Non-invasive Wearable Device Research Articles

Development and Validation of a Wearable Device to Provide Rich Somatosensory Stimulation for Rehabilitation After Sensorimotor Impairment.

Training sensory discrimination of the skin has the potential to reduce chronic pain due to sensorimotor impairments and increase sensorimotor function. Currently, there is no such device that can systematically provide rich skin stimulation suitable for a training protocol for individuals with amputation or major sensory impairment. This study describes the development and validation of a non-invasive wearable device meant to repeatedly and safely deliver somatosensory stimulations. The development was guided by a structured design control process to ensure the verifiability and validity of the design outcomes. Two sub-systems were designed: 1) a tactile display for touch and vibration sensations, and 2) a set of bands for sliding, pressure, and strain sensations. The device was designed with a versatile structure that allows for its application on different body parts. We designed a device-paired interactive computer program to enable structured sensory training sessions. Validation was performed with 11 individuals with intact limbs whose upper arm tactile sensitivity was measured over 5 training sessions. Tactile discrimination and perception threshold were measured using the standard 2-point discrimination and Semmes-Weinstein monofilament tests, respectively. The results of the monofilament test showed a significant improvement (p = 0.011), but the improvement was not significant for the 2-point discrimination test(p = 0.141). These promising results confirm the potential of the proposed training to increase the sensory acuity in the upper arms of individuals with intact limbs. Further studies will be conducted to determine how to transfer the findings of this work to improve the pain and/or functional rehabilitation in individuals with sensorimotor impairments.

Performance of artificial intelligence models in estimating blood glucose level among diabetic patients using non-invasive wearable device data

IntroductionDiabetes Mellitus (DM) is characterized by impaired ability to metabolize glucose for use in cells for energy, resulting in high blood sugar (hyperglycemia). DM impacted 463 million individuals worldwide in 2019, with over four million fatalities documented. Blood glucose levels (BGL) are usually measured, as standard protocols, through invasive procedures. Recently, Artificial Intelligence (AI) based techniques have demonstrated the potential to estimate BGL using data collected by non-invasive Wearable Devices (WDs), thereby, facilitating monitoring and management of diabetics. One of the key aspects of WDs with machine learning (ML) algorithms is to find specific data signatures, called Digital biomarkers, that can be used in classification or gaging the extent of the underlying condition. The use of such biomarkers to monitor glycemic events represents a major shift in technology for self-monitoring and developing digital biomarkers using non-invasive WDs. To do this, it is necessary to investigate the correlations between characteristics acquired from non-invasive WDs and indicators of glycemic health; furthermore, much work is needed to validate accuracy. Research Design & MethodsThe study aimed to investigate performance of AI models in estimating BGL among diabetic patients using non-invasive wearable devices data An open-source dataset was used which provided BGL readings, diabetic status (Diabetic or non-diabetic), heart rate, Blood oxygen level (SPO2), Diastolic Blood pressure, Systolic Blood Pressure, Body temperature, Sweating, and Shivering for 13 participants by age group taken from WDs. Our experimental design included Data Collection, Feature Engineering, ML model selection/development, and reporting evaluation of metrics. ResultsWe were able to estimate with high accuracy (RMSE range: 0.099 to 0.197) the relationship between glycemic metrics and features that can be derived from non-invasive WDs when utilizing AI models. ConclusionWe provide further evidence of the feasibility of using commercially available WDs for the purpose of BGL estimation amongst diabetics.

Sleep Classification With Artificial Synthetic Imaging Data Using Convolutional Neural Networks.

We propose a new analytic framework, "Artificial Synthetic Imaging Data (ASID) Workflow," for sleep classification from a wearable device comprising: 1) the creation of ASID from data collected by a non-invasive wearable device that permits real-time multi-modal physiological monitoring on heart rate (HR), 3-axis accelerometer, electrodermal activity, and skin temperature, denoted as "Temporal E4 Data" (TED) and 2) the use of an image classification supervised learning algorithm, convolutional neural network (CNN), to classify periods of sleep. We investigate ASID Workflow under 6 settings (3 data resolutions × 2 HR scenarios). Competing machine/deep learning classification algorithms, including logistic regression, support vector machine, random forest, k-nearest neighbors, and Long Short-Term Memory, are applied to TED as comparisons, termed "Competing Workflow." The ASID Workflow achieves excellent performance with mean weighted accuracy across settings of 94.7%, and is superior to the Competing Workflow with high and low resolution data regardless of the inclusion of HR modality. This superiority is maximized for low resolution data without HR. Additionally, CNN has a relatively low subject-wise test computational cost compared with competing algorithms. We demonstrate the utility of creating ASID from multi-modal physiological data and applying a preexisting image classification algorithm to achieve better classification accuracy. We shed light on the influence of data resolution and HR modality on the Workflow's performance. Applying CNN to ASID allows us to capture both temporal and spatial dependency among physiological variables and modalities by using 2D images' topological structure that competing algorithms fail to utilize.

