NLP for Clinical Research Tool
Version 1

Motivation: By using the NLP4CR tool, medical facts (e.g. diagnoses, laboratory values) can be extracted from German medical full texts.

Description: The NLP4CR tool is a prototype that demonstrates the applicability of Apache UIMA and cTakes to medical full texts in German language.

LHA ID: 7Q0CR2P5JK-1

1 item is associated with this Model:
  • NLP4CR-Tool.zip (Zip file - 496 MB)

Human Disease: Not specified

Model type: Not specified

Model format: Not specified

Execution or visualisation environment: Not specified




Model image: No image specified

Help
help Creators and Submitter
Creators
Additional credit

Colleen Goldberg

Submitter
License
Creative Commons Attribution 4.0
Activity

Views: 4255   Downloads: 2

Created: 6th May 2019 at 13:59

Last updated: 14th Dec 2020 at 14:43

Last used: 22nd Feb 2025 at 08:27

help Attributions

None

Version History

Version 1 Created 6th May 2019 at 13:59 by Christoph Beger

No revision comments

Related items

NLP4CR - Natural Language Processing for Clinical Research

The NLP4CR project was initiated as part of Colleen Goldberg's master thesis. Medical information is not always available in a structured form, but as free text documentation. NLP techniques make it possible to analyse, annotate and extract these free texts. In this way, medical data can be made accessible for machine processing and for clinical research.

Programme: This Project is not associated with a Programme

Public web page: http://www.imise.uni-leipzig.de/Gruppen/MIG

Start date: 1st Jan 2015

Towards Phenotyping of Clinical Trial Eligibility Criteria.
NLP4CR - Natural Language Processing for Clinical Research

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 texts … 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: M. Lobe, S. Staubert, C. Goldberg, I. Haffner, A. Winter

Date Published: 5th May 2018

Publication Type: Journal article

Human Diseases: breast cancer

Christoph Beger adminproject_administratorasset_housekeeper

Projects: LHA - Leipzig Health Atlas, Onto-Med Research Group, SMITH - Smart Medical Information Technology for Healthcare, Task Force COVID-19 Leipzig, NFDI4Health, LIFE Child, LIFE - Leipzig Research Center for Civilization Diseases, Project Test Demonstrator

Institutions: Institute for Medical Informatics, Statistics and Epidemiology (IMISE), Universitätsklinikum Leipzig, AöR, invalid

https://orcid.org/0000-0002-1166-0368
Matthias Löbe project_administratorasset_housekeeperasset_gatekeeperprogramme_administrator

Projects: NLP4CR - Natural Language Processing for Clinical Research, Evaluation Metadata Repository, SMITH - Smart Medical Information Technology for Healthcare, FAIR4Health, 3LGM² Enterprise Architecture Modeling, Student Thesis, MI-Lab

Institutions: Institute for Medical Informatics, Statistics and Epidemiology (IMISE)

https://orcid.org/0000-0002-2344-0426
Sebastian Stäubert adminasset_gatekeeper

Projects: NLP4CR - Natural Language Processing for Clinical Research, SMITH - Smart Medical Information Technology for Healthcare, 3LGM² Enterprise Architecture Modeling, MI-Lab

Institutions: Institute for Medical Informatics, Statistics and Epidemiology (IMISE)

https://orcid.org/0000-0002-7221-7415

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