Towards Non-invasive Labour Detection: A Free-Living Evaluation.

In this paper we show early evidence of the feasibility of detecting labour during pregnancy, non-invasively and in free-living. In particular, we present machine learning models aiming at dealing with the challenges of unsupervised, free-living data collection, such as identifying periods of high quality data and detecting physiological changes as labour approaches. During a first phase, physiological data including electrohysterography (EHG, the electrical activity of the uterus), heart rate (HR) and gestational age (GA) were collected in laboratory conditions for model development. In particular, data were collected 1) during simulated activities of daily living, aiming at eliciting artifacts and developing diagnostic models for free-living data 2) during pregnancy, including labour, aiming at developing labour probability models from clean, supervised physiological recordings. Machine learning models using datasets 1) and 2) were deployed in free-living, longitudinally, in 142 pregnant women, between week 22 of pregnancy and delivery. A total of 1014 hours of data and an average of 7 hours per person were collected. Output of the developed models was analyzed to determine the feasibility of detecting labour non-invasively using physiological data, acquired with a single sensor placed on the abdomen. Results showed that the probability of being in labour for recordings collected during the last 24 hours of pregnancy was consistently higher than the probability during any other pregnancy week. Thus, non-invasive labour detection from physiological data seems promising.

Cardiorespiratory fitness estimation in free-living using wearable sensors.

OBJECTIVE: In this paper we propose artificial intelligence methods to estimate cardiorespiratory fitness (CRF) in free-living using wearable sensor data. METHODS: Our methods rely on a computational framework able to contextualize heart rate (HR) in free-living, and use context-specific HR as predictor of CRF without need for laboratory tests. In particular, we propose three estimation steps. Initially, we recognize activity primitives using accelerometer and location data. Using topic models, we group activity primitives and derive activities composites. We subsequently rank activity composites, and analyze the relation between ranked activity composites and CRF across individuals. Finally, HR data in specific activity primitives and composites is used as predictor in a hierarchical Bayesian regression model to estimate CRF level from the participant's habitual behavior in free-living. RESULTS: We show that by combining activity primitives and activity composites the proposed framework can adapt to the user and context, and outperforms other CRF estimation models, reducing estimation error between 10.3% and 22.6% on a study population of 46 participants. CONCLUSIONS: Our investigation showed that HR can be contextualized in free-living using activity primitives and activity composites and robust CRF estimation in free-living is feasible.

Cardiorespiratory fitness estimation using wearable sensors: Laboratory and free-living analysis of context-specific submaximal heart rates.

In this work, we propose to use pattern recognition methods to determine submaximal heart rate (HR) during specific contexts, such as walking at a certain speed, using wearable sensors in free living, and using context-specific HR to estimate cardiorespiratory fitness (CRF). CRF of 51 participants was assessed by a maximal exertion test (V̇o2 max). Participants wore a combined accelerometer and HR monitor during a laboratory-based simulation of activities of daily living and for 2 wk in free living. Anthropometrics, HR while lying down, and walking at predefined speeds in laboratory settings were used to estimate CRF. Explained variance (R(2)) was 0.64 for anthropometrics, and increased up to 0.74 for context-specific HR (0.73-0.78 when including fat-free mass). Next, we developed activity recognition and walking speed estimation algorithms to determine the same contexts (i.e., lying down and walking) in free living. Context-specific HR in free living was highly correlated with laboratory measurements (Pearson's r = 0.71-0.75). R(2) for CRF estimation was 0.65 when anthropometrics were used as predictors, and increased up to 0.77 when including free-living context-specific HR (i.e., HR while walking at 5.5 km/h). R(2) varied between 0.73 and 0.80 when including fat-free mass among the predictors. Root mean-square error was reduced from 354.7 to 281.0 ml/min by the inclusion of context-specific HR parameters (21% error reduction). We conclude that pattern recognition techniques can be used to contextualize HR in free living and estimated CRF with accuracy comparable to what can be obtained with laboratory measurements of HR response to walking.

Detection of fetal kicks using body-worn accelerometers during pregnancy: Trade-offs between sensors number and positioning.

