Abstract Introduction Of 34M US adults affected by insomnia, 75% are older adults. Cognitive Behavioral Therapy for Insomnia (CBTi) is recommended because polypharmacy and fall risks accompany pharmacotherapies. We evaluated telehealth CBTi with an interactive patient-therapist application, SleepSpace, which integrates data from wearables and Internet of Things (IoT) devices. Methods This RCT (NCT05015803) followed community-dwelling participants 60-90 years old with an Insomnia Severity Index (ISI) score ≥11. Absence of mild cognitive impairment was affirmed with the Montreal Cognitive Assessment (MoCA) Blind v.8 (score ≥ 18). Participants wore actigraphy and an Apple Watch throughout and independently completed a weekly electronic ISI. They attended 7 weekly, ~1hr video-conference sessions (1 intake, 6 procedural) with a clinical therapist. Participants were randomly assigned to one of 3 study conditions (age-, gender-stratified): 1) education about sleep hygiene only (20%; “Hygiene”), 2) telehealth CBTi (40%; “CBTi”), and 3) telehealth CBTi with phone/IoT platform application enhancement (40%; “CBTi+”) including meditations, sound machines, smart light bulbs, an electronic diary, with visualizations, metrics, and wearable data shared with participants in the CBTi+ condition. Linear mixed models compared ISI change across time by group. Results Of 60 individuals enrolled, 54 were randomized and retained (39F, mean±SD age=71±4y). ISI slopes for both CBTi (-.09/day) and CBTi+ (-.09/day) declined at a significantly steeper rate than Hygiene (-.05/day; each p<.05), but did not differ from one another. Significantly more CBTi+ participants exhibited full remission (ISI < 8; 18/21, 85.7%) than in the Hygiene group (5/11, 45.4%; p=.03 Fisher’s Exact); CBTi alone (16/22, 72.7%) did not significantly differ from Hygiene, although with limited statistical power. Diary-reported sleep measures to calculate self-reported sleep efficiency (sSE) in the final week at end of treatment revealed differences in mean±SD for Hygiene (81±05%) vs. CBTI (88±07%), and vs. CBTI+ (90±04%, p< 0.05, t-test). Conclusion This research supports the efficacy of a remote, technology-assisted telehealth CBTi platform to improve insomnia symptoms comparable to standard telehealth-CBTi in older adults with insomnia. The platform provides enhanced data access for therapists and opportunities for data-driven engagement with patients. Support (if any) R44 AG056250, UL1TR002014

Aging populations are at increased risk of sleep deficiencies (e.g., insomnia) that are associated with a variety of chronic health risks, including Alzheimer's disease and related dementias (ADRD). Insomnia medications carry additional risk, including increased drowsiness and falls, as well as polypharmacy risks. The recommended first line treatment for insomnia is cognitive behavioral therapy for insomnia (CBTi), but access is limited. Telehealth is one way to increase access, particularly for older adults, but to date telehealth has been typically limited to simple videoconferencing portals. While these portals have been shown to be non-inferior to in-person treatment, it is plausible that telehealth could be significantly improved. This work describes a protocol designed to evaluate whether a clinician-patient dashboard inclusive of several user-friendly features (e.g., patterns of sleep data from ambulatory devices, guided relaxation resources, and reminders to complete in-home CBTi practice) could improve CBTi outcomes for middle-to older-aged adults (N = 100). Participants were randomly assigned to one of three telehealth interventions delivered through 6-weekly sessions: (1) CBTi augmented with a clinician patient dashboard, smartphone application, and integrated smart devices; (2) standard CBTi (i.e., active comparator); or (3) sleep hygiene education (i.e., active control). All participants were assessed at screening, pre study evaluation, baseline, throughout treatment, and at 1-week post-treatment. The primary outcome is the Insomnia Severity Index. Secondary and exploratory outcomes span sleep diary, actiwatch and Apple watch assessed sleep parameters (e.g., efficiency, duration, timing, variability), psychosocial correlates (e.g., fatigue, depression, stress), cognitive performance, treatment adherence, and neurodegenerative and systemic inflammatory biomarkers.

