Publications | Robert Richer

2026

Contactless Sleep Staging with Radar: A Transfer Learning Approach

Daniel Krauss, Robert Richer, Nils Albrecht, and 8 more authors

IEEE Open Journal of Engineering in Medicine and Biology, 2026

DOI Code
A Study Protocol for a Systematic Review and Meta-Analysis on Macroscopic Body Movements as a Marker for Acute Stress

Miriam Kurz, Veronika Ringgold, Luca Abel, and 6 more authors

Systematic Reviews, Jan 2026

Abs DOI

Abstract Background Experiencing stress is a normative part of human life. Due to its major impact on health and longevity, effort has been put into understanding underlying determinants and consequences. For stress measurement, a vast number of different methods, including physiological, subjective, and behavioral assessments, can be used. Previous measurement methods have already provided valuable insights into the role of the stress systems. However, their application has some drawbacks, highlighting the need for more convenient, less expensive, less intrusive, and continuous methods. A promising alternative could be the assessment of macroscopic body movements, which we define as body movements that are actively, consciously, or unconsciously, initiated by the muscular system. Methods The study protocol was registered with PROSPERO, and PRISMA-P guidelines were followed. We will screen MEDLINE, PsycInfo, Web of Science, Embase, and Google Scholar for suitable studies in German or English with no restrictions towards the publication date. To do so, an a priori defined search strategy will be employed. Furthermore, we will carry out backward and forward citation searches. Inclusion criteria comprise studies examining macroscopic body movements in response to stress or related psychological constructs induced by standardized protocols. Exclusion criteria include studies on non-human populations as well as studies that do not report on a control group/condition nor pre-/post-comparisons nor traditional stress markers. The search, selection, and data extraction processes will be performed by two reviewers independently, while a third reviewer will be consulted in case of discrepancy. We will assess Risk of Bias using the revised Cochrane Risk of Bias tool or ROBINS-I, as appropriate. We will conduct random-effects meta-analyses where feasible. The quality of evidence will be evaluated using the GRADE approach. Furthermore, results will undergo critical examination towards meta-biases. Discussion Due to the growing number of studies assessing macroscopic movements in the context of stress, the field is becoming complex, highlighting the need for a summary of current findings. Thus, here we outline a study protocol for a systematic review and meta-analysis on macroscopic movements as a potential novel marker for stress. Systematic review registration PROSPERO CRD42024539659
Differential Effects of Body Posture on Biological and Psychological Responses in the Trier Social Stress Test

Miriam Kurz, Luca Abel, Felicitas Burkhardt, and 5 more authors

Biopsychosocial Science and Medicine, Feb 2026

Abs DOI

Objective: Acute stress protocols are important tools for laboratory research on acute stress mechanisms. Several reasons necessitate varying body posture. However, the effect of such variations has not been systematically studied. We therefore examined the impact of body posture (sitting vs. standing) on biological and psychological stress responses induced by the Trier Social Stress Test (TSST) and its control condition (friendly TSST; f-TSST). Methods: One hundred four participants (57.69% female, mean age: 22.28, SD = 3.44) were randomly assigned to the sitting versus standing group and underwent the TSST and f-TSST on 2 separate days in randomized order. Stress responses were measured through salivary cortisol and alpha-amylase, HR, HRV, and self-reports. Results: Biological stress responses were higher in the TSST condition and the standing group (eg, maximum cortisol increase: p = .004). Psychological stress response was higher in the stress condition (eg, negative affect: p < .001), but was not different between posture groups (eg, negative affect: p = .819). No differences were observed in any markers after adjusting the stress-response measures for the non-stress condition (smallest p = .173). Conclusions: Although biological, but not psychological stress responses were affected by body posture overall, these effects did not persist when responses in the stress condition were adjusted by subtracting the non-stress values from the f-TSST. This implies that the effect of body posture can be neglected in studies with a non-stress control condition, but that its effects should be taken into account in studies with only the stress protocol.

2025

Preprint

Beat-to-Beat Aortic Valve Opening Detection from Impedance Cardiography Using Machine Learning

Luca Abel, Sebastian Stühler, Tobias Steigleder, and 4 more authors

Dec 2025

DOI
Editor’s Choice

Body Movements as Biomarkers: Machine Learning-based Prediction of HPA Axis Reactivity to Stress

Luca Abel, Robert Richer, Felicitas Burkhardt, and 5 more authors

Psychoneuroendocrinology, Jun 2025

DOI Code
Preprint

Thermal Imaging-based Breathing Phase Classification Using Video Transformer

Sophie Fischerauer, Mischa Dombrowski, Marie Oesten, and 2 more authors

Oct 2025

DOI
Investigating Psychosocial Stress Arising from Marker-Based Optical Motion Capture and Subsequent Effects on Gait

Sophie Fleischmann, Miriam Kurz, Robert Richer, and 5 more authors

Scientific Reports, Dec 2025

Abs DOI Code

Abstract Optical motion capture (OMC) requires participants to wear minimal clothing for precise marker placement and involves physical contact with the examiner. We investigate whether the standard OMC procedure induces psychosocial stress in participants and whether it leads to alterations in their gait patterns. Thirty-nine participants took part in a between-groups gait experiment. The OMC group wore short, tight clothing and 39 markers, while the control group wore everyday clothing without markers. Gait was recorded via sagittal-plane video, and gait features (stride times, variability, ranges of motion) were computed from 2-dimensional pose estimation trajectories. Physiological and psychological state changes were assessed using salivary cortisol and self-report questionnaires at multiple time points. Marker placement led to significantly increased negative affect and decreased positive affect among OMC participants, as well as a noticeable but non-significant cortisol response that varied in intensity across individuals. The negative psychological state did not result in significant gait differences on group level, except for late stance knee flexion during slow walking, which may be attributed to reduced pose estimation accuracy due to differences in clothing between groups. Our study suggests that OMC can be used without unwanted gait alterations due to stress at group level. However, contactless measurements that allow participants to wear clothing could alleviate their perceived discomfort.
The EmpkinS-EKSpression Reappraisal Training Augmented With Kinesthesia in Depression: One-Armed Feasibility Study

