The integration of Artificial Intelligence (AI) into clinical research has great potential to reveal patterns that are difficult for humans to detect, creating impactful connections between inputs and clinical outcomes. However, these methods often require large amounts of labeled data, which can be difficult to obtain in healthcare due to strict privacy laws and the need for experts to annotate data. This requirement creates a bottleneck when investigating unexplored clinical questions. This study explores the application of Self-Supervised Learning (SSL) as a way to obtain preliminary results from clinical studies with limited sized cohorts. To assess our approach, we focus on an underexplored clinical task: screening subjects for Paroxysmal Atrial Fibrillation (P-AF) using remote monitoring, single-lead ECG signals captured during normal sinus rhythm. We evaluate state-of-the-art SSL methods alongside supervised learning approaches, where SSL outperforms supervised learning in this task of interest. More importantly, it prevents misleading conclusions that may arise from poor performance in the latter paradigm when dealing with limited cohort settings.

BERT-based models for Electronic Health Records (EHR) have surged in popularity following the release of BEHRT and Med-BERT. Subsequent models have largely built on these foundations despite the fundamental design choices of these pioneering models remaining underexplored. To address this issue, we introduce CORE-BEHRT, a Carefully Optimized and Rigorously Evaluated BEHRT. Through incremental optimization, we isolate the sources of improvement for key design choices, giving us insights into the effect of data representation and individual technical components on performance. Evaluating this across a set of generic tasks (death, pain treatment, and general infection), we showed that improving data representation can increase the average downstream performance from 0.785 to 0.797 AUROC, primarily when including medication and timestamps. Improving the architecture and training protocol on top of this increased average downstream performance to 0.801 AUROC. We then demonstrated the consistency of our optimization through a rigorous evaluation across 25 diverse clinical prediction tasks. We observed significant performance increases in 17 out of 25 tasks and improvements in 24 tasks, highlighting the generalizability of our findings. Our findings provide a strong foundation for future work and aim to increase the trustworthiness of BERT-based EHR models.

Experts at the University of Copenhagen, Denmark, have begun using artificial intelligence to create computer models that calculate the risk of a corona patient's needing intensive care or a ventilator. As coronavirus patients are hospitalized, it is difficult for doctors to predict which of them will require intensive care and a respirator. Many different factors come into play, some yet to be fully understood by doctors . As such, computer scientists at the University of Copenhagen are now developing computer models based on artificial intelligence that calculate the risk of an individual patient's need for a ventilator or intensive care. The new initiative is being conducted in a collaboration with Rigshospitalet and Bispebjerg Hospital.