Filter and export

Publications

1005 Publications visible to you, out of a total of 1005
Use of Natural Language Processing for Precise Retrieval of Key Elements of Health IT Evaluation Studies
Management of health information systems

Abstract (Expand)

Having precise information about health IT evaluation studies is important for evidence-based decisions in medical informatics. In a former feasibility study, we used a faceted search based on ontological … modeling of key elements of studies to retrieve precisely described health IT evaluation studies. However, extracting the key elements manually for the modeling of the ontology was time and resource-intensive. We now aimed at applying natural language processing to substitute manual data extraction by automatic data extraction. Four methods (Named Entity Recognition, Bag-of-Words, Term-Frequency-Inverse-Document-Frequency, and Latent Dirichlet Allocation Topic Modeling were applied to 24 health IT evaluation studies. We evaluated which of these methods was best suited for extracting key elements of each study. As gold standard, we used results from manual extraction. As a result, Named Entity Recognition is promising but needs to be adapted to the existing study context. After the adaption, key elements of studies could be collected in a more feasible, time- and resource-saving way.

Authors: Verena Dornauer, Franziska Jahn, Konrad Hoeffner, Alfred Winter, Elske Ammenwerth

Date Published: 2020

Publication Type: Journal article

Towards a Comparison of National eHealth Portals: Poster
Management of health information systems

Abstract

Not specified

Authors: Maryam Ghalandari, Franziska Jahn, Alfred Winter

Date Published: 2020

Publication Type: Misc

Agiles Lernzielmanagement mit dem Health Informatics-Learning Objective Navigator (HI-LONa)
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

Fragestellung/Zielsetzung: Zentraler Baustein curricularer Entwicklung sind kompetenzorientierte Lernziele [ref:1], wie sie im NKLM dargestellt sind. Webbasierte Datenbanken machen Lernzielkataloge … zugänglich und strukturiert nutzbar. Das Web-Portal LOOOP [ref:2] bietet[zum vollständigen Text gelangen Sie über die oben angegebene URL]

Authors: Ulrike Schemmann, Birgit Schneider, Lo An Phan-Vogtmann, Susanne Müller, Cord Spreckelsen

Date Published: 2020

Publication Type: Misc

Organisation von Teilgraphen semantischer Netze zur ontologiegestützten Wissensvermittlung
Semantisches Netz des integrierten Informationsmanagements im Krankenhaus (SNIK)

Abstract

Not specified

Author: Thomas Pause

Date Published: 2020

Publication Type: Masters Thesis

Use of Natural Language Processing for Precise Retrieval of Key Elements of Health IT Evaluation Studies
Health IT Ontology (HITO)

Abstract

Not specified

Authors: Verena Dornauer, Franziska Jahn, Konrad Höffner, Alfred Winter, Elske Ammenwerth

Date Published: 2020

Publication Type: Journal article

Towards Precise Descriptions of Medical Free/Libre and Open Source Software
Health IT Ontology (HITO)

Abstract

Not specified

Authors: Franziska Jahn, Michelle Bindel, Konrad Hoeffner, Maryam Ghalandari, Birgit Schneider, Sebastian Staeubert, Verena Dornauer, Thomas Karopka, Elske Ammenwerth, Alfred Winter

Date Published: 2020

Publication Type: Journal article

Four versus six cycles of CHOP chemotherapy in combination with six applications of rituximab in patients with aggressive B-cell lymphoma with favourable prognosis (FLYER): a randomised, phase 3, non-inferiority trial.
GLA - German Lymphoma Alliance

Abstract (Expand)

