Papers nuevos sobre IA para ciencia y medicina
187 papers nuevos sobre ia para ciencia y medicina en los últimos 7 días, dentro de IA y aprendizaje automático. Acá están los 50 que Pipette considera más valiosos, con el resultado principal en palabras de sus autores.
Lo mejor de la semana
High-resolution Nitrogen Dioxide Maps Reveal Exposure Limit Breaches across Europe
We reconstruct the daily compliance statistic across those regions and find limit breaches in 91 EU air quality zones deemed compliant by the regulatory monitoring network, covering a population of approximately 135M.
PreprintUso en el mundo realVirtual sensing to enable real-time monitoring of inaccessible locations & unmeasurable parameters
Here we introduce neural operator-based virtual sensing as a general framework for recovering inaccessible interior fields from sparse, heterogeneous measurements and operating conditions, instantiated with MIMONet, a multi-input, multi-output neural operator that fuses heterogeneous inputs and decodes coupled physical fields through a shared latent representation.
Revista con revisión por paresUso en el mundo realMachine learning of honey bee olfactory behavior identifies repellent odorants in free-flying bees in the field
Additional testing of the top seven candidates using freely foraging honey bees in a field assay confirmed strong repellency, thus predicting a high probability to repel foraging bees from pesticide-treated crops.
Revista con revisión por paresUso en el mundo realGenerating protein hydrogels with customizable stress relaxation behavior via deep learning-driven entanglement design
Here, we introduce TangleDiff, a deep learning framework for the de novo design of homodimeric entangled proteins with programmable features.
Revista con revisión por paresUso en el mundo realClimate Variability Modulates the Impact of Price Spikes on Food Insecurity
Integrating remote sensing, socioeconomic data, and causal machine learning, we find that in regions where ENSO systematically suppresses vegetation, a price spike raises the share of the population at acute risk by 5.4 percentage points in the following month.
PreprintUso en el mundo realGenerative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases
AI-designed T-domains support product formation across architectures, enable catalytically active hybrids at recombined junctions, and increase yields by up to ~3-fold relative to NRPSs carrying the native T-domain.
Revista con revisión por paresUso en el mundo realBlind Thermodynamic Ontology Discovery from Anonymous Experiments
We present an operational identifiability theory and a constructive polynomial-time algorithm that extracts extensive and intensive scaling sectors from replication contrasts, recovers their dual cotangent pairing from thermal contact and reciprocity, verifies a globally admissible concave potential via discrete cyclic concavity, and determines an invariant matroid of reservoir ensembles.
PreprintDice ser un gran avanceLow-altitude aircraft will reshape noise exposure across global cities
These findings show that low-altitude aircraft can reshape noise exposure across global cities, requiring route assessment to distinguish newly exposed from already exposed areas and to account for three-dimensional exposure.
PreprintUso en el mundo realReal-time Generalizable Heart Valve Mechanics for Clinical Disease Assessment via a Physics-Conditioned Neural Operator
Trained on functional, regurgitated, and pathological valves, including tethering, P2 prolapse, and annular dilation, PCNO achieves up to a 15,260x speedup over fine mesh finite element simulations with comparable accuracy, identifies pathology class, and resolves diagnostic metrics within 3.5% error under out-of-distribution extrapolation.
PreprintAfirmaciones fuertes, leer con cuidadoUso en el mundo realMultiplexed deep visual proteomics resolves spatial heterogeneity and rare endocrine states in human pancreatic islets
Applied to human pancreatic islets, mxDVP segments over 860,000 cells and resolves twelve endocrine subtypes, including rare polyhormonal and intermediate-state populations that exhibit spatial organization patterns, co-expression of INSM1 and SCG3, and hybrid α/β/δ signatures.
Revista con revisión por paresFrom greenhouse climate to individual leaves: an organ-resolved model of lettuce growth
A unified framework was developed to simulate lettuce growth from the physiology of individual leaves.
PreprintUso en el mundo realDiscovering Physical Representation Languages
We give an identifiability theory and constructive polynomial-time procedure that recovers a carrier and differential sequence, measurement types and orientation twist, noninvertible refinement semantics, primal-dual Maxwell diagrams, and the residual equivalences that no permitted experiment can break.