Wearable devices in palliative care for people 65 years and older: A scoping review.

The objective of this scoping review is to map existing evidence on the use of wearable devices in palliative care for older people. The databases searched included MEDLINE (via Ovid), Cumulative Index to Nursing and Allied Health Literature (CINAHL) and Google Scholar, which was included to capture grey literature. Databases were searched in the English language, without date restrictions. Reviewed results included studies and reviews involving patients aged 65 years or older who were active users of non-invasive wearable devices in the context of palliative care, with no limitations on gender or medical condition. The review followed the Joanna Briggs Institute's comprehensive and systematic guidelines for conducting scoping reviews. Of the 1,520 reports identified through searching the databases, reference lists, and citations, six reports met our inclusion criteria. The types of wearable devices discussed in these reports were accelerometers and actigraph units. Wearable devices were found to be useful in various health conditions, as the patient monitoring data enabled treatment adjustments. The results are mapped in tables as well as a Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) chart. The findings indicate limited and sparse evidence for the population group of patients aged 65 years and older in the palliative context. Hence, more research on this particular age group is needed. The available evidence shows the benefits of wearable device use in enabling patient-centred palliative care, treatment adjustments and symptom management, and reducing the need for patients to travel to clinics while maintaining communication with healthcare professionals.

Artificial intelligence for non-invasive glycaemic-events detection via ECG in a paediatric population: study protocol

PurposePaediatric Type 1 Diabetes (T1D) patients are at greater risk for developing severe hypo and hyperglycaemic events due to poor glycaemic control. To reduce the risk of adverse events, patients need to achieve the best possible glycaemic management through frequent blood glucose monitoring with finger prick or Continuous Glucose Monitoring (CGM) systems. However, several non-invasive techniques have been proposed aiming at exploiting changes in physiological parameters based on glucose levels. The overall objective of this study is to validate an artificial intelligence (AI) based algorithm to detect glycaemic events using ECG signals collected through non-invasive device.MethodsThis study will enrol T1D paediatric participants who already use CGM. Participants will wear an additional non-invasive wearable device for recording physiological data and respiratory rate. Glycaemic measurements driven through ECG variables are the main outcomes. Data collected will be used to design, develop and validate the personalised and generalized classifiers based on a deep learning (DL) AI algorithm, able to automatically detect hypoglycaemic events by using few ECG heartbeats recorded with wearable devices.ResultsData collection is expected to be completed approximately by June 2023. It is expected that sufficient data will be collected to develop and validate the AI algorithm.ConclusionThis is a validation study that will perform additional tests on a larger diabetes sample population to validate the previous pilot results that were based on four healthy adults, providing evidence on the reliability of the AI algorithm in detecting glycaemic events in paediatric diabetic patients in free-living conditions.Trial registrationClinicalTrials.gov identifier: NCT03936634. Registered on 11 March 2022, retrospectively registered, https://www.clinicaltrials.gov/ct2/show/NCT05278143?titles=AI+for+Glycemic+Events+Detection+Via+ECG+in+a+Pediatric+Population&draw=2&rank=1.

UX assessment strategy to identify potential stressful conditions for workers

The European Commission defined the new concept of Industry 5.0 meaning a more human-centric, resilient, and sustainable approach for the design of industrial systems and operations. A deep understanding of the work environment and organization is important to start analysing the working conditions and the resulting User eXperience (UX) of the operators. Also, the knowledge about users’ needs and ergonomics is fundamental to optimize the workers’ wellbeing, working conditions, and industrial results. In this context, the paper presents a strategy to effectively assess the UX of workers to promote human-centric vision of manufacturing sites, enhancing the overall sustainability of the modern factories. A set of non-invasive wearable devices is used to monitor human activities and collect physiological parameters, as well as questionnaires to gather subjective self-assessment. This set-up was applied to virtual reality (VR) simulation, replicating heavy duty work sequence tasks that took place in an oil and gas pipes manufacturing site. This approach allowed the identification of possible stressful conditions for the operator, from physical and mental perspectives, which may compromise the performance. This research was funded by the European Community's HORIZON 2020 programme under grant agreement No. 958303 (PENELOPE).

