Heightened interoception in adults with fibromyalgia.

Previous research suggests that the processing of internal body sensations (interoception) affects how we experience pain. Some evidence suggests that people with fibromyalgia syndrome (FMS) - a condition characterised by chronic pain and fatigue - may have altered interoceptive processing. However, extant findings are inconclusive, and some tasks previously used to measure interoception are of questionable validity. Here, we used an alternative measure - the Phase Adjustment Task (PAT) - to examine cardiac interoceptive accuracy in adults with FMS. We examined: (i) the tolerability of the PAT in an FMS sample (N = 154); (ii) if there are differences in facets of interoception (PAT performance, PAT-related confidence, and scores on the Private Body Consciousness Scale) between an FMS sample and an age- and gender-matched pain-free sample (N = 94); and (iii) if subgroups of participants with FMS are identifiable according to interoceptive accuracy levels. We found the PAT was tolerable in the FMS sample, with additional task breaks and a recommended hand posture. The FMS sample were more likely to be classified as 'interoceptive' on the PAT, and had significantly higher self-reported interoception compared to the pain-free sample. Within the FMS sample, we identified a subgroup who demonstrated very strong evidence of being interoceptive, and concurrently had lower fibromyalgia symptom impact (although the effect size was small). Conversely, self-reported interoception was positively correlated with FMS symptom severity and impact. Overall, interoception may be an important factor to consider in understanding and managing FMS symptoms. We recommend future longitudinal work to better understand associations between fluctuating FMS symptoms and interoception.

Uncertainties in the Analysis of Heart Rate Variability: A Systematic Review.

Heart rate variability (HRV) is an important metric with a variety of applications in clinical situations such as cardiovascular diseases, diabetes mellitus, and mental health. HRV data can be potentially obtained from electrocardiography and photoplethysmography signals, then computational techniques such as signal filtering and data segmentation are used to process the sampled data for calculating HRV measures. However, uncertainties arising from data acquisition, computational models, and physiological factors can lead to degraded signal quality and affect HRV analysis. Therefore, it is crucial to address these uncertainties and develop advanced models for HRV analysis. Although several reviews of HRV analysis exist, they primarily focus on clinical applications, trends in HRV methods, or specific aspects of uncertainties such as measurement noise. This paper provides a comprehensive review of uncertainties in HRV analysis, quantifies their impacts, and outlines potential solutions. To the best of our knowledge, this is the first study that presents a holistic review of uncertainties in HRV methods and quantifies their impacts on HRV measures from an engineer's perspective. This review is essential for developing robust and reliable models, and could serve as a valuable future reference in the field, particularly for dealing with uncertainties in HRV analysis.

Combining machine learning with Cox models to identify predictors for incident post-menopausal breast cancer in the UK Biobank.

We aimed to identify potential novel predictors for breast cancer among post-menopausal women, with pre-specified interest in the role of polygenic risk scores (PRS) for risk prediction. We utilised an analysis pipeline where machine learning was used for feature selection, prior to risk prediction by classical statistical models. An "extreme gradient boosting" (XGBoost) machine with Shapley feature-importance measures were used for feature selection among [Formula: see text] 1.7 k features in 104,313 post-menopausal women from the UK Biobank. We constructed and compared the "augmented" Cox model (incorporating the two PRS, known and novel predictors) with a "baseline" Cox model (incorporating the two PRS and known predictors) for risk prediction. Both of the two PRS were significant in the augmented Cox model ([Formula: see text]). XGBoost identified 10 novel features, among which five showed significant associations with post-menopausal breast cancer: plasma urea (HR = 0.95, 95% CI 0.92-0.98, [Formula: see text]), plasma phosphate (HR = 0.68, 95% CI 0.53-0.88, [Formula: see text]), basal metabolic rate (HR = 1.17, 95% CI 1.11-1.24, [Formula: see text]), red blood cell count (HR = 1.21, 95% CI 1.08-1.35, [Formula: see text]), and creatinine in urine (HR = 1.05, 95% CI 1.01-1.09, [Formula: see text]). Risk discrimination was maintained in the augmented Cox model, yielding C-index 0.673 vs 0.667 (baseline Cox model) with the training data and 0.665 vs 0.664 with the test data. We identified blood/urine biomarkers as potential novel predictors for post-menopausal breast cancer. Our findings provide new insights to breast cancer risk. Future research should validate novel predictors, investigate using multiple PRS and more precise anthropometry measures for better breast cancer risk prediction.