Monitoring fetal wellbeing is key in modern obstetrics. While fetal movement is routinely used as a proxy to fetal wellbeing, accurate, noninvasive, long-term monitoring of fetal movement is challenging. A few accelerometer-based systems have been developed in the past few years, to tackle common issues in ultrasound measurement and enable remote, self-administrated monitoring of fetal movement during pregnancy. However, many questions remain unanswered to date on the optimal setup in terms of body-worn accelerometers as well as signal processing and machine learning techniques used to detect fetal movement. In this paper, we systematically analyze the trade-offs between sensor number and positioning, the presence of reference accelerometers outside of the abdominal area and provide guidelines on dealing with class imbalance. Using a dataset of 15 measurements collected employing 6 three-axial accelerometers we show that including a reference accelerometer on the back of the participant consistently improves fetal movement detection performance regardless of the number of sensors utilized. We also show that two accelerometers plus a reference accelerometer are sufficient for optimal results.

Estimating Oxygen Uptake During Nonsteady-State Activities and Transitions Using Wearable Sensors.

In this paper, we present a method to estimate oxygen uptake ( VO2) during daily life activities and transitions between them. First, we automatically locate transitions between activities and periods of nonsteady-state VO2. Subsequently, we propose and compare activity-specific linear functions to model steady-state activities and transition-specific nonlinear functions to model nonsteady-state activities and transitions. We evaluate our approach in study data from 22 participants that wore a combined accelerometer and heart rate sensor while performing a wide range of activities (clustered into lying, sedentary, dynamic/household, walking, biking and running), including many transitions between intensities, thus resulting in nonsteady-state VO2. Indirect calorimetry was used in parallel to obtain VO2 reference. VO2 estimation error during transitions between sedentary, household and walking activities could be reduced by 16% on average using the proposed approach, compared to state of the art methods.

Personalized cardiorespiratory fitness and energy expenditure estimation using hierarchical Bayesian models.

Accurate estimation of energy expenditure (EE) and cardiorespiratory fitness (CRF) is a key element in determining the causal relation between aspects of human behavior related to physical activity and health. In this paper we estimate CRF without requiring laboratory protocols and personalize energy expenditure (EE) estimation models that rely on heart rate data, using CRF. CRF influences the relation between heart rate and EE. Thus, EE estimation based on heart rate typically requires individual calibration. Our modeling technique relies on a hierarchical approach using Bayesian modeling for both CRF and EE estimation models. By including CRF level in a hierarchical Bayesian model, we avoid the need for individual calibration or explicit heart rate normalization since CRF accounts for the different relation between heart rate and EE in different individuals. Our method first estimates CRF level from heart rate during low intensity activities of daily living, showing that CRF can be determined without specific protocols. Reference VO2max and EE were collected on a sample of 32 participants with varying CRF level. CRF estimation error could be reduced up to 27.0% compared to other models. Secondly, we show that including CRF as a group level predictor in a hierarchical model for EE estimation accounts for the relation between CRF, heart rate and EE. Thus, reducing EE estimation error by 18.2% on average. Our results provide evidence that hierarchical modeling is a promising technique for generalized CRF estimation from activities of daily living and personalized EE estimation.

Personalization of Energy Expenditure Estimation in Free Living Using Topic Models.

We introduce an approach to personalize energy expenditure (EE) estimates in free living. First, we use topic models to discover activity composites from recognized activity primitives and stay regions in daily living data. Subsequently, we determine activity composites that are relevant to contextualize heart rate (HR). Activity composites were ranked and analyzed to optimize the correlation to HR normalization parameters. Finally, individual-specific HR normalization parameters were used to normalize HR. Normalized HR was then included in activity-specific regression models to estimate EE. Our HR normalization minimizes the effect of individual fitness differences from entering in EE regression models. By estimating HR normalization parameters in free living, our approach avoids dedicated individual calibration or laboratory tests. In a combined free-living and laboratory study dataset, including 34 healthy volunteers, we show that HR normalization in 14-day free-living data improves accuracy compared to no normalization and normalization based on activity primitives only ( 29.4% and 19.8 % error reduction against lab reference). Based on acceleration and HR, both recorded from a necklace, and GPS acquired from a smartphone, EE estimation error was reduced by 10.7 % in a leave-one-participant-out analysis.

