Comparison of Bayesian Networks, G-estimation and linear models to estimate causal treatment effects in aggregated N-of-1 trials with carry-over effects.

BACKGROUND: The aggregation of a series of N-of-1 trials presents an innovative and efficient study design, as an alternative to traditional randomized clinical trials. Challenges for the statistical analysis arise when there is carry-over or complex dependencies of the treatment effect of interest. METHODS: In this study, we evaluate and compare methods for the analysis of aggregated N-of-1 trials in different scenarios with carry-over and complex dependencies of treatment effects on covariates. For this, we simulate data of a series of N-of-1 trials for Chronic Nonspecific Low Back Pain based on assumed causal relationships parameterized by directed acyclic graphs. In addition to existing statistical methods such as regression models, Bayesian Networks, and G-estimation, we introduce a carry-over adjusted parametric model (COAPM). RESULTS: The results show that all evaluated existing models have a good performance when there is no carry-over and no treatment dependence. When there is carry-over, COAPM yields unbiased and more efficient estimates while all other methods show some bias in the estimation. When there is known treatment dependence, all approaches that are capable to model it yield unbiased estimates. Finally, the efficiency of all methods decreases slightly when there are missing values, and the bias in the estimates can also increase. CONCLUSIONS: This study presents a systematic evaluation of existing and novel approaches for the statistical analysis of a series of N-of-1 trials. We derive practical recommendations which methods may be best in which scenarios.

Optimization of data pre-processing methods for time-series classification of electroencephalography data.

The performance of time-series classification of electroencephalographic data varies strongly across experimental paradigms and study participants. Reasons are task-dependent differences in neuronal processing and seemingly random variations between subjects, amongst others. The effect of data pre-processing techniques to ameliorate these challenges is relatively little studied. Here, the influence of spatial filter optimization methods and non-linear data transformation on time-series classification performance is analyzed by the example of high-frequency somatosensory evoked responses. This is a model paradigm for the analysis of high-frequency electroencephalography data at a very low signal-to-noise ratio, which emphasizes the differences of the explored methods. For the utilized data, it was found that the individual signal-to-noise ratio explained up to 74% of the performance differences between subjects. While data pre-processing was shown to increase average time-series classification performance, it could not fully compensate the signal-to-noise ratio differences between the subjects. This study proposes an algorithm to prototype and benchmark pre-processing pipelines for a paradigm and data set at hand. Extreme learning machines, Random Forest, and Logistic Regression can be used quickly to compare a set of potentially suitable pipelines. For subsequent classification, however, machine learning models were shown to provide better accuracy.

Online Learning for Wearable EEG-Based Emotion Classification.

Giving emotional intelligence to machines can facilitate the early detection and prediction of mental diseases and symptoms. Electroencephalography (EEG)-based emotion recognition is widely applied because it measures electrical correlates directly from the brain rather than indirect measurement of other physiological responses initiated by the brain. Therefore, we used non-invasive and portable EEG sensors to develop a real-time emotion classification pipeline. The pipeline trains different binary classifiers for Valence and Arousal dimensions from an incoming EEG data stream achieving a 23.9% (Arousal) and 25.8% (Valence) higher F1-Score on the state-of-art AMIGOS dataset than previous work. Afterward, the pipeline was applied to the curated dataset from 15 participants using two consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. Mean F1-Scores of 87% (Arousal) and 82% (Valence) were achieved for an immediate label setting. Additionally, the pipeline proved to be fast enough to achieve predictions in real-time in a live scenario with delayed labels while continuously being updated. The significant discrepancy from the readily available labels on the classification scores leads to future work to include more data. Thereafter, the pipeline is ready to be used for real-time applications of emotion classification.

Food Choices after Cognitive Load: An Affective Computing Approach.