BACKGROUND: Six cycles of R-CHOP (rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone) are the standard treatment for aggressive B-cell non-Hodgkin lymphoma. In the FLYER trial, … we assessed whether four cycles of CHOP plus six applications of rituximab are non-inferior to six cycles of R-CHOP in a population of patients with B-cell non-Hodgkin lymphoma with favourable prognosis. METHODS: This two-arm, open-label, international, multicentre, prospective, randomised phase 3 non-inferiority trial was done at 138 clinical sites in Denmark, Israel, Italy, Norway, and Germany. We enrolled patients aged 18-60 years, with stage I-II disease, normal serum lactate dehydrogenase concentration, ECOG performance status 0-1, and without bulky disease (maximal tumour diameter <7.5 cm). Randomisation was computer-based and done centrally in a 1:1 ratio using the Pocock minimisation algorithm after stratification for centres, stage (I vs II), and extralymphatic sites (no vs yes). Patients were assigned to receive either six cycles of R-CHOP or four cycles of R-CHOP plus two doses of rituximab. CHOP comprised cyclophosphamide (750 mg/m(2)), doxorubicin (50 mg/m(2)), and vincristine (1.4 mg/m(2), with a maximum total dose of 2 mg), all administered intravenously on day 1, plus oral prednisone or prednisolone at the discretion of the investigator (100 mg) administered on days 1-5. Rituximab was given at a dose of 375 mg/m(2) of body surface area. Cycles were repeated every 21 days. No radiotherapy was planned except for testicular lymphoma treatment. The primary endpoint was progression-free survival after 3 years. The primary analysis was done in the intention-to-treat population. Safety was assessed in all patients who received at least one dose of assigned treatment. A non-inferiority margin of -5.5% was chosen. The trial, which is completed, was prospectively registered at ClinicalTrials.gov, NCT00278421. FINDINGS: Between Dec 2, 2005, and Oct 7, 2016, 592 patients were enrolled, of whom 295 patients were randomly assigned to receive six cycles of R-CHOP and 297 were assigned to receive four cycles of R-CHOP plus two doses of rituximab. Four patients in the four-cycles group withdrew informed consent before the start of treatment, so 588 patients were included in the intention-to-treat analysis. After a median follow-up of 66 months (IQR 42-100), 3-year progression-free survival of patients who had four cycles of R-CHOP plus two doses of rituximab was 96% (95% CI 94-99), which was 3% better (lower limit of the one-sided 95% CI for the difference was 0%) than six cycles of R-CHOP, demonstrating the non-inferiority of the four-cycles regimen. 294 haematological and 1036 non-haematological adverse events were documented in the four-cycles group compared with 426 haematological and 1280 non-haematological adverse events in the six-cycles group. Two patients, both in the six-cycles group, died during study therapy. INTERPRETATION: In young patients with aggressive B-cell non-Hodgkin lymphoma and favourable prognosis, four cycles of R-CHOP is non-inferior to six cycles of R-CHOP, with relevant reduction of toxic effects. Thus, chemotherapy can be reduced without compromising outcomes in this population. FUNDING: Deutsche Krebshilfe.

Authors: V. Poeschel, G. Held, M. Ziepert, M. Witzens-Harig, H. Holte, L. Thurner, P. Borchmann, A. Viardot, M. Soekler, U. Keller, C. Schmidt, L. Truemper, R. Mahlberg, R. Marks, H. G. Hoeffkes, B. Metzner, J. Dierlamm, N. Frickhofen, M. Haenel, A. Neubauer, M. Kneba, F. Merli, A. Tucci, P. de Nully Brown, M. Federico, E. Lengfelder, A. di Rocco, R. Trappe, A. Rosenwald, C. Berdel, M. Maisenhoelder, O. Shpilberg, J. Amam, K. Christofyllakis, F. Hartmann, N. Murawski, S. Stilgenbauer, M. Nickelsen, G. Wulf, B. Glass, N. Schmitz, B. Altmann, M. Loeffler, M. Pfreundschuh

Date Published: 21st Dec 2019

Publication Type: Journal article

Human Diseases: lymphoma, diffuse large B-cell lymphoma

Navigate

Health Atlas - Local Data Hub/Leipzig

The Health Atlas - Local Data Hub/Leipzig is an alliance of medical ontologists, medical systems biologists and clinical trials groups to design and implement a multi-functional and quality-assured atlas. It provides models, data and metadata on specific use cases from medical research fields.

Registered Repository

re3data.org Badge
Powered by
 (v.1.13.0-master)
Health Atlas | Funding and Programmes | Credits | Terms & Conditions | Privacy Policy | Imprint
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