(Invited) Development of Fuel Cell-Based Electrochemical Micro Gas Sensor for Monitoring Anesthetic Organic Compounds

Surgical procedures require administering anesthetic agents in concentrations between 0.5 and 2.0% to maintain a patient's sedation. Maintaining the concentration of the anesthetic agents within the specified range is vital in preventing overdose or awareness during procedures. There is an increasing demand for developing an accessible, low-cost, wearable anesthetic sensor to ensure patient and personnel safety. This work focuses on fulfilling the clinical demand by developing a transcutaneous biosensor device that can accurately measure and monitor the concentration of anesthetic agent isoflurane (1-chloro-2,2,2-trifluoromethyl difluoromethyl ether) in the human body at a lower cost per unit to address this unmet need. The approach utilizes the creative form of a micro-fuel cell sensor that is composed of a proton exchange membrane (PEM) sandwiched between two metal electrodes to measure the isoflurane excreted through the subject's skin. At the anode, the isoflurane oxidative reaction generates electrons transferred to the cathode electrode. The oxygen reduction reaction is triggered by protons moving across the PEM at the cathode. Isoflurane concentration is measured in terms of electrical signals from the electrons traveling in the external circuit that produce a current proportional to concentration. Furthermore, we investigate the impact of different catalysts, platinum-group metals (PGM) and PGM-free, on the voltage and current output. The fuel cell-based electrochemical biosensor exhibits excellent sensitivity, linearity, and a low detection limit. Higher accuracy in the ultra-low concentration range of sub 40ppm is achieved by imputing the obtained data into a principal component regression (PCR) algorithm. This work highlights an integrated microsensor to monitor transcutaneous isoflurane concentration continuously. Current research enables understanding the dynamic interaction between sensing surface area and volatile anesthetics excreted through the patient's skin. Furthermore, creating a novel approach for non-invasive wearable healthcare devices for detecting volatile organic compounds in the human body. Figure 1

Predicting Hydration Status Using Machine Learning Models From Physiological and Sweat Biomarkers During Endurance Exercise: A Single Case Study.

Improper hydration routines can reduce athletic performance. Recent studies show that data from noninvasive biomarker recordings can help to evaluate the hydration status of subjects during endurance exercise. These studies are usually carried out on multiple subjects. In this work, we present the first study on predicting hydration status using machine learning models from single-subject experiments, which involve 32 exercise sessions of constant moderate intensity performed with and without fluid intake. During exercise, we measured four noninvasive physiological and sweat biomarkers including heart rate, core temperature, sweat sodium concentration, and whole-body sweat rate. Sweat sodium concentration was measured from six body regions using absorbent patches. We used three machine learning models to determine the percentage of body weight loss as an indicator of dehydration with these biomarkers and compared the prediction accuracy. The results on this single subject show that these models gave similar mean absolute errors, while in general the nonlinear models slightly outperformed the linear model in most of the experiments. The prediction accuracy of using the whole-body sweat rate or heart rate was higher than using core temperature or sweat sodium concentration. In addition, the model trained on the sweat sodium concentration collected from the arms gave slightly better accuracy than from the other five body regions. This exploratory work paves the way for the use of these machine learning models to develop personalized health monitoring together with emerging, noninvasive wearable sensor devices.

Observational Clinical Outcomes of a Postpartum Hemorrhage Detection Device Development Study

Postpartum hemorrhage (PPH) is a leading cause of maternal morbidity and mortality worldwide. However, current efforts to manage this problem have limited efficacy, accuracy, and accessibility. Although certain risk factors increase the odds of developing PPH, the majority of cases are unexpected. Risk-screening tools are limited in their use for predicting PPH. This research study investigates whether a noninvasive wearable device (a smart watch) can detect certain signals using infrared light (similar to what is used in pulse oximeters to detect blood oxygen levels) that would indicate excessive blood loss found with PPH.

Automated seizure detection with noninvasive wearable devices: A systematic review and meta-analysis.