Psychology and nutritional science research has highlighted the impact of negative emotions and cognitive load on calorie consumption behaviour using subjective questionnaires. Isolated studies in other domains objectively assess cognitive load without considering its effects on eating behaviour. This study aims to explore the potential for developing an integrated eating behaviour assistant system that incorporates cognitive load factors. Two experimental sessions were conducted using custom-developed experimentation software to induce different stimuli. During these sessions, we collected 30 h of physiological, food consumption, and affective states questionnaires data to automatically detect cognitive load and analyse its effect on food choice. Utilising grid search optimisation and leave-one-subject-out cross-validation, a support vector machine model achieved a mean classification accuracy of 85.12% for the two cognitive load tasks using eight relevant features. Statistical analysis was performed on calorie consumption and questionnaire data. Furthermore, 75% of the subjects with higher negative affect significantly increased consumption of specific foods after high-cognitive-load tasks. These findings offer insights into the intricate relationship between cognitive load, affective states, and food choice, paving the way for an eating behaviour assistant system to manage food choices during cognitive load. Future research should enhance system capabilities and explore real-world applications.

HARE: Unifying the Human Activity Recognition Engineering Workflow.

Sensor-based human activity recognition is becoming ever more prevalent. The increasing importance of distinguishing human movements, particularly in healthcare, coincides with the advent of increasingly compact sensors. A complex sequence of individual steps currently characterizes the activity recognition pipeline. It involves separate data collection, preparation, and processing steps, resulting in a heterogeneous and fragmented process. To address these challenges, we present a comprehensive framework, HARE, which seamlessly integrates all necessary steps. HARE offers synchronized data collection and labeling, integrated pose estimation for data anonymization, a multimodal classification approach, and a novel method for determining optimal sensor placement to enhance classification results. Additionally, our framework incorporates real-time activity recognition with on-device model adaptation capabilities. To validate the effectiveness of our framework, we conducted extensive evaluations using diverse datasets, including our own collected dataset focusing on nursing activities. Our results show that HARE's multimodal and on-device trained model outperforms conventional single-modal and offline variants. Furthermore, our vision-based approach for optimal sensor placement yields comparable results to the trained model. Our work advances the field of sensor-based human activity recognition by introducing a comprehensive framework that streamlines data collection and classification while offering a novel method for determining optimal sensor placement.

State Space Modeling of Event Count Time Series.

This paper proposes a class of algorithms for analyzing event count time series, based on state space modeling and Kalman filtering. While the dynamics of the state space model is kept Gaussian and linear, a nonlinear observation function is chosen. In order to estimate the states, an iterated extended Kalman filter is employed. Positive definiteness of covariance matrices is preserved by a square-root filtering approach, based on singular value decomposition. Non-negativity of the count data is ensured, either by an exponential observation function, or by a newly introduced "affinely distorted hyperbolic" observation function. The resulting algorithm is applied to time series of the daily number of seizures of drug-resistant epilepsy patients. This number may depend on dosages of simultaneously administered anti-epileptic drugs, their superposition effects, delay effects, and unknown factors, making the objective analysis of seizure counts time series arduous. For the purpose of validation, a simulation study is performed. The results of the time series analysis by state space modeling, using the dosages of the anti-epileptic drugs as external control inputs, provide a decision on the effect of the drugs in a particular patient, with respect to reducing or increasing the number of seizures.

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-ray Data.

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of a privacy breach, we integrated Rényi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε∈{1,3,6,10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.94 for ε=6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.

SensorHub: Multimodal Sensing in Real-Life Enables Home-Based Studies.

