256 papers
Health informatics sits at the vibrant intersection of medicine, data science, and technology, transforming how we store, analyze, and utilize health information. This rapidly evolving field empowers clinicians and researchers to uncover patterns in patient data, improve diagnostic accuracy, and personalize treatment plans without getting lost in complex databases. By turning raw medical records into actionable insights, these innovations are reshaping the future of healthcare delivery and population health management.
At Gist.Science, we bridge the gap between cutting-edge research and public understanding by curating the latest preprints from medRxiv specifically within this domain. Our team processes every new submission in this category, providing both accessible plain-language explanations and detailed technical summaries to ensure the science is clear for everyone, from policymakers to curious readers. Below are the latest papers in health informatics, freshly distilled and ready for you to explore.
This study demonstrates that a locally deployed 20-billion parameter LLM, utilizing a sensitivity-enhanced prompting strategy, can significantly accelerate systematic review abstract screening with high accuracy and zero data privacy risks, though its performance varies by domain and is best used as a second screener alongside human experts.
A cross-sectional survey of Traditional, Complementary, and Integrative Medicine journal editors reveals that while they recognize the potential of artificial intelligence to support routine editorial tasks, its actual adoption remains limited due to a lack of institutional policies, training, and ethical guidance.
This qualitative study reveals that cybersecurity professionals view health AI as a fragile, augmented clinical infrastructure where institutional trust is contingent upon visible governance and accountability rather than technical performance alone.
This paper proposes a Deep Image Prior-based framework that integrates anatomical proton MRI and metabolic sodium MRI guidance through fused directional total variation regularization to achieve high-quality, accelerated sodium MRI reconstruction with improved structural fidelity and signal preservation.
This study demonstrates that few-shot prompted large language models can effectively categorize specific types of clinician edits to ambient AI draft notes, achieving strong performance for medication and symptom modifications while identifying complex, context-dependent edits as better suited for human review triage.
The 2025 review of healthcare AI research reveals a near-doubling of publication volume and a significant maturation of the field, characterized by a shift from classical machine learning and text-only models toward the rapid adoption of multimodal foundation models that better reflect the complexity of real-world clinical practice.
This cohort study found that the type of editorial response (retraction, expression of concern, or editorial notice) issued for integrity concerns in randomized controlled trials did not significantly influence subsequent citation rates or accelerate citation decline compared to control trials.
This study presents a governance-driven health informatics framework that leverages real-world longitudinal data to model patient treatment sequencing, persistence, and provider adoption, thereby significantly improving the accuracy of healthcare utilization forecasts for oncology and complex chronic conditions compared to traditional static market-share approaches.
This study evaluates the representational robustness of 15 locally deployable large language models on neurological terminology, revealing that while performance generally scales with model size, neither size nor medical fine-tuning guarantees clinical reliability due to significant variations based on terminological complexity and subdomain.
This study demonstrates that a Nash bargaining-based multi-agent language model framework significantly improves the safety and efficiency of care plans for underserved Medicaid patients compared to a single-model baseline, while highlighting that equity requires explicit design attention rather than emerging automatically from multi-objective optimization.