ObjectiveThis study was undertaken to review the reported performance of noninvasive wearable devices in detecting epileptic seizures and psychogenic nonepileptic seizures (PNES).MethodsWe conducted a systematic review and meta‐analysis of studies reported up to November 15, 2021. We included studies that used video‐electroencephalographic (EEG) monitoring as the gold standard to determine the sensitivity and false alarm rate (FAR) of noninvasive wearables for automated seizure detection.ResultsTwenty‐eight studies met the criteria for the systematic review, of which 23 were eligible for meta‐analysis. These studies (1269 patients in total, median recording time = 52.9 h per patient) investigated devices for tonic–clonic seizures using wrist‐worn and/or ankle‐worn devices to measure three‐dimensional accelerometry (15 studies), and/or wearable surface devices to measure electromyography (eight studies). The mean sensitivity for detecting tonic–clonic seizures was .91 (95% confidence interval [CI] = .85–.96, I 2 = 83.8%); sensitivity was similar between the wrist‐worn (.93) and surface devices (.90). The overall FAR was 2.1/24 h (95% CI = 1.7–2.6, I 2 = 99.7%); FAR was higher in wrist‐worn (2.5/24 h) than in wearable surface devices (.96/24 h). Three of the 23 studies also detected PNES; the mean sensitivity and FAR from these studies were 62.9% and .79/24 h, respectively. Four studies detected both focal and tonic–clonic seizures, and one study detected focal seizures only; the sensitivities ranged from 31.1% to 93.1% in these studies.SignificanceReported noninvasive wearable devices had high sensitivity but relatively high FARs in detecting tonic–clonic seizures during limited recording time in a video‐EEG setting. Future studies should focus on reducing FAR, detection of other seizure types and PNES, and longer recording in the community.

Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps.

An important function of the construction of the Brain-Computer Interface (BCI) device is the development of a model that is able to recognize emotions from electroencephalogram (EEG) signals. Research in this area is very challenging because the EEG signal is non-stationary, non-linear, and contains a lot of noise due to artifacts caused by muscle activity and poor electrode contact. EEG signals are recorded with non-invasive wearable devices using a large number of electrodes, which increase the dimensionality and, thereby, also the computational complexity of EEG data. It also reduces the level of comfort of the subjects. This paper implements our holographic features, investigates electrode selection, and uses the most relevant channels to maximize model accuracy. The ReliefF and Neighborhood Component Analysis (NCA) methods were used to select the optimal electrodes. Verification was performed on four publicly available datasets. Our holographic feature maps were constructed using computer-generated holography (CGH) based on the values of signal characteristics displayed in space. The resulting 2D maps are the input to the Convolutional Neural Network (CNN), which serves as a feature extraction method. This methodology uses a reduced set of electrodes, which are different between men and women, and obtains state-of-the-art results in a three-dimensional emotional space. The experimental results show that the channel selection methods improve emotion recognition rates significantly with an accuracy of 90.76% for valence, 92.92% for arousal, and 92.97% for dominance.

The Potential of Current Noninvasive Wearable Technology for the Monitoring of Physiological Signals in the Management of Type 1 Diabetes: Literature Survey.

BackgroundMonitoring glucose and other parameters in persons with type 1 diabetes (T1D) can enhance acute glycemic management and the diagnosis of long-term complications of the disease. For most persons living with T1D, the determination of insulin delivery is based on a single measured parameter—glucose. To date, wearable sensors exist that enable the seamless, noninvasive, and low-cost monitoring of multiple physiological parameters.ObjectiveThe objective of this literature survey is to explore whether some of the physiological parameters that can be monitored with noninvasive, wearable sensors may be used to enhance T1D management.MethodsA list of physiological parameters, which can be monitored by using wearable sensors available in 2020, was compiled by a thorough review of the devices available in the market. A literature survey was performed using search terms related to T1D combined with the identified physiological parameters. The selected publications were restricted to human studies, which had at least their abstracts available. The PubMed and Scopus databases were interrogated. In total, 77 articles were retained and analyzed based on the following two axes: the reported relations between these parameters and T1D, which were found by comparing persons with T1D and healthy control participants, and the potential areas for T1D enhancement via the further analysis of the found relationships in studies working within T1D cohorts.ResultsOn the basis of our search methodology, 626 articles were returned, and after applying our exclusion criteria, 77 (12.3%) articles were retained. Physiological parameters with potential for monitoring by using noninvasive wearable devices in persons with T1D included those related to cardiac autonomic function, cardiorespiratory control balance and fitness, sudomotor function, and skin temperature. Cardiac autonomic function measures, particularly the indices of heart rate and heart rate variability, have been shown to be valuable in diagnosing and monitoring cardiac autonomic neuropathy and, potentially, predicting and detecting hypoglycemia. All identified physiological parameters were shown to be associated with some aspects of diabetes complications, such as retinopathy, neuropathy, and nephropathy, as well as macrovascular disease, with capacity for early risk prediction. However, although they can be monitored by available wearable sensors, most studies have yet to adopt them, as opposed to using more conventional devices.ConclusionsWearable sensors have the potential to augment T1D sensing with additional, informative biomarkers, which can be monitored noninvasively, seamlessly, and continuously. However, significant challenges associated with measurement accuracy, removal of noise and motion artifacts, and smart decision-making exist. Consequently, research should focus on harvesting the information hidden in the complex data generated by wearable sensors and on developing models and smart decision strategies to optimize the incorporation of these novel inputs into T1D interventions.