Observational studies are an important tool for determining whether the findings from controlled experiments can be transferred into scenarios that are closer to subjects' real-life circumstances. A rigorous approach to observational studies involves collecting data from different sensors to comprehensively capture the situation of the subject. However, this leads to technical difficulties especially if the sensors are from different manufacturers, as multiple data collection tools have to run simultaneously. We present SensorHub, a system that can collect data from various wearable devices from different manufacturers, such as inertial measurement units, portable electrocardiographs, portable electroencephalographs, portable photoplethysmographs, and sensors for electrodermal activity. Additionally, our tool offers the possibility to include ecological momentary assessments (EMAs) in studies. Hence, SensorHub enables multimodal sensor data collection under real-world conditions and allows direct user feedback to be collected through questionnaires, enabling studies at home. In a first study with 11 participants, we successfully used SensorHub to record multiple signals with different devices and collected additional information with the help of EMAs. In addition, we evaluated SensorHub's technical capabilities in several trials with up to 21 participants recording simultaneously using multiple sensors with sampling frequencies as high as 1000 Hz. We could show that although there is a theoretical limitation to the transmissible data rate, in practice this limitation is not an issue and data loss is rare. We conclude that with modern communication protocols and with the increasingly powerful smartphones and wearables, a system like our SensorHub establishes an interoperability framework to adequately combine consumer-grade sensing hardware which enables observational studies in real life.

Wearable Devices Are Well Accepted by Patients in the Study and Management of Inflammatory Bowel Disease: A Survey Study.

BACKGROUND: Wearable devices are designed to capture health-related and physiological data. They may be able to improve inflammatory bowel disease management and address evolving research needs. Little is known about patient perceptions for their use in the study and management of inflammatory bowel disease. AIMS: The aim of this survey study is to understand patient preferences and interest in wearable technology. METHODS: Consecutive adult patients who self-reported having inflammatory bowel disease were approached at the Susan and Leonard Feinstein Inflammatory Bowel Disease Center at the Mount Sinai Hospital to complete a 28-question survey. Reponses were analyzed with descriptive statistics. The Pearson Chi-square test and Fischer's exact test were used to determine the association between demographic and disease-related features and survey responses. RESULTS: Four hundred subjects completed the survey. 42.7% of subjects reported prior or current use of wearable devices. 89.0% of subjects believed that wearable devices can provide important information about their health, while 93.8% reported that they would use a wearable device if it could help their doctor manage their IBD. Subjects identified wrist-worn devices as the preferred device type and a willingness to wear these devices at least daily. CONCLUSIONS: Patients with inflammatory bowel disease believe that wearable devices can provide important information about their health and report a willingness to wear them frequently in research studies and as part the routine management of inflammatory bowel disease.

IMU-Based Movement Trajectory Heatmaps for Human Activity Recognition.

Recent trends in ubiquitous computing have led to a proliferation of studies that focus on human activity recognition (HAR) utilizing inertial sensor data that consist of acceleration, orientation and angular velocity. However, the performances of such approaches are limited by the amount of annotated training data, especially in fields where annotating data is highly time-consuming and requires specialized professionals, such as in healthcare. In image classification, this limitation has been mitigated by powerful oversampling techniques such as data augmentation. Using this technique, this work evaluates to what extent transforming inertial sensor data into movement trajectories and into 2D heatmap images can be advantageous for HAR when data are scarce. A convolutional long short-term memory (ConvLSTM) network that incorporates spatiotemporal correlations was used to classify the heatmap images. Evaluation was carried out on Deep Inertial Poser (DIP), a known dataset composed of inertial sensor data. The results obtained suggest that for datasets with large numbers of subjects, using state-of-the-art methods remains the best alternative. However, a performance advantage was achieved for small datasets, which is usually the case in healthcare. Moreover, movement trajectories provide a visual representation of human activities, which can help researchers to better interpret and analyze motion patterns.

How We Found Our IMU: Guidelines to IMU Selection and a Comparison of Seven IMUs for Pervasive Healthcare Applications.

Inertial measurement units (IMUs) are commonly used for localization or movement tracking in pervasive healthcare-related studies, and gait analysis is one of the most often studied topics using IMUs. The increasing variety of commercially available IMU devices offers convenience by combining the sensor modalities and simplifies the data collection procedures. However, selecting the most suitable IMU device for a certain use case is increasingly challenging. In this study, guidelines for IMU selection are proposed. In particular, seven IMUs were compared in terms of their specifications, data collection procedures, and raw data quality. Data collected from the IMUs were then analyzed by a gait analysis algorithm. The difference in accuracy of the calculated gait parameters between the IMUs could be used to retrace the issues in raw data, such as acceleration range or sensor calibration. Based on our algorithm, we were able to identify the best-suited IMUs for our needs. This study provides an overview of how to select the IMUs based on the area of study with concrete examples, and gives insights into the features of seven commercial IMUs using real data.

Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study.

Gait analysis is an important tool for the early detection of neurological diseases and for the assessment of risk of falling in elderly people. The availability of low-cost camera hardware on the market today and recent advances in Machine Learning enable a wide range of clinical and health-related applications, such as patient monitoring or exercise recognition at home. In this study, we evaluated the motion tracking performance of the latest generation of the Microsoft Kinect camera, Azure Kinect, compared to its predecessor Kinect v2 in terms of treadmill walking using a gold standard Vicon multi-camera motion capturing system and the 39 marker Plug-in Gait model. Five young and healthy subjects walked on a treadmill at three different velocities while data were recorded simultaneously with all three camera systems. An easy-to-administer camera calibration method developed here was used to spatially align the 3D skeleton data from both Kinect cameras and the Vicon system. With this calibration, the spatial agreement of joint positions between the two Kinect cameras and the reference system was evaluated. In addition, we compared the accuracy of certain spatio-temporal gait parameters, i.e., step length, step time, step width, and stride time calculated from the Kinect data, with the gold standard system. Our results showed that the improved hardware and the motion tracking algorithm of the Azure Kinect camera led to a significantly higher accuracy of the spatial gait parameters than the predecessor Kinect v2, while no significant differences were found between the temporal parameters. Furthermore, we explain in detail how this experimental setup could be used to continuously monitor the progress during gait rehabilitation in older people.

Stress detection in daily life scenarios using smart phones and wearable sensors: A survey.

Stress has become a significant cause for many diseases in the modern society. Recently, smartphones, smartwatches and smart wrist-bands have become an integral part of our lives and have reached a widespread usage. This raised the question of whether we can detect and prevent stress with smartphones and wearable sensors. In this survey, we will examine the recent works on stress detection in daily life which are using smartphones and wearable devices. Although there are a number of works related to stress detection in controlled laboratory conditions, the number of studies examining stress detection in daily life is limited. We will divide and investigate the works according to used physiological modality and their targeted environment such as office, campus, car and unrestricted daily life conditions. We will also discuss promising techniques, alleviation methods and research challenges.

Inertial Sensor-Based Robust Gait Analysis in Non-Hospital Settings for Neurological Disorders.

The gold standards for gait analysis are instrumented walkways and marker-based motion capture systems, which require costly infrastructure and are only available in hospitals and specialized gait clinics. Even though the completeness and the accuracy of these systems are unquestionable, a mobile and pervasive gait analysis alternative suitable for non-hospital settings is a clinical necessity. Using inertial sensors for gait analysis has been well explored in the literature with promising results. However, the majority of the existing work does not consider realistic conditions where data collection and sensor placement imperfections are imminent. Moreover, some of the underlying assumptions of the existing work are not compatible with pathological gait, decreasing the accuracy. To overcome these challenges, we propose a foot-mounted inertial sensor-based gait analysis system that extends the well-established zero-velocity update and Kalman filtering methodology. Our system copes with various cases of data collection difficulties and relaxes some of the assumptions invalid for pathological gait (e.g., the assumption of observing a heel strike during a gait cycle). The system is able to extract a rich set of standard gait metrics, including stride length, cadence, cycle time, stance time, swing time, stance ratio, speed, maximum/minimum clearance and turning rate. We validated the spatio-temporal accuracy of the proposed system by comparing the stride length and swing time output with an IR depth-camera-based reference system on a dataset comprised of 22 subjects. Furthermore, to highlight the clinical applicability of the system, we present a clinical discussion of the extracted metrics on a disjoint dataset of 17 subjects with various neurological conditions.

Variability Analysis of Therapeutic Movements using Wearable Inertial Sensors.

