Hannah Greß, M. Sc.
Personalized Digital Health and Telemedicine
Affiliation:
Department for Epileptology
University Hospital Bonn
Medical Faculty
University of Bonn
Location:
Venusberg-Campus 1,
Building 74, Room 2G-015
53127 Bonn, Germany
Telephone: +49-228/287-51705
Email: hannah.gress@ukbonn.de
Short CV: Hannah Greß earned her Bachelor’s degree in Audiovisual Media (B.Eng.) in 2018 from the Stuttgart Media University and her Master’s degree in Computer Science (M.Sc.) in 2022 from Philipps University of Marburg. She began her Ph.D. studies at Cologne University of Applied Sciences in 2022 and since 2023, she has been continuing her Ph.D. in Computer Science at the University Hospital Bonn/University of Bonn.
Publications
2024
Müllers, Johannes; Greß, Hannah; Haaga, Lisa; Krüger, Björn
Sensorik am Krankenbett – Synchrone Datenakquise für Studien in der Epileptologie Conference
62. Jahrestagung der Deutschen Gesellschaft für Epileptologie, 2024.
@conference{muellers2024,
title = {Sensorik am Krankenbett – Synchrone Datenakquise für Studien in der Epileptologie},
author = {Johannes Müllers and Hannah Greß and Lisa Haaga and Björn Krüger},
year = {2024},
date = {2024-06-14},
urldate = {2024-06-14},
booktitle = {62. Jahrestagung der Deutschen Gesellschaft für Epileptologie},
abstract = {Die Möglichkeit der Anfallserkennung oder -vorhersage außerhalb des Krankenhauses kann die Lebensqualität und das Sicherheitsbedürfnis von Epilepsiepatienten erhöhen. Die Überwachung von Vitalparametern, Bewegungen und weiteren Messgrößen kann von einer Vielzahl von Wearables oder sonstigen neuartigen Sensorsystemen gewährleistet werden. Videoüberwachte EEG-Messplätze dienen als Goldstandard und werden für Studien mit solchen Sensoren genutzt, um Korrelationen festzustellen. Hierbei stellen technische Herausforderungen ein wiederkehrendes Problem dar. Neben der Inbetriebnahme der Sensorsysteme, die ohne informationstechnische Kenntnisse oft nur mit proprietären Mitteln möglich ist, ist insbesondere die Synchronizität zur EEG-Aufzeichnung anspruchsvoll. Aktuelle Vorbereitungen einer Studie mit Eye-Tracker Brillen bieten den Anlass, ein neues System zur Datenakquisition aufzubauen. },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Die Möglichkeit der Anfallserkennung oder -vorhersage außerhalb des Krankenhauses kann die Lebensqualität und das Sicherheitsbedürfnis von Epilepsiepatienten erhöhen. Die Überwachung von Vitalparametern, Bewegungen und weiteren Messgrößen kann von einer Vielzahl von Wearables oder sonstigen neuartigen Sensorsystemen gewährleistet werden. Videoüberwachte EEG-Messplätze dienen als Goldstandard und werden für Studien mit solchen Sensoren genutzt, um Korrelationen festzustellen. Hierbei stellen technische Herausforderungen ein wiederkehrendes Problem dar. Neben der Inbetriebnahme der Sensorsysteme, die ohne informationstechnische Kenntnisse oft nur mit proprietären Mitteln möglich ist, ist insbesondere die Synchronizität zur EEG-Aufzeichnung anspruchsvoll. Aktuelle Vorbereitungen einer Studie mit Eye-Tracker Brillen bieten den Anlass, ein neues System zur Datenakquisition aufzubauen.
Schulte-Rüther, Martin; Lemken, Johannes; Krüger, Björn; Greß, Hannah; Stroth, Sanna; Kamp-Becker, Inge; Poustka, Luise
Automated annotation and quantification of non-verbal behavior from eye tracking and accelerometer data during live social interaction Conference
Wissenschaftliche Tagung Autismus-Spektrum (WTAS), 2024.
