Latest AI and machine learning research in clinical trials for healthcare professionals.
Lower-grade gliomas (World Health Organization [WHO] grades 2-3) exhibit variable treatment responses, yet clinical decisions remain guided by population-level trial results. Standard causal survival forests estimate treatment effects at individual time horizons but lack methodology to synthesize these into interpretable temporal trajectories. Here, we apply the Causal Analysis of Survival Traject...
Immune-related adverse events (irAEs) affect up to 40% of patients receiving immune checkpoint inhibitors, yet their identification depends on laborious and inconsistent manual chart review. Here we developed and evaluated an agentic large language model system to extract the presence, temporality, severity grade, attribution, and certainty of six irAE types from clinical notes. Retrospectively (2...
Background: Sepsis remains a leading cause of preventable hospital mortality in England, with NHS England reporting over 48,000 sepsis-related deaths ...
Artificial intelligence (AI), particularly large language models (LLMs), is increasingly explored in healthcare, yet its real-world usability and safe...
Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must co...
Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critica...
Medical oncology education faces a dual crisis: knowledge velocity that outpaces static curricula and large language model (LLM) risks hallucination a...
Background Clinicians in care management programs are often in low supply relative to patient demand, especially in US Medicaid programs, and must sim...
Introduction: Deep learning-based segmentation models are increasingly integrated into clinical imaging workflows, yet their robustness to adversarial...
Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety conc...
Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributio...
Background: Diagnostic errors are a leading cause of preventable patient harm, often occurring during early clinical encounters where diagnostic uncer...
Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety conc...
Standard Test-Time Adaptation (TTA) methods typically treat inference as a blind optimization task, applying generic objectives to all or filtered tes...
Background: EHR documentation and chart review contribute to clinician workload and burnout. To alleviate pre-charting burden, Epic has released a new...
Objective: Electronic Health Record (EHR)-based trial emulation can support translation of randomized clinical trial (RCT) evidence into practice, yet...
Antisense oligonucleotides (ASOs) are a promising class of therapeutic agents capable of selectively modulating gene expression and treating a wide ra...
Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and he...
Background: Large language models show promise for clinical decision support, yet their propensity for hallucination--generating plausible but unsuppo...
Autism Spectrum Disorder (ASD) is a heterogenous condition that has no biologically relevant subtypes yet. Here, we utilized a multidimensional approa...