Machine learning (ML) offers some of the most cost-effective methods for extracting useful insights from large data sets. Availability of large data sets and tools for modular, scalable, reproducible, open, shareable data analytic workflows, allow researchers to rapidly train, rigorously validate and share predictive models in health research. These developments offer unprecedented opportunities for overcoming some of the limitations in the analyses of sleep- and circadian-related data, including data collected using the field's "gold standard" clinical monitoring techniques, such as polysomnography (PSG) and evaluation of ML-trained models, e.g., for estimating sleep parameters. Sleep and circadian rhythms researchers increasingly use multi-modal monitoring techniques, often with humans evaluating the data who make inferences about the collective integration of those signals when "scoring" or annotating the data (e.g., with sleep vs. wake states, sleep stage, etc. We support and extend the rationale supporting the AASM's position statement that the multi-modal and complex nature of data collected in clinical sleep monitoring is "uniquely positioned to benefit from the use of artificial intelligence". We emphasize some specific applications to sleep and circadian rhythms research, and argue for the expanding potential of ML and Artificial Intelligence (AI) in the broader scientific approach to sleep and circadian research. We also underscore some of the factors that must be addressed to ensure methodologically rigorous applications of ML in this area.

GOAL AND AIMS:Commonly used actigraphy algorithms are designed to operate within a known in-bed interval. However, in free-living scenarios this interval is often unknown. We trained and evaluated a sleep/wake classifier that operates on actigraphy over ∼24-hour intervals, without knowledge of in-bed timing. FOCUS TECHNOLOGY:Actigraphy counts from ActiWatch Spectrum devices. REFERENCE TECHNOLOGY:Sleep staging derived from polysomnography, supplemented by observation of wakefulness outside of the staged interval. Classifications from the Oakley actigraphy algorithm were additionally used as performance reference. SAMPLE:Adults, sleeping in either a home or laboratory environment. DESIGN:Machine learning was used to train and evaluate a sleep/wake classifier in a supervised learning paradigm. The classifier is a temporal convolutional network, a form of deep neural network. CORE ANALYTICS:Performance was evaluated across ∼24 hours, and additionally restricted to only in-bed intervals, both in terms of epoch-by-epoch performance, and the discrepancy of summary statistics within the intervals. ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES:Performance of the trained model applied to the Multi-Ethnic Study of Atherosclerosis dataset. CORE OUTCOMES:Over ∼24 hours, the temporal convolutional network classifier produced the same or better performance as the Oakley classifier on all measures tested. When restricting analysis to the in-bed interval, the temporal convolutional network remained favorable on several metrics. IMPORTANT SUPPLEMENTAL OUTCOMES:Performance decreased on the Multi-Ethnic Study of Atherosclerosis dataset, especially when restricting analysis to the in-bed interval. CORE CONCLUSION:A classifier using data labeled over ∼24-hour intervals allows for the continuous classification of sleep/wake without knowledge of in-bed intervals. Further development should focus on improving generalization performance.

Abstract Introduction Wrist-worn research-grade actigraphy devices are commonly used to identify sleep and wakefulness in freely-living people. However, common existing algorithms were developed primarily to classify sleep-wake within a defined in-bed period with PSG, and exhibit relatively high sensitivity (accuracy on sleep epochs) but relatively low specificity (accuracy on wake epochs). This classification imbalance results in the algorithms performing poorly when attempting to classify data that does not have a predefined sleep period, such as over a 24-hour interval. Here, we develop a 24-hour actigraphy classifier to overcome limitations in specificity (accuracy on wake epochs), which typically afflict in-bed focused algorithms. Methods Four datasets scored via either PSG or direct observation of daytime wakefulness were combined (n=52 participants of mean age 49.8yrs, age range 19 - 86; 52% male; 221 total days/nights). Actigraphy (counts) and PSG (RPSGT-staged epochs) were temporally aligned. A model was trained to transform a time-series actigraphy counts to a time series of sleep-wake classifications, using the TensorFlow library for Python. 5-fold cross-validation was used to train and evaluate the model. Classification performance was compared to the output of the Spectrum device (Philips-Respironics) using the Oakley algorithm with a wake threshold of ‘medium’. Results The developed classifier was compared to the Spectrum classifications across the 24-hour intervals. The developed classifier had higher accuracy (95.4% vs. 76.8%), higher specificity (95.9% vs. 68.9%) and higher balanced-accuracy (95.2% vs. 81.6%) relative to the Spectrum classifications, each assessed via paired-sample t-test. Sensitivity did not statistically differ (94.5% vs. 94.4%). Conclusion The model trained and evaluated on 24-hour data outperformed the existing algorithm output in terms of overall accuracy, specificity, and balanced accuracy, while sensitivity did not significantly differ. A model trained on 24-hour data may be more appropriate for analyses of freely living people, or older populations where napping is more common. Developing an accurate 24-hour sleep/wake classifier fosters new opportunities to evaluate sleep patterns in the absence of self-reports or assumptions about time in bed. Support (If Any) UL1TR002014, NSF#1622766, R43/44-AG056250

