Medical Informatics Research Group

Description

The dashboard project aims to display multimodal and heterogeneous data from different studies on one website. Target variables are pre-aggregated by various dimensions. This allows domain experts to follow the data progress of their studies on a daily basis and to display graphics of interest and save them locally as pdf or jpg if required. We hope to simplify and accelerate the knowledge generation from the studies and make it possible for non-programmers to analyze the data more deeply, more quickly and more easily.

Team

• Johannes Allgaier
• Carsten Vogel
• Jens Scheible
• Fabian Hofmann (prev. Ulm University)
• Prof. Rüdiger Pryss

Description

Countless complex biological and cognitive processes take place in the brain of a human being. In addition, the human brain is flooded with information originating from the perceived environment. Whether consciously or unconsciously, these internal processes ultimately lead to human decision-making behavior and determine our subsequent actions. Despite the importance of this behavior, our knowledge of human decision making and the corresponding perception is still in its infancy. In the field of process modeling, the application of cognitive neuroscience and psychology offers promising perspectives. With a view to understanding process models, we have developed a conceptual framework that incorporates methods and theories from these two disciplines as cornerstones. The goal of CONSCIOUS is to promote the comprehensibility of process models, with particular emphasis on (1) improving existing statistical and empirical evaluations in this context, (2) identifying rules to promote understanding of process models, (3) categorizing (e.g., complexity level or construct-related similarities) process models based on experimental data, and (4) providing guidelines for building more readable process models.

Team

• Michael Winter
• Prof. Manfred Reichert (Ulm University)
• Prof. Rüdiger Pryss

Description

CAYPVAR aimed to clarify widespread misconceptions about COVID-19, convey relevant information in an age-appropriate manner, and use appropriate channels by employing serious games were used to achieve learning objectives. The target population was asylum seekers in community shelters between the ages of 16 and 26 who owned a smartphone.

Team

• Fabian Haug
• Julian Haug
• Prof. Rüdiger Pryss

Team

• Robin Kraft
• Prof. Manfred Reichert (Ulm University)
• Prof. Harald Baumeister (Ulm University)
• Prof. Rüdiger Pryss

Description

In this research, we aim to explore different methods of designing more engaging eHealth platforms. We focus on persuasive design, gamification and behavior change theories. We work in an interdisciplinary field at the crossroads between computer science and psychology. We aspire to understand the driving forces behind user interactions with eHealth applications. From there, we try to find ways to emphasize the positive elements that influence the user experience constructively. Furthermore, we seek out methods to minimize any features that may disturb the user or impact their experience negatively. Our end goal is to improve the overall user experience and help the user to attain the benefits that their eHealth modules are intended to confer.

Team

• Abdul Rahman Idrees
• Robin Kraft
• Prof. Manfred Reichert (Ulm University)
• Prof. Harald Baumeister (Ulm University)
• Prof. Rüdiger Pryss

Description

With the MHAD project, we want to support both patients and practitioners in making informed and quality-assured health decisions. Most people in Germany already use m-Health apps on their smartphones. Very often, however, the quality of content and data security are difficult to assess, so that risks, misinformation and negative developments cannot be ruled out when using these m-Health apps. MHAD can remedy this situation by having m-health apps assessed by at least two specially trained experts using a validated diagnostic instrument (MARS or MARS-G).

Team

• Michael Stach
• Prof. Harald Baumeister (Ulm University)
• Prof. Manfred Reichert (Ulm University)
• Prof. Rüdiger Pryss

Description

Within the framework of the BETTER-CARE study, a multidisciplinary care network and supporting digital applications are to be developed in order to establish and assess aftercare adapted to individual needs. Currently, Germany lacks concepts for the implementation of individualized aftercare treatment for breast cancer, which is why, depending on the risk of recurrence or metastasis, there may be a possible overuse or underuse of affected patients in the current aftercare system.
The project is led by Prof. Dr. Achim Wöckel of the University Hospital Würzburg and Prof. Dr. Peter Heuschmann of the University of Würzburg.