Feasibility of using intermittent active monitoring of vital signs by smartphone users to predict SARS-CoV-2 PCR positivity.

Early detection of highly infectious respiratory diseases, such as COVID-19, can help curb their transmission. Consequently, there is demand for easy-to-use population-based screening tools, such as mobile health applications. Here, we describe a proof-of-concept development of a machine learning classifier for the prediction of a symptomatic respiratory disease, such as COVID-19, using smartphone-collected vital sign measurements. The Fenland App study followed 2199 UK participants that provided measurements of blood oxygen saturation, body temperature, and resting heart rate. Total of 77 positive and 6339 negative SARS-CoV-2 PCR tests were recorded. An optimal classifier to identify these positive cases was selected using an automated hyperparameter optimisation. The optimised model achieved an ROC AUC of 0.695 ± 0.045. The data collection window for determining each participant's vital sign baseline was increased from 4 to 8 or 12 weeks with no significant difference in model performance (F(2) = 0.80, p = 0.472). We demonstrate that 4 weeks of intermittently collected vital sign measurements could be used to predict SARS-CoV-2 PCR positivity, with applicability to other diseases causing similar vital sign changes. This is the first example of an accessible, smartphone-based remote monitoring tool deployable in a public health setting to screen for potential infections.

Fashion-Oriented Image Captioning with External Knowledge Retrieval and Fully Attentive Gates.

Research related to fashion and e-commerce domains is gaining attention in computer vision and multimedia communities. Following this trend, this article tackles the task of generating fine-grained and accurate natural language descriptions of fashion items, a recently-proposed and under-explored challenge that is still far from being solved. To overcome the limitations of previous approaches, a transformer-based captioning model was designed with the integration of external textual memory that could be accessed through k-nearest neighbor (kNN) searches. From an architectural point of view, the proposed transformer model can read and retrieve items from the external memory through cross-attention operations, and tune the flow of information coming from the external memory thanks to a novel fully attentive gate. Experimental analyses were carried out on the fashion captioning dataset (FACAD) for fashion image captioning, which contains more than 130k fine-grained descriptions, validating the effectiveness of the proposed approach and the proposed architectural strategies in comparison with carefully designed baselines and state-of-the-art approaches. The presented method constantly outperforms all compared approaches, demonstrating its effectiveness for fashion image captioning.

Modeling Mood Polarity and Declaration Occurrence by Neural Temporal Point Processes.

Neural point processes provide the flexibility needed to deal with time series of heterogeneous nature within the robust framework of point processes. This aspect is of particular relevance when dealing with real-world data, mixing generative processes characterized by radically different distributions and sampling. This brief discusses a neural point process approach for health and behavioral data, comprising both sparse events coming from user subjective declarations as well as fast-flowing time series from wearable sensors. We propose and empirically validate different neural architectures and we assess the effect of including input sources of different nature. The empirical analysis is built on the top of a challenging original dataset, never published before, and collected as part of a real-world experiment in an uncontrolled setting. Results show the potential of neural point processes both in terms of predicting the next event type as well as in predicting the time to next user interaction.

Physiological recovery among workers in long-distance sleddog races: A case study on female veterinarians in Finnmarksløpet.

BACKGROUND: During Finnmarksløpet (FL, one of the longest distance sleddog races in the world), veterinarians are exposed to extreme environmental conditions and tight working schedules, with little and fragmented sleep. OBJECTIVE: The aim of this case study was to examine cardiovascular parameters and sleep-wake patterns among veterinarians working within FL, during and after (for a month) the end of the race. METHODS: Six female veterinarians volunteered for the study. The participants wore a wrist device for a total of eight weeks in order to passively and semi-continuously record physiological responses throughout the day (i.e., heart rate, heart rate variability, number of steps, and sleep quality). Moreover, perceived sleep quality was assessed by Pittsburgh Sleep Quality Index (PSQI) at three time-points. RESULTS: During and for one month after completion of the FL, most veterinarians presented an alteration of cardiovascular parameters and sleep quality. The heart rate circadian rhythm returned to pre-race values within about two weeks. CONCLUSIONS: The long-lasting alteration of the veterinarians' cardiovascular parameters and sleep-wake patterns might have negative consequences for their health in the long-term, especially if similar experiences are repeated more times though the course of a year or season. More research is needed in order to understand the health risks, as well as how to prevent them, among veterinarians in long-distance sleddog races or other similar events.