Marie Keinert, Lena Schindler-Gmelch, Lydia Helene Rupp, and 5 more authors

JMIR Formative Research, Apr 2025

Abs DOI

Background Harboring dysfunctional depressogenic cognitions contributes to the development and maintenance of depression. A central goal of cognitive behavioral therapy (CBT) for depression is to invalidate such cognitions via cognitive reappraisal (CR). However, relatively low remission rates and high dropout rates in CBT demonstrate the need for further improvement. Potentially, the effects of CBT could be enhanced by addressing not only dysfunctional depressogenic cognitions but also body states associated with depression. This may be done, for example, by systematically pairing the invalidation of depressogenic cognitions with the performance of antidepressive kinesthesia. Objective This study aimed to examine the feasibility and clinical potential of a smartphone-based cognitive restructuring task that required users to deliberately perform antidepressive kinesthesia in conjunction with the rejection of depressogenic statements and the affirmation of antidepressive statements. This feasibility study was conducted as a precursor to a large-scale randomized controlled trial. Methods In total, 10 healthy participants engaged in a single 90-120-minute session of smartphone-based CR training. During the training, they completed 2 phases in which they were required to reject 20 depressogenic and affirm 20 antidepressive statements, respectively. Diagnostic assessments were conducted 1 week (T1) before and directly prior (T2) to the training, and again directly posttraining (T3) and at a 2-week follow-up posttraining (T4). Feasibility outcomes assessed at T3 included intervention safety recorded by study therapists, compliance, technical feasibility, usability assessed using the Short Version of the User Experience Questionnaire (UEQ-S), and acceptability assessed using the UEQ-S and self-developed items. Preliminary clinical potential was evaluated via single-item ratings of current depressed and positive mood assessed continuously during the training. Feasibility outcomes were analyzed descriptively, and clinical potential was examined using paired-sample t tests of pre and post ratings of mood at each training phase. Results Overall, the results indicated that the training was safe, feasible, and usable (UEQ-S pragmatic quality scale: mean 1.45, SD 0.71). However, acceptance was limited (UEQ-S hedonic quality scale: mean 1.05, SD 0.79). While 80% (8/10) of the participants were generally satisfied with the training, 80% (8/10) would recommend it to a friend, 90% (9/10) found it interesting, and 80% (8/10) rated it as “leading edge,” 40% (4/10) to 70% (7/10) did not consider it particularly helpful and 50% (5/10) found it repetitive. Preliminary results regarding clinical potential were promising, with significant increases in positive mood (rejection: Hedges g=0.63; affirmation: Hedges g=0.25), whereas changes in depressed mood were not significant. Conclusions This study evaluated the feasibility and acceptability of a smartphone-based CR training augmented with validating and invalidating kinesthesia. This provided valuable insights for further optimizing the intervention for the subsequent randomized controlled trial, but also potential similar interventions. If future studies confirm their clinical potential, such interventions offer a promising approach to enhancing CBT for depression. Trial Registration OSF Registries pw6ma; https://osf.io/pw6ma/
Incorporating Respiratory Signals for ML-based Multi-Modal Sleep Stage Classification: A Large-Scale Benchmark Study with Actigraphy and HRV

Daniel Krauss, Robert Richer, Arne Küderle, and 6 more authors

SLEEP, Apr 2025

Abs DOI Code

Abstract Insufficient sleep quality is directly linked to various diseases, making reliable sleep monitoring crucial for prevention, diagnosis, and treatment. As sleep laboratories are cost- and resource-prohibitive, wearable sensors offer a promising alternative for long-term unobtrusive sleep monitoring at home. Current unobtrusive sleep detection systems are mostly based on actigraphy (ACT) that tend to overestimate sleep due to a lack of movement in short periods of wakefulness. Previous research established sleep stage classification by combining ACT with cardiac information but has not investigated the incorporation of respiration in large-scale studies. For that reason, this work aims to systematically compare ACT-based sleep-stage classification with multimodal approaches combining ACT, heart rate variability (HRV) as well as respiration rate variability (RRV) using state-of-the-art machine- and deep learning algorithms. The evaluation is performed on a publicly available sleep dataset including more than 1,000 recordings. Respiratory information is introduced through ECG-derived respiration (EDR) features, which are evaluated against traditional respiration belt data. Results show that including RRV features improves the Matthews Correlation Coefficient (MCC), with long short-term memory (LSTM) algorithms performing best. For sleep staging based on AASM standards, the LSTM achieved a median MCC of 0.51 (0.16 IQR). Respiratory information enhanced classification performance, particularly in detecting Wake and Rapid eye movement (REM) sleep epochs. Our findings underscore the potential of including respiratory information in sleep analysis to improve sleep detection algorithms and, thus, help to transfer sleep laboratories into a home monitoring environment. The code used in this work can be found online at https://github.com/mad-lab-fau/sleep_analysis.
Systematic Investigation of Heart Sound Propagation Using Continuous Wave Radar

Marie Oesten, Luca Abel, Nils C. Albrecht, and 8 more authors

IEEE Journal of Biomedical and Health Informatics, 2025

DOI
Open Sync Board – An Open-Source Tool for Hardware Synchronization of Multimodal Physiological Sensor Setups

Mareike Pitzal, Annika Muecke, Johanna Bräunig, and 7 more authors

Journal of Open Hardware, 2025

DOI Code
Software

PEPbench – Open, Reproducible, and Systematic Benchmarking of Automated Pre-Ejection Period Extraction Algorithms

Robert Richer, Julia Jorkowitz, Sebastian Stühler, and 11 more authors

Psychophysiology, Nov 2025

Abs DOI Code

ABSTRACT The pre-ejection period (PEP) is a widely used cardiac parameter in psychophysiology that reflects the duration between the onset of ventricular depolarization and the opening of the aortic valve. PEP is often used as a marker of cardiac sympathetic nervous system (SNS) activity, particularly in within-subject comparisons under similar hemodynamic conditions. While many algorithms for automated PEP extraction from electrocardiography (ECG) and impedance cardiography (ICG) signals (more precisely, its first derivative, dZ / dt ) have been proposed in literature, they have not been systematically benchmarked. This lack of standardized algorithm comparisons originates from the absence of open-source algorithms and annotated datasets for evaluating PEP extraction algorithms. To address this issue, we introduce PEPbench , an open-source Python package with different Q-peak and B-point detection algorithms from literature that can be combined to create comprehensive PEP extraction pipelines, and a standardized framework for evaluating PEP extraction algorithms. We use PEPbench to systematically compare 108 different algorithm combinations. All combinations are evaluated on two datasets with manually annotated Q-peaks and B-points, which we make publicly available as the first datasets with reference PEP annotations. Our results show that the algorithms can differ vastly in their performance and that B-point detection algorithms introduce a considerable amount of error. Thus, we suggest that automated PEP extraction algorithms should be used with caution on a beat-to-beat level as their error rates are relatively high. This highlights the need for open and reproducible benchmarking frameworks for PEP extraction algorithms to improve the quality of research findings in the field of psychophysiology. With PEPbench , we aim to take a first step toward this goal and encourage other researchers to engage in the evaluation of PEP extraction algorithms by contributing algorithms, data, and annotations. We hope to establish a community-driven platform, fostering innovation and collaboration in the field of psychophysiology and beyond. , Impact Statement This study introduces PEPbench , the first open-source framework for systematically benchmarking pre-ejection period (PEP) extraction algorithms, addressing a critical gap in the field. By providing standardized datasets with annotated ECG and dZ / dt signals, and enabling the evaluation of different PEP extraction approaches, our PEPbench framework sets a foundation for reproducible, systematic comparisons in psychophysiological research. This work fosters transparency, innovation, and collaboration, advancing the accuracy and reliability of psychophysiological studies.
Multimodal Stress Assessment: Connecting Task-Related Changes in Self-Reported Stress, Salivary Biomarkers, Heart Rate, and Facial Expressions in the Context of the Stress Response to the Trier Social Stress Test

Veronika Ringgold, Felicitas Burkhardt, Luca Abel, and 6 more authors

Psychoneuroendocrinology, Jul 2025

DOI
Radiometric Measurement of the Effect of Nonpharmacological Interventions on Vital Signs of Patients with Palliative Care Using the Example of Music Therapy