PreprintAfirmaciones fuertes, leer con cuidadoDice ser un gran avanceSparse Identification for Automatic Large-Scale Screening: A Constraint-Aware Framework with Ultra Fast Decoding Algorithm
In this article, we propose the Logic Screening method (LoSc), an ultra fast, accurate, and theoretically grounded framework for large-scale screening.
PreprintAfirmaciones fuertes, leer con cuidadoUso en el mundo realDeep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria
Our model robustly classifies MoAs of established antibiotics and recognizes the MoA of previously unseen antibiotics.
Revista con revisión por paresUso en el mundo realThe Entropy Triangle Method (ETM): A novel framework for the prevention of cardiac arrhythmia with a review of more than 10,000 patients
In this article, we introduce two firsts in machine learning and medicine that can predict non-sinus rhythm with over 85% accuracy.
PreprintAfirmaciones fuertes, leer con cuidadoDice ser un gran avanceUso en el mundo realOn Growth and Form, and Function: Reusable Regulatory Handles Control Phenotypic Variation
Together, our results provide a computational realization of D'Arcy Thompson's remarkable grid transformations in a 2D NCA---a minimal cybernetic tissue in which variations of fully grown emoji phenotypes can be encoded, combined, and controlled through low-dimensional directions in regulatory weight space.
PreprintAfirmaciones fuertes, leer con cuidadoCredit Access is Associated with Improved Food Security in the Horn of Africa
Results indicate that greater credit access is associated with a 2% reduction in acute food insecurity at the population level over the study period.
PreprintUso en el mundo realCLEAR: Complex Learned Explicit Analytical Regularization for Ultra-Accelerated 4D Flow CMR Reconstruction
In the ultra-accelerated \(10\times\)--\(50\times\) regime of the CMRx4DFlow2026 challenge, CLEAR outperforms compressed sensing locally low-rank (LLR) and the popular variational network FlowVN, while using less than 10k parameters and preserving an interpretable regularization structure.
PreprintAfirmaciones fuertes, leer con cuidadoDice ser un gran avanceUso en el mundo realDecomposing Error and Style in Automated Clinical Coding
Much of what single-gold evaluation charges to model error is recoverable, unmodeled style.
PreprintUso en el mundo realDesign of white circularly polarized luminescence with high glum across entire visible regions by dual-loop active learning
High-performance WCPL materials with excellent |glum | (>1.5) range of 410 to 680 nm, high CRI ( > 90) at ideal CIE coordinates (0.33, 0.33) can simultaneously be achieved with limited experimental date.
Revista con revisión por paresAfirmaciones fuertes, leer con cuidadoUso en el mundo realTRACE: Tractable Routing Autoencoder for Clinical ECG
On PTB-XL and Georgia, TRACE exceeds unconstrained classifiers and stays ahead of an ECG foundation model pretrained on ten million recordings, evaluated by linear probe on frozen features, at roughly an eighth of the parameter count.
PreprintUso en el mundo realGenVoid: Uncertainty-Aware Learning of Subsurface Material Defects with an Experimentally Validated Physics-Informed Generative Model
Here we introduce GenVoid, a physics-informed generative model-based framework for identifying internal voids in complex two- and three-dimensional solids from surface displacement measurements alone.
PreprintUso en el mundo realPersonalized single-cell transcriptomics reveals molecular diversity in Alzheimer’s disease
Personalized functional genomics atlas for Alzheimer’s disease that uses knowledge-guided graph neural networks to analyze donor-level functional genomics, identify disease subpopulations and trajectories, and link genetic variants to gene regulation.
Revista con revisión por paresNeural Transport Nested Sampling
We develop a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods.
PreprintDice ser un gran avanceDiscovering how ice crystals grow using neural ODEs and symbolic regression
By optimizing against mass growth time series from 290 ice crystals grown in a levitation diffusion chamber, we identify a modified capacitance growth model that more accurately captures observed early-stage growth.