A Preliminary Experimental Study on the Workers’ Workload Assessment to Design Industrial Products and Processes

The human-centered design (HCD) approach places humans at the center of design in order to improve both products and processes, and to give users an effective, efficient and satisfying interactive experience. In industrial design and engineering, HCD is very useful in helping to achieve the novel Industry 5.0 concept, based on improving workers’ wellbeing by providing prosperity beyond jobs and growth, while respecting the production limits of the planet as recently promoted by the European Commission. In this context, the paper proposes an ergonomic assessment method based on the analysis of the workers’ workload to support the design of industrial products and processes. This allows the simultaneous analysis of the physical and cognitive workload of operators while performing their tasks during their shift. The method uses a minimum set of non-invasive wearable devices to monitor human activity and physiological parameters, in addition to questionnaires for subjective self-assessment. The method has been preliminarily tested on a real industrial case in order to demonstrate how it can help companies to support the design of optimized products and processes promoting the workers’ wellbeing.

Design and development of a wearable system for the analysis of respiratory patterns for health monitoring in seniors

Wearable technology for non-invasive breathing monitoring has shown positive results in clinical tests for the early detection of more severe diseases. Due to the above, this project proposes to predict respiratory diseases by applying Artificial Intelligence techniques to the data obtained from the respiratory rate to identify risks to people's health through a non-invasive wearable device. User-centered methods are being used to design a prototype informed by the needs and characteristics of the users.

Ambulatory seizure forecasting with a wrist-worn device using long-short term memory deep learning

The ability to forecast seizures minutes to hours in advance of an event has been verified using invasive EEG devices, but has not been previously demonstrated using noninvasive wearable devices over long durations in an ambulatory setting. In this study we developed a seizure forecasting system with a long short-term memory (LSTM) recurrent neural network (RNN) algorithm, using a noninvasive wrist-worn research-grade physiological sensor device, and tested the system in patients with epilepsy in the field, with concurrent invasive EEG confirmation of seizures via an implanted recording device. The system achieved forecasting performance significantly better than a random predictor for 5 of 6 patients studied, with mean AUC-ROC of 0.80 (range 0.72–0.92). These results provide the first clear evidence that direct seizure forecasts are possible using wearable devices in the ambulatory setting for many patients with epilepsy.

Detecting Pathogen Exposure During the Non-symptomatic Incubation Period Using Physiological Data: Proof of Concept in Non-human Primates.