Katharina Roth, Anke Malessa, Stefan Grießhammer, and 8 more authors

Journal of Palliative Medicine, Aug 2025

Abs DOI

Background: Nonpharmacological, psychosocial interventions such as music therapy (MT) are common in palliative care. However, measuring the effects of these interventions is challenging. Contactless and therefore burden-free vital sign monitoring may provide a feasible solution. Aim: The aim is to investigate the use of a radar system for measuring the effect of nonpharmacological interventions on heart and respiratory rate in patients with palliative care utilizing MT as an example. Design: Radar devices were installed under patients? mattresses of the palliative care ward to record heart and respiratory rate data. The pre-, peri-, and post-intervention heart rates were compared for 10-minute intervals, respectively. Heart rate changes were assessed for all interventions and two subgroups (receiving MT and MT with physiotherapy). Data from 77 patients were recorded as part of the GUARDIAN project performed at the palliative care unit of the University Hospital Erlangen-Nürnberg. Results: The heart rate of patients with palliative care was monitored continuously, prior to and following a complex intervention. Significant changes in heart rate were recorded depending on the intervention: A reduction of heart rate by ?3.342 bpm (?3.913%, \textpm 6.011 bpm, p = 0.0229) was found in the first 10 minutes after the MT intervention. The monitoring of the respiratory rate was only possible on an intermittent basis. Conclusions: Our study shows that radiometric heart rate monitoring is feasible during MT, highlighting the radar system?s potential for assessing complex interventions in palliative care. However, reliability issues in respiratory rate measurement call for further research.
Continuous-Wave Radar and Motion-Derived Biomarkers for Non-Contact Vital Status Classification in End-of-Life Care: A Clinically Validated Machine Learning Approach

\relax Julia. B. Yip, Stefan Griesshammer, Heike Leutheuser, and 6 more authors

IEEE Journal of Biomedical and Health Informatics, 2025

DOI

2024

EmRad: Ubiquitous Vital Sign Sensing Using Compact Continuous-Wave Radars

Nils C. Albrecht, Dominik Langer, Daniel Krauss, and 5 more authors

IEEE Open Journal of Engineering in Medicine and Biology, 2024

Abs DOI

In biomedical monitoring, non-intrusive and continuous tracking of vital signs is a crucial yet challenging objective. Although accurate, traditional methods, such as electrocardiography (ECG) and photoplethysmography (PPG), necessitate direct contact with the patient, posing limitations for longterm and unobtrusive monitoring. To address this challenge, we introduce the EmRad system, an innovative solution harnessing the capabilities of continuous-wave (CW) radar technology for the contactless detection of vital signs, including heart rate and respiratory rate. EmRad discerns itself by emphasizing miniaturization, performance, scalability, and its ability to generate large-scale datasets in various environments. This article explains the system’s design, focusing on signal processing strategies and motion artifact reduction to ensure precise vital sign extraction. The EmRad system’s versatility is showcased through various case studies, highlighting its potential to transform vital sign monitoring in research and clinical contexts.
Contactless Radar-Based Heart Rate Estimation in Palliative Care – a Feasibility Study and Possible Use in Symptom Management

Stefan G. Grießhammer, Anke Malessa, Hui Lu, and 12 more authors

BMC Palliative Care, Nov 2024

Abs DOI

Background Heart rate (HR) monitoring is a medical standard to provide information about a patient’s health status. In palliative care, relationship and social engagement are crucial therapeutic concepts. For fear of disrupting communication, social contact, and care, continuous HR monitoring is underutilised despite its potential to inform on symptom burden and therapeutic effects. This study investigates radar-based HR monitoring as an innovative and burden-free approach for palliative care patients, compares its accuracy with conventional ECG methods, and shows potential for therapeutic guidance. Methods A single-centre, comparative clinical trial was conducted with palliative care patients at the ward of the Department of Palliative Medicine of the University Hospital of Erlangen. The HR measurements obtained with radar were compared with Holter ECG (study arm I, overnight) and Task Force\textregistered Monitor (TFM)-based ECG validation recordings (study arm II, one hour). In addition, long-term radar measurements without validation were analysed in comparison with clinical health records (study arm III).
Facing Depression: Evaluating the Efficacy of the EmpkinS-EKSpression Reappraisal Training Augmented with Facial Expressions – Protocol of a Randomized Controlled Trial

Marie Keinert, Lena Schindler-Gmelch, Lydia Helene Rupp, and 8 more authors

BMC Psychiatry, Dec 2024

DOI
A Review and Tutorial on Machine Learning-Enabled Radar-Based Biomedical Monitoring

Daniel Krauss, Lukas Engel, Tabea Ott, and 12 more authors

IEEE Open Journal of Engineering in Medicine and Biology, 2024

Abs DOI

Radio detection and ranging-based (radar) sensing offers unique opportunities for biomedical monitoring and can help overcome the limitations of currently established solutions. Due to its contactless and unobtrusive measurement principle, it can facilitate the longitudinal recording of human physiology and can help to bridge the gap from laboratory to real-world assessments. However, radar sensors typically yield complex and multidimensional data that are hard to interpret without domain expertise. Machine learning (ML) algorithms can be trained to extract meaningful information from radar data for medical experts, enhancing not only diagnostic capabilities but also contributing to advancements in disease prevention and treatment. However, until now, the two aspects of radar-based data acquisition and MLbased data processing have mostly been addressed individually and not as part of a holistic and end-to-end data analysis pipeline. For this reason, we present a tutorial on radar-based ML applications for biomedical monitoring that equally emphasizes both dimensions. We highlight the fundamentals of radar and ML theory, data acquisition and representation and outline categories of clinical relevance. Since the contactless and unobtrusive nature of radar-based sensing also raises novel ethical concerns regarding biomedical monitoring, we additionally present a discussion that carefully addresses the ethical aspects of this novel technology, particularly regarding data privacy, ownership, and potential biases in ML algorithms.
Gaitmap—An Open Ecosystem for IMU-Based Human Gait Analysis and Algorithm Benchmarking

Arne Küderle, Martin Ullrich, Nils Roth, and 11 more authors

IEEE Open Journal of Engineering in Medicine and Biology, 2024

Abs DOI Code

Goal: Gait analysis using inertial measurement units (IMUs) has emerged as a promising method for monitoring movement disorders. However, the lack of public data and easy-to-use open-source algorithms hinders method comparison and clinical application development. To address these challenges, this publication introduces the gaitmap ecosystem, a comprehensive set of open source Python packages for gait analysis using foot-worn IMUs. Methods: This initial release includes over 20 state-of-the-art algorithms, enables easy access to seven datasets, and provides eight benchmark challenges with reference implementations. Together with its extensive documentation and tooling, it enables rapid development and validation of new algorithm and provides a foundation for novel clinical applications. Conclusion: The published software projects represent a pioneering effort to establish an open-source ecosystem for IMU-based gait analysis. We believe that this work can democratize the access to high-quality algorithm and serve as a driver for open and reproducible research in the field of human gait analysis and beyond.
Machine Learning-Based Detection of Acute Psychosocial Stress from Body Posture and Movements

