We also have X and podcasts
Daily AI medical research digest in English
A new study comparing large language models with traditional machine learning reveals that while LLMs show promise for predicting bone cement leakage after spine surgery, they fall short for more complex complications and lack clinical readiness. Original paper: Comparative performance…
A new vision transformer framework eliminates cross-platform PET imaging biases, enabling consistent diagnostic standards across different scanner types and manufacturers—a critical breakthrough for neurodegenerative disease assessment. Original paper: A unified deep learning framework for cross-platform harmonization of multi-tracer PET quantification…
Analyzing eye movements during reading could be the answer to objectively identifying depression and suicidal ideation in young adults — a measurable alternative to the subjective screening we rely on today. Original paper: Deep learning characterizes depression and suicidal ideation…
A transformer-based deep learning model called KongMing predicts visual and anatomical outcomes of anti-VEGF therapy in neovascular AMD patients—outperforming experienced ophthalmologists across all accuracy metrics. Original paper: Development and validation of a deep learning model to predict visual and anatomical…
Groundbreaking AI research shows how fine particulate matter (PM2.5) increases SARS-CoV-2 infection risk through a molecular pathway controlled by the NPC1 gene—finally explaining why COVID-19 hits populations in polluted areas so much harder. Original paper: AI-guided multi-omics analysis identifies NPC1-modulated…
A new study reveals how genetic differences in patient neurons shape brain structure and cognitive symptoms in schizophrenia—establishing a mechanistic link between cellular dysfunction and the clinical reality patients experience. Original paper: Bridging the Scales via Personalized Cellular Modeling and…
Researchers discovered two distinct brain-based subtypes of Internet Gaming Disorder risk linked to specific brain connectivity patterns related to impulsivity. Here’s what matters: over two years, high-risk youth developed IGD at 23.61% versus just 6.76% in low-risk peers. That gap…
A machine learning model can predict how sepsis will unfold in individual patients—and alert clinicians a median 17.6 hours before deterioration strikes. That advance warning makes personalized, proactive interventions possible. Original paper: Machine learning predicts sepsis deterioration trajectories. — NPJ…
A multisite study of 8,581 clinicians shows that AI-powered clinical scribes reduce documentation burden by 10% and increase patient visits by 1.7%, with outsized benefits for primary care and female physicians. Original paper: Changes in Clinician Time Expenditure and Visit…
Machine learning analysis of over 70,000 suicide death narratives uncovers substantially more mental health dysfunction than standard diagnostic tools catch—and the pattern is especially striking in women and younger people. What emerges could fundamentally reshape suicide prevention strategies. Original paper:…