Relatively little is known about the relation between subthreshold error corrections and post-error behavioral compensations. The present study utilized lateralized beta power, which has been shown to index response preparation, to examine subthreshold error corrections in a task known to produce response conflict, the Simon task. We found that even when an overt correction is not made, greater activation of the corrective response, indexed by beta suppression ipsilateral to the initial responding hand, predicted post-error speeding, and enhanced post-error accuracy at the single-trial level. This provides support for the notion that response conflict associated with errors can be adaptive, and suggests that subthreshold corrections should be taken into account to fully understand error-monitoring processes. Furthermore, we expand on previous findings that demonstrate that post-error slowing and post-error accuracy can be dissociated, as well as findings that suggest that frontal midline theta oscillations and the error-related negativity (ERN) are dissociable neurocognitive processes.

STUDY OBJECTIVES:Multisensor wearable consumer devices allowing the collection of multiple data sources, such as heart rate and motion, for the evaluation of sleep in the home environment, are increasingly ubiquitous. However, the validity of such devices for sleep assessment has not been directly compared to alternatives such as wrist actigraphy or polysomnography (PSG).METHODS:Eight participants each completed four nights in a sleep laboratory, equipped with PSG and several wearable devices. Registered polysomnographic technologist-scored PSG served as ground truth for sleep-wake state. Wearable devices providing sleep-wake classification data were compared to PSG at both an epoch-by-epoch and night level. Data from multisensor wearables (Apple Watch and Oura Ring) were compared to data available from electrocardiography and a triaxial wrist actigraph to evaluate the quality and utility of heart rate and motion data. Machine learning methods were used to train and test sleep-wake classifiers, using data from consumer wearables. The quality of classifications derived from devices was compared.RESULTS:For epoch-by-epoch sleep-wake performance, research devices ranged in d' between 1.771 and 1.874, with sensitivity between 0.912 and 0.982, and specificity between 0.366 and 0.647. Data from multisensor wearables were strongly correlated at an epoch-by-epoch level with reference data sources. Classifiers developed from the multisensor wearable data ranged in d' between 1.827 and 2.347, with sensitivity between 0.883 and 0.977, and specificity between 0.407 and 0.821.CONCLUSIONS:Data from multisensor consumer wearables are strongly correlated with reference devices at the epoch level and can be used to develop epoch-by-epoch models of sleep-wake rivaling existing research devices.

The present study investigated the neural dynamics of error processing in both the time and frequency domains, as well as associated behavioral phenomena, at the single-trial level. We used a technique that enabled us to separately investigate the evoked and induced aspects of the EEG signal (Cohen & Donner, 2013, Journal of Neurophysiology, 110[12], 2752–2763). We found that at the single-trial level, while the (evoked) error-related negativity (ERN) predicted only post-error slowing (PES)—and only when errors occurred on incongruent trials—induced frontal midline theta power served as a robust predictor of both PES and post-error accuracy (PEA) regardless of stimulus congruency. Mediation models of both electrophysiological indices demonstrated that although the relationship between theta and PEA was mediated by PES, there was not a relationship between the ERN and PEA. Our data suggest that although the ERN and frontal midline theta index functionally related underlying cognitive processes, they are not simply the same process manifested in different domains. In addition, our findings are consistent with the adaptive theory of post-error slowing, as PES was positively associated with post-error accuracy at the single-trial level. More generally, our study provides additional support for the inclusion of a time-frequency approach to better understand the role of medial frontal cortex in action monitoring.

Purpose: In non-rapid eye movement (NREM) stage 3 sleep (N3), phase-locked pink noise auditory stimulation can amplify slow oscillatory activity (0.5-1 Hz). Open-loop pink noise auditory stimulation can amplify slow oscillatory and delta frequency activity (0.5-4 Hz). We assessed the ability of pink noise and other sounds to elicit delta power, slow oscillatory power, and N3 sleep. Participants and Methods: Participants (n = 8) underwent four consecutive inpatient nights in a within-participants design, starting with a habituation night. A registered polysomnographic technologist live-scored sleep stage and administered stimuli on randomized counterbalanced Enhancing and Disruptive nights, with a preceding Habituation night (night 1) and an intervening Sham night (night 3). A variety of non-phase-locked pink noise stimuli were used on Enhancing night during NREM; on Disruptive night, environmental sounds were used throughout sleep to induce frequent auditory-evoked arousals. Results: Total sleep time did not differ between conditions. Percentage of N3 was higher in the Enhancing condition, and lower in the Disruptive condition, versus Sham. Standard 0.8 Hz pink noise elicited low-frequency power more effectively than other pink noise, but was not the most effective stimulus. Both pink noise on the "Enhancing" night and sounds intended to Disrupt sleep administered on the "Disruptive" night increased momentary delta and slow-wave activity (ie, during stimulation versus the immediate pre-stimulation period). Disruptive auditory stimulation degraded sleep with frequent arousals and increased next-day vigilance lapses versus Sham despite preserved sleep duration and momentary increases in delta and slow-wave activity. Conclusion: These findings emphasize sound features of interest in ecologically valid, translational auditory intervention to increase restorative sleep. Preserving sleep continuity should be a primary consideration if auditory stimulation is used to enhance slow-wave activity.