Robert Richer, Veronika Koch, Luca Abel, and 8 more authors

Scientific Reports, Apr 2024

Abs DOI Code

Abstract Investigating acute stress responses is crucial to understanding the underlying mechanisms of stress. Current stress assessment methods include self-reports that can be biased and biomarkers that are often based on complex laboratory procedures. A promising additional modality for stress assessment might be the observation of body movements, which are affected by negative emotions and threatening situations. In this paper, we investigated the relationship between acute psychosocial stress induction and body posture and movements. We collected motion data from N = 59 individuals over two studies ( Pilot Study : N = 20, Main Study : N = 39) using inertial measurement unit (IMU)-based motion capture suits. In both studies, individuals underwent the Trier Social Stress Test (TSST) and a stress-free control condition (friendly-TSST; f-TSST) in randomized order. Our results show that acute stress induction leads to a reproducible freezing behavior, characterized by less overall motion as well as more and longer periods of no movement. Based on these data, we trained machine learning pipelines to detect acute stress solely from movement information, achieving an accuracy of \\\textbraceleft 75.0 \pm 17.7\textbraceright\textbraceleft\%\textbraceright\ 75.0 \textpm 17.7 % ( Pilot Study ) and \\\textbraceleft 73.4 \pm 7.7\textbraceright\textbraceleft\%\textbraceright\ 73.4 \textpm 7.7 % ( Main Study ). This, for the first time, suggests that body posture and movements can be used to detect whether individuals are exposed to acute psychosocial stress. While more studies are needed to further validate our approach, we are convinced that motion information can be a valuable extension to the existing biomarkers and can help to obtain a more holistic picture of the human stress response. Our work is the first to systematically explore the use of full-body body posture and movement to gain novel insights into the human stress response and its effects on the body and mind.
The Short Stress State Questionnaire in German (SSSQ-G): A Multi-Study Validation

Veronika Ringgold, Grant S. Shields, Felicitas Hauck, and 6 more authors

European Journal of Health Psychology, Oct 2024

Abs DOI

Abstract: Background: Although the physiological stress response is well established, self-reported stress has received less attention. Some validated measures assess task-related stress via self-report in English. However, no such measure exists in Germany. Aims: To address this research gap, we translated and validated the Short Stress State Questionnaire in German (SSSQ-G). It assesses stress-related affective states (e.g., anger) and appraisals (e.g., feelings of control). We expected to replicate the factor structure of the English SSSQ in the SSSQ-G. Methods: We included the SSSQ-G in five studies that induced stress either via the gold standard task for acute stress induction – the Trier Social Stress Test (TSST) – or via a novel virtual reality (VR) task. The sample consisted of 213 participants (112 women; age: 23.36 \textpm 3.62 years). Results: The SSSQ-G demonstrated sensitivity to stress-induced changes ( ps < .01), particularly in response to the TSST compared to the VR stress induction ( p < .001 for total scale comparison between stressors). In TSST participants, the magnitudes of stress-induced changes on the SSSQ-G were larger than those on the Positive and Negative Affect Schedule (PANAS), p = .008, indicating strong construct validity. Although the SSSQ-G total score was highly reliable (α = .85, \textohm = .86), factor analyses revealed a six-factor solution, with the factors representing Distress, Worry, Confidence, Negative affect, Motivation, and Self-evaluation. Limitations: The SSSQ-G appears more sensitive to state changes induced by moderate-to-severe stress tasks. Conclusion: The SSSQ-G is a reliable and valid instrument for assessing states of subjective stress.
Harnessing Multimodal Approaches for Depression Detection Using Large Language Models and Facial Expressions

Misha Sadeghi, Robert Richer, Bernhard Egger, and 5 more authors

npj Mental Health Research, Dec 2024

Abs DOI

Abstract Detecting depression is a critical component of mental health diagnosis, and accurate assessment is essential for effective treatment. This study introduces a novel, fully automated approach to predicting depression severity using the E-DAIC dataset. We employ Large Language Models (LLMs) to extract depression-related indicators from interview transcripts, utilizing the Patient Health Questionnaire-8 (PHQ-8) score to train the prediction model. Additionally, facial data extracted from video frames is integrated with textual data to create a multimodal model for depression severity prediction. We evaluate three approaches: text-based features, facial features, and a combination of both. Our findings show the best results are achieved by enhancing text data with speech quality assessment, with a mean absolute error of 2.85 and root mean square error of 4.02. This study underscores the potential of automated depression detection, showing text-only models as robust and effective while paving the way for multimodal analysis.

2023

Software

Tpcp: Tiny Pipelines for Complex Problems - A Set of Framework Independent Helpers for Algorithms Development and Evaluation

Arne Küderle, Robert Richer, Raul C. Sîmpetru, and 1 more author

Journal of Open Source Software, 2023

DOI Code
Software

CARWatch – A Smartphone Application for Improving the Accuracy of Cortisol Awakening Response Sampling

Robert Richer, Luca Abel, Arne Küderle, and 2 more authors

Psychoneuroendocrinology, May 2023

Abs DOI Code

Background: Many studies investigating the cortisol awakening response (CAR) suffer from low adherence to the study protocol as well as from the lack of precise and objective methods for assessing the awakening and saliva sampling times which leads to measurement bias on CAR quantification. Methods: To address this issue, we have developed “CARWatch”, a smartphone application that aims to enable low-cost and objective assessment of saliva sampling times as well as to concurrently increase protocol adher\-ence. As proof-of-concept study, we assessed the CAR of N = 117 healthy participants (24.2 \textpm 8.7 years, 79.5% female) on two consecutive days. During the study, we recorded awakening times (AW) using self-reports, the CARWatch application, and a wrist-worn sensor, and saliva sampling times (ST) using self-reports and the CARWatch application. Using combinations of different AW and ST modalities, we derived different reporting strategies and compared the reported time information to a Naive sampling strategy assuming an ideal sampling schedule. Additionally, we compared the AUCI, computed using information from different reporting strategies, against each other to demonstrate the effect of inaccurate sampling on the CAR. Results: The use of CARWatch led to a more consistent sampling behavior and reduced sampling delay compared to self-reported saliva sampling times. Additionally, we observed that inaccurate saliva sampling times, as resulting from self-reports, were associated with an underestimation of CAR measures. Our findings also revealed potential error sources for inaccuracies in self-reported sampling times and showed that CARWatch can help in better identifying, and possibly excluding, sampling outliers that would remain undiscovered by self-reported sampling. Conclusion: The results from our proof-of-concept study demonstrated that CARWatch can be used to objectively record saliva sampling times. Further, it suggests its potential of increasing protocol adherence and sampling accuracy in CAR studies and might help to reduce inconsistencies in CAR literature resulting from inaccurate saliva sampling. For that reason, we published CARWatch and all necessary tools under an open-source license, making it freely accessible to every researcher.
Radar-Based Recognition of Activities of Daily Living in the Palliative Care Context Using Deep Learning

