A5101773732- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- linguistics and terminology studies
- Topic Modeling
- Electronic Health Records Systems
- Bioinformatics and Genomic Networks
- Medical Coding and Health Information
- Clinical practice guidelines implementation
- Genomics and Rare Diseases
- Machine Learning in Healthcare
- Data Quality and Management
- Advanced Text Analysis Techniques
- Information Systems and Technology Applications
- Statistical and Computational Modeling
- Scientific Computing and Data Management
- Education Methods and Technologies
- Sociology and Education Studies
- Medical and Biological Sciences
- Radiomics and Machine Learning in Medical Imaging
- Mobile Health and mHealth Applications
- AI in cancer detection
- Artificial Intelligence in Healthcare
- Wildlife Conservation and Criminology Analyses
- Phase Equilibria and Thermodynamics
Medical University of Graz
2015-2024
Averbis (Germany)
2018-2023
Klinik und Poliklinik für Psychosomatische Medizin und Psychotherapie
2022
Johannes Gutenberg University Mainz
2022
Philipps University of Marburg
2017-2021
Schiller International University
2020
University of Graz
2011-2018
University of Freiburg
2003-2018
Berlin Heart (Germany)
2018
University of Nebraska Medical Center
2016
In the life sciences, there is an ample need for semantic interoperability of data. Thus shared vocabularies are needed consistently expressing metadata in terms annotations as well querying bibliographic information systems. I
Machine learning models trained on electronic health records have achieved high prognostic accuracy in test datasets, but little is known about their embedding into clinical workflows. We implemented a random forest-based algorithm to identify hospitalized patients at risk for delirium, and evaluated its performance setting.Delirium was predicted admission recalculated the evening of admission. The defined prediction outcome delirium coded recent hospital stay. During 7 months prospective...
Abstract Early identification of patients with life-threatening risks such as delirium is crucial in order to initiate preventive actions quickly possible. Despite intense research on machine learning for the prediction clinical outcomes, acceptance integration complex models routine remains unclear. The aim this study was evaluate user an already implemented learning-based application predicting risk in-patients. We applied a mixed methods design collect opinions and concerns from health...
In Western languages the period character is highly ambiguous, due to its double role as sentence delimiter and abbreviation marker. This particularly relevant in clinical free-texts characterized by numerous anomalies spelling, punctuation, vocabulary with a high frequency of short forms. The problem addressed two binary classifiers for detection. A support vector machine exploiting linear kernel trained on different combinations feature sets each classification task. Feature relevance...
SNOMED CT is a clinical terminology that uses logical axioms to provide terms with meaning. This enforces precise agreements about the ontological nature of entities denoted by terms, commonly described as commitment. We demonstra
This paper provides a survey of the state art in terminologies and ontologies applied to Biology Medicine.Not intending be fully comprehensive, we describe some most relevant resources that currently attract interest from industry academia.We introduce description framework compare systems terms their architectural elements, expressiveness, coverage, as well analyze nature entities they denote.In particular, scrutinize International Classification Diseases (ICD), Medical Subject Headings...
Objective To (1) evaluate the GoodOD guideline for ontology development by applying OQuaRE evaluation method and metrics to artefacts that were produced students in a randomized controlled trial, (2) informally compare with gold standard competency questions based methods, respectively. Background In last decades many methods construction have been proposed. However, none of them has become there is no empirical evidence comparative such methods. This paper brings together OQuaRE. developing...
Abstract Background The realm of pathological entities can be subdivided into dispositions, processes, and structures. latter are the bearer which then realized by their manifestations — pathologic processes. Despite its ontological soundness, implementing this model via purpose-oriented domain ontologies will likely require considerable effort, both in ontology construction maintenance, constitutes a problem for SNOMED CT, presently largest biomedical ontology. Results We describe an design...
Abstract Motivation: The classification of biological entities in terms species and taxa is an important endeavor biology. Although a large amount statements encoded current biomedical ontologies taxon-dependent there no obvious or standard way for introducing taxon information into integrative ontology architecture, supposedly because ongoing controversies about the ontological nature taxa. Results: In this article, we discuss different approaches on how to represent using existing...
Summary Background: Information technology in health care has a clear potential to improve the quality and efficiency of care, especially area medication processes. On other hand, existing studies show possible adverse effects on patient safety when IT for medication-related processes is developed, introduced or used inappropriately. Objectives: To summarize definitions observations usage pharmacotherapy derive recommendations future research priorities decision makers domain experts....
The time has come to end unproductive competitions among different types of biomedical terminology artefacts. Tools and strategies create the foundation a seamless environment covering clinical jargon, terminologies, classifications are necessary. Whereas language processing relies on human interface which represent their link reference terminologies such as SNOMED CT is essential guarantee semantic interoperability. There also need for interoperation between aggregation terminologies....