Filter and export

Publications

1004 Publications visible to you, out of a total of 1004
Aspects of FAIRness for Research Software Registries.
Student Theses

Abstract (Expand)

Research software registries play an integral role in the process of making software findable, accessible, interoperable and reusable (FAIR). However, there are no guidelines available for FAIRifying … registries listing research software. Identifying applicable criteria is a necessary step to develop recommendations that apply to software registries and can later be utilized to measure and improve their FAIRness. Principles that relate to FAIR research software were mapped to granular metrics. Afterwards, registry-applicable aspects were selected and summarized. This resulted in 17 aspects directed at metadata listed in research software registries. Each aspect is expressed in three tables, allowing easy access to relevant information as well as resolvable references to previous works regarding FAIRification. These can be used to develop new, quantifiable metrics. They also provide a meaningful reference point when establishing or improving such registries, an increasingly relevant field in light of the upcoming international initiatives, such as the EOSC.

Authors: W. Herbst, C. Draeger, M. Perbix, A. Winter, M. Lobe

Date Published: 8th Apr 2025

Publication Type: Journal article

SNIK Graph—Visualizing Knowledge about Management of Hospital Information Systems
Semantisches Netz des integrierten Informationsmanagements im Krankenhaus (SNIK)

Abstract

Not specified

Authors: Konrad Höffner, Thomas Pause, Franziska Jahn, Hannes Raphael Brunsch, Anna Brakemeier, Alfred Winter

Date Published: 1st Jul 2024

Publication Type: Journal article

Skin single-cell transcriptomics reveals a core of sebaceous gland-relevant genes shared by mice and humans.
Project Test Demonstrator

Abstract (Expand)

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) has been widely applied to dissect cellular heterogeneity in normal and diseased skin. Sebaceous glands, essential skin components with established … functions in maintaining skin integrity and emerging roles in systemic energy metabolism, have been largely neglected in scRNA-seq studies. METHODS: Departing from mouse and human skin scRNA-seq datasets, we identified gene sets expressed especially in sebaceous glands with the open-source R-package oposSOM. RESULTS: The identified gene sets included sebaceous gland-typical genes as Scd3, Mgst1, Cidea, Awat2 and KRT7. Surprisingly, however, there was not a single overlap among the 100 highest, exclusively in sebaceous glands expressed transcripts in mouse and human samples. Notably, both species share a common core of only 25 transcripts, including mitochondrial and peroxisomal genes involved in fatty acid, amino acid, and glucose processing, thus highlighting the intense metabolic rate of this gland. CONCLUSIONS: This study highlights intrinsic differences in sebaceous lipid synthesis between mice and humans, and indicates an important role for peroxisomal processes in this context. Our data also provides attractive starting points for experimentally addressing novel candidates regulating sebaceous gland homeostasis.

Authors: T. Thalheim, M. R. Schneider

Date Published: 3rd Feb 2024

Publication Type: Journal article

SNIK Ontology
Semantisches Netz des integrierten Informationsmanagements im Krankenhaus (SNIK)

Abstract

SNIK is an ontology of information management in hospitals that consists of a meta model and several subontologies.

Authors: Alfred Winter, Barbara Paech, Franziska Jahn, Birgit Schneider, Christian Kücherer, Konrad Höffner

Date Published: 2024

Publication Type: Misc

Modeling the Application of IHE QRPH Profiles in Data Integration Centers: A Practical Approach with 3LGM2.
3LGM² Enterprise Architecture Modeling

Abstract (Expand)

The Data Integration Centers (DICs), all part of the German Medical Informatics Initiative (MII), prepare routine care data captured in university hospitals to enable its reuse in clinical research. … Tackling this challenging task requires them to maintain multiple data stores, implement the necessary transformation processes, and provide the required terminology services, all while also addressing the use case specific needs researchers might have. An MII wide application of the standardized profiles defined in the IHE QRPH domain might therefore be able to drastically reduce the overhead at any one DIC. The MII DIC reference model built in 3LGM2, a method to describe complex information system architectures, serves as a starting point to evaluate whether such an application is possible. We first extend the IHE modeling capabilities of 3LGM2 to also support the five profiles from the QRPH domain that our experts evaluated as relevant in the MII DIC context. We then expand the DIC reference model by some IHE QRPH actors and transactions, showing that their application could be beneficial in the MII DIC context, provided they surpass their trial status.