Johanna Braeunig, Desar Mejdani, Daniel Krauss, and 8 more authors

In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Oct 2023

Abs DOI

The accurate detection and quantification of activities of daily life are crucial for assessing the health status of palliative patients to allow an optimized treatment in the last phase of life. Current evaluation methods heavily rely on subjective self-reports or external observations by clinical staff, lacking objectivity. To address this limitation, we propose a radar-based approach for recognizing ADLs in a palliative care context. In our proof of concept study, we recorded five different activities of daily living relevant to palliative care, all occurring within a hospital bed, from N=14 healthy participants (57 % women, aged 28.6 \textpm 5.3 years). All movements were recorded using two frequency-modulated continuous wave radar systems measuring velocity, range, and angle. A convolutional neural network combined with long short-term memory achieved a classification accuracy of 99.8 \textpm 0.4 % across five cross-validation folds. Furthermore, we compare our initial approach, which takes into account all dimensions of the available radar data, to a simplified version, where only velocity information over time is fed into the network. While these results demonstrate the high potential of radar-based sensing to automatically detect and quantify activities in a palliative care context, future work is still necessary to assess the applicability to real-world hospital scenarios.
VoStress – Voice-based Detection of Acute Psychosocial Stress

Marie Oesten, Robert Richer, Luca Abel, and 2 more authors

In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Oct 2023

Abs DOI

Current stress assessment methods include self- reports and biomarkers which are evaluated in often complex, laboratory procedures. Due to that investigating new indicators for acute stress is crucial for the development of automatic stress detection systems. A promising extension might be provided by investigating speech, which has been shown to be affected by negative emotions and threatening situations. For that reason, we extracted verbal acoustics from audio data collected during a study where N=21 participants underwent the Trier Social Stress Test (TSST), the gold standard for laboratory stress in- duction, and a stress-free control condition (friendly-TSST) while concurrently collecting cortisol via saliva samples to assess the biological response to stress. Our results show that acute stress leads to significant (p \textexclamdown 0.05) alterations of acoustic features. A stepwise backward multiple linear regression model explained 58.8 % of the variance of the maximum cortisol increase. In addition to that, we performed classification experiments that distinguished stress from non-stress situations with an accuracy of 80.0 \textpm 12.7 %. While further research is needed to validate our approach, we are convinced that the information extracted from speech can be a valuable indicator for automatic stress detection systems and can even predict the biological response to stress situations.
Exploring the Capabilities of a Language Model-Only Approach for Depression Detection in Text Data

Misha Sadeghi, Bernhard Egger, Reza Agahi, and 6 more authors

In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Oct 2023

Abs DOI

Depression is a prevalent and debilitating mental health condition that requires accurate and efficient detection for timely and effective treatment. In this study, we utilized the E-DAIC (Extended Distress Analysis Interview Corpus-Wizard-of-Oz) dataset, an extended version of the DAIC-WOZ dataset, which consists of semi-clinical interviews conducted by an animated virtual interviewer called Ellie, controlled by a human interviewer in another room. With 275 participants, the E-DAIC dataset represents a valuable resource for investigating depression detection methods. Our aim is to predict PHQ-8 scores through text analysis. Leveraging state-of-the-art speech processing, LLM-based text summarization, and a specialized depression detection module, we demonstrate the transformative potential of language data analysis in enhancing depression screening. By overcoming the limitations of manual feature extraction methods, our automated techniques provide a more efficient and effective means of evaluating depression. In our evaluation, we achieve robust accuracy on the development set of the E-DAIC dataset, with a Mean Absolute Error (MAE) of 3.65 in estimating PHQ-8 scores from recorded interviews. This remarkable performance highlights the efficacy of our approach in automatically predicting depression severity. Our research contributes to the growing evidence supporting the use of LLMs in mental health assessment, showcasing the role of innovative technologies in advancing patient care for depression.
Award

Prediction of Stress Coping Capabilities from Nightly Heart Rate Patterns Using Machine Learning

Linda Vorberg, Siri Pflueger, Robert Richer, and 4 more authors

In 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Oct 2023

Abs DOI

Stress is related to short- and long-term alterations in stress systems, including the hypothalamic-pituitary-adrenal (HPA) axis and the sympathetic nervous system (SNS). While it is well established that stress experienced during the day can affect sleep quality, less is known about how it affects stress systems during the night. We assume that stress coping strategies can have an impact on how stress carries over into the night and that individuals with bad coping mechanisms show elevated activation of stress systems during sleep. For that reason, we recorded the heart rate (HR) and heart rate variability (HRV) of 21 healthy participants on two consecutive nights during sleep and the first hour after awakening, Additionally, we extracted cortisol and alpha-amylase from saliva samples collected in the first hour after awakening and assessed stress coping capabilities using self-reports. To analyze the relationship between HR(V) parameters and stress coping we performed backward stepwise regression models and trained different machine learning-based regression algorithms to predict positive (SVF_Pos) and negative (SVF_Neg) stress coping capabilities, respectively. Our results show that individuals with higher SVF_Neg scores showed higher SNS activity during the night, whereas higher SVF_Pos scores indicated lower SNS activity. SVF_Pos was predicted with a mean absolute error (MAE) of 1.51\textpm 0.73 and SVF_Neg with an MAE of 2.79\textpm 1.53. Our findings indicate an association between nightly HR(V) and the individual’s capability of coping with stress. This provides further information about how stress influences sleep and might be used for tailored intervention and feedback on successful stress coping.

2022

Software

Imucal - A Python Library to Calibrate 6 DOF IMUs

Arne Küderle, Nils Roth, Robert Richer, and 1 more author

Journal of Open Source Software, May 2022

Abs DOI Code

Inertial measurement units (IMUs) have wide application areas from human movement analysis to commercial drone navigation. However, to use modern micro-electromechanical systems (MEMS)-based IMUs a calibration is required to transform the raw output of the sensor into physically meaningful units. To obtain such calibrations one needs to perform sets of predefined motions with the sensor unit and then apply a calibration algorithm to obtain the required transformation and correction factors for this unit. The imucal library implements the calibration algorithm described by Ferraris et al. (F. Ferraris et al., 1994; Franco Ferraris et al., 1995) and provides functionality to calculate calibration parameters and apply them to new measurements. As typically multiple calibrations are recorded per sensor over time, imucal further provides a set of opinionated tools to save, organize, and retrieve recorded calibrations. This helps to make sure that always the best possible calibration is applied for each recording even when dealing with multiple sensors and dozens of measurements.
Vagus Activation by Cold Face Test Reduces Acute Psychosocial Stress Responses

Robert Richer, Janis Zenkner, Arne Küderle, and 2 more authors

Scientific Reports, Nov 2022

Abs DOI Code

Abstract Chronic stress is linked to dysregulations of the two major stress pathways—the sympathetic nervous system and the hypothalamic-pituitary-adrenal (HPA) axis, which could for example result from maladaptive responses to repeated acute stress. Improving recovery from acute stress could therefore help to prevent this dysregulation. One possibility of physiologically interfering with an acute stress reaction might be provided by applying a cold stimulus to the face (Cold Face Test, CFT) which activates the parasympathetic nervous system (PNS), leading to immediate heart rate decreases. Therefore, we investigated the use of the CFT protocol as an intervention to reduce acute stress responses. Twenty-eight healthy participants were exposed to acute psychosocial stress via the Montreal Imaging Stress Task (MIST) in a randomized between-subjects design while heart rate (HR), heart rate variability (HRV), and salivary cortisol were assessed. While both groups were equally stressed during the procedure, participants with CFT intervention showed better recovery, indicated by significant ( \\p<0.05\ p < 0.05 ) differences in HR(V). We additionally found a significantly ( \\p<0.05\ p < 0.05 ) lower cortisol response to the MIST and less overall cortisol secretion in the CFT condition. Both findings indicate that the CFT can successfully stimulate the PNS and inhibit the HPA axis. To the best of our knowledge, our experiment is the first to successfully use the CFT as a simple and easy-to-apply method to modify biological responses to acute stress.
Influence of Sensor Position and Body Movements on Radar-Based Heart Rate Monitoring

