Rüdiger Pryss’s research while affiliated with University Hospital Würzburg and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (315)


Voice Assessment and Vocal Biomarkers in Heart Failure: A Systematic Review
  • Literature Review

April 2025

·

8 Reads

Circulation Heart Failure

Maximilian Bauser

·

Fabian Kraus

·

·

[...]

·

Despite major advances in recent years, the timely detection and prevention of incipient congestion in patients with chronic heart failure remains challenging. Most approaches are either invasive or require the acquisition of additional hardware. Leveraging voice analysis for the purposes of diagnosing, predicting risks, and telemonitoring clinical outcomes of patients with heart failure represents a promising, cost-effective, and convenient alternative compared with hitherto deployed methods. To expand this field, close collaboration of several disciplines of medicine and computer science is an obligatory requirement. The current review aims to lay out the state-of-the-art in this quickly advancing area of research. It elucidates the foundation for voice feature extraction, describes the prospective capabilities of this evolving technology, and outlines the challenges involved in identifying vocal biomarkers both in general and in the context of heart failure.




Fig. 1 | Screenshots of the Android CoronaCheck app illustrating its key functionalities. This figure presents screenshots of the Android CoronaCheck app illustrating its key functionalities across the user journey: a the cover screen, where users can initiate a COVID-19 self-assessment; b the screening process interface,
Fig. 2 | Screenshots of the iOS CoronaCheck app illustrating its key functionalities. This figure shows screenshots of the iOS CoronaCheck app illustrating its key functionalities across the user journey: a the cover screen, where users can initiate a COVID-19 self-assessment; b the screening process interface, where users report
Fig. 3 | Response times by platform. This figure visualizes the temporal distribution of assessments from Android (blue) and iOS (red) users between April 2020 and February 2023. The figure shows that the majority of assessments were recorded within the first 12 months of the app's availability.
Sociodemographic characteristics of Android versus iOS users of the CoronaCheck self-help app
Self-reported potential COVID-19 symptoms of Android versus iOS users of the CoronaCheck self-help app
A comparison of self-reported COVID-19 symptoms between android and iOS CoronaCheck app users
  • Article
  • Full-text available

April 2025

·

10 Reads

npj Digital Medicine

This study explored differences in COVID-19 infections and symptoms between Android and iOS users using data from the CoronaCheck app. This cross-sectional analysis included 23,063 global users (20,753 Android and 2310 iOS) from April 2020 to February 2023. Participants reported COVID-19 symptoms and contact risks, with data analyzed to adjust for age, sex, education, and country. Android users were generally younger, more often male, had a lower educational level, and reported more symptoms on average (2.1 vs. 1.6) than iOS users. Android users also had higher suspected COVID-19 infection rates (24% vs. 11%), with an adjusted odds ratio of 2.21 (95% CI: 1.93–2.54). These findings suggest platform-based differences in COVID-19 infection rates and symptom reporting, highlighting potential biases in mobile health research. Adjusting for device operating systems may be crucial in improving the reliability of population-based health data collected through mobile platforms.

Download

Physical Health and Ecological Momentary Assessments During COVID-19: Data from the ’Corona Health’ App Users

April 2025

·

10 Reads

Data in Brief

The dataset published in this work is derived from the ‘Corona Health’ app, developed in collaboration with the German Robert Koch Institute (RKI) during the early stages of the COVID-19 pandemic. The smartphone application aimed to monitor the mental and physical health of the public through real-time data collection. The dataset incorporates Ecological Momentary Assessments (EMA), Patient-reported Outcome Measures (PROMs), GPS data, and digital phenotyping from app users who consented. The data includes responses from 1805 mostly German users who completed baseline and follow-up questionnaires, capturing their physical health status over time. These questionnaires cover health-related topics, including medical history, cardiovascular risk factors, lifestyle habits, and the impact of the pandemic on health behaviors. The resulting dataset offers insights into health trajectories and behaviors during the pandemic and can be utilized for further research on physical health, user engagement, and the efficacy of EMA and digital phenotyping in health monitoring. The data is publicly available under a Creative Commons license on zenodo.org/records/11093394.