@conference{schulteruether2024,
title = {Automated annotation and quantification of non-verbal behavior from eye tracking and accelerometer data during live social interaction},
author = {Martin Schulte-Rüther and Johannes Lemken and Björn Krüger and Hannah Greß and Sanna Stroth and Inge Kamp-Becker and Luise Poustka},
year = {2024},
date = {2024-03-21},
booktitle = {Wissenschaftliche Tagung Autismus-Spektrum (WTAS)},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
2023
Krüger, Björn; Weber, Christian; Greß, Hannah; Knaub, Jessica; Pukropski, Jan; Hütwohl, Daniela; Hahn, Kai; Grond, Martin; Jonas, Stephan; Surges, Rainer
Telekonsil zur Verbesserung der Epilepsiediagnostik Conference
Digitalisierung der Gesundheitsversorgung älterer Menschen, 2023.
@conference{krueger2023,
title = {Telekonsil zur Verbesserung der Epilepsiediagnostik},
author = {Björn Krüger and Christian Weber and Hannah Greß and Jessica Knaub and Jan Pukropski and Daniela Hütwohl and Kai Hahn and Martin Grond and Stephan Jonas and Rainer Surges},
year = {2023},
date = {2023-07-01},
booktitle = {Digitalisierung der Gesundheitsversorgung älterer Menschen},
abstract = {Erfolgreiche Diagnose von Epilepsien bedürfen einer engen Zusammenarbeit von Hausärzt:innen, Kinderärzt:innen und neurologischen und epileptologischen Fachärzt:innen sowie den entsprechenden Fachkliniken. Zusätzlich zu der Expertise der Ärzt:innen ist ein fortlaufender Austausch und die kontinuierliche Anreicherung von Fachwissen von Bedeutung. Neben der frühzeitigen Überweisung an Fachkliniken kann die gemeinsame Fall-begleitende und Klinikübergreifende Aufnahme, der Austausch und die Pflege von Falldokumentationen ein wichtiger Baustein für die langfristige und erfolgreiche Begleitung der Patient:innen sein. },
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Erfolgreiche Diagnose von Epilepsien bedürfen einer engen Zusammenarbeit von Hausärzt:innen, Kinderärzt:innen und neurologischen und epileptologischen Fachärzt:innen sowie den entsprechenden Fachkliniken. Zusätzlich zu der Expertise der Ärzt:innen ist ein fortlaufender Austausch und die kontinuierliche Anreicherung von Fachwissen von Bedeutung. Neben der frühzeitigen Überweisung an Fachkliniken kann die gemeinsame Fall-begleitende und Klinikübergreifende Aufnahme, der Austausch und die Pflege von Falldokumentationen ein wichtiger Baustein für die langfristige und erfolgreiche Begleitung der Patient:innen sein.
Schulte-Rüther, Martin; Krüger, Björn; Lemken, Johannes; Greß, Hannah; Stroth, Sanna; Kamp-Becker, Inge; Poustka, Luise
2023.
@conference{schulteruether2023,
title = {Automatic Delineation and Classification of Head Movements Using 3D Accelerometer Data from Live Social Interaction},
author = {Martin Schulte-Rüther and Björn Krüger and Johannes Lemken and Hannah Greß and Sanna Stroth and Inge Kamp-Becker and Luise Poustka},
url = {https://cdn.ymaws.com/www.autism-insar.org/resource/resmgr/docs/annualmeeting/insar_2023_full_abstract_boo.pdf, INSAR 2023 Abstract Book (p. 1246)},
year = {2023},
date = {2023-05-06},
urldate = {2023-05-06},
abstract = {Individuals with autism spectrum disorder (ASD) often show reduced non-verbal communication during social interactive encounters, e.g. facial expressions, deictic and communicative gestures, eye gaze. This includes reduced usage and expression of gestures of the head, such as nodding, shaking the head, and head turning. Diagnostic criteria of ASD suggest that reduced non-verbal communicative behavior is an important symptom, but current diagnostic tools are restricted to subjective, clinical evaluation.