Estimating energy expenditure using body-worn accelerometers: a comparison of methods, sensors number and positioning.

Several methods to estimate energy expenditure (EE) using body-worn sensors exist; however, quantifications of the differences in estimation error are missing. In this paper, we compare three prevalent EE estimation methods and five body locations to provide a basis for selecting among methods, sensors number, and positioning. We considered 1) counts-based estimation methods, 2) activity-specific estimation methods using METs lookup, and 3) activity-specific estimation methods using accelerometer features. The latter two estimation methods utilize subsequent activity classification and EE estimation steps. Furthermore, we analyzed accelerometer sensors number and on-body positioning to derive optimal EE estimation results during various daily activities. To evaluate our approach, we implemented a study with 15 participants that wore five accelerometer sensors while performing a wide range of sedentary, household, lifestyle, and gym activities at different intensities. Indirect calorimetry was used in parallel to obtain EE reference data. Results show that activity-specific estimation methods using accelerometer features can outperform counts-based methods by 88% and activity-specific methods using METs lookup for active clusters by 23%. No differences were found between activity-specific methods using METs lookup and using accelerometer features for sedentary clusters. For activity-specific estimation methods using accelerometer features, differences in EE estimation error between the best combinations of each number of sensors (1 to 5), analyzed with repeated measures ANOVA, were not significant. Thus, we conclude that choosing the best performing single sensor does not reduce EE estimation accuracy compared to a five sensors system and can reliably be used. However, EE estimation errors can increase up to 80% if a nonoptimal sensor location is chosen.

Wearable, wireless EEG solutions in daily life applications: what are we missing?

Monitoring human brain activity has great potential in helping us understand the functioning of our brain, as well as in preventing mental disorders and cognitive decline and improve our quality of life. Noninvasive surface EEG is the dominant modality for studying brain dynamics and performance in real-life interaction of humans with their environment. To take full advantage of surface EEG recordings, EEG technology has to be advanced to a level that it can be used in daily life activities. Furthermore, users have to see it as an unobtrusive option to monitor and improve their health. To achieve this, EEG systems have to be transformed from stationary, wired, and cumbersome systems used mostly in clinical practice today, to intelligent wearable, wireless, convenient, and comfortable lifestyle solutions that provide high signal quality. Here, we discuss state-of-the-art in wireless and wearable EEG solutions and a number of aspects where such solutions require improvements when handling electrical activity of the brain. We address personal traits and sensory inputs, brain signal generation and acquisition, brain signal analysis, and feedback generation. We provide guidelines on how these aspects can be advanced further such that we can develop intelligent wearable, wireless, lifestyle EEG solutions. We recognized the following aspects as the ones that need rapid research progress: application driven design, end-user driven development, standardization and sharing of EEG data, and development of sophisticated approaches to handle EEG artifacts.

Personalizing energy expenditure estimation using physiological signals normalization during activities of daily living.

In this paper we propose a generic approach to reduce inter-individual variability of different physiological signals (HR, GSR and respiration) by automatically estimating normalization parameters (e.g. baseline and range). The proposed normalization procedure does not require a dedicated personal calibration during system setup. On the other hand, normalization parameters are estimated at system runtime from sedentary and low intensity activities of daily living (ADLs), such as lying and walking. When combined with activity-specific energy expenditure (EE) models, our normalization procedure improved EE estimation by 15 to 33% in a study group of 18 participants, compared to state of the art activity-specific EE models combining accelerometer and non-normalized physiological signals.

Comparative evaluation of an ambulatory EEG platform vs. clinical gold standard.