Team

• Anna Horn (Julius-Maximilians-University of Würzburg)
• Carsten Vogel
• Prof. Rüdiger Pryss
• Prof. Peter Heuschmann (University Hospital Würzburg)
• Prof. Achim Wöckel (Julius-Maximilians-University of Würzburg)

Description

As part of the interdisciplinary project „Problemverhalten verstehen und vorbeugen bei intellektueller Entwicklungsstörung und Autismusspektrumstörungen“ (ProVIA), an app is being developed to provide support to caregivers in everyday life. It helps to identify the multifactorial causes of problem behavior and provides recommendations for action to prevent and deal with problem behavior. In addition to providing relief in everyday life, the goal is also to reduce the need for custodial measures. The app is being developed in collaboration between the KJPPP, the Chair of Special Education IV and the Chair of Medical Informatics at the University of Würzburg.

Team

• Klaus Kammerer
• Lena Mulansky
• Carsten Vogel
• Prof. Rüdiger Pryss

Description

Within the framework of the BETTER-CARE study, a multidisciplinary care network and supporting digital applications are to be developed in order to establish and assess aftercare adapted to individual needs. Currently, Germany lacks concepts for the implementation of individualized aftercare treatment for breast cancer, which is why, depending on the risk of recurrence or metastasis, there may be a possible overuse or underuse of affected patients in the current aftercare system.
The project is led by Prof. Dr. Achim Wöckel of the University Hospital Würzburg and Prof. Dr. Peter Heuschmann of the University of Würzburg.

The resulting Mobile App Framework was presented at the IEEE 36th International Symposium on Computer Based Medical Systems (CBMS) 2023 conference.

Team

• Carsten Vogel
• Eileen Bendig (Ulm University)
• Patricia Garatva (Ulm University)
• Lena Stenzel (formerly Ulm University)
• Abdul Rahman Idrees
• Robin Kraft
• Prof. Harald Baumeister (Ulm University)
• Prof. Rüdiger Pryss

Description

In this project, we want to provide a brief overview of the taxonomy of explainability methods and review popular methods in medicine. Therefore, we conducted a systematic literature search on PubMed to investigate which explainable artificial intelligence (XAI) methods are used in 450 specific medical supervised ML use cases, how the use of XAI methods has emerged recently, and how the precision of describing ML pipelines has evolved over the past 20 years.

Team

• Johannes Allgaier
• Lena Mulansky
• Rachel Draelos (Duke University)
• Prof. Rüdiger Pryss

Team

• Pia Beyer-Wunsch
• Prof. Dr. Manfred Reichert (Ulm University)
• Prof. Rüdiger Pryss

Description

In this project, a methodology regarding the creation and reading of modularized process models and their model perspectives will be created. The methodology will be based on results from neuroscience and cognitive psychology.

Team

• Julia Baß
• Michael Winter
• Manfred Reichert (Ulm University)
• Prof. Rüdiger Pryss

Description

"UNITI's overall aim is to deliver a predictive computational model based on existing and longitudinal data attempting to address the question which tinnitus treatment approach is optimal for a specific patient based on specific parameters. Clinical, epidemiological, medical, genetic and audiological data, including signals reflecting ear-brain communication, will be analysed from existing databases. Predictive factors for different patient groups will be extracted and their prognostic relevance will be tested in a randomized controlled trial (RCT) in which different groups of patients wil undergo a combination of therapies targeting the auditory and central nervous systems." [Source: https://uniti.tinnitusresearch.net, accessed 2023-05-23]

The UNITI Mobile apps for Android and iOS offer their users three Tinnitus related modules: (1) A Tinnitus Diary, which contains questions about the momentary and daily Tinnitus burden. (2) TinEdu, a psychological education intervention, encompassing twelve chapters with seven sections of Tinnitus knowledge each as well as a quiz per chapter to test the progress. (3) The ShadesOfNoise module, contains sounds for auditory stimulation. For the RCT study the users were assigned one or more modules of the app as well as other forms of therapy (outside the mobile platforms).