As semiautonomous driving systems are becoming prevalent in late model vehicles, it is important to understand how such systems affect driver attention. This study investigated whether measures from low-cost devices monitoring peripheral physiological state were comparable to standard EEG in predicting lapses in attention to system failures. Twenty-five participants were equipped with a low-fidelity eye-tracker and heart rate monitor and with a high-fidelity NuAmps 32-channel quick-gel EEG system and asked to detect the presence of potential system failure while engaged in a fully autonomous lane changing driving task. To encourage participant attention to the road and to assess engagement in the lane changing task, participants were required to: (a) answer questions about that task; and (b) keep a running count of the type and number of billboards presented throughout the driving task. Linear mixed effects analyses were conducted to model the latency of responses reaction time (RT) to automation signals using the physiological metrics and time period. Alpha-band activity at the midline parietal region in conjunction with heart rate variability (HRV) was important in modeling RT over time. Results suggest that current low-fidelity technologies are not sensitive enough by themselves to reliably model RT to critical signals. However, that HRV interacted with EEG to significantly model RT points to the importance of further developing heart rate metrics for use in environments where it is not practical to use EEG.

Empirical research demonstrates that when the time following error commission is constrained, subsequent sensory processing can be impaired (Buzzell et al., 2017). This reduction in sensory processing is presumably due to a bottleneck for cognitive resources produced by an overlap between error processing and subsequent stimulus processing. This finding suggests that the system dedicated to improving task performance can actually sometimes be the source of performance failures. Although this finding established that data-limited errors lead to a reduction in sensory processing at short response stimulus intervals (RSIs), it remains unclear if the relationship between error processing and subsequent sensory processing can be modulated by speeded-response errors. In the present study, event-related potentials and behavioral measures were recorded while participants performed a modified version of a Simon task, in which RSI duration was varied. We found that sensory processing, indexed by the P1 component, was reduced following errors at short (200-533 ms), but not long (866-1200 ms), RSIs. Moreover, the magnitude of error processing differentially influenced subsequent sensory processing as a function of RSI. However, whereas prior work demonstrated that the error positivity (Pe) modulated sensory processing on the subsequent trial, only the error-related negativity (ERN) did so within the Simon task. This suggests that although both data-limited errors and speeded-response errors can impact subsequent sensory processing, different stages of error processing appear to mediate this phenomenon.

Mind wandering is a poorly understood phenomenon that can undermine driving safety. Driving performance measures have been found to be associated with mind wandering (e.g., steering wheel movements, standard deviation of lateral position, and speed variation). However, no one measure can fully describe the driver behavior associated with mind wandering. Therefore, in this paper we explore the effect of mind wandering on nine steering measures with data collected from a study that included nine drivers over two sessions of driving over five days. Participants were periodically probed to report their attentional state–whether they were mind wandering or focusing on the task. We used two dimensionality-reduction techniques—Principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE)—to visualize the dimensions underlying the nine measures. Comparing PCA to t-SNE highlights the benefits of t-SNE in revealing the fine structure that differentiates driving behavior. These visualizations show that a) driver engagement increased during roadway curve segments, and b) mind wandering manifests itself through several types of steering behavior.

