arXiv subjects

Juliane Fluck

Publications and source records attributed to Juliane Fluck.

5 recordsLinked to original sources

arXiv2024

NFDI4Health workflow and service for synthetic data generation, assessment and risk management

Individual health data is crucial for scientific advancements, particularly in developing Artificial Intelligence (AI); however, sharing real patient information is often restricted due to privacy concerns. A promising solution to this challenge is synthetic data generation. This technique creates entirely new datasets that mimic the statistical properties of real data, while preserving confidential patient information. In this paper, we present the workflow and different services developed in the context of Germany's National Data Infrastructure project NFDI4Health. First, two state-of-the-art AI tools (namely, VAMBN and MultiNODEs) for generating synthetic health data are outlined. Further, we introduce SYNDAT (a public web-based tool) which allows users to visualize and assess the quality and risk of synthetic data provided by desired generative models. Additionally, the utility of the proposed methods and the web-based tool is showcased using data from Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Center for Cancer Registry Data of the Robert Koch Institute (RKI).

cs.LG↗

arXiv2023

Synthetic data generation for a longitudinal cohort study -- Evaluation, method extension and reproduction of published data analysis results

Access to individual-level health data is essential for gaining new insights and advancing science. In particular, modern methods based on artificial intelligence rely on the availability of and access to large datasets. In the health sector, access to individual-level data is often challenging due to privacy concerns. A promising alternative is the generation of fully synthetic data, i.e. data generated through a randomised process that have similar statistical properties as the original data, but do not have a one-to-one correspondence with the original individual-level records. In this study, we use a state-of-the-art synthetic data generation method and perform in-depth quality analyses of the generated data for a specific use case in the field of nutrition. We demonstrate the need for careful analyses of synthetic data that go beyond descriptive statistics and provide valuable insights into how to realise the full potential of synthetic datasets. By extending the methods, but also by thoroughly analysing the effects of sampling from a trained model, we are able to largely reproduce significant real-world analysis results in the chosen use case.

stat.ME↗

arXiv2022

Interactive cohort exploration for spinocerebellar ataxias using synthetic cohort data for visualization

Motivation: Visualization of data is a crucial step to understanding and deriving hypotheses from clinical data. However, for clinicians, visualization often comes with great effort due to the lack of technical knowledge about data handling and visualization. The application offers an easy-to-use solution with an intuitive design that enables various kinds of plotting functions. The aim was to provide an intuitive solution with a low entrance barrier for clinical users. Little to no onboarding is required before creating plots, while the complexity of questions can grow up to specific corner cases. To allow for an easy start and testing with SCAview, we incorporated a synthetic cohort dataset based on real data of rare neurological movement disorders: the most common autosomal-dominantly inherited spinocerebellar ataxias (SCAs) type 1, 2, 3, and 6 (SCA1, 2, 3 and 6). Methods: We created a Django-based backend application that serves the data to a React-based frontend that uses Plotly for plotting. A synthetic cohort was created to deploy a version of SCAview without violating any data protection guidelines. Here, we added normal distributed noise to the data and therefore prevent re-identification while keeping distributions and general correlations. Results: This work presents SCAview, an user-friendly, interactive web-based service that enables data visualization in a clickable interface allowing intuitive graphical handling that aims to enable data visualization in a clickable interface. The service is deployed and can be tested with a synthetic cohort created based on a large, longitudinal dataset from observational studies in the most common SCAs.

q-bio.QM↗

arXiv2022

BERT WEAVER: Using WEight AVERaging to enable lifelong learning for transformer-based models in biomedical semantic search engines

Recent developments in transfer learning have boosted the advancements in natural language processing tasks. The performance is, however, dependent on high-quality, manually annotated training data. Especially in the biomedical domain, it has been shown that one training corpus is not enough to learn generic models that are able to efficiently predict on new data. Therefore, in order to be used in real world applications state-of-the-art models need the ability of lifelong learning to improve performance as soon as new data are available - without the need of re-training the whole model from scratch. We present WEAVER, a simple, yet efficient post-processing method that infuses old knowledge into the new model, thereby reducing catastrophic forgetting. We show that applying WEAVER in a sequential manner results in similar word embedding distributions as doing a combined training on all data at once, while being computationally more efficient. Because there is no need of data sharing, the presented method is also easily applicable to federated learning settings and can for example be beneficial for the mining of electronic health records from different clinics.

cs.CL↗

arXiv2021

Integrative Data Semantics through a Model-enabled Data Stewardship

Motivation: The importance of clinical data in understanding the pathophysiology of complex disorders has prompted the launch of multiple initiatives designed to generate patient-level data from various modalities. While these studies can reveal important findings relevant to the disease, each study captures different yet complementary aspects and modalities which, when combined, generate a more comprehensive picture of disease aetiology. However, achieving this requires a global integration of data across studies, which proves to be challenging given the lack of interoperability of cohort datasets. Results: Here, we present the Data Steward Tool (DST), an application that allows for semi-automatic semantic integration of clinical data into ontologies and global data models and data standards. We demonstrate the applicability of the tool in the field of dementia research by establishing a Clinical Data Model (CDM) in this domain. The CDM currently consists of 277 common variables covering demographics (e.g. age and gender), diagnostics, neuropsychological tests, and biomarker measurements. The DST combined with this disease-specific data model shows how interoperability between multiple, heterogeneous dementia datasets can be achieved.

q-bio.QM↗