학술논문
Development and Implementation of the Data Science Learning Platform for Research Physician.
Document Type
Academic Journal
Author
Begic Fazlic L; ISS, Trier University of Applied Sciences, Trier, Germany.; Schacht M; ISS, Trier University of Applied Sciences, Trier, Germany.; Morgen M; ISS, Trier University of Applied Sciences, Trier, Germany.; Schmeink A; Chair of Information Theory and Data Analytics, RWTH Aachen University, Aachen, Germany.; Lipp R; Chair of Information Theory and Data Analytics, RWTH Aachen University, Aachen, Germany.; Martin L; Department of Intensive and Intermediate Care, University Hospital Aachen.; Vollmer T; Philips GmbH Innovative Technologies, Aachen, Germany.; Winter S; Philips GmbH Innovative Technologies, Aachen, Germany.; Dartmann G; ISS, Trier University of Applied Sciences, Trier, Germany.
Source
Publisher: IOS Press Country of Publication: Netherlands NLM ID: 9214582 Publication Model: Print Cited Medium: Internet ISSN: 1879-8365 (Electronic) Linking ISSN: 09269630 NLM ISO Abbreviation: Stud Health Technol Inform
Subject
Language
English
Abstract
Data analysis and their application are the unavoidable factors in the activities analyses in health care. Unfortunately, the acquisition of data from large available medical databases is a complex process and requires deep knowledge of computer science and especially knowledge of tools for data management. According to the European General Data Protection Regulation, the problem becomes much more complex. Recognizing these problems and difficulties, we have developed a Data Science Learning Platform (DSLP) that primarily targets practitioners and researchers but also the computer science students. Using our proposed tool chain together with the developed graphical user interface, data scientists and research physicians will be able to use available medical databases, apply and analyze different anonymization methods, analyze data according to the patient's risk and quickly formulate new studies to target a disease in a complex data model. This article presents a clinical research discovery toolbox that implements and demonstrates tools for data anonymization, patient data visualization, NLP-tools for guideline search and data science learning tools.