Publications

1004 Publications visible to you, out of a total of 1004

Abstract

Not specified

Authors: Alfred Winter, Sebastian Stäubert, Danny Ammon, Stephan Aiche, Oya Beyan, Verena Bischoff, Philipp Daumke, Stefan Decker, Gert Funkat, Jan Erik Gewehr, Armin de Greiff, Silke Haferkamp, Udo Hahn, Andreas Henkel, Toralf Kirsten, Thomas Klöss, Jörg Lippert, Matthias Löbe, Volker Lowitsch, Oliver Maassen, Jens Maschmann, Sven Meister, Rafael Mikolajczyk, Matthias Nüchter, Mathias W. Pletz, Erhard Rahm, Morris Riedel, Kutaiba Saleh, Andreas Schuppert, Stefan Smers, André Stollenwerk, Stefan Uhlig, Thomas Wendt, Sven Zenker, Wolfgang Fleig, Gernot Marx, André Scherag, Markus Löffler

Date Published: 2018

Publication Type: Journal article

Abstract

Not specified

Authors: Jan-David Liebe, Moritz Esdar, Franziska Jahn, Ursula Hübner

Date Published: 2018

Publication Type: InCollection

Abstract (Expand)

BACKGROUND Medical plaintext documents contain important facts about patients, but they are rarely available for structured queries. The provision of structured information from natural language textss in addition to the existing structured data can significantly speed up the search for fulfilled inclusion criteria and thus improve the recruitment rate. OBJECTIVES This work is aimed at supporting clinical trial recruitment with text mining techniques to identify suitable subjects in hospitals. METHOD Based on the inclusion/exclusion criteria of 5 sample studies and a text corpus consisting of 212 doctor’s letters and medical follow-up documentation from a university cancer center, a prototype was developed and technically evaluated using NLP procedures (UIMA) for the extraction of facts from medical free texts. RESULTS It was found that although the extracted entities are not always correct (precision between 23% and 96%), they provide a decisive indication as to which patient file should be read preferentially. CONCLUSION The prototype presented here demonstrates the technical feasibility. In order to find available, lucrative phenotypes, an in-depth evaluation is required.

Authors: Matthias Löbe, Sebastian Stäubert, Colleen Goldberg, Ivonne Haffner, Alfred Winter

Date Published: 2018

Publication Type: Journal article

Abstract

Not specified

Authors: Salma El-Oualydy, Matthias Löbe, Frank Meineke, Alfred Winter

Date Published: 2018

Publication Type: Misc

Abstract

Not specified

Author: Benjamin Rösch

Date Published: 2018

Publication Type: Masters Thesis

Abstract

Not specified

Author: Christian Kücherer

Date Published: 2018

Publication Type: Phd Thesis

Abstract (Expand)

Optical coherence tomography (OCT) manufacturers graphically present circumpapillary retinal nerve fiber layer thickness (cpRNFLT) together with normative limits to support clinicians in diagnosing ophthalmic diseases. The impact of age on cpRNFLT is typically implemented by linear models. cpRNFLT is strongly location-specific, whereas previously published norms are typically restricted to coarse sectors and based on small populations. Furthermore, OCT devices neglect impacts of lens or eye size on the diameter of the cpRNFLT scan circle so that the diameter substantially varies over different eyes. We investigate the impact of age and scan diameter reported by Spectralis spectral-domain OCT on cpRNFLT in 5646 subjects with healthy eyes. We provide cpRNFLT by age and diameter at 768 angular locations. Age/diameter were significantly related to cpRNFLT on 89%/92% of the circle, respectively (pointwise linear regression), and to shifts in cpRNFLT peak locations. For subjects from age 42.1 onward but not below, increasing age significantly decreased scan diameter (r=-0.28, p<0.001), which suggests that pathological cpRNFLT thinning over time may be underestimated in elderly compared to younger subjects, as scan diameter decrease correlated with cpRNFLT increase. Our detailed numerical results may help to generate various correction models to improve diagnosing and monitoring optic neuropathies.

Authors: M. Wang, T. Elze, D. Li, N. Baniasadi, K. Wirkner, T. Kirsten, J. Thiery, M. Loeffler, C. Engel, F. G. Rauscher

Date Published: 25th Dec 2017

Publication Type: Journal article

Powered by
(v.1.13.0-master)
Copyright © 2008 - 2021 The University of Manchester and HITS gGmbH
Institute for Medical Informatics, Statistics and Epidemiology, University of Leipzig

By continuing to use this site you agree to the use of cookies