Filter and export

Publications

959 Publications visible to you, out of a total of 959
GAN-Based Approaches for Generating Structured Data in the Medical Domain
Synthetica: generation and evaluation of synthetic data

Abstract (Expand)

Modern machine and deep learning methods require large datasets to achieve reliable and robust results. This requirement is often difficult to meet in the medical field, due to data sharing limitations …ng limitations imposed by privacy regulations or the presence of a small number of patients (e.g., rare diseases). To address this data scarcity and to improve the situation, novel generative models such as Generative Adversarial Networks (GANs) have been widely used to generate synthetic data that mimic real data by representing features that reflect health-related information without reference to real patients. In this paper, we consider several GAN models to generate synthetic data used for training binary (malignant/benign) classifiers, and compare their performances in terms of classification accuracy with cases where only real data are considered. We aim to investigate how synthetic data can improve classification accuracy, especially when a small amount of data is available. To this end, we have developed and implemented an evaluation framework where binary classifiers are trained on extended datasets containing both real and synthetic data. The results show improved accuracy for classifiers trained with generated data from more advanced GAN models, even when limited amounts of original data are available.

Authors: Masoud Abedi, Lars Hempel, Sina Sadeghi, Toralf Kirsten

Date Published: 1st Jul 2022

Publication Type: Journal article

GGPONC 2.0 — The German Clinical Guideline Corpus for Oncology: Curation Workflow, Annotation Policy, Baseline NER Taggers
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

Despite remarkable advances in the development of language resources over the recent years, there is still a shortage of annotated, publicly available corpora covering (German) medical language. With … the initial release of the German Guideline Program in Oncology NLP Corpus (GGPONC), we have demonstrated how such corpora can be built upon clinical guidelines, a widely available resource in many natural languages with a reasonable coverage of medical terminology. In this work, we describe a major new release for GGPONC. The corpus has been substantially extended in size and re-annotated with a new annotation scheme based on SNOMED CT top level hierarchies, reaching high inter-annotator agreement (γ=.94). Moreover, we annotated elliptical coordinated noun phrases and their resolutions, a common language phenomenon in (not only German) scientific documents. We also trained BERT-based named entity recognition models on this new data set, which achieve high performance on short, coarse-grained entity spans (F1=.89), while the rate of boundary errors increases for long entity spans. GGPONC is freely available through a data use agreement. The trained named entity recognition models, as well as the detailed annotation guide, are also made publicly available.

Editor: Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Jan Odijk, Stelios Piperidis

Date Published: 19th Jun 2022

Publication Type: Journal article

System for context-specific visualization of clinical practice guidelines (GuLiNav): Concept and software implementation
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

BACKGROUND: Clinical decision support systems often adopt and operationalize existing clinical practice guidelines leading to higher guideline availability, increased guideline adherence, and data … integration. Most of these systems use an internal state-based model of a clinical practice guideline to derive recommendations but do not provide the user with comprehensive insight into the model. OBJECTIVE: Here we present a novel approach based on dynamic guideline visualization that incorporates the individual patient’s current treatment context. METHODS: We derived multiple requirements to be fulfilled by such an enhanced guideline visualization. Using business process and model notation as the representation format for computer-interpretable guidelines, a combination of graph-based representation and logical inferences is adopted for guideline processing. A context-specific guideline visualization is inferred using a business rules engine. RESULTS: We implemented and piloted an algorithmic approach for guideline interpretation and processing. As a result of this interpretation, a context-specific guideline is derived and visualized. Our implementation can be used as a software library but also provides a representational state transfer interface. Spring, Camunda, and Drools served as the main frameworks for implementation. A formative usability evaluation of a demonstrator tool that uses the visualization yielded high acceptance among clinicians. CONCLUSIONS: The novel guideline processing and visualization concept proved to be technically feasible. The approach addresses known problems of guideline-based clinical decision support systems. Further research is necessary to evaluate the applicability of the approach in specific medical use cases.

Authors: Jonas Fortmann, Marlene Lutz, Cord Spreckelsen

Date Published: 1st Jun 2022

Publication Type: Journal article

A privacy-preserving distributed analytics platform for health care data
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

Abstract Background In recent years, data-driven medicine has gained increasing importance in terms of diagnosis, treatment, and research due to the exponential growth of health care data. However, … data protection regulations prohibit data centralisation for analysis purposes because of potential privacy risks like the accidental disclosure of data to third parties. Therefore, alternative data usage policies, which comply with present privacy guidelines, are of particular interest. Objective We aim to enable analyses on sensitive patient data by simultaneously complying with local data protection regulations using an approach called the Personal Health Train (PHT), which is a paradigm that utilises distributed analytics (DA) methods. The main principle of the PHT is that the analytical task is brought to the data provider and the data instances remain in their original location. Methods In this work, we present our implementation of the PHT paradigm, which preserves the sovereignty and autonomy of the data providers and operates with a limited number of communication channels. We further conduct a DA use case on data stored in three different and distributed data providers. Results We show that our infrastructure enables the training of data models based on distributed data sources. Conclusion Our work presents the capabilities of DA infrastructures in the health care sector, which lower the regulatory obstacles of sharing patient data. We further demonstrate its ability to fuel medical science by making distributed data sets available for scientists or health care practitioners.