Background and Objectives: Early warning of bacterial and viral infection, prior to the development of overt clinical symptoms, allows not only for improved patient care and outcomes but also enables faster implementation of public health measures (patient isolation and contact tracing). Our primary objectives in this effort are 3-fold. First, we seek to determine the upper limits of early warning detection through physiological measurements. Second, we investigate whether the detected physiological response is specific to the pathogen. Third, we explore the feasibility of extending early warning detection with wearable devices.Research Methods: For the first objective, we developed a supervised random forest algorithm to detect pathogen exposure in the asymptomatic period prior to overt symptoms (fever). We used high-resolution physiological telemetry data (aortic blood pressure, intrathoracic pressure, electrocardiograms, and core temperature) from non-human primate animal models exposed to two viral pathogens: Ebola and Marburg (N = 20). Second, to determine reusability across different pathogens, we evaluated our algorithm against three independent physiological datasets from non-human primate models (N = 13) exposed to three different pathogens: Lassa and Nipah viruses and Y. pestis. For the third objective, we evaluated performance degradation when the algorithm was restricted to features derived from electrocardiogram (ECG) waveforms to emulate data from a non-invasive wearable device.Results: First, our cross-validated random forest classifier provides a mean early warning of 51 ± 12 h, with an area under the receiver-operating characteristic curve (AUC) of 0.93 ± 0.01. Second, our algorithm achieved comparable performance when applied to datasets from different pathogen exposures – a mean early warning of 51 ± 14 h and AUC of 0.95 ± 0.01. Last, with a degraded feature set derived solely from ECG, we observed minimal degradation – a mean early warning of 46 ± 14 h and AUC of 0.91 ± 0.001.Conclusion: Under controlled experimental conditions, physiological measurements can provide over 2 days of early warning with high AUC. Deviations in physiological signals following exposure to a pathogen are due to the underlying host’s immunological response and are not specific to the pathogen. Pre-symptomatic detection is strong even when features are limited to ECG-derivatives, suggesting that this approach may translate to non-invasive wearable devices.

A hybrid neural network for continuous and non-invasive estimation of blood pressure from raw electrocardiogram and photoplethysmogram waveforms

Background and objectives: Continuous and non-invasive blood pressure monitoring would revolutionize healthcare. Currently, blood pressure (BP) can only be accurately monitored using obtrusive cuff-based devices or invasive intra-arterial monitoring. In this work, we propose a novel hybrid neural network for the accurate estimation of blood pressure (BP) using only non-invasive electrocardiogram (ECG) and photoplethysmogram (PPG) waveforms as inputs.Methods: This work proposes a hybrid neural network combines the feature detection abilities of temporal convolutional layers with the strong performance on sequential data offered by long short-term memory layers. Raw electrocardiogram and photoplethysmogram waveforms are concatenated and used as network inputs. The network was developed using the TensorFlow framework. Our scheme is analysed and compared to the literature in terms of well known standards set by the British Hypertension Society (BHS) and the Association for the Advancement of Medical Instrumentation (AAMI).Results: Our scheme achieves extremely low mean absolute errors (MAEs) of 4.41 mmHg for SBP, 2.91 mmHg for DBP, and 2.77 mmHg for MAP. A strong level of agreement between our scheme and the gold-standard intra-arterial monitoring is shown through Bland Altman and regression plots. Additionally, the standard for BP devices established by AAMI is met by our scheme. We also achieve a grade of ‘A’ based on the criteria outlined by the BHS protocol for BP devices.Conclusions: Our CNN-LSTM network outperforms current state-of-the-art schemes for non-invasive BP measurement from PPG and ECG waveforms. These results provide an effective machine learning approach that could readily be implemented into non-invasive wearable devices for use in continuous clinical and at-home monitoring.

193 Sleep Variability and Affect Dynamics Among College Students during COVID-19 Pandemic

IntroductionSleep disturbance is a transdiagnostic risk factor that is so prevalent among emerging adults it is considered to be a public health epidemic. For emerging adults, who are already at greater risk for psychopathology, the COVID-19 pandemic has disrupted daily routines, potentially changing sleep patterns and heightening risk factors for the emergence of affective dysregulation, and consequently mood-related disturbances. This study aimed to determine whether variability in sleep patterns across a 3-month period was associated with next-day positive and negative affect, and affective dynamics, proximal affective predictors of depressive symptoms among young adults during the pandemic.MethodsCollege student participants (N=20, 65% female, Mage=19.80, SDage=1.0) wore non-invasive wearable devices (the Oura ring https://ouraring.com/) continuously for a period of 3-months, measuring sleep onset latency, sleep efficiency, total sleep, and time spent in different stages of sleep (light, deep and rapid eye movement). Participants reported daily PA and NA using the Positive and Negative Affect Schedule on a 0-100 scale to report on their affective state.ResultsMultilevel models specifying a within-subject process of the relation between sleep and affect revealed that participants with higher sleep onset latency (b= -2.98, p<.01) and sleep duration on the prior day (b= -.35, p=.01) had lower PA the next day. Participants with longer light sleep duration had lower PA (b= -.28, p=.02), whereas participants with longer deep sleep duration had higher PA (b= .36, p=.02) the next day. On days with higher total sleep, participants experienced lower NA compared to their own average (b= -.01, p=.04). Follow-up exploratory bivariate correlations revealed significant associations between light sleep duration instability and higher instability in both PA and NA, whereas higher deep sleep duration was linked with lower instability in both PA and NA (all ps< .05). In the full-length paper these analyses will be probed using linear regressions controlling for relevant covariates (main effects of sleep, sex/age/ethnicity).ConclusionSleep, an important transdiagnostic health outcome, may contribute to next-day PA and NA. Sleep patterns predict affect dynamics, which may be proximal predictors of mood disturbances. Affect dynamics may be one potential pathway through which sleep has implications for health disparities.Support (if any):