Team

• Carsten Vogel
• Prof. Johannes Schobel (University of Applied Sciences, Neu-Ulm)
• Prof. Winfried Schlee (University of Regensburg & Eastern Switzerland University of Applied Sciences, St. Gallen)
• Milena Engelke (University of Regensburg)
• Fabian Haug
• Julian Haug
• Prof. Rüdiger Pryss

Description

"Through lockdowns and other severe changes to daily life, almost everyone is affected by the COVID-19 pandemic. Scientists and medical doctors are - among others - mainly interested in researching, monitoring, and improving physical and mental health of the general population. Mobile health apps (mHealth), and apps conducting ecological momentary assessments (EMA) respectively, can help in this context. However, developing such mobile applications poses many challenges like costly software development efforts, strict privacy rules, compliance with ethical guidelines, local laws, and regulations. In this paper, we present TrackYourHealth (TYH), a highly configurable, generic, and modular mobile data collection and EMA platform, which enabled us to develop and release two mobile multiplatform applications related to COVID-19 in just a few weeks. We present TYH and highlight specific challenges researchers and developers of similar apps may also face, especially when developing apps related to the medical field." [Source: C. Vogel, R. Pryss, J. Schobel, W. Schlee and F. Beierle, "Developing Apps for Researching the COVID-19 Pandemic with the TrackYourHealth Platform," 2021 IEEE/ACM 8th International Conference on Mobile Software Engineering and Systems (MobileSoft), Madrid, Spain, 2021, pp. 65-68, doi: 10.1109/MobileSoft52590.2021.00015.]

Description

"The aim of this study was to investigate the impact of different coping styles on situational coping in everyday life situations and gender differences. An ecological momentary assessment study with the mobile health app TrackYourStress was conducted with 113 participants. The coping styles Positive Thinking, Active Stress Coping, Social Support, Support in Faith, and Alcohol and Cigarette Consumption of the Stress and Coping Inventory were measured at baseline. Situational coping was assessed by the question “How well can you cope with your momentary stress level” over 4 weeks. Multilevel models were conducted to test the effects of the coping styles on situational coping. Additionally, gender differences were evaluated." [Source: O'Rourke T, Vogel C, John D, Pryss R, Schobel J, Haug F, Haug J, Pieh C, Nater UM, Feneberg AC, Reichert M, Probst T. The Impact of Coping Styles and Gender on Situational Coping: An Ecological Momentary Assessment Study With the mHealth Application TrackYourStress. Front Psychol. 2022 Jun 20;13:913125. doi: 10.3389/fpsyg.2022.913125. PMID: 35795429; PMCID: PMC9252427.]

Team

• Teresa O'Rourke (University for Continuing Education Krems)
• Carsten Vogel
• Dennis John (Lutheran University of Applied Sciences, Nuremberg)
• Prof. Rüdiger Pryss
• Prof. Johannes Schobel (University of Applied Sciences, Neu-Ulm)
• Fabian Haug
• Julian Haug
• Christoph Pieh (University for Continuing Education Krems)
• Urs M. Nater (University of Vienna)
• Anja C. Feneberg (University of Vienna)
• Manfred Reichert (Ulm University)
• Thomas Probst (University for Continuing Education Krems)

Description

More information about the setting can be found in the publication .

Team

• Laura Popp
• Prof. Dr. Manfred Reichert (Ulm University)
• Prof. Rüdiger Pryss

Description

The rise in health monitoring apps has yielded extensive individual health data across various well-being aspects. Statista reports global downloads of top fitness apps surged from 2.76 million monthly in January 2017 to over 20 million in January 2023, almost doubling during the COVID-19 pandemic. Integrating diverse health app data into a unified dashboard provides users a holistic view, enabling early trend detection and timely intervention. This aggregated data empowers healthcare professionals with tools for informed decision-making, personalized patient care and public health research. The thesis explores technological and design considerations in creating such dashboards.

The approach involves modular data collection via mHealth apps, Python-based aggregation and visualization through an interactive web application, offering a versatile health analysis tool. The data aggregation connects to a predefined server, storing data locally in CSV format, aggregating it and saving it in JSON files. The web app manages data for multiple projects, allowing users to navigate project-specific pages and load data from JSON files in to charts. Various chart types, including line, bar and geo charts, are rendered through a universal component. User interaction is enhanced with filtering and configuration options, including a download function for customized chart exporting. Manual addition of custom charts is possible for specific use-cases.

Student(s)

• Jonas Kindermann (Ulm University)

Supervisor(s)

• Carsten Vogel
• Prof. Rüdiger Pryss

Description

FHIR is a widely used standard defining resources for interoperable software. The Questionnaire-resource is used to model medical forms, research questionnaires and more, which lead to the COMPASS project developing an editor working with Questionnaire-resources. The editor is a web application allowing importing and exporting a JSON-file containing one Questionnaire-resource, after optionally editing its values.