Electroencephalography (EEG) testing in clinical labs makes use of large amplifiers and complex software for data acquisition. While there are new ambulatory electroencephalogram (EEG) systems, few have been directly compared to a gold standard system. Here, an ultra-low power wireless EEG system designed by Imec is tested against the gold standard Neuroscan SynAmps2 EEG system, recording simultaneously from the same laboratory cap prepared with electrode gel. The data was analyzed using correlation analysis for both time domain and frequency domain data. The analysis indicated a high Pearson's correlation coefficient (mean=0.957, median=0.985) with high confidence (mean P=0.002) for 10-second sets of data transformed to the frequency domain. The time domain results had acceptable Pearson's coefficient (mean=0.580, median =0.706) with high confidence (mean P=0.008).

Investigating the impact of force and movements on impedance magnitude and EEG.

The success of applying dry sensor technology in measuring electroencephalogram (EEG) signals will have a significant impact on a wider adoption of brain activity monitoring in ambulatory as well as real life solutions. The presence of motion artifacts is the major obstacle in applying dry sensors for long-term EEG monitoring. In this paper we assess the impact of external forces applied on a dry EEG electrode as well as the impact of head and body movements on the electrode-tissue contact impedance and the EEG signal. The data collection method and the preliminary correlation analysis are presented. The analysis demonstrates that the impedance magnitude and EEG changes are highly correlated when artifacts are induced by the application of force or head and body movements, only in case these artifacts are short (less than 3s) and exhibit regular pattern. The correlation between the EEG and impedance magnitude is lower for longer artifact segments, especially the ones containing artifacts with irregular movements or large variations in the applied force. This indicates a time-dependent, non-linear relation between the artifact-related phenomena, impedance magnitude, and EEG.

Body weight-normalized Energy Expenditure estimation using combined activity and allometric scaling clustering.

Wearable sensors have great potential for accurate estimation of Energy Expenditure (EE) in daily life. Advances in wearable technology (miniaturization, lower costs), and machine learning techniques as well as recently developed self-monitoring movements, such as the Quantified Self, are facilitating mass adoption. However, EE estimations are affected by a person's body weight (BW). BW is a confounding variable preventing meaningful individual and group comparisons. In this paper we present a machine learning approach for BW normalization and activities clustering. In our approach to activity-specific EE modeling, we adopt a genetic algorithm-based clustering scheme, not only based on accelerometer (ACC) features, but also on allometric coefficients derived from 19 subjects performing a wide set of lifestyle and gym activities. We show that our approach supports making comparisons between individuals performing the same activities independently of BW, while maintaining accuracy in the EE estimate.

Autonomic effects of refractory epilepsy on heart rate variability in children: influence of intermittent vagus nerve stimulation.

AIM: Vagus nerve stimulation (VNS) is a therapeutic option for individuals with refractory epilepsy. Individuals with refractory epilepsy are prone to dysfunction of the autonomic nervous system. Reduced heart rate variability is a marker of dysfunction of the autonomic nervous system. Our goal was to study heart rate variability in children with refractory epilepsy and the influence of VNS on this parameter. METHODS: In 17 children (13 male; four female; mean age 7 y 6 mo; age range 3-16 y) with refractory epilepsy, electroencephalographic and electrocardiographic data were obtained before and after implantation of VNS during stage 2 and slow-wave sleep. Time and frequency domain parameters were calculated and the results were compared with an age- and sex-matched group of individuals without refractory epilepsy. RESULTS: Our results show that autonomic cardiac control is affected in individuals with refractory epilepsy. There is a striking reduction in vagal tone during slow-wave sleep and modulation capacity is smaller than in individuals without refractory epilepsy. Implantation of VNS induces a shift in sympathovagal balance towards sympathetic predominance and an improvement in autonomic modulation. INTERPRETATION: Heart rate variability is affected in children with refractory epilepsy, and changes after implantation of VNS. The observed changes could be of importance in the cardiac complications of individuals with epilepsy and should be explored in more detail.

A lightweight security scheme for wireless body area networks: design, energy evaluation and proposed microprocessor design.