Development of Digitally Obtainable 10-Year Risk Scores for Depression and Anxiety in the General Population.

The burden of depression and anxiety in the world is rising. Identification of individuals at increased risk of developing these conditions would help to target them for prevention and ultimately reduce the healthcare burden. We developed a 10-year predictive algorithm for depression and anxiety using the full cohort of over 400,000 UK Biobank (UKB) participants without pre-existing depression or anxiety using digitally obtainable information. From the initial 167 variables selected from UKB, processed into 429 features, iterative backward elimination using Cox proportional hazards model was performed to select predictors which account for the majority of its predictive capability. Baseline and reduced models were then trained for depression and anxiety using both Cox and DeepSurv, a deep neural network approach to survival analysis. The baseline Cox model achieved concordance of 0.7772 and 0.7720 on the validation dataset for depression and anxiety, respectively. For the DeepSurv model, respective concordance indices were 0.7810 and 0.7728. After feature selection, the depression model contained 39 predictors and the concordance index was 0.7769 for Cox and 0.7772 for DeepSurv. The reduced anxiety model, with 53 predictors, achieved concordance of 0.7699 for Cox and 0.7710 for DeepSurv. The final models showed good discrimination and calibration in the test datasets. We developed predictive risk scores with high discrimination for depression and anxiety using the UKB cohort, incorporating predictors which are easily obtainable via smartphone. If deployed in a digital solution, it would allow individuals to track their risk, as well as provide some pointers to how to decrease it through lifestyle changes.

Measuring Interoception: The CARdiac Elevation Detection Task.

Interoception has increasingly been the focus of psychiatric research, due to its hypothesized role in mental health. Existing interoceptive tasks either suffer from important methodological limitations, impacting their validity, or are burdensome and require specialized equipment, which limits their usage in vulnerable populations. We report on the development of the CARdiac Elevation Detection (CARED) task. Participants' heart rate is recorded by a wearable device connected to a mobile application. Notifications are sent to participants' mobile throughout the day over a period of 4 weeks. Participants are asked to state whether their heart rate is higher than usual, rate their confidence and describe the activity they were involved in when the notification occurred. Data (N = 30) revealed that 1/3 of the sample was classified as interoceptive and that participants presented overall good insight into their interoceptive abilities. Given its ease of administration and accessibility, the CARED task has the potential to be a significant asset for psychiatric and developmental research.

Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study.

The COVID-19 pandemic has created an urgent need for robust, scalable monitoring tools supporting stratification of high-risk patients. This research aims to develop and validate prediction models, using the UK Biobank, to estimate COVID-19 mortality risk in confirmed cases. From the 11,245 participants testing positive for COVID-19, we develop a data-driven random forest classification model with excellent performance (AUC: 0.91), using baseline characteristics, pre-existing conditions, symptoms, and vital signs, such that the score could dynamically assess mortality risk with disease deterioration. We also identify several significant novel predictors of COVID-19 mortality with equivalent or greater predictive value than established high-risk comorbidities, such as detailed anthropometrics and prior acute kidney failure, urinary tract infection, and pneumonias. The model design and feature selection enables utility in outpatient settings. Possible applications include supporting individual-level risk profiling and monitoring disease progression across patients with COVID-19 at-scale, especially in hospital-at-home settings.

SDNN24 Estimation from Semi-Continuous HR Measures.