Liv Herzer, Annika Muecke, Robert Richer, and 7 more authors

In 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), Sep 2022

Abs DOI

Cardiac parameters are important indicators for health assessment. Radar-based monitoring with microwave interferometric sensors (MIS) is a promising alternative to conventional measurement methods, as it enables completely contactless cardiac function diagnostics. In this study, we evaluated the effects of sensor positioning and movement on the accuracy of radar-based heart rate measurements with MIS. For this purpose, we recruited 29 participants which performed semistandardized movements, a reading task, and a standardized laboratory stress test in a seated position. Furthermore, we compared three different sensor positions (dorsal, upper pectoral, and lower pectoral) to a gold standard 1-channel wearable ECG sensor node. The dorsal positioning achieved the best results with a mean error (ME) of 0.2\textpm 5.4 bpm and a mean absolute error (MAE) of 3.5\textpm 4.1 bpm for no movement and also turned out to be most robust against motion artifacts with an overall ME of 0.1\textpm 14.1 bpm (MAE: 9.5\textpm 10.4 bpm). No correlation was found between movement intensity and measurement error. Instead, movement type and direction were identified as primary impact factors. This study provides a valuable contribution towards the applicability of radar-based vital sign monitoring with MIS in real-world scenarios. However, further research is needed to sufficiently prevent and compensate for movement artifacts.
Machine Learning-based Detection of In-Utero Fetal Presentation from Non-Invasive Fetal ECG

Katharina M. Jaeger, Michael Nissen, Robert Richer, and 5 more authors

In 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), Sep 2022

Abs DOI

Preterm births account for more than 10 % of all newborns. An adverse fetal presentation is a risk factor for intrapartum and neonatal mortality. To date, no technology enables a longitudinal, ubiquitous, and unobtrusive monitoring of fetal presentation. This study presents a first approach to fetal orientation detection based on non-invasive fetal electrocardiography (NI-fECG) using the non-invasive multimodal foetal ECG-Doppler data set for antenatal cardiology research. The data set contains 60 recordings from 39 pregnant women (21–27 weeks), including NI-fECG and ultrasound position ground truth. We evaluated both handcrafted and generic features for five different classifiers (k-Nearest-Neighbor, Decision Tree Classifier, Support Vector Classification, AdaBoost Classifier, and Multilayer Perceptron) using cross-validation on subject splits on a cleaned subset. Best results for the distinction between vertex (head down) and breech (head up) were achieved using an AdaBoost classifier with a balanced accuracy of 86.5 \textpm 15.0 %. With this work, we take a first step towards longitudinal fetal presentation monitoring, which contributes to a better understanding of reduced fetal movements and extends the potential applications of NI-fECG in prenatal care. In future work, we will expand our classification system to detect more detailed fetal presentations using a newly created data set.
The Stroop Competition: A Social-Evaluative Stroop Test for Acute Stress Induction

Victoria Mueller, Robert Richer, Lea Henrich, and 5 more authors

In 2022 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), Sep 2022

DOI

2021

Software

BioPsyKit: A Python Package for the Analysis of Biopsychological Data

Robert Richer, Arne Küderle, Martin Ullrich, and 2 more authors

Journal of Open Source Software, Oct 2021

Abs DOI Code

Biopsychology is a field of psychology that analyzes how biological processes interact with behaviour, emotion, cognition, and other mental processes. Biopsychology covers, among others, the topics of sensation and perception, emotion regulation, movement (and control of such), sleep and biological rhythms, as well as acute and chronic stress.
Real-Time Work Environment Optimization Using Multimodal Media and Body Sensor Network

Nan Zhao, Susanne Seitinger, Robert Richer, and 1 more author

Smart Health, Mar 2021

Abs DOI

The ambient environment has a significant influence on our cognition and behavior. We envision an adaptive space that improves our productivity and wellbeing at work and related settings by forming a closed control loop around our responses to the environment’s properties. To explore this vision, we created a responsive office named Mediated Atmospheres (MA) that can transform its ambiance as driven by a network of physiological sensors. We conducted a user study investigating near-natural use of the system with a panel of non-experts and experts in the field of the built environment (N = 9). Two control modes were implemented: (1) Learning Mode, where the system learns from the user’s response and (2) Preset Mode, where the office responds to the user’s physiological state based on predefined rules. Our result showed that using the Learning Mode, participants were able to increase the amount of time in which they were focused when the system optimized for both focus and stress restoration rather than focus alone. Participants were able to double the time in which they achieved high-stress restoration when their environment optimized for restoration rather than focus. Both application modes achieved high System Usability Scores (SUS > 82), which is evidence that our method for compressing the multivariate control problem into a multidimensional model of the user’s physiological state is a viable approach for closed-loop control of a multimodal environment. We offer a discussion on the preferred level of control for an office application.
Evaluation of Orthostatic Reactions in Real-World Environments Using Wearable Sensors

Johanna Happold, Robert Richer, Arne Küderle, and 4 more authors

In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Nov 2021

DOI
Assessing the Influence of the Inner Clock on the Cortisol Awakening Response and Pre-Awakening Movement

Robert Richer, Arne Küderle, Jana Dörr, and 2 more authors

In 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Jul 2021

Abs DOI

Our inner clock is responsible for creating a circadian rhythm that controls our sleep-wake cycle, and, hence, is also involved in the process of awakening from sleep. Awakening is accompanied by the cortisol awakening response (CAR). The purpose of the CAR is, presumably, to prepare our body for the upcoming challenges of the day. It is assumed that our inner clock is anticipating awakening, and thus, initiates the awakening process while we are still asleep, leading to the common phenomenon of waking up immediately before a known alarm. However, the role of the inner clock on the awakening process was only assessed in sleep laboratories and using invasive, blood-based biomarkers. For that reason, we investigated n = 117 participants by collecting cortisol data from saliva samples and IMU data from a wrist-worn inertial measurement unit (IMU) sensor node in a home environment over two nights. We compared cortisol data, characterizing the CAR, and IMU features, characterizing pre-awakening movement, between spontaneous awakening, awakening by a known alarm, and by an unknown alarm. We observed significant differences between the three study conditions in both cortisol and IMU data indicating higher cortisol reactivity and less movement if participants woke up by an unknown alarm. Our findings all support the assumption that our inner clock is anticipating our wake-up time. Utilizing our results, this work lays the foundation for the development of automatic classification models aimed at determining the ideal awakening time of individuals based on the analysis of preawakening movement.