This video summarizes the results of the Master's thesis "Conceptual design and implementation of a FHIR-agnostic questionnaire-editor for PROM-based mHealth Apps". It motivates and showcases a Questionnaire-resource editor based on the implementation provided by the COMPASS project. It extends the supported FHIR features, introduces multiple language versions for one questionnaire and splits all functionalities into regular and advanced segments, so end-users with limited FHIR knowledge can still create FHIR compliant questionnaires. The introduction to the editor starts at 02:41.

Further information

• Editor Repository: https://github.com/patricksteiger/compass-questionnaire-editor/tree/thesis
• COMPASS Project: https://github.com/NUMde/compass-questionnaire-editor
• FHIR Specification: https://www.hl7.org/fhir/R5/questionnaire.html

Student(s)

• Patrick Steiger (Ulm University)

Supervisor(s)

• Carsten Vogel
• Prof. Rüdiger Pryss

Description

...

Student(s)

• tba

Supervisor(s)

• Carsten Vogel

Description

"Over the last decade a continual increase of mobile health care services has been recorded. Analogous to this the interest of researches has raised as well. As the COVID-19 pandemic spread around the globe in 2020 the Institute of Databases and Information Systems at Ulm Univeristy in cooperiation with the Institute of Clinical Epidemiology and Biometry of the University of Würzburg where able to release several Corona-related mobile Health applications in a short period. This thesis investigates possibilities to accelerate the implementation phase even more. Therefore a prototype of a framework, called SmartSense, is provided. SmartSense is able to gather and provide Android sensor data in an efficient and convenient way. Current generation smartphones provide several embedded sensors and added value can be gathered by using software. This thesis provides an overview of the IEC 62304. An international standard for developing mobile health applications. Existing sensor data libraries are examined and the benefits of enriching ecological momentary assessments and interventions by sensor data are elaborated. The thesis provides a wholesome documentation of the software development process of SmartSense, containing the requirement engineering, detailed information about the architecture and implementation, unit and integration tests by providing a demo application and a requirement comparison." [Master's Thesis by Chris Gabler]

Student(s)

• Chris Gabler

Supervisor(s)

• Carsten Vogel

Description

[Master's Thesis by Ismail Memis]

Student(s)

• Ismail Memis

Supervisor(s)

• Carsten Vogel
• Prof. Rüdiger Pryss

Description

We develop an electronic screening tool for patients undergoing CAR-T-cell-therapy in cooperation with patients, nurses, therapists and software engineers. This "Neurotox-Tool" is a systematic and comprehensive electronic screening tool for neurological symptoms, which includes the questionnary, which is currently routinely used in stationary care and beyond that a detailed recording of further neuro-psychiatric symptoms, including concentration, attention, memory and cognitive processing. Innovative data analysis (machine learning) will be used to detect the risk of side effects more quickly. The identification and early recording of clinical findings that indicate an increased probability of occurrence of a neurotoxicity syndrome enables countermeasures to be implemented earlier and therefore more effectively. Involving patients in the development of new interventions and providing them with information adapted to their needs promotes their motivation to systematically document their findings and also has a positive influence on satisfaction with treatment and on health-related quality of life.

Team

• Anna Fleischer
• Luna Dressler
• Max Topp
• Johannes Düll
• Barbara Huber
• Lena Volk
• Rouven-Alexander Remmel
• Rüdiger Pryss
• Imad Maatouk

Description

Convolutional neural networks have emerged as a powerful means to quantify video material. We develop and deploy sophisticated frameworks to quantify the effects of disease and neuromodulation on movement abnormalities in the context of neurological disorders. The resulting digital biomarkers can facilitate and scale clinical research and provide an attractive translational platform to generate pathophysiological insights.

Frameworks are developed and validated against sophisticated gold standard equipment for several use cases such as eye, head and limb movement analysis. Next step will be prospective application in multicentric trials to generate novel, "deep digital phenotypes" of devastating neurological movement and balance disorders such as Parkinson's disease, ataxia and dystonia.

Team

• Maximilian U. Friedrich
• Robert Peach
• Chi Wang Ip
• Jens Volkmann
• Martin Reich