Personalisierte Schmerztherapie durch digitale Interventionen: Eine Just-In-Time Adaptive Intervention zur Unterstützung von Menschen mit chronischen Rückenschmerzen

March 2025

·

12 Reads

Hintergrund Chronische Rückenschmerzen betreffen rund ein Drittel der deutschen Bevölkerung und stellen eine erhebliche Herausforderung im Gesundheitswesen dar. Die Förderung von Selbstwirksamkeit und Autonomie der Patient*innen spielt eine zentrale Rolle in der erfolgreichen Schmerztherapie. Dazu können digitale Interventionen eingesetzt werden. Bisherige digitale Interventionen zum Einsatz bei Rückenschmerzen sind jedoch häufig nicht an die aktuellen Beschwerden und die aktuelle Situation von Patient*innen angepasst. Ziele Ziel der Studie war die Entwicklung der BackUp-App, die durch individualisierte selbstmanagementbasierte Mikrointerventionen die Autonomie der Patient*innen stärkt und zur Reduktion von Schmerzintensität und Schmerzkatastrophisierung beitragen soll. Methoden Die BackUp-App folgt einem Just-in-Time Adaptive Intervention (JITAI)-Ansatz, um bedarfsorientierte Interventionen zu bieten. Mehrfach tägliche Ecological Momentary Assessments (EMA) erfassen Schmerzempfinden und Schmerzkatastrophisierung im Alltag der Patien*tinnen und ermöglichen so bedarfsgerechte Anpassungen. Die Inhalte der App umfassen Interventionen aus Physiotherapie, Entspannung und Achtsamkeit, entwickelt auf Basis einer 2023 durchgeführten Meta-Analyse zur Wirksamkeit digitaler Selbstmanagement-Interventionen. Strukturierte Interviews mit 15 Expert*innen und 15 Patient*innen lieferten Einblicke in bevorzugte Mikrointerventionen und Designpräferenzen. Schließlich wurde die BackUp-App auf Grundlage der eSano Plattform für digitale Interventionen programmiert. Ergebnisse Die Interviews ergaben wertvolle Hinweise zur Individualisierung der App und offenbarten Präferenzunterschiede zwischen Expert*innen und Patienti*nnen . Insgesamt konnten 14 Mikrointerventionen ausgewählt werden und Design-Kriterien wie die Schwelle der Schmerzkatastrophisierung, die zur Auslösung einer Mikrointerventionen notwendig ist, festgelegt werden. Zur individualisierten Umsetzung der JITAI-Prinzipien wurden die Funktionen der eSano-Plattform um zufällige Auswahlmöglichkeiten von Mikrointerventionen erweitert. Diskussion Die nächste Projektphase umfasst eine randomisierte kontrollierte Studie (RCT), die den Einfluss der BackUp-App auf Schmerzkatastrophisierung und Schmerzintensität evaluieren soll. Diese Ergebnisse sollen wertvolle Einblicke in den Nutzen adaptiver digitaler Interventionen in der Schmerztherapie liefern und zur Optimierung zukünftiger Therapieansätze beitragen.


Fig. 3 | Data preparation. The steps used for data preparation and the resulting number of users included in the analysis per step.
Fig. 4 | Distribution of samples. The number of EMA-D samples contributed (a) per year and month and (b) per country. Data were collected between April 2014 and June 2024.
Parameter estimates of the three identified groups of growth trajectories with respect to the relationship between environmental sound level and tinnitus loudness in the final growth model
Global 10 year ecological momentary assessment and mobile sensing study on tinnitus and environmental sounds

March 2025

·

16 Reads

npj Digital Medicine

In most tinnitus patients, tinnitus can be masked by external sounds. However, evidence for the efficacy of sound-based treatments is scarce. To elucidate the effect of sounds on tinnitus under real-world conditions, we collected data through the TrackYourTinnitus mobile platform over a ten-year period using Ecological Momentary Assessment and Mobile Crowdsensing. Using this dataset, we analyzed 67,442 samples from 572 users. Depending on the effect of environmental sounds on tinnitus, we identified three groups (T-, T+, T0) using Growth Mixture Modeling (GMM). Moreover, we compared these groups with respect to demographic, clinical, and user characteristics. We found that external sound reduces tinnitus (T-) in about 20% of users, increases tinnitus (T+) in about 5%, and leaves tinnitus unaffected (T0) in about 75%. The three groups differed significantly with respect to age and hearing problems, suggesting that the effect of sound on tinnitus is a relevant criterion for clinical subtyping.


