Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

'Federated Learning' (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the "EXAM" (EMR CXR AI Model) model. EXAM achieved an average Area Under the Curve (AUC) of over 0.92, an average improvement of 16%, and a 38% increase in generalisability over local models. The FL paradigm was successfully applied to facilitate a rapid data science collaboration without data exchange, resulting in a model that generalised across heterogeneous, unharmonized datasets. This provided the broader healthcare community with a validated model to respond to COVID-19 challenges, as well as set the stage for broader use of FL in healthcare.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7805458PMC
http://dx.doi.org/10.21203/rs.3.rs-126892/v1DOI Listing

Publication Analysis

Top Keywords

broader healthcare
8
data
6
federated learning
4
learning predicting
4
predicting outcomes
4
outcomes sars-cov-2
4
sars-cov-2 patients
4
patients 'federated
4
'federated learning'
4
learning' method
4

Similar Publications

Digital health self-management interventions for musicians with playing-related musculoskeletal disorders: A scoping review.

Musculoskelet Sci Pract

September 2025

Biomechanics and Bioengineering Research Centre Versus Arthritis, Cardiff University, Cardiff, CF10 3AT, UK; School of Health Sciences, University of Southampton, SO17 1BJ, UK.

Introduction: Playing-related musculoskeletal disorders are common in musicians. Self-management interventions are recommended to improve the management of musculoskeletal disorders and support individuals to safely take responsibility for their own health. Digital health interventions are increasingly used to support self-management of musculoskeletal disorders.

View Article and Find Full Text PDF

Background: Breast cancer treatment, particularly during the perioperative period, is often accompanied by significant psychological distress, including anxiety and uncertainty. Mobile health (mHealth) interventions have emerged as promising tools to provide timely psychosocial support through convenient, flexible, and personalized platforms. While research has explored the use of mHealth in breast cancer prevention, care management, and survivorship, few studies have examined patients' experiences with mobile interventions during the perioperative phase of breast cancer treatment.

View Article and Find Full Text PDF

Background: Immune checkpoint inhibitors (ICIs) are clinically beneficial but associated with high costs that represent a growing challenge for healthcare budgets and may affect affordability, especially in resource-limited settings. Moreover, the healthcare sector is a significant source of greenhouse gas emissions, and medication-related waste-such as that from vial-based therapies-has been identified as a contributing factor. Alternative dosing strategies could reduce the environmental and financial impact of ICI therapy while maintaining clinical safety and efficacy.

View Article and Find Full Text PDF

Spiritual interventions, including meditation, prayer, mindfulness, and compassionate care, have gained increasing attention for their potential to enhance both psychological resilience and overall health. This systematic review and meta-analysis examined eight eligible studies conducted across the USA, Europe, and China to assess the impact of such interventions on key outcomes, namely anxiety reduction, quality of life, chronic disease symptom management, and patient satisfaction. Seven studies contributed quantitative data.

View Article and Find Full Text PDF

Background: Research Capacity and Culture (RCC) is important for research engagement. Little is known of what speech and language therapy staff perceives to be the barriers or enablers to this at individual, team and organisational levels.

Aims: To identify the barriers and enablers to RCC among speech and language therapy staff, using behaviour change theory as a framework, and to explore their self-reported level of research engagement.

View Article and Find Full Text PDF