In order for wireless body area networks to meet widespread adoption, a number of security implications must be explored to promote and maintain fundamental medical ethical principles and social expectations. As a result, integration of security functionality to sensor nodes is required. Integrating security functionality to a wireless sensor node increases the size of the stored software program in program memory, the required time that the sensor's microprocessor needs to process the data and the wireless network traffic which is exchanged among sensors. This security overhead has dominant impact on the energy dissipation which is strongly related to the lifetime of the sensor, a critical aspect in wireless sensor network (WSN) technology. Strict definition of the security functionality, complete hardware model (microprocessor and radio), WBAN topology and the structure of the medium access control (MAC) frame are required for an accurate estimation of the energy that security introduces into the WBAN. In this work, we define a lightweight security scheme for WBAN, we estimate the additional energy consumption that the security scheme introduces to WBAN based on commercial available off-the-shelf hardware components (microprocessor and radio), the network topology and the MAC frame. Furthermore, we propose a new microcontroller design in order to reduce the energy consumption of the system. Experimental results and comparisons with other works are given.

Closing the loop for Deep Brain Stimulation implants enables personalized healthcare for Parkinson's disease patients.

DEEP brain stimulation implants have improved life quality for more than 70,000 patients world-wide with diseases like Parkinson's, essential tremor, or obsessive-compulsive disorder where pharmaceutical therapies alone could not offer sufficient relief. Still, optimization and monitoring relies heavily on regular clinical visits, putting a burden on patient's comfort and clinicians. Permanent monitoring and combination with other patient health signals could ultimately lead to a personalized closed-loop therapy with remote quality monitoring. This requires technological improvements on the DBS implants such as integration of recording capabilities for brain activity monitoring, active low-power electronics, rechargeable battery technology, and body sensor networks for integration with e.g. gait, speech, and other vital information sensors on the patient's body and a link to a telemedicine platform using mobile technologies.

Towards mental stress detection using wearable physiological sensors.

Early mental stress detection can prevent many stress related health problems. This study aimed at using a wearable sensor system to measure physiological signals and detect mental stress. Three different stress conditions were presented to a healthy subject group. During the procedure, ECG, respiration, skin conductance, and EMG of the trapezius muscles were recorded. In total, 19 physiological features were calculated from these signals. After normalization of the feature values and analysis of correlations among these features, a subset of 9 features was selected for further analysis. Principal component analysis reduced these 9 features to 7 principal components (PCs). Using these PCs and different classifiers, a consistent classification accuracy between stress and non stress conditions of almost 80% was found. This suggests that a promising feature subset was found for future development of a personalized stress monitor.

A low-power multi-modal body sensor network with application to epileptic seizure monitoring.

Monitoring patients' physiological signals during their daily activities in the home environment is one of the challenge of the health care. New ultra-low-power wireless technologies could help to achieve this goal. In this paper we present a low-power, multi-modal, wearable sensor platform for the simultaneous recording of activity and physiological data. First we provide a description of the wearable sensor platform, and its characteristics with respect to power consumption. Second we present the preliminary results of the comparison between our sensors and a reference system, on healthy subjects, to test the reliability of the detected physiological (electrocardiogram and respiration) and electromyography signals.

Towards wireless emotional valence detection from EEG.

Intelligent affective computers can have many medical and non-medical applications. However today's affective computers are limited in scope by their transferability to other application environments or that they monitor only one aspect of physiological emotion expression. Here, the use of a wireless EEG system, which can be implemented in a body area network, is used to investigate the potential of monitoring emotional valence in EEG, for application in real-life situations. The results show 82% accuracy for automatic classification of positive, negative and neutral valence based on film clip viewing, using features containing information on both the frequency content of the EEG and how this changes over time.

Early results on wrist based heart rate monitoring using mechanical transducers.

Heart rate monitoring has been a significant topic of interest in the areas of healthcare, sports and gaming. Compared to locations such as the neck, ear, or chest, the wrist is a convenient measurement point, as the measurement technology can be integrated into a wristwatch. However, key technical challenges exist, namely a small physiological SNR and large disturbances due to motion artifact. This paper reports early results on a packaging concept to monitor the heartrate during rest and motion using off-the-shelf piezoelectric PVDF film sensors. Evaluation has shown good results at rest and unsatisfactory results during motion. Results from this investigation will nonetheless be used as input for the development of a wrist-based heartrate monitor which could function during activities such as running, walking or typing on a keyboard.