Accuracy of a wearable device to non‐invasively predict continuous core body temperature

The need to obtain continuous non-invasive and accurate measurements of core body temperature (TC) has heightened with the current SARS-CoV-2 pandemic, along with exposure to increasingly hotter environmental temperatures in athletic and work settings as a result of climate change. Not only can accurate TC monitoring predict and prevent the spread of contagious illnesses at the worksite, but also can protect workers and athletes from heat-related injuries and illnesses. Although many non-invasive solutions currently exist for conducting spot-checks of TC, the accuracy of these solutions is highly variable, and is dependent upon subject characteristics and their environmental conditions. Therefore, the purpose of this study was to evaluate the accuracy of a new wearable device's TC algorithm in comparison to ground truth TC continuously across 24 h (n=46 male and female subjects for 65 total trials; mean age ± SD=31 ± 12 y; age range=18-62 y; mean height ± SD=172.2 ± 10.0 cm; mean weight ± SD=72.6±17.9 kg). Subjects ingested a gastrointestinal pill (e-Celsius, BodyCap Inc.) 1 h prior to the start of each trial, and then went about their normal daily routine while wearing a non-invasive wearable device around their upper arm (Kenzen Inc.). Kenzen's wearable device continuously monitors heart rate (via PPG), skin and ambient temperature, relative humidity of the skin and environment, and activity (via accelerometry); gastrointestinal temperatures were recorded every 5 min throughout the monitoring period. Subjects either completed one (n=27 subjects) or two trials (n=19 subjects for 38 trials). Based on gastrointestinal pill transit times, trial times ranged from 8.5 to 84.5 h, with a mean trial time of 34.5 h. To our knowledge, this is the largest dataset to date that has collected ground truth TC continuously throughout a 24 h monitoring period, and across two timepoints. See Table 1 for ground truth TC statistics. Overall accuracy of Kenzen vs. ground truth TC: mean absolute error (MAE) = 0.27°C, mean percent error = 0.72%, mean bias = -0.07°C, root mean squared error = 0.35°C, limits of agreement = ±0.68°C (see Fig. 1). Subjects’ completing two trials had a similar TC range and circadian rhythm of TC during both trials. Resting heart rate was the single best predictor of the TC range for each subject during their trial (r = –0.41, P=0.01). In conclusion, according to previously established accuracy criteria for TC devices (i.e. MAE ≤0.27°C; Casa et al., JAT, 2007), the Kenzen device can be used as an accurate, non-invasive measurement of continuous core body temperature, where TC ranges from 36-41°C.

Determining respiratory rate from photoplethysmogram and electrocardiogram signals using respiratory quality indices and neural networks.

Continuous and non-invasive respiratory rate (RR) monitoring would significantly improve patient outcomes. Currently, RR is under-recorded in clinical environments and is often measured by manually counting breaths. In this work, we investigate the use of respiratory signal quality quantification and several neural network (NN) structures for improved RR estimation. We extract respiratory modulation signals from the electrocardiogram (ECG) and photoplethysmogram (PPG) signals, and calculate a possible RR from each extracted signal. We develop a straightforward and efficient respiratory quality index (RQI) scheme that determines the quality of each moonddulation-extracted respiration signal. We then develop NNs for the estimation of RR, using estimated RRs and their corresponding quality index as input features. We determine that calculating RQIs for modulation-extracted RRs decreased the mean absolute error (MAE) of our NNs by up to 38.17%. When trained and tested using 60-sec waveform segments, the proposed scheme achieved an MAE of 0.638 breaths per minute. Based on these results, our scheme could be readily implemented into non-invasive wearable devices for continuous RR measurement in many healthcare applications.