Level 1 general anamnestic patient data
Development and application of a clinical core data set for deep brain stimulation in Parkinson's disease, dystonia or tremor: from data collection to data exchange and data sharing

January 2025

·

44 Reads

·

1 Citation

Neurological Research and Practice

Background Comprehensive clinical data regarding factors influencing the individual disease course of patients with movement disorders treated with deep brain stimulation might help to better understand disease progression and to develop individualized treatment approaches. Methods The clinical core data set was developed by a multidisciplinary working group within the German transregional collaborative research network ReTune. The development followed standardized methodology comprising review of available evidence, a consensus process and performance of the first phase of the study. To ensure high data quality, measures for standardized training, monitoring as well as plausibility and data quality tests were implemented. Results The clinical core data set comprises information about medical history, clinical symptoms, information about deep brain stimulation surgery, complications and outcome for the main neurological movement disorders Parkinson’s disease, tremor, and dystonia. Its applicability as well as data exchange and quality control was tested within the first phase of the study in 51 patients from Würzburg. Conclusions Within the ReTune project, a standardised clinical core data set for Parkinson’s disease, dystonia and tremor was developed. The collection as well as concepts for the implementation of monitoring and data exchange were elaborated and successfully tested. Trial registration number ClinicalTrials.gov (DRKS-ID: DRKS00031878).


Automated reading of handheld echocardiograms is feasible and shows strong agreement with high-resolution echocardiography - Results from the PAVE project

January 2025

·

15 Reads

European Heart Journal Cardiovascular Imaging

Background We recently showed that population data-based machine-learning can improve the automated echocardiographic quantification of cardiac structure and function. The respective gain in accuracy and precision strengthens the confidence into automated echocardiographic readings and carries potential for applications in various settings. Purpose We applied the automated detector to high-resolution standard echocardiograms and to echocardiograms acquired with a handheld device. Methods and Results PAVE (Pathology-oriented reading of echocardiography) is a cooperation project between University Hospital Wuerzburg (UKW) and Tomtec Imaging Systems using an established federated machine-learning environment. We recruited 2043 patients (mean age 64±16, 44% women) presenting at the UKW for transthoracic echocardiography (TTE). After high-resolution standard TTE (Vivid E95, GE) trained sonographers acquired images with a handheld ultrasound device (Lumify 2.0, Philips) according to a pre-specified protocol. Images of both modalities were loaded into the analysis platform of the Academic CoreLab Ultrasound-based Cardiovascular Imaging (TomtecArena®, Tomtec, Germany). For the current analysis, we selected n=51 random patients (mean age 65±16, 39% women) from the PAVE cohort. Reading of high-resolution and handheld TTE, respectively, was performed by a trained sonographer (>14 days apart and blinded to the reading results) as well as by the automated detector. We here present first results regarding 2D (parasternal long axis) measurements of interventricular septum (IVS), left ventricular diameter (LVD) and posterior wall thickness (PW) at end-diastole from manual CoreLab reading (CL) and automated detector reading (AD) of high-resolution TTE (11.3±4.1mm, 10.9±2.5mm; 48.3±8.1mm, 49.5±7.4mm; PW 9.3±3.2mm, 10.0±1.7mm) as well as of the respective handheld echocardiograms (IVS 10.7±3.4mm, 11.0±2.2mm; LVD 47.7±7.4mm, 48.3±6.6mm; PW 9.7±2.7mm, 10.2±1.6mm). The agreement between measurements performed in high-resolution and handheld TTE was assessed using Bland-Altman analysis (Table 1; Figure 1). Conclusions The application of an automated detector to handheld TTE was feasible and led to measurement values in the same range but with higher agreement of measurements when compared to human reading. Our results await extension to further echocardiographic parameters and confirmation in larger cohorts but suggest that automated echocardiographic reading might become a valuable tool in patient care. Accurate automated reading of handheld TTE might extend applicability of echocardiography to non-expert settings.


Citations (39)


... Parkinson's Disease (PD) is a progressive neurodegenerative disorder characterized by the degeneration of dopaminergic neurons, leading to hallmark motor symptoms such as bradykinesia, rigidity, resting tremor, and postural instability [1][2][3][4][5][6][7][8]. In addition to motor impairments, PD is associated with non-motor symptoms, including cognitive decline, mood disturbances, and autonomic dysfunction, which significantly impact patients' quality of life and contribute to increased disability [9][10][11][12]. ...