While many tools for automatic delineation and classification of facial expressions and gestures from video data are available, less work has been done with respective to the usage of accelerometer sensor data. Considering the current lack of objective, quantitative measures of non-verbal behavior during social interaction, an automated analysis pipeline for movement annotation from accelerometer data would be helpful for both clinical evaluation and research.
},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Individuals with autism spectrum disorder (ASD) often show reduced non-verbal communication during social interactive encounters, e.g. facial expressions, deictic and communicative gestures, eye gaze. This includes reduced usage and expression of gestures of the head, such as nodding, shaking the head, and head turning. Diagnostic criteria of ASD suggest that reduced non-verbal communicative behavior is an important symptom, but current diagnostic tools are restricted to subjective, clinical evaluation.
While many tools for automatic delineation and classification of facial expressions and gestures from video data are available, less work has been done with respective to the usage of accelerometer sensor data. Considering the current lack of objective, quantitative measures of non-verbal behavior during social interaction, an automated analysis pipeline for movement annotation from accelerometer data would be helpful for both clinical evaluation and research.
While many tools for automatic delineation and classification of facial expressions and gestures from video data are available, less work has been done with respective to the usage of accelerometer sensor data. Considering the current lack of objective, quantitative measures of non-verbal behavior during social interaction, an automated analysis pipeline for movement annotation from accelerometer data would be helpful for both clinical evaluation and research.
Xu, Jing; Greß, Hannah; Seefried, Sabine; van Drongelen, Stefan; Schween, Raphael; Sommer, Claudia; Endres, Dominik; Krüger, Björn; Stief, Felix
Diagnosing Rare Diseases by Movement Primitive-Based Classification of Kinematic Gait Data Proceedings
Bernstein Conference, 2023.
@proceedings{JingXu2023,
title = {Diagnosing Rare Diseases by Movement Primitive-Based Classification of Kinematic Gait Data},
author = {Jing Xu and Hannah Greß and Sabine Seefried and Stefan van Drongelen and Raphael Schween and Claudia Sommer and Dominik Endres and Björn Krüger and Felix Stief},
url = {https://abstracts.g-node.org/conference/BC23/abstracts#/uuid/31c21041-91a0-46bd-87dc-46271501fdc0},
doi = {10.12751/nncn.bc2023.313},
year = {2023},
date = {2023-01-10},
urldate = {2023-01-10},
booktitle = { Bernstein Conference 2023},
abstract = {Of over 6.000 known rare diseases, a considerable portion involves motor symptoms [1]. Whereas aiding diagnosis by artificial intelligence based on non-motor symptoms has shown promise [2], the potential of using movement data to this purpose has not yet been fully investigated. We therefore aim to implement a machine learning algorithm inspired by biological motor control to aid diagnosis of rare diseases by classifying data from standard kinematic clinical gait analysis.
Starting from 42-degrees-of-freedom time series of joint angles extracted from motion capture data with custom routines [3], we employ a Gaussian process-based temporal movement primitive algorithm [4] in order to reduce the data to sets of movement primitives and weight vectors that capture the essential characteristics of the gait movement. The primitives are participant (and disease) -independent and represent general human gait. The weights are participant-specific and thus contain disease-specific information. A weighted combination of the primitives can thus generate participant specific gait data. We then apply standard classification tools such as Support Vector Machines and Random Forests to the weights to distinguish the disease from the control gait. The primary goal is to reliably differentiate patients from age-matched controls in an existing data set on patients with Legg–Calvé–Perthes disease (LCPD). A secondary goal is to allow the classifier to expand the set of diseases using nonparametric methods such as the Dirichlet process.