2020

The Footprint of Orthostatic Hypotension in Parkinsonian Syndromes

Cecilia Raccagni, Victoria Sidoroff, Georg Goebel, and 8 more authors

Parkinsonism & Related Disorders, Jul 2020

DOI
Exploring Smart Agents for the Interaction with Multimodal Mediated Environments

Robert Richer, Nan Zhao, Bjoern M. Eskofier, and 1 more author

Multimodal Technologies and Interaction, Jun 2020

Abs DOI

After conversational agents have been made available to the broader public, we speculate that applying them as a mediator for adaptive environments reduces control complexity and increases user experience by providing a more natural interaction. We implemented and tested four agents, each of them differing in their system intelligence and input modality, as personal assistants for Mediated Atmospheres, an adaptive smart office prototype. They were evaluated in a user study ( N = 33 ) to collect subjective and objective measures. Results showed that a smartphone application was the most favorable system, followed by conversational text and voice agents that were perceived as being more engaging and intelligent than a non-conversational voice agent. Significant differences were observed between native and non-native speakers in both subjective and objective measures. Our findings reveal the potential of conversational agents for the interaction with adaptive environments to reduce work and information overload.

2019

Classification of Acute Stress-Induced Response Patterns

Luca Abel, Robert Richer, Arne Küderle, and 3 more authors

In Proc of the 13th EAI Int Conf Pervasive Comput Technol for Healthc - PervasiveHealth’19, 2019

Abs DOI

Modern machine learning techniques enable new possibilities for the analysis of psychological data. In the field of health psychology, it is of interest to explore the biological processes triggered by acute stress. This work introduces a method to automatically classify individuals into distinct stress responder groups based on these biological processes. Two important stress-sensitive markers were used: Salivary cortisol and Interleukin-6 (IL-6) in blood plasma. Controlled stress was induced using the Trier Social Stress Test on two consecutive days. Results show that Support Vector Machines performed best on the given dataset. We distinguished four different cortisol and three different IL-6 responder types with high mean accuracies (92.2% \textpm 9.7% and 91.2% \textpm 6.3%, respectively). Classification results were mainly limited by class imbalances and high intra-class standard deviations. Whereas promising as a first application of machine learning on such datasets, generalizability and real-world applicability of our results need to be proven by further research.
Deep Reality: Towards Increasing Relaxation in VR by Subtly Changing Light, Sound and Movement Based on HR, EDA, and EEG

Judith Amores, Anna Fuste, and Robert Richer

In Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems, 2019

Abs DOI

We present an interactive Virtual Reality (VR) experience that uses biometric information for reflection and relaxation. We monitor in real-time brain activity using a modified version of the Muse EEG and track heart rate (HR) and electro dermal activity (EDA) using an Empatica E4 wristband. We use this data to procedurally generate 3D creatures and change the lighting of the environment to reflect the internal state of the viewer in a set of visuals depicting an underwater audiovisual composition. These 3D creatures are created to unconsciously influence the body signals of the observer via subtle
Deep Reality: An Underwater VR Experience to Promote Relaxation by Unconscious HR, EDA and Brain Activity Biofeedback

Judith Amores, Anna Fuste, Robert Richer, and 1 more author

In 46th International Conference & Exhibition on Computer Graphics & Interactive Techniques (SIGGRAPH ’19), 2019

Abs DOI

Deep Reality is an interactive Virtual Reality (VR) experience that aims to decrease heart and respiration rate by subtle, almost imperceptible light flickering, sound pulsations and slow movements of 3D underwater creatures. Our goal is to improve relaxation by unconsciously influencing the body signals of the user by passively displaying audio-visual cues that are synchronized with a slower frequency of the user’s heart and breathing rate, as well as lighting changes of the environment that reflect its brain wave activity associated to relaxation. We monitor in real-time brain activity using the Muse flexible EEG headband and electrodermal activity (EDA) using an Empatica E4 wristband and dynamically adapt the virtual experience.
An Overview of the Feasibility of Permanent, Real-Time, Unobtrusive Stress Measurement with Current Wearables

Stefan Gradl, Markus Wirth, Robert Richer, and 2 more authors

In 13th EAI International Conference on Pervasive Computing Technologies for Healthcare - PervasiveHealth’19, 2019

Abs DOI

Negative consequences of stress are a pervasive problem in our modern society. Recent developments in wearable lifestyle hardware have led to unobtrusive, sensor-packed, always-on devices that might finally be able to continuously monitor biosignals to detect, determine or even prevent stress or some of its negative outcomes. In this work, we give a concise overview of a majority of biosignals that are in some way relevant for stress classification and outline state-of-the-art machine learning algorithms for this task. Additionally, we provide a list of all recent wearables including an evaluation of their feasibility to implement such algorithms as well as directions to look for an assessment of the accuracy and validity of their recorded data with respect to stress tracking.

2018

Award

Promoting Relaxation Using Virtual Reality, Olfactory Interfaces and Wearable EEG

Judith Amores, Robert Richer, Nan Zhao, and 2 more authors

In 2018 IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN 2018), 2018

Abs DOI

The ability to relax is sometimes challenging to achieve, nevertheless it is extremely important for mental and physical health, particularly to effectively manage stress and anxiety. We propose a virtual reality experience that integrates a wearable, low-cost EEG headband and an olfactory necklace that passively promotes relaxation. The physiological response was measured from the EEG signal. Relaxation scores were computed from EEG frequency bands associated with a relaxed mental state using an entropy-based signal processing approach. The subjective perception of relaxation was determined using a questionnaire. A user study involving 12 subjects showed that the subjective perception of relaxation increased by 26.1 % when using a VR headset with the olfactory necklace, compared to not being exposed to any stimulus. Similarly, the physiological response also increased by 25.0 %. The presented work is the first Virtual Reality Therapy system that uses scent in a wearable manner and proves its effectiveness to increase relaxation in everyday life situations.
Real-Time Mental State Recognition Using a Wearable EEG

Robert Richer, Nan Zhao, Judith Amores, and 2 more authors

In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2018

Abs DOI

The increasing quality and availability of low-cost EEG systems offer new possibilities for non-medical purposes. Existing openly available algorithms to assess the user’s mental state in real-time have been mainly performed with medical-grade equipment. In this paper, an approach to assess the user’s Focus or Relax states in real-time using a consumer-grade, wearable EEG headband is evaluated. One naive measure and four entropy-based measures, computed using relative frequency band powers in the EEG signal, were introduced. Classifiers for relax and focus state detection, based on the estimation of probability distributions, were developed and evaluated in a user study. Results showed that the Tsallis entropy-based measure performed best for the Focus score, whereas the Renyi measure performed best for the Relax score. Sensitivities of 82.0% and 80.4% with specificities of 82.8% and 80.8% were achieved for the Focus and Relax scores, respectively. The results demonstrated the possibilities of using a wearable EEG system for real-time mental state recognition.
Exploring the Feasibility of EMG Based Interaction for Assessing Cognitive Capacity in Virtual Reality

Markus Wirth, Stefan Gradl, Dino Poimann, and 3 more authors

In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2018), 2018

Abs DOI

With the growth and aging of the world population, the prevalence of cognitive diseases and disabilities like dementia and mild cognitive impairments increases. To determine the influence of such diseases, find therapeutic effects and further improve quality of life, cognitive assessment and training is required. This can be done with the application of high immersive technologies like virtual reality.In this paper we evaluate the feasibility of an electromyography (EMG) arm muscle-motion based interaction technique for controlling a VR cognitive performance diagnostic and training environment. Therefore, we compared the state-of-theart controller input to our EMG based approach in terms of presence and user experience.Results show significant differences in terms of Novelty and Dependability. Since there are only few significant differences regarding presence and user experience, the advantage of applying a more demanding physical motion interaction approach (EMG), seems to be a promising method with the potential of having a positive effect on the cognitive training progress. This is mainly caused by the fact that the implemented gesture interaction reinforces the connection between decision making and action execution.