Authors: C. Draeger, S. Staubert, A. Kuntz, C. Henke, A. Winter, U. Sax, M. Lobe

Date Published: 20th Oct 2023

Publication Type: Journal article

Prediction of Intensive Care Unit Length of Stay in the MIMIC-IV Dataset
Prediction model of Length of Stay and probability of rehospitalization

Abstract (Expand)

Accurately estimating the length of stay (LOS) of patients admitted to the intensive care unit (ICU) in relation to their health status helps healthcare management allocate appropriate resources and … resources and better plan for the future. This paper presents predictive models for the LOS of ICU patients from the MIMIC-IV database based on typical demographic and administrative data, as well as early vital signs and laboratory measurements collected on the first day of ICU stay. The goal of this study was to demonstrate a practical, stepwise approach to predicting patient’s LOS in the ICU using machine learning and early available typical clinical data. The results show that this approach significantly improves the performance of models for predicting actual LOS in a pragmatic framework that includes only data with short stays predetermined by a prior classification.

Authors: Lars Hempel, Sina Sadeghi, Toralf Kirsten

Date Published: 1st Jun 2023

Publication Type: Journal article

Medical multivariate time series imputation and forecasting based on a recurrent conditional Wasserstein GAN and attention
SMITH - Smart Medical Information Technology for Healthcare

Abstract (Expand)

OBJECTIVE: In the fields of medical care and research as well as hospital management, time series are an important part of the overall data basis. To ensure high quality standards and enable suitable … decisions, tools for precise and generic imputations and forecasts that integrate the temporal dynamics are of great importance. Since forecasting and imputation tasks involve an inherent uncertainty, the focus of our work lay on a probabilistic multivariate generative approach that samples infillings or forecasts from an analysable distribution rather than producing deterministic results. MATERIALS AND METHODS: For this task, we developed a system based on generative adversarial networks that consist of recurrent encoders and decoders with attention mechanisms and can learn the distribution of intervals from multivariate time series conditioned on the periods before and, if available, periods after the values that are to be predicted. For training, validation and testing, a data set of jointly measured blood pressure series (ABP) and electrocardiograms (ECG) (length: 1,250=ˆ10s) was generated. For the imputation tasks, one interval of fixed length was masked randomly and independently in both channels of every sample. For the forecasting task, all masks were positioned at the end. RESULTS: The models were trained on around 65,000 bivariate samples and tested against 14,000 series of different persons. For the evaluation, 50 samples were produced for every masked interval to estimate the range of the generated infillings or forecasts. The element-wise arithmetic average of these samples served as an estimator for the mean of the learned conditional distribution. The approach showed better results than a state-of-the-art probabilistic multivariate forecasting mechanism based on Gaussian copula transformation and recurrent neural networks. On the imputation task, the proposed method reached a mean squared error (MSE) of 0.057 on the ECG channel and an MSE of 28.30 on the ABP channel, while the baseline approach reached MSEs of 0.095 (ECG) and 229.1 (ABP). Moreover, on the forecasting task, the presented system achieved MSEs of 0.069 (ECG) and 33.73 (ABP), outperforming the recurrent copula approach, which reached MSEs of 0.082 (ECG) and 196.53 (ABP). CONCLUSION: The presented generative probabilistic system for the imputation and forecasting of (medical) time series features the flexibility to handle masks of different sizes and positions, the ability to quantify uncertainty due to its probabilistic predictions, and an adjustable trade-off between the goals of minimising errors in individual predictions and minimising the distance between the learned and the real conditional distribution of the infillings or forecasts.

Authors: Sven Festag, Cord Spreckelsen

Date Published: 1st Feb 2023

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