Importantly, our movement primitive algorithm is inspired by current theories of biological motor control with a potential edge over standard algorithms in training on small case numbers. The temporal primitives are analogous to central pattern generators in the spinal cord [5], whereas the weights reflect activation of these central patterns by more central mechanisms in a hierarchical control scheme. In such a control scheme, disease-specific changes in weights may be caused directly by disease-specific influences on neural signaling, such as in the Stiff Person Syndrome [6], or indirectly through pain-avoidance in orthopedic conditions such as LCPD.
With further development, our approach holds potential for facilitating early detection and improving treatment strategies across a wide range of rare movement disorders and orthopedic conditions.},
howpublished = {Bernstein Conference},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Of over 6.000 known rare diseases, a considerable portion involves motor symptoms [1]. Whereas aiding diagnosis by artificial intelligence based on non-motor symptoms has shown promise [2], the potential of using movement data to this purpose has not yet been fully investigated. We therefore aim to implement a machine learning algorithm inspired by biological motor control to aid diagnosis of rare diseases by classifying data from standard kinematic clinical gait analysis.
Starting from 42-degrees-of-freedom time series of joint angles extracted from motion capture data with custom routines [3], we employ a Gaussian process-based temporal movement primitive algorithm [4] in order to reduce the data to sets of movement primitives and weight vectors that capture the essential characteristics of the gait movement. The primitives are participant (and disease) -independent and represent general human gait. The weights are participant-specific and thus contain disease-specific information. A weighted combination of the primitives can thus generate participant specific gait data. We then apply standard classification tools such as Support Vector Machines and Random Forests to the weights to distinguish the disease from the control gait. The primary goal is to reliably differentiate patients from age-matched controls in an existing data set on patients with Legg–Calvé–Perthes disease (LCPD). A secondary goal is to allow the classifier to expand the set of diseases using nonparametric methods such as the Dirichlet process.
Importantly, our movement primitive algorithm is inspired by current theories of biological motor control with a potential edge over standard algorithms in training on small case numbers. The temporal primitives are analogous to central pattern generators in the spinal cord [5], whereas the weights reflect activation of these central patterns by more central mechanisms in a hierarchical control scheme. In such a control scheme, disease-specific changes in weights may be caused directly by disease-specific influences on neural signaling, such as in the Stiff Person Syndrome [6], or indirectly through pain-avoidance in orthopedic conditions such as LCPD.
With further development, our approach holds potential for facilitating early detection and improving treatment strategies across a wide range of rare movement disorders and orthopedic conditions.
Starting from 42-degrees-of-freedom time series of joint angles extracted from motion capture data with custom routines [3], we employ a Gaussian process-based temporal movement primitive algorithm [4] in order to reduce the data to sets of movement primitives and weight vectors that capture the essential characteristics of the gait movement. The primitives are participant (and disease) -independent and represent general human gait. The weights are participant-specific and thus contain disease-specific information. A weighted combination of the primitives can thus generate participant specific gait data. We then apply standard classification tools such as Support Vector Machines and Random Forests to the weights to distinguish the disease from the control gait. The primary goal is to reliably differentiate patients from age-matched controls in an existing data set on patients with Legg–Calvé–Perthes disease (LCPD). A secondary goal is to allow the classifier to expand the set of diseases using nonparametric methods such as the Dirichlet process.
Importantly, our movement primitive algorithm is inspired by current theories of biological motor control with a potential edge over standard algorithms in training on small case numbers. The temporal primitives are analogous to central pattern generators in the spinal cord [5], whereas the weights reflect activation of these central patterns by more central mechanisms in a hierarchical control scheme. In such a control scheme, disease-specific changes in weights may be caused directly by disease-specific influences on neural signaling, such as in the Stiff Person Syndrome [6], or indirectly through pain-avoidance in orthopedic conditions such as LCPD.
With further development, our approach holds potential for facilitating early detection and improving treatment strategies across a wide range of rare movement disorders and orthopedic conditions.