The standard deviation of the interval between QRS complexes recorded over 24 h (SDNN24) is an important metric of cardiovascular health. Wrist-worn fitness wearable devices record heart beats 24/7 having a complete overview of users' heart status. Due to motion artefacts affecting QRS complexes recording, and the different nature of the heart rate sensor used on wearable devices compared to ECG, traditionally used to compute SDNN24, the estimation of this important Heart Rate Variability (HRV) metric has never been performed from wearable data. We propose an innovative approach to estimate SDNN24 only exploiting the Heart Rate (HR) that is normally available on wearable fitness trackers and less affected by data noise. The standard deviation of inter-beats intervals (SDNN24) and the standard deviation of the Average inter-beats intervals (ANN) derived from the HR (obtained in a time window with defined duration, i.e., 1, 5, 10, 30 and 60 min), i.e., ANN=60HR (SDANNHR24), were calculated over 24 h. Power spectrum analysis using the Lomb-Scargle Peridogram was performed to assess frequency domain HRV parameters (Ultra Low Frequency, Very Low Frequency, Low Frequency, and High Frequency). Due to the fact that SDNN24 reflects the total power of the power of the HRV spectrum, the values estimated from HR measures (SDANNHR24) underestimate the real values because of the high frequencies that are missing. Subjects with low and high cardiovascular risk show different power spectra. In particular, differences are detected in Ultra Low and Very Low frequencies, while similar results are shown in Low and High frequencies. For this reason, we found that HR measures contain enough information to discriminate cardiovascular risk. Semi-continuous measures of HR throughout 24 h, as measured by most wrist-worn fitness wearable devices, should be sufficient to estimate SDNN24 and cardiovascular risk.

Development and Feasibility of a Digital Acceptance and Commitment Therapy-Based Intervention for Generalized Anxiety Disorder: Pilot Acceptability Study.

BACKGROUND: Generalized anxiety disorder (GAD) is characterized by excessive worry that is difficult to control and has high comorbidity with mood disorders including depression. Individuals experience long wait times for diagnosis and often face accessibility barriers to treatment. There is a need for a digital solution that is accessible and acceptable to those with GAD. OBJECTIVE: This paper aims to describe the development of a digital intervention prototype of acceptance and commitment therapy (ACT) for GAD that sits within an existing well-being app platform, BioBase. A pilot feasibility study evaluating acceptability and usability is conducted in a sample of adults with a diagnosis of GAD, self-referred to the study. METHODS: Phase 1 applied the person-based approach (creation of guiding principles, intervention design objectives, and the key intervention features). In Phase 2 participants received the app-based therapeutic and paired wearable for 2 weeks. Self-report questionnaires were obtained at baseline and posttreatment. The primary outcome was psychological flexibility (Acceptance and Action Questionnaire-II [AAQ-II]) as this is the aim of ACT. Mental well-being (Warwick-Edinburgh Mental Well-being Scale [WEMWBS]) and symptoms of anxiety (7-item Generalized Anxiety Disorder Assessment [GAD-7]) and depression (9-item Patient Health Questionnaire [PHQ-9]) were also assessed. Posttreatment usability was assessed via self-report measures (System Usability Scale [SUS]) in addition to interviews that further explored feasibility of the digital intervention in this sample. RESULTS: The app-based therapeutic was well received. Of 13 participants, 10 (77%) completed the treatment. Results show a high usability rating (83.5). Participants found the digital intervention to be relevant, useful, and helpful in managing their anxiety. Participants had lower anxiety (d=0.69) and depression (d=0.84) scores at exit, and these differences were significantly different from baseline (P=.03 and .008 for GAD-7 and PHQ-9, respectively). Participants had higher psychological flexibility and well-being scores at exit, although these were not significantly different from baseline (P=.11 and .55 for AAQ-II and WEMWBS, respectively). CONCLUSIONS: This ACT prototype within BioBase is an acceptable and feasible digital intervention in reducing symptoms of anxiety and depression. This study suggests that this intervention warrants a larger feasibility study in adults with GAD.

Accelerometer-derived sleep onset timing and cardiovascular disease incidence: a UK Biobank cohort study.

Aims: Growing evidence suggests that poor sleep health is associated with cardiovascular risk. However, research in this area often relies upon recollection dependent questionnaires or diaries. Accelerometers provide an alternative tool for measuring sleep parameters objectively. This study examines the association between wrist-worn accelerometer-derived sleep onset timing and cardiovascular disease (CVD). Methods and results: We derived sleep onset and waking up time from accelerometer data collected from 103 712 UK Biobank participants over a period of 7 days. From this, we examined the association between sleep onset timing and CVD incidence using a series of Cox proportional hazards models. A total of 3172 cases of CVD were reported during a mean follow-up period of 5.7 (±0.49) years. An age- and sex-controlled base analysis found that sleep onset time of 10:00 p.m.-10:59 p.m. was associated with the lowest CVD incidence. An additional model, controlling for sleep duration, sleep irregularity, and established CVD risk factors, did not attenuate this association, producing hazard ratios of 1.24 (95% confidence interval, 1.10-1.39; P < 0.005), 1.12 (1.01-1.25; P = 0.04), and 1.25 (1.02-1.52; P = 0.03) for sleep onset <10:00 p.m., 11:00 p.m.-11:59 p.m., and ≥12:00 a.m., respectively, compared to 10:00 p.m.-10:59 p.m. Importantly, sensitivity analyses revealed this association with increased CVD risk was stronger in females, with only sleep onset <10:00 p.m. significant for males. Conclusions: Our findings suggest the possibility of a relationship between sleep onset timing and risk of developing CVD, particularly for women. We also demonstrate the potential utility of collecting information about sleep parameters via accelerometry-capable wearable devices, which may serve as novel cardiovascular risk indicators.

