure increased while observed. Interestingly, participants' subjective ratings were sensitive only to intelligibility level, not the observation state. This study was the first to report results from a range of different cardiovascular variables measured from hearing-impaired participants during a speech reception task. Due to the timing of the observers' presence, we were not able to conclusively attribute these physiological changes to being task related. Therefore, instead of representing listening effort, we suggest that the increased cardiovascular response detected during observation reveals increased physiological stress associated with potential evaluation.

Absolute Eye Gaze Estimation With Biosensors in Hearing Aids.

People with hearing impairment typically have difficulties following conversations in multi-talker situations. Previous studies have shown that utilizing eye gaze to steer audio through beamformers could be a solution for those situations. Recent studies have shown that in-ear electrodes that capture electrooculography in the ear (EarEOG) can estimate the eye-gaze relative to the head, when the head was fixed. The head movement can be estimated using motion sensors around the ear to create an estimate of the absolute eye-gaze in the room. In this study, an experiment was designed to mimic a multi-talker situation in order to study and model the EarEOG signal when participants attempted to follow a conversation. Eleven hearing impaired participants were presented speech from the DAT speech corpus (Bo Nielsen et al., 2014), with three targets positioned at -30°, 0° and +30° azimuth. The experiment was run in two setups: one where the participants had their head fixed in a chinrest, and the other where they were free to move their head. The participants' task was to focus their visual attention on an LED-indicated target that changed regularly. A model was developed for the relative eye-gaze estimation, taking saccades, fixations, head movement and drift from the electrode-skin half-cell into account. This model explained 90.5% of the variance of the EarEOG when the head was fixed, and 82.6% when the head was free. The absolute eye-gaze was also estimated utilizing that model. When the head was fixed, the estimation of the absolute eye-gaze was reliable. However, due to hardware issues, the estimation of the absolute eye-gaze when the head was free had a variance that was too large to reliably estimate the attended target. Overall, this study demonstrated the potential of estimating absolute eye-gaze using EarEOG and motion sensors around the ear.

A History of Drug-Induced Torsades de Pointes Is Associated With T-wave Morphological Abnormalities.

The hypothesis of the study is that Torsades de pointes (TdP) history can be better identified using T-wave morphology compared to Fridericia-corrected QT interval (QTcF) at baseline. ECGs were recorded at baseline and during sotalol challenge in 20 patients with a history of TdP (+TdP) and 16 patients without previous TdP (-TdP). The QTcF and T-wave morphology combination score (MCS) were calculated. At baseline, there was no significant difference in QTcF between the groups (+TdP: QTcF = 446 ± 9 ms; -TdP: QTcF = 431 ± 9 ms, P = 0.27). In contrast, MCS was significantly different between the groups at baseline (+TdP: MCS = 1.07 ± 0.095; -TdP: MCS = 0.74 ± 0.07, P = 0.012). Both QTcF and MCS could be used to discriminate between +TdP and -TdP after sotalol but only MCS reached statistical significance at baseline. Combining QTcF with MCS provided a significantly larger difference between groups than QTcF alone.

The T-peak-T-end interval as a marker of repolarization abnormality: a comparison with the QT interval for five different drugs.

BACKGROUND AND OBJECTIVE: The T-peak to T-end (TpTe) interval has been suggested as an index of transmural dispersion and as a marker of drug-induced abnormal repolarization. In this study, we investigate the relation between TpTe and the QT interval. METHODS: Electrocardiograms (ECGs) from five different drugs (sotalol, sertindole, moxifloxacin, nalmefene, and Lu 38-135) and from a placebo group were analyzed. Semi-automatic measurements of T-peak, T-end, and QRS onset were obtained. The TpTe/QT ratio was calculated to investigate the proportional relationship of QT and TpTe. RESULTS: Although a significant increase of both TpTe and QT from baseline is apparent with QT-prolonging drugs, the TpTe/QT ratio remained the same at baseline and after drug administration, thus indicating that prolongation of TpTe is just a fractional part of total QT prolongation. In the presence of notched or flattened T-waves, the uncertainty associated with measurement of the TpTe interval increases. The errors in TpTe for individual subjects may be substantial, thus complicating the use of TpTe for follow-up of individuals. CONCLUSIONS: The duration of the QT interval and TpTe are closely related. Drugs appear to prolong the TpTe interval as a predictable fraction of the total QT prolongation.