Artificial Intelligence has revolutionised critical care for common conditions. Yet, rare conditions in the intensive care unit (ICU), including recognised rare diseases and low-prevalence conditions in the ICU, remain underserved due to data scarcity…
Continue Reading
We're excited to be back for another episode of the Life Sciences Today Podcast by Healthcare IT Today. My guest today is David Bates, Founder and CEO at Linus Health. I talk with David…
Continue Reading
Modern medicine increasingly relies on multimodal data, ranging from clinical notes to imaging and genomics, to guide diagnosis and treatment. However, integrating these heterogeneous data sources in a principled and interpretable manner remains a…
Continue Reading
The efficacy of immunotherapy in bladder cancer (BCa) is highly influenced by tumor heterogeneity, underscoring the urgent need for mechanistic insights and precise molecular subtyping. Adenosine-to-inosine RNA editing (AIRE), a critical post-transcriptional mechanism driving…
Continue Reading
We're excited to be back for another episode of the Life Sciences Today Podcast by Healthcare IT Today. My guest today is Tiffany Callahan, Lead Architect of Agentic AI Systems at SandboxAQ. As a…
Continue Reading
Remote photoplethysmography (rPPG) offers a non-invasive means of estimating heart rate in telemedicine settings. Yet its reliability remains uncertain due to the limited diversity and ecological validity of existing benchmark datasets. In this work,…
Continue Reading
Vision-language models (VLMs) show promise for answering clinically relevant questions, but their robustness to medical image artefacts remains unclear. We evaluated VLMs’ robustness through their performance on images with and without weak artefacts across…
Continue Reading
Careful selection of skin lesions that require expert evaluation is important for early skin cancer detection. Yet challenges include lack of cost-effective asymptomatic screening, geographical inequality in access to specialty dermatology, and long wait…
Continue Reading
Current AI approaches for cardiac diagnosis require condition-specific supervised learning with extensive labeled datasets, leading to fundamental scalability barriers. We developed an ECG-CLIP model, applying contrastive multimodal learning to enable zero-shot cardiac diagnosis from…
Continue Reading
The complexity and variability of high-resolution pathological images present significant challenges in computational pathology. While AI-driven pathology foundation models have advanced the field, they require large-scale datasets, substantial storage, and significant computational resources, as…
Continue Reading