Development of an accessible 10-year Digital CArdioVAscular (DiCAVA) risk assessment: a UK Biobank study.

Aims: Cardiovascular diseases (CVDs) are among the leading causes of death worldwide. Predictive scores providing personalized risk of developing CVD are increasingly used in clinical practice. Most scores, however, utilize a homogenous set of features and require the presence of a physician. The aim was to develop a new risk model (DiCAVA) using statistical and machine learning techniques that could be applied in a remote setting. A secondary goal was to identify new patient-centric variables that could be incorporated into CVD risk assessments. Methods and results: Across 466 052 participants, Cox proportional hazards (CPH) and DeepSurv models were trained using 608 variables derived from the UK Biobank to investigate the 10-year risk of developing a CVD. Data-driven feature selection reduced the number of features to 47, after which reduced models were trained. Both models were compared to the Framingham score. The reduced CPH model achieved a c-index of 0.7443, whereas DeepSurv achieved a c-index of 0.7446. Both CPH and DeepSurv were superior in determining the CVD risk compared to Framingham score. Minimal difference was observed when cholesterol and blood pressure were excluded from the models (CPH: 0.741, DeepSurv: 0.739). The models show very good calibration and discrimination on the test data. Conclusion: We developed a cardiovascular risk model that has very good predictive capacity and encompasses new variables. The score could be incorporated into clinical practice and utilized in a remote setting, without the need of including cholesterol. Future studies will focus on external validation across heterogeneous samples.

Error Estimation of Ultra-Short Heart Rate Variability Parameters: Effect of Missing Data Caused by Motion Artifacts.

Application of ultra-short Heart Rate Variability (HRV) is desirable in order to increase the applicability of HRV features to wrist-worn wearable devices equipped with heart rate sensors that are nowadays becoming more and more popular in people's daily life. This study is focused in particular on the the two most used HRV parameters, i.e., the standard deviation of inter-beat intervals (SDNN) and the root Mean Squared error of successive inter-beat intervals differences (rMSSD). The huge problem of extracting these HRV parameters from wrist-worn devices is that their data are affected by the motion artifacts. For this reason, estimating the error caused by this huge quantity of missing values is fundamental to obtain reliable HRV parameters from these devices. To this aim, we simulate missing values induced by motion artifacts (from 0 to 70%) in an ultra-short time window (i.e., from 4 min to 30 s) by the random walk Gilbert burst model in 22 young healthy subjects. In addition, 30 s and 2 min ultra-short time windows are required to estimate rMSSD and SDNN, respectively. Moreover, due to the fact that ultra-short time window does not permit assessing very low frequencies, and the SDNN is highly affected by these frequencies, the bias for estimating SDNN continues to increase as the time window length decreases. On the contrary, a small error is detected in rMSSD up to 30 s due to the fact that it is highly affected by high frequencies which are possible to be evaluated even if the time window length decreases. Finally, the missing values have a small effect on rMSSD and SDNN estimation. As a matter of fact, the HRV parameter errors increase slightly as the percentage of missing values increase.

Exploring the Effects of a Brief Biofeedback Breathing Session Delivered Through the BioBase App in Facilitating Employee Stress Recovery: Randomized Experimental Study.