There is increasing interest in real-time brain-computer interfaces (BCIs) for the passive monitoring of human cognitive state, including cognitive workload. Too often, however, effective BCIs based on machine learning techniques may function as “black boxes” that are difficult to analyze or interpret. In an effort toward more interpretable BCIs, we studied a family of N-back working memory tasks using a machine learning model, Gaussian Process Regression (GPR), which was both powerful and amenable to analysis. Participants performed the N-back task with three stimulus variants, auditory-verbal, visual-spatial, and visual-numeric, each at three working memory loads. GPR models were trained and tested on EEG data from all three task variants combined, in an effort to identify a model that could be predictive of mental workload demand regardless of stimulus modality. To provide a comparison for GPR performance, a model was additionally trained using multiple linear regression (MLR). The GPR model was effective when trained on individual participant EEG data, resulting in an average standardized mean squared error (sMSE) between true and predicted N-back levels of 0.44. In comparison, the MLR model using the same data resulted in an average sMSE of 0.55. We additionally demonstrate how GPR can be used to identify which EEG features are relevant for prediction of cognitive workload in an individual participant. A fraction of EEG features accounted for the majority of the model’s predictive power; using only the top 25% of features performed nearly as well as using 100% of features. Subsets of features identified by linear models (ANOVA) were not as efficient as subsets identified by GPR. This raises the possibility of BCIs that require fewer model features while capturing all of the information needed to achieve high predictive accuracy.

Driver distraction is a persistent threat to traffic safety. External distraction has been examined extensively, but few studies have focused on internal distraction such as mind wandering. Equivocal results from the few existing studies are likely due, at least in part, to different experimental methods. Mind wandering is commonly assessed using either a self-caught or probe-caught method. The current investigation sought to better understand the effects of mind wandering on driving performance using the self-caught method and the probecaught method. In the Self-Caught Experiment, lateral control measures such as, lateral position variability and steering reversal rate were greater when drivers reported on-task thoughts versus mind wandering. In the Probe-Caught Experiment, these results were not replicated using the traditional probe-caught analysis. Instead, when analyzing the results of the Probe-Caught Experiment in a similar manner as the Self-Caught Experiment, the results were replicated. These results highlight methodological concerns in detecting mind wandering while driving. Additional research is needed to determine which method should be employed in future studies.

Empirical evidence indicates that detecting one's own mistakes can serve as a signal to improve task performance. However, little work has focused on how task constraints, such as the response–stimulus interval (RSI), influence post-error adjustments. In the present study, event-related potential (ERP) and behavioral measures were used to investigate the time course of error-related processing while humans performed a difficult visual discrimination task. We found that error commission resulted in a marked reduction in both task performance and sensory processing on the following trial when RSIs were short, but that such impairments were not detectable at longer RSIs. Critically, diminished sensory processing at short RSIs, indexed by the stimulus-evoked P1 component, was predicted by an ERP measure of error processing, the Pe component. A control analysis ruled out a general lapse in attention or mind wandering as being predictive of subsequent reductions in sensory processing; instead, the data suggest that error detection causes an attentional bottleneck, which can diminish sensory processing on subsequent trials that occur in short succession. The findings demonstrate that the neural system dedicated to monitoring and improving behavior can, paradoxically, at times be the source of performance failures. SIGNIFICANCE STATEMENT The performance-monitoring system is a network of brain regions dedicated to monitoring behavior to adjust task performance when necessary. Previous research has demonstrated that activation of the performance monitoring system following incorrect decisions serves to improve future task performance. However, the present study provides evidence that, when perceptual decisions must be made rapidly (within approximately half a second of each other), activation of the performance-monitoring system is predictive of impaired task-related attention on the subsequent trial. The data illustrate that the cognitive demands imposed by error processing can interfere with, rather than enhance, task-related attention when subsequent decisions need to be made quickly.

Mind wandering is a pervasive threat to transportation safety, potentially accounting for a substantial number of crashes and fatalities. In the current study, mind wandering was induced through completion of the same task for 5 days, consisting of a 20-min monotonous freeway-driving scenario, a cognitive depletion task, and a repetition of the 20-min driving scenario driven in the reverse direction. Participants were periodically probed with auditory tones to self-report whether they were mind wandering or focused on the driving task. Self-reported mind wandering frequency was high, and did not statistically change over days of participation. For measures of driving performance, participant labeled periods of mind wandering were associated with reduced speed and reduced lane variability, in comparison to periods of on task performance. For measures of electrophysiology, periods of mind wandering were associated with increased power in the alpha band of the electroencephalogram (EEG), as well as a reduction in the magnitude of the P3a component of the event related potential (ERP) in response to the auditory probe. Results support that mind wandering has an impact on driving performance and the associated change in driver's attentional state is detectable in underlying brain physiology. Further, results suggest that detecting the internal cognitive state of humans is possible in a continuous task such as automobile driving. Identifying periods of likely mind wandering could serve as a useful research tool for assessment of driver attention, and could potentially lead to future in-vehicle safety countermeasures.