An ontology‐based clinical data warehouse for scientific research

Girardi, Dominic; Dirnberger, Johannes; Giretzlehner, Michael

doi:10.1186/2056-5917-1-6

Cited by 10 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, it focused only on MRI-based methods which might not encompass the full spectrum of diagnostic tools for dementia. A domain-independent, ontology-based clinical data warehouse for medical research was presented in [84]. It was created using a generalized metadata paradigm and can accommodate both the current domain ontology and the relevant research data.…”

Section: Review Of Related Workmentioning

confidence: 99%

A systematic review and meta-data analysis of clinical data repositories in Africa and beyond: recent development, challenges, and future directions

Adewole,

Alozie,

Olagunju

et al. 2024

Discov Data

View full text Add to dashboard Cite

A Clinical Data Repository (CDR) is a dynamic database capable of real-time updates with patients' data, organized to facilitate rapid and easy retrieval. CDRs offer numerous benefits, ranging from preserving patients' medical records for follow-up care and prescriptions to enabling the development of intelligent models that can predict, and potentially mitigate serious health conditions. While several research works have attempted to provide state-of-the-art reviews on CDR design and implementation, reviews from 2013 to 2023 cover CDR regulations, guidelines, standards, and challenges in CDR implementation without providing a holistic overview of CDRs. Additionally, these reviews need to adequately address critical aspects of CDR; development and utilization, CDR architecture and metadata, CDR management tools, CDR security, use cases, and artificial intelligence (AI) in CDR design and implementation. The collective knowledge gaps in these works underscore the imperative for a comprehensive overview of the diverse spectrum of CDR as presented in the current study. Existing reviews conducted over the past decade, from 2013 to 2023 have yet to comprehensively cover the critical aspects of CDR development, which are essential for uncovering trends and potential future research directions in Africa and beyond. These aspects include architecture and metadata, security and privacy concerns, tools employed, and more. To bridge this gap, in particular, this study conducts a comprehensive systematic review of CDR, considering critical facets such as architecture and metadata, security and privacy issues, regulations guiding development, practical use cases, tools employed, the role of AI and machine learning (ML) in CDR development, existing CDRs, and challenges faced during CDR development and deployment in Africa and beyond. Specifically, the study extracts valuable discussions and analyses of the different aspects of CDR. Key findings revealed that most architectural models for CDR are still in the theoretical phase, with low awareness and adoption of CDR in healthcare environments, susceptibility to several security threats, and the need to integrate federated learning in CDR systems. Overall, this paper would serve as a valuable reference for designing and implementing cutting-edge clinical data repositories in Africa and beyond.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

A systematic review and meta-data analysis of clinical data repositories in Africa and beyond: recent development, challenges, and future directions

Adewole,

Alozie,

Olagunju

et al. 2024

Discov Data

View full text Add to dashboard Cite

show abstract

“…For a more detailed description on the platform itself and the usage of the domain-ontology for data exploration the reader is kindly referred to [3,4,5].…”

Section: An Ontology-based Research Platformmentioning

confidence: 99%

Semi-automated Quality Assurance for Domain-Expert-Driven Data Exploration – An Application to Principal Component Analysis

Wartner

Wiesinger-Widi

Girardi

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Processing and exploring large quantities of electronic data is often a particularly interesting but yet challenging task. Both the lack of statistical and mathematical skills and the missing know-how of handling masses of (health) data constitute high barriers for profound data exploration -especially when performed by domain experts. This paper presents guided visual pattern discovery, by taking the wellestablished data mining method Principal Component Analysis as an example. Without guidance, the user has to be conscious about the reliability of computed results at any point during the analysis (GIGOprinciple). In the course of the integration of principal component analysis into an ontology-guided research infrastructure, we include a guidance system supporting the user through the separate analysis steps and we introduce a quality measure, which is essential for profound research results.

show abstract

Ontologies, Machine Learning and Deep Learning in Obstetrics

Malgieri

2023

Practical Guide to Simulation in Delivery Room Emergencies

View full text Add to dashboard Cite

An ontology‐based clinical data warehouse for scientific research

Cited by 10 publications

References 22 publications

A systematic review and meta-data analysis of clinical data repositories in Africa and beyond: recent development, challenges, and future directions

A systematic review and meta-data analysis of clinical data repositories in Africa and beyond: recent development, challenges, and future directions

Semi-automated Quality Assurance for Domain-Expert-Driven Data Exploration – An Application to Principal Component Analysis

Ontologies, Machine Learning and Deep Learning in Obstetrics

Contact Info

Product

Resources

About