DailyHealthcareAI
@aipulserx
Sharing research papers and news on AI applications in radiology, pathology, genetics, protein design and many more. Let's learn together!
📎📢ICML WORKSHOP 2025 1. 2nd Generative AI for Biology Workshop(icml.cc/virtual/2025/w…) 2. Workshop on Multi-modal Foundation Models and Large Language Models for Life Sciences(icml.cc/virtual/2025/w…)
For years I have dreamt of a tool that could neutralize pathogens the moment they emerge. Today we unveil ApexOracle—an AI that, from a pathogen’s genome and phenotypic knowledge alone, predicts which antibiotics will work and invents new molecules for threats it has never seen.…
📣 Excited to share our real-world study of an LLM clinical copilot, a collab between @OpenAI and @PendaHealth. Across 39,849 live patient visits, clinicians with AI had a 16% relative reduction in diagnostic errors and a 13% reduction in treatment errors vs. those without. 🧵
Can foundation models truly decode single-cell biology, or do they fall short of learning generalizable cellular representations?@biorxivpreprint @tudresden_de "Counterfactual Diffusion Models for Interpretable Morphology-based Explanations of Artificial Intelligence Models in…

Can large language models generate reliable scientific content, or do they subtly drift from factual accuracy?@NatMachIntell @UniOfSurrey "Bioinspired trajectory modulation for effective slip control in robot manipulation" 1. Language models are increasingly used for…


Can protein language models trained on sequence data alone predict mutation effects with accuracy comparable to lab experiments?@NatMachIntell @uniklinik_hd "Unifying multi-sample network inference from prior knowledge and omics data with CORNETO" 1. Despite the vast space of…


Can deep learning unravel the complex interplay between genes, tissue images, and cancer outcomes?@NatMachIntell @EMBLHeidelberg "Integrating multimodal cancer data using deep latent variable path modelling" 1. Cancer arises from highly complex interactions among genetic,…


How do specific neuronal subtypes in the human dorsal striatum influence motor behavior and disease states?@NatureCVR @Yale "Identification of hypertrophic cardiomyopathy on electrocardiographic images with deep learning" 1. The human dorsal striatum, essential for movement…

Can machine learning models applied to large-scale genomic data uncover novel genetic risk factors for Alzheimer's disease that traditional linear models miss?@NatureComms @cardiffuni "Machine learning in Alzheimer’s disease genetics" 1. To overcome the limitations of linear…

How can we uncover and measure the specific visual cues that AI models use to predict sensitive patient information like race and sex from medical images, a task even expert physicians find difficult?@medrxivpreprint @StanfordMed @UW "DREAM: A framework for discovering…

How can the accuracy and accessibility of a leading splice-site prediction tool be improved for broader genomic research across different species?@eLife @johnhopkinsuni "OpenSpliceAI: An efficient, modular implementation of SpliceAI enabling easy retraining on non-human species"…

Curious about how neural "noise" evolves as we grow, and how it might shape memory and cognition?@NatureHumBehav @NorthwesternU "The development of aperiodic neural activity in the human brain" 1. The human brain matures over decades, yet how region-specific aperiodic…


How can natural language interfaces democratize access to powerful AI protein design tools for scientists without computational expertise?@tamarindbio @ProjectBiomni "Tamarind Bio X Biomni: Towards an AI Protein Designer" • Molecular design using AI models like AlphaFold and…

How can researchers identify effective drug combinations to treat Alzheimer's disease by targeting different brain cell types simultaneously?@CellCellPress @UCSF_BCHSI "Cell-type-directed network-correcting combination therapy for Alzheimer’s disease" • Alzheimer's disease…

Can deep brain stimulation targeting specific thalamic regions and neural pathways effectively restore consciousness in patients with severe brain injuries?@MassGenBrigham @NatureComms "A human brain network linked to restoration of consciousness after deep brain stimulation"…

Can artificial intelligence bridge the gap between human intentions and biomolecular design to revolutionize drug discovery and enzyme engineering?@NatMachIntell "Advancing biomolecular understanding and design following human instructions" • Recent AI breakthroughs like…


Can machine learning models that integrate behavioral theory truly outperform pure data-driven approaches in predicting human decision-making under uncertainty?@NatureHumBehav @TechnionLive "Predicting human decisions with behavioural theories and machine learning" •…

How can deep learning revolutionize the identification of solenoid proteins in the vast landscape of structural biology?@imperialcollege @OUPAcademic "SOLeNNoID: A Deep Learning Pipeline For Solenoid Residue Detection in Protein Structures" • Solenoid proteins represent a…

How can machine learning leverage transcript colocalization patterns to simultaneously segment cells and predict their types in spatial transcriptomics data without relying heavily on traditional cell staining images?@NatureComms @Mila_Quebec @uofcincy "Bering: joint cell…