BACKGROUND: Recovery from stress is a predictive factor for cardiovascular health, and heart rate variability (HRV) is suggested to be an index of how well people physiologically recover from stress. Biofeedback and mindfulness interventions that include guided breathing have been shown to be effective in increasing HRV and facilitating stress recovery. OBJECTIVE: This study aims to assess the effectiveness of a brief app-based breathing intervention (BioBase) in enhancing physiological recovery among employees who were induced to cognitive and emotional stress. METHODS: In total, we recruited 75 full-time employees. Interbeat (RR) intervals were recorded continuously for 5 min at baseline and during cognitive and emotional stress induction. The session ended with a 5-min recovery period during which participants were randomly allocated into 3 conditions: app-based breathing (BioBase), mindfulness body scan, or control. Subjective tension was assessed at the end of each period. RESULTS: Subjective tension significantly increased following stress induction. HRV significantly decreased following the stress period. In the recovery phase, the root mean square of successive RR interval differences (P=.002), the percentage of successive RR intervals that differed by >50 ms (P=.008), and high frequency (P=.01) were significantly higher in the BioBase breathing condition than in the mindfulness body scan and the control groups. CONCLUSIONS: Biofeedback breathing interventions digitally delivered through a commercially available app can be effective in facilitating stress recovery among employees. These findings contribute to the mobile health literature on the beneficial effects of brief app-based breathing interventions on employees' cardiovascular health.

Effectiveness of a Smartphone App (BioBase) for Reducing Anxiety and Increasing Mental Well-Being: Pilot Feasibility and Acceptability Study.

BACKGROUND: The prevalence of workplace-related stress and anxiety is high, resulting in stress-related physical and mental illness. Digital self-guided interventions aimed at key areas of workplace design may be able to provide remote anxiolytic effects. OBJECTIVE: The aim of this feasibility study is to assess changes in anxiety and mental well-being after use of the BioBase programme, a mobile phone platform for psycho-educational modules, tools, and real-time feedback of physiological data. METHODS: A 4-week observational study was carried out in 55 healthy adults who were screened for stress with the Depression Anxiety Stress Scale (DASS) Stress subscale. Participants completed anxiety (6-item State-Trait Anxiety Inventory [STAI]) and mental well-being (Warwick-Edinburgh Mental Well-being Scale [WEMWBS]) questionnaires at baseline and at 4 weeks. Feedback questionnaires were administered after 4 weeks. RESULTS: After 4 weeks of using the programme and controlling for any effect of being paid to take part in the study, STAI significantly decreased (baseline mean 45.52 [SD 13.2]; 4-week mean 39.82 [SD 11.2]; t54=-3.51; P<.001; CI -8.88 to -2.52; Cohen d=0.96) and WEMWBS significantly increased (baseline mean 48.12 [SD 6.4]; 4-week mean 50.4 [SD 6.9]; t53=2.41; P=.019; CI 0.44-4.23; Cohen d=0.66). Further, higher baseline stress was significantly associated with a greater decrease in STAI (t53=-3.41; P=.001; CI -8.10 to -2.10; R2=0.180) and a greater increase in WEMWBS (t52=2.41; P=.019; CI 0.38-4.11, R2=0.101). On feedback, participants found the programme easy to use/navigate, with the content being acceptable and relevant to workplace-related stressors; 70% (21/30) of participants would recommend the programme to a friend. CONCLUSIONS: The BioBase programme is a potentially effective intervention in decreasing anxiety and increasing mental well-being, with larger changes in those with higher baseline levels of stress.

Efficacy of the Digital Therapeutic Mobile App BioBase to Reduce Stress and Improve Mental Well-Being Among University Students: Randomized Controlled Trial.

BACKGROUND: University students in the United Kingdom are experiencing increasing levels of anxiety. A program designed to increase awareness of one's present levels of well-being and suggest personalized health behaviors may reduce anxiety and improve mental well-being in students. The efficacy of a digital version of such a program, providing biofeedback and therapeutic content based on personalized well-being metrics, is reported here. OBJECTIVE: The aim of this study was to test the efficacy and sustained effects of using a mobile app (BioBase) and paired wearable device (BioBeam), compared with a waitlist control group, on anxiety and well-being in university students with elevated levels of anxiety and stress. METHODS: The study employed a randomized, waitlist-controlled trial with assessments at baseline, 2 weeks, postintervention (4 weeks), and follow-up (6 weeks). Participants were eligible if they were current full-time undergraduate students and (1) at least 18 years of age, (2) scored >14 points on the Depression, Anxiety, and Stress Scale-21 items (DASS-21) stress subscale or >7 points on the DASS-21 anxiety subscale, (3) owned an iOS mobile phone, (4) did not have any previous psychiatric or neurological conditions, (6) were not pregnant at the time of testing, and (7) were able to read and understand English. Participants were encouraged to use BioBase daily and complete at least one course of therapeutic content. A P value ≤.05 was considered statistically significant. RESULTS: We found that a 4-week intervention with the BioBase program significantly reduced anxiety and increased perceived well-being, with sustained effects at a 2-week follow-up. Furthermore, a significant reduction in depression levels was found following the 4-week usage of BioBase. CONCLUSIONS: This study shows the efficacy of a biofeedback digital intervention in reducing self-reported anxiety and increasing perceived well-being in UK university students. Results suggest that digital mental health interventions could constitute a novel approach to treat stress and anxiety in students, which could be combined or integrated with existing therapeutic pathways. TRIAL REGISTRATION: Open Science Framework (OSF.io) 2zd45; https://osf.io/2zd45/.