Reference:

Dancing Towards Stability: The Therapeutic Potential of Argentine Tango for Balance and Mobility in Parkinson’s Disease
Development and application of a clinical core data set for deep brain stimulation in Parkinson's disease, dystonia or tremor: from data collection to data exchange and data sharing

Neurological Research and Practice

... Additionally, Kaizen has demonstrated its applicability across various sectors and industries [152]; • Data Quality Improvement: Developing standardized methods for cleaning and structuring healthcare data is crucial to ensure compatibility with PM tools and maximize the accuracy of insights. A perspective article explored how PM can extract clinical insights from mobile health data and complement data-driven techniques like machine learning, emphasizing the importance of data quality in such analyses [153]; • Human-Centric Adaptations: Examining strategies to further integrate frontline staff input and enhance their engagement in data-driven improvement processes, ensuring that the framework remains both actionable and practical [149]. ...

Process mining in mHealth data analysis

npj Digital Medicine

... A comprehensive analysis conducted in European countries of self-reported COVID-19 symptoms from 2021 observed a higher prevalence of symptoms such as loss of smell and taste among younger individuals, consistent with our findings of age-related differences in symptom reporting 24 . Juxtaposed to our findings, analyses on the TrackYourTinnitus app from 2018 and 2023 with 1517 and 2693 users, respectively, observed that Android users tended to be older on average 6,7 . This study did not include children, and therefore, the findings are not generalizable to this age group. ...

Follow-Up Evaluation to Explore Disparities Between Android and iOS Users Utilizing the TrackYourTinnitus Mobile Health Platform
  • Citing Conference Paper
  • December 2023

... In this manner, cognitive load, as one of the most prominent HCI elements, will be mitigated, and the user can focus on clinical decision-making rather than system navigation or data troubleshooting [39]. The functionality of the data transformation pipeline consists of several stages [40][41][42], as shown in Figure 3. These stages are described as the following:  Process: Scales data into consistent ranges (e.g., blood pressure in mmHg) or formats (e.g., dates in "YYYY-MM-DD"); ...

Exploring Concepts for Pipeline-Driven Mobile Health Data Dashboards: Insights from Personal Projects and GitHub Contributions
  • Citing Conference Paper
  • December 2023

... By leveraging 5-fold cross-validation, each data point in the training set is used once for validation and four times for training. This strategy results in a more reliable and generalizable meta-classifier, particularly beneficial for small or imbalanced datasets, as described by (Allgaier & Pryss, 2024). ...

Cross-Validation Visualized: A Narrative Guide to Advanced Methods

Machine Learning and Knowledge Extraction

... The use of persuasive techniques in mobile applications has the potential to influence user behavior (Idrees et al., 2024;Matthews et al., 2016). The Fogg Behavioral Model (FBM) is a theoretical framework developed by B.J. Fogg for the purpose of assessing the process of persuasive techniques. ...

Persuasive technologies design for mental and behavioral health platforms: A scoping literature review

... Present study was conducted independently, without financial support or contributions by industrial partners, to prevent any potential conflicts of interest. This manuscript represents one of the secondary endpoints of the "Monitor project" (NCT05418881) and therefore by design comprises the same patient cohort investigated in our complementary manuscript [11]. ...

Reliability of continuous vital sign monitoring in post-operative patients employing consumer-grade fitness trackers: A randomised pilot trial

... Predictive phenotyping. Predictive phenotyping aims to forecast future health events or risks of diseases ( Fig. 1d) 30,33,34 . For instance, by monitoring physical activity and heart rate data over time, it is possible to predict an individual's risk of developing cardiovascular diseases 33,34 . ...

The predictive value of supervised machine learning models for insomnia symptoms through smartphone usage behavior

Sleep Medicine X

... Moreover, the lack of rigorous machine learning techniques (e.g., proper cross-validation) or their incorrect implementation may have led to optimism bias in the previously reported 98.00% accuracy [7]. This bias can lead to an overestimation of the actual effectiveness of a method [13]. Although FC has shown potential as a biomarker for distinguishing between SZ and BD, its reported prediction accuracy of 63.92% is relatively low [8], suggesting that further research is required to improve its performance and establish its potential as a reliable biomarker. ...

Practical approaches in evaluating validation and biases of machine learning applied to mobile health studies

Communications Medicine

... Furthermore, Wrzus et al. [45] emphasized the need to employ sensors in the understanding of the interplay between participant behavior, EMA responsiveness, and response quality. Stach et al. [46] observe that mobile notification responsiveness is influenced not only by the app delivering the notification but also by user demographics. In our analysis, we will leverage continuously collected sensor data to examine the relationship between EMA responses (as patientreported outcome measures), digital markers extracted from sensor data (digital phenotyping), and demographics across multiple studies. ...

Call to Action: Investigating Interaction Delay in Smartphone Notifications