A variability analysis of upper limb therapeutic movements using wearable inertial sensors is presented. Five healthy young adults were asked to perform a set of movements using two sensors placed on the upper arm and forearm. Reference data were obtained from three therapists. The goal of the study is to determine an intra and inter-group difference between a number of given movements performed by young people with respect to the movements of therapists. This effort is directed toward studying other groups characterized by motion impairments, and it is relevant to obtain a quantified measure of the quality of movement of a patient to follow his/her recovery. The sensor signals were processed by applying two approaches, time-domain features and similarity distance between each pair of signals. The data analysis was divided into classification and variability using features and distances calculated previously. The classification analysis was made to determine if the movements performed by the test subjects of both groups are distinguishable among them. The variability analysis was conducted to measure the similarity of the movements. According to the results, the flexion/extension movement had a high intra-group variability. In addition, meaningful information were provided in terms of change of velocity and rotational motions for each individual.

Unobtrusive measurement of cognitive load and physiological signals in uncontrolled environments.

While individuals fail to assess their mental health subjectively in their day-to-day activities, the recent development of consumer-grade wearable devices has enormous potential to monitor daily workload objectively by acquiring physiological signals. Therefore, this work collected consumer-grade physiological signals from twenty-four participants, following a four-hour cognitive load elicitation paradigm with self-chosen tasks in uncontrolled environments and a four-hour mental workload elicitation paradigm in a controlled environment. The recorded dataset of approximately 315 hours consists of electroencephalography, acceleration, electrodermal activity, and photoplethysmogram data balanced across low and high load levels. Participants performed office-like tasks in the controlled environment (mental arithmetic, Stroop, N-Back, and Sudoku) with two defined difficulty levels and in the uncontrolled environments (mainly researching, programming, and writing emails). Each task label was provided by participants using two 5-point Likert scales of mental workload and stress and the pairwise NASA-TLX questionnaire. This data is suitable for developing real-time mental health assessment methods, conducting research on signal processing techniques for challenging environments, and developing personal cognitive load assistants.

Analyzing population-level trials as N-of-1 trials: An application to gait.

Studying individual causal effects of health interventions is important whenever intervention effects are heterogeneous between study participants. Conducting N-of-1 trials, which are single-person randomized controlled trials, is the gold standard for their analysis. As an alternative method, we propose to re-analyze existing population-level studies as N-of-1 trials, and use gait as a use case for illustration. Gait data were collected from 16 young and healthy participants under fatigued and non-fatigued, as well as under single-task (only walking) and dual-task (walking while performing a cognitive task) conditions. As a reference to the N-of-1 trials approach, we first computed standard population-level ANOVA models to evaluate differences in gait parameters (stride length and stride time) across conditions. Then, we estimated the effect of the interventions on gait parameters on the individual level through Bayesian repeated-measures models, viewing each participant as their own trial, and compared the results. The results illustrated that while few overall population-level effects were visible, individual-level analyses revealed differences between participants. Baseline values of the gait parameters varied largely among all participants, and the effects of fatigue and cognitive task were also heterogeneous, with some individuals showing effects in opposite directions. These differences between population-level and individual-level analyses were more pronounced for the fatigue intervention compared to the cognitive task intervention. Following our empirical analysis, we discuss re-analyzing population studies through the lens of N-of-1 trials more generally and highlight important considerations and requirements. Our work encourages future studies to investigate individual effects using population-level data.

ARTEMIS: An alarm threshold and policy mining system for the intensive care unit.