A computationally efficient algorithm to obtain an accurate and interpretable model of the effect of circadian rhythm on resting heart rate.

OBJECTIVE: Wrist-worn wearable devices equipped with heart rate (HR) sensors have become increasingly popular. The ability to correctly interpret the collected data is fundamental to analyse user's well-being and perform early detection of abnormal physiological data. Circadian rhythm is a strong factor of variability in HR, yet few models attempt to accurately model its effect on HR. APPROACH: In this paper we present a mathematical derivation of the single-component cosinor model with multiple components that fits user data to a predetermined arbitrary function (the expected shape of the circadian effect on resting HR (RHR)), thus permitting us to predict the user's circadian rhythm component (i.e. MESOR, Acrophase and Amplitude) with a high accuracy. MAIN RESULTS: We show that our model improves the accuracy of HR prediction compared to the single component cosinor model (10% lower RMSE), while retaining the readability of the fitted model of the single component cosinor. We also show that the model parameters can be used to detect sleep disruption in a qualitative experiment. The model is computationally cheap, depending linearly on the size of the data. The computation of the model does not need the full dataset, but only two surrogates, where the data is accumulated. This implies that the model can be implemented in a streaming approach, with important consequences for security and privacy of the data, that never leaves the user devices. SIGNIFICANCE: The multiple component model provided in this paper can be used to approximate a user's RHR with higher accuracy than single component model, providing traditional parameters easy to interpret (i.e. the same produced by the single component cosinor model). The model we developed goes beyond fitting circadian activity on RHR, and it can be used to fit arbitrary periodic real valued time series, vectorial data, or complex data.

Analysis of the Impact of Interpolation Methods of Missing RR-intervals Caused by Motion Artifacts on HRV Features Estimations.

Wearable physiological monitors have become increasingly popular, often worn during people's daily life, collecting data 24 hours a day, 7 days a week. In the last decade, these devices have attracted the attention of the scientific community as they allow us to automatically extract information about user physiology (e.g., heart rate, sleep quality and physical activity) enabling inference on their health. However, the biggest issue about the data recorded by wearable devices is the missing values due to motion and mechanical artifacts induced by external stimuli during data acquisition. This missing data could negatively affect the assessment of heart rate (HR) response and estimation of heart rate variability (HRV), that could in turn provide misleading insights concerning the health status of the individual. In this study, we focus on healthy subjects with normal heart activity and investigate the effects of missing variation of the timing between beats (RR-intervals) caused by motion artifacts on HRV features estimation by randomly introducing missing values within a five min time windows of RR-intervals obtained from the nsr2db PhysioNet dataset by using Gilbert burst method. We then evaluate several strategies for estimating HRV in the presence of missing values by interpolating periods of missing values, covering the range of techniques often deployed in the literature, via linear, quadratic, cubic, and cubic spline functions. We thereby compare the HRV features obtained by handling missing data in RR-interval time series against HRV features obtained from the same data without missing values. Finally, we assess the difference between the use of interpolation methods on time (i.e., the timestamp when the heartbeats happen) and on duration (i.e., the duration of the heartbeats), in order to identify the best methodology to handle the missing RR-intervals. The main novel finding of this study is that the interpolation of missing data on time produces more reliable HRV estimations when compared to interpolation on duration. Hence, we can conclude that interpolation on duration modifies the power spectrum of the RR signal, negatively affecting the estimation of the HRV features as the amount of missing values increases. We can conclude that interpolation in time is the optimal method among those considered for handling data with large amounts of missing values, such as data from wearable sensors.