With the advent of artificial intelligence and Big Data - projects, the necessity for a transition from analog medicine to modern-day solutions such as cloud computing becomes unavoidable. Even though this need is now common knowledge, the process is not always easy to start. Legislative changes, for example at the level of the European Union, are helping the respective healthcare systems to take the necessary steps. This article provides an overview of how a German university hospital is dealing with European data protection laws on the integration of cloud computing into everyday clinical practice. By describing our model approach, we aim to identify opportunities and possible pitfalls to sustainably influence digitization in Germany.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10787755 | PMC |
| http://dx.doi.org/10.1038/s41746-024-01000-3 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
CPhaMAS: The first pharmacokinetic analysis cloud platform developed by China.
Zhong Nan Da Xue Xue Bao Yi Xue Ban
August 2024
Center of Clinical Pharmacology, Third Xiangya Hospital, Central South University, Changsha 410013.
Objectives: Software for pharmacological modeling and statistical analysis is essential for drug development and individualized treatment modeling. This study aims to develop a pharmacokinetic analysis cloud platform that leverages cloud-based benefits, offering a user-friendly interface with a smoother learning curve.
Methods: The platform was built using Rails as the framework, developed in Julia language, and employs PostgreSQL 14 database, Redis cache, and Sidekiq for asynchronous task management.
AIScholar: An OpenFaaS-enhanced cloud platform for intelligent medical data analytics.
Comput Biol Med
January 2025
Machine Intelligence Lab, College of Computer Science, Sichuan University, Chengdu, 610065, China.
This paper presents AIScholar, an intelligent research cloud platform developed based on artificial intelligence analysis methods and the OpenFaaS serverless framework, designed for intelligent analysis of clinical medical data with high scalability. AIScholar simplifies the complex analysis process by encapsulating a wide range of medical data analytics methods into a series of customizable cloud tools that emphasize ease of use and expandability, within OpenFaaS's serverless computing framework. As a multifaceted auxiliary tool in medical scientific exploration, AIScholar accelerates the deployment of computational resources, enabling clinicians and scientific personnel to derive new insights from clinical medical data with unprecedented efficiency.
View Article and Find Full Text PDFBiomarkers.
Alzheimers Dement
December 2024
Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, The Sahlgrenska Academy, University of Gothenburg, Mölndal, Sweden.
Background: To understand the progression of Alzheimer's disease (AD), neuroimaging and biomarker research relies increasingly on sophisticated data analysis techniques that are often restricted to expert lab environments. Here, we demonstrate how complex analyses on modeling tau spreading across interconnected brain regions from our previous studies (e.g.
View Article and Find Full Text PDFBackground: Recent developments in physiological and digital biomarkers provide an opportunity to shift the first diagnostic steps to the home-setting, thus allowing earlier detection and treatment of Alzheimer's disease (AD). Blood-based, magnetic resonance imaging, electrophysiological, digital and microbiome biomarkers have shown great promise and call for an evaluation of their accuracy, feasibility and safety in primary care and the community. The aim of PREDICTOM is to develop and test the accuracy of an artificial intelligence (AI) driven screening platform for the prediction and early detection of AD and to extend the clinical pathway to home-based screening using established and novel biomarkers.
View Article and Find Full Text PDFBiomarkers.
Alzheimers Dement
December 2024
Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
Background: Recent studies have demonstrated that deep learning of magnetic resonance imaging (MRI) brain scans can accurately predict Alzheimer's disease (AD) dementia and cognitive decline. However, the translational potential of this technique remains unfulfilled, as the underlying deep learning techniques are not yet available for immediate clinical use. To address this issue, we develop a web-based tool to facilitate real-time imaging data visualization and analyses, including brain image segmentation, cortical surface reconstruction, and early prediction of Alzheimer's disease dementia based on structural MRI data.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!