BACKGROUND: Alarm fatigue is a major technology-induced hazard for patients and staff in intensive care units. Too many - mostly unnecessary - alarms cause desensitisation and lack of response in medical staff. Unsuitable alarm policies are one reason for alarm fatigue. But changing alarm policies is a delicate issue since it concerns patient safety. OBJECTIVE: We present ARTEMIS, a novel, computer-aided clinical decision support system for policy makers that can help to considerably improve alarm policies using data from hospital information systems. METHODS: Policy makers can use different policy components from ARTEMIS' internal library to assemble tailor-made alarm policies for their intensive care units. Alternatively, policy makers can provide even more highly customised policy components as Python functions using data the hospital information systems. This can even include machine learning models - for example for setting alarm thresholds. Finally, policy makers can evaluate their system of policies and compare the resulting alarm loads. RESULTS: ARTEMIS reports and compares numbers of alarms caused by different alarm policies for an easily adaptable target population. ARTEMIS can compare policies side-by-side and provides grid comparisons and heat maps for parameter optimisation. For example, we found that the utility of alarm delays varies based on target population. Furthermore, policy makers can introduce virtual parameters that are not in the original data by providing a formula to compute them. Virtual parameters help measuring and alarming on the right metric, even if the patient monitors do not directly measure this metric. CONCLUSION: ARTEMIS does not release the policy maker from assessing the policy from a medical standpoint. But as a knowledge discovery and clinical decision support system, it provides a strong quantitative foundation for medical decisions. At comparatively low cost of implementation, ARTEMIS can have a substantial impact on patients and staff alike - with organisational, economic, and clinical benefits for the implementing hospital.

Enabling machine learning models in alarm fatigue research: Creation of a large relevance-annotated oxygen saturation alarm data set.

BACKGROUND: Too many unnecessary alarms in the intensive care unit are one of the main reasons for alarm fatigue: Medical staff is overburdened and fails to respond appropriately. This endangers both patients and staff. Currently, there are no algorithms that can determine which alarms are clinically relevant and which are not. OBJECTIVE: This paper presents a computer-aided method to automatically determine whether and which interventions followed an alarm. Our algorithm annotates a large data set of oxygen saturation alarms. Previous studies only presented analyses on smaller data sets of manually annotated alarms. Future research can use our large data set of labelled alarms to train machine learning models, for example for alarm prioritisation. METHODS: We propose an alarm annotation algorithm that can efficiently label oxygen saturation alarms from respiratory alarm management by actionability. This algorithm is based on an alarm annotation guideline and works on data from 1961 patients from the hospital information system recorded 06/2019-06/2021. The algorithm analyses a pre-defined time frame after an alarm to determine whether an intervention followed or not. The resulting data set can be used to train machine learning models that predict alarm actionability. RESULTS: Our open-source algorithm is the first to create a large data set of around 2.5 million relevance-annotated alarms in mere hours. A task that would take years using manual annotation. Our algorithm denotes about 9% of the alarms as actionable. This is in line with previous research. The data set also shows which respiratory management interventions medical staff used to counteract the cause of an alarm. CONCLUSION: The data set can be a starting point to reduce the number of unnecessary oxygen saturation alarms. For example, it can serve as a training data set for machine learning models that assess future alarms. The algorithm might be re-used to annotate other alarm data sets as well.

The role of the (in)accessibility of social media data for infodemic management: a public health perspective on the situation in the European Union in March 2024.

Public health institutions rely on the access to social media data to better understand the dynamics and impact of infodemics - an overabundance of information during a disease outbreak, potentially including mis-and disinformation. The scope of the COVID-19 infodemic has led to growing concern in the public health community. The spread of harmful information or information voids may negatively impact public health. In this context, social media are of particular relevance as an integral part of our society, where much information is consumed. In this perspective paper, we discuss the current state of (in)accessibility of social media data of the main platforms in the European Union. The European Union's relatively new Digital Services Act introduces the obligation for platforms to provide data access to a wide range of researchers, likely including researchers at public health institutions without formal academic affiliation. We examined eight platforms (Facebook, Instagram, LinkedIn, Pinterest, Snapchat, TikTok, X, YouTube) affected by the new legislation in regard to data accessibility. We found that all platforms apart from TikTok offer data access through the Digital Services Act. Potentially, this presents a fundamentally new situation for research, as before the Digital Services Act, few platforms granted data access or only to very selective groups of researchers. The access regime under the Digital Services Act is, however, still evolving. Specifics such as the application procedure for researcher access are still being worked out and results can be expected in spring 2024. The impact of the Digital Services Act on research will therefore only become fully apparent in the future.