Daniel Schofield
YOU?
Author Swipe
View article: Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder
Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder Open
Camera traps are revolutionising wildlife monitoring by capturing vast amounts of visual data; however, the manual identification of individual animals remains a significant bottleneck. This study introduces a fully self-supervised approac…
View article: Towards deployment-centric multimodal AI beyond vision and language
Towards deployment-centric multimodal AI beyond vision and language Open
Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimod…
View article: Developing healthcare language model embedding spaces
Developing healthcare language model embedding spaces Open
Pre-trained Large Language Models (LLMs) have revolutionised Natural Language Processing (NLP) tasks, but often struggle when applied to specialised domains such as healthcare. The traditional approach of pre-training on large datasets fol…
View article: Representing multimorbid disease progressions using directed hypergraphs
Representing multimorbid disease progressions using directed hypergraphs Open
Objective To introduce directed hypergraphs as a novel tool for assessing the temporal relationships between coincident diseases, addressing the need for a more accurate representation of multimorbidity and leveraging the growing availabil…
View article: Delineating COVID-19 subgroups using routine clinical data identifies distinct in-hospital outcomes
Delineating COVID-19 subgroups using routine clinical data identifies distinct in-hospital outcomes Open
The COVID-19 pandemic has been a great challenge to healthcare systems worldwide. It highlighted the need for robust predictive models which can be readily deployed to uncover heterogeneities in disease course, aid decision-making and prio…
View article: An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis
An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis Open
Background The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better unde…
View article: An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis
An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis Open
The National COVID-19 Chest Imaging Database (NCCID) is a centralised database containing chest X-rays, chest Computed Tomography (CT) scans and cardiac Magnetic Resonance Images (MRI) from patients across the UK, jointly established by NH…
View article: Towards nationally curated data archives for clinical radiology image analysis at scale: Learnings from national data collection in response to a pandemic
Towards nationally curated data archives for clinical radiology image analysis at scale: Learnings from national data collection in response to a pandemic Open
The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to exe…