Authors: Sascha Welten, Yongli Mou, Laurenz Neumann, Mehrshad Jaberansary, Yeliz Yediel Ucer, Toralf Kirsten, Stefan Decker, Oya Beyan

Date Published: 1st Jun 2022

Publication Type: Journal article

Charts and LMS tables of transfontanellar and transvertical ear-to-ear distances for gestational age
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

Introduction: To date cranial development has only been described by analyzing occipitofrontal circumference (OFC). More precise methods of determining head measurements have not been widely adopted. … The use of additional measurements has the potential to better account for the three-dimensional structure of the head. Our aim was to put forward centile curves of such measurements for gestational age along with a compound head volume index. Methods: We created generalized additive models for location, scale, and shape of two ear-to-ear distances (EED), transfontanellar (fEED) and transvertical (vEED), from birth anthropometric data. Same was done for OFC, crown-heel length, and birth weight to allow for comparison of our models with growth charts by Voigt et al. and Fenton and Kim. Results: Growth charts and tables of LMS parameters for fEED and vEED were derived from 6,610 patients admitted to our NICU and 625 healthy term newborns. With increasing gestational age EEDs increase about half as fast compared to OFC in absolute terms, their relative growths are fairly similar. Discussion: Differences to the charts by Fenton and Kim are minute. Tape measurements, such as fEED or vEED can be added to routine anthropometry at little extra costs. These charts may be helpful for following and evaluating head sizes and growth of preterm and term infants in three dimensions.

Authors: Nancy Arnold, Rudolf Georg Ascherl, Ulrich Herbert Thome

Date Published: 1st May 2022

Publication Type: Journal article

Towards an ontology-based phenotypic query model
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

Clinical research based on data from patient or study data management systems plays an important role in transferring basic findings into the daily practices of physicians. To support study recruitment, … diagnostic processes, and risk factor evaluation, search queries for such management systems can be used. Typically, the query syntax as well as the underlying data structure vary greatly between different data management systems. This makes it difficult for domain experts (e.g., clinicians) to build and execute search queries. In this work, the Core Ontology of Phenotypes is used as a general model for phenotypic knowledge. This knowledge is required to create search queries that determine and classify individuals (e.g., patients or study participants) whose morphology, function, behaviour, or biochemical and physiological properties meet specific phenotype classes. A specific model describing a set of particular phenotype classes is called a Phenotype Specification Ontology. Such an ontology can be automatically converted to search queries on data management systems. The methods described have already been used successfully in several projects. Using ontologies to model phenotypic knowledge on patient or study data management systems is a viable approach. It allows clinicians to model from a domain perspective without knowing the actual data structure or query language.

Authors: Christoph Beger, Franz Matthies, Ralph Schäfermeier, Toralf Kirsten, Heinrich Herre, Alexandr Uciteli

Date Published: 1st May 2022

Publication Type: Journal article

Generative adversarial networks for biomedical time series forecasting and imputation
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

In the present systematic review we identified and summarised current research activities in the field of time series forecasting and imputation with the help of generative adversarial networks (GANs). … We differentiate between imputation which describes the filling of missing values at intermediate steps and forecasting defining the prediction of future values. Especially the utilisation of such methods in the biomedical domain was to be investigated. To this end, 1057 publications were identified with the help of PubMed, Web of Science and Scopus. All studies that describe the use of GANs for the imputation/forecasting of time series were included irrespective of the application domain. Finally, 33 records were identified as eligible and grouped according to the topologies, losses, inputs and outputs of the presented GANs. In combination with a summary of all described application domains, this grouping served as a basis for analysing the peculiarities of the method in the biomedical context. Due to the broad spectrum of biomedical research, nearly all recognised methodologies are also applied in this domain. We could not identify any approach that proved itself superior in the biomedical area. Although GANs were initially designed to work in the image domain, many publications show that they are capable of imputing/forecasting non-visual time series.

Authors: Sven Festag, Joachim Denzler, Cord Spreckelsen

Date Published: 1st May 2022

Publication Type: Journal article

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