2017

Wearable Current-Based ECG Monitoring System with Non-Insulated Electrodes for Underwater Application

Stefan Gradl, Tobias Cibis, Jasmine Lauber, and 7 more authors

Applied Sciences, 2017

Abs DOI

The second most common cause of diving fatalities is cardiovascular diseases. Monitoring the cardiovascular system in actual underwater conditions is necessary to gain insights into cardiac activity during immersion and to trigger preventive measures. We developed a wearable, current-based electrocardiogram (ECG) device in the eco-system of the FitnessSHIRT platform. It can be used for normal/dry ECG measuring purposes but is specifically designed to allow underwater signal acquisition without having to use insulated electrodes. Our design is based on a transimpedance amplifier circuit including active current feedback. We integrated additional cascaded filter components to counter noise characteristics specific to the immersed condition of such a system. The results of the evaluation show that our design is able to deliver high-quality ECG signals underwater with no interferences or loss of signal quality. To further evaluate the applicability of the system, we performed an applied study with it using 12 healthy subjects to examine whether differences in the heart rate variability exist between sitting and supine positions of the human body immersed in water and outside of it. We saw significant differences, for example, in the RMSSD and SDSD between sitting outside the water (36 ms) and sitting immersed in water (76 ms) and the pNN50 outside the water (6.4%) and immersed in water (18.2%). The power spectral density for the sitting positions in the TP and HF increased significantly during water immersion while the LF/HF decreased significantly. No significant changes were found for the supine position. \copyright 2017 by the authors.

2016

Unobtrusive Real-time Heart Rate Variability Analysis for the Detection of Orthostatic Dysregulation

Robert Richer, Benjamin H. Groh, Peter Blank, and 4 more authors

In IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN 2016), 2016

Abs DOI

The possibilities for wearable health care technology to improve the quality of life for chronic disease patients has been increasing within recent years. For instance, unobtrusive cardiac monitoring can be applied to people suffering from a disorder of the autonomic nervous system (ANS) which show a significantly lower heart rate variability (HRV) than healthy people. Although recent work presented solutions to analyze this relationship, they did not perform it during daily life situations. For that reason, this work presents a system for a real-time analysis of the user’s HRV on an Android-based mobile device throughout the day. The system was used for the detection of an orthostatic dysregulation which can be an indicator for a disorder of the ANS. Measures for HRV analysis were computed from acquired ECG data and compared before and after a posture change. For triggering the HRV analysis, an IMU-based algorithm which detects stand up events was developed. As a proof of concept for an automatic assessment of an orthostatic dysregulation, a classification based on the derived HRV measures was performed. The performance of the stand up detection was evaluated in the first part of this study. The second part was conducted for the evaluation of the derived HRV measures and involved healthy subjects as well as patients with idiopathic Parkinson’s Disease. The results of the evaluation showed a recognition rate of 90.0 % for the stand up detection algorithm. Furthermore, a clear difference in the change of HRV measures between the two groups before and after standing up was observed. The classification provided an accuracy of 96.0%, and a sensitivity of 93.3%. The results demonstrated the possibility of unobtrusive HRV monitoring during daily life situations. \copyright 2016 IEEE.

2015

Unobtrusive Heart Rate Estimation during Physical Exercise Using Photoplethysmographic and Acceleration Data

Patrick Mullan, Christoph M. Kanzler, Benedikt Lorch, and 9 more authors

In 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2015), 2015

Abs DOI

Photoplethysmography (PPG) is a non-invasive, inexpensive and unobtrusive method to achieve heart rate monitoring during physical exercises. Motion artifacts during exercise challenge the heart rate estimation from wrist-type PPG signals. This paper presents a methodology to overcome these limitation by incorporating acceleration information. The proposed algorithm consisted of four stages: (1) A wavelet based denoising, (2) an acceleration based denoising, (3) a frequency based approach to estimate the heart rate followed by (4) a postprocessing step. Experiments with different movement types such as running and rehabilitation exercises were used for algorithm design and development. Evaluation of our heart rate estimation showed that a mean absolute error 1.96 bpm (beats per minute) with standard deviation of 2.86 bpm and a correlation of 0.98 was achieved with our method. These findings suggest that the proposed methodology is robust to motion artifacts and is therefore applicable for heart rate monitoring during sports and rehabilitation.
Novel Human Computer Interaction Principles for Cardiac Feedback Using Google Glass and Android Wear

Robert Richer, Tim Maiwald, Cristian F. Pasluosta, and 2 more authors

In IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN 2015), 2015

Abs DOI

This work presents a system for unobtrusive cardiac feedback in daily life. It addresses the whole pipeline from data acquisition over data processing to data visualization including wearable integration. ECG signals are recorded with a novel ECG sensor supporting Bluetooth Low Energy, which is able to transmit raw ECG data as well as estimated heart rate. ECG signals are processed in real-time on a mobile device to automatically classify the user’s heart beats. A novel application for Android-based mobile devices was developed for data visualization. It offers several modes for cardiac feedback, from measuring the current heart rate to continuously monitoring the user’s heart status. It also allows to store acquired data in an internal database as well as in the Google Fit platform. Further, the application provides extensions for wearables like Google Glass and smartwatches running on Android Wear. Hardware performance evaluation was performed by comparing the course of heart rate between the novel ECG sensor and a commercial ECG sensor. The mean absolute error between the two sensors was 4.83 bpm with a standard deviation of 4.46 bpm, and a Pearson correlation of 0.922. A qualitative evaluation was performed for the Android application with special emphasis on the daily usability and the wearable integration. When the Google Glass was integrated, the subjects rated the application as 2.8/5 (0 = Bad, 5 = Excellent), whereas when the application was integrated with a smartwatch the rating increased to 4.2/5.

2014

Real-Time ECG and EMG Analysis for Biking Using Android-based Mobile Devices

Robert Richer, Peter Blank, Dominik Schuldhaus, and 1 more author

In IEEE 11th International Conference on Wearable and Implantable Body Sensor Networks (BSN 2014), 2014

Abs DOI

We developed an application for Android-based mobile devices that enables a real-time calculation of heart rate and cadence for biking. Therefore, both ECG and EMG data are acquired in real time by Shimmer sensors and transmitted via Bluetooth, as well as processed and evaluated on the mobile device. The ECG algorithm is based on the Pan-Tompkins algorithm for QRS-Detection and offers a heart beat detection rate of more than 94%. The EMG algorithm offers a treadle detection rate of more than 91%. The application’s range of features is complemented by GPS data for the calculation of speed and location information. It is available for download and can for example be used for controlling the user’s training status, for live training supervision and for the subsequent analysis of the various training runs.