Revista con revisión por paresDeep learning of longitudinal visual fields predicts glaucoma progression rate and identifies fast progressors
On the open-access University of Washington Humphrey Visual Field dataset (4,276 patient-eyes), GLAM achieved an MD-rate mean absolute error of 0.139 dB yr (; 73.5% reduction over a ridge baseline) and an AUC of 0.990 for fast-progressor detection.
PreprintUso en el mundo realBeyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers
Collectively, these interventions reduce long-rollout error by approximately 40% and match or exceed the accuracy of full-resolution models on two physics benchmarks, while requiring 2 orders of magnitude fewer floating point operations and half the GPU memory.
PreprintReal-Time Atomic-Resolution Electron Phase Imaging without Probe Calibration via Ptychography-Supervised Learning
The approach amortizes ptychographic redundancy into a fast, generalizable workflow that enables real-time atomic-scale phase imaging for materials microscopy.
PreprintAfirmaciones fuertes, leer con cuidadoDice ser un gran avanceAn Accurate and Interpretable Hyper Graph Neural Network for GBM Survival Prediction
We propose a multi-modal framework that inte- grates three components to address both objectives simultaneously: (1) a sheaf hypergraph neural network that captures higher-order relationships among tissue patches through direc- tional, asymmetric message passing; (2) a concept bottleneck layer that compresses learned representations into clinically grounded concepts, enforcing ante-hoc interpretability; and (3) an extension sufficiency test (EST) regularizer that penalizes unfaithful explanations during training, ensuring that model explanations genuinely reflect the internal decision process.
PreprintAfirmaciones fuertes, leer con cuidadoUso en el mundo realTool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks
Together, OmicsBench and TA-OPD provide a framework for diagnosing reasoning failures in multi-omics LLMs and a path toward models whose predictions are better grounded in biologically meaningful evidence.
PreprintLearning to Defer with Guidance on Real World Medical Data
Our results show that two-stage L2D with Guidance outperforms classic two-stage learning to defer, as well as human-alone, AI-alone and AI-guided human baselines.
PreprintUso en el mundo realPhysics-residual machine learning predicts oxygen-evolution catalyst activity beyond the training range from sparse polarization measurements
In a separately fabricated 322-candidate library, 282 above the training maximum, two measurements per candidate gave a mean absolute error of 0.203 mA cm against 1.330 for the selected data-driven machine-learning model.
PreprintUso en el mundo realLong-range interdependencies aware signal analysis for rapid and accurate obstructive sleep apnea prediction
The method achieves robust and consistent performance, with area-under-the-curve values exceeding 0.91 and improvements of 8–18% over state-of-the-art models.
Revista con revisión por paresUso en el mundo realLearning 3D biophysical cell properties from 2D images and cell-population statistics
Here we develop a population-supervised framework that maps single 2D red-cell images to latent biophysical quantities and aggregates them to mean corpuscular volume, red-cell distribution width and mean corpuscular haemoglobin.
PreprintUso en el mundo realArtificial intelligence surrogates for treatment effect estimation with before-and-after data
To this end, we develop a framework for estimating treatment effects from paired measurements obtained before and after treatment for each treated individual.
PreprintUso en el mundo realTransferable Evidence Reconstruction for Longitudinal Glucose Representations
We introduce transferable evidence reconstruction (TER), which constructs evidence from unlabeled recordings, fits a fresh low-capacity reader on one recording group, and requires that reader to recover the same evidence in another group without refitting.
PreprintUso en el mundo realShadow Reduction in Ultrasound Imaging Using Differentiable Simulation and Radiance Field Decomposition
We present RFlash, a physics-informed post-processing method that decomposes beamformed ultrasound images into explicit attenuation and scatter-intensity maps using a differentiable radiance-field formulation of image formation.
PreprintUso en el mundo realUpTCR: a unified progressive knowledge transfer foundation model for robust T-cell receptor-antigen binding recognition
Here, we present UpTCR, a unified progressive knowledge-transfer foundation model that learns from incomplete data to predict TCR-antigen-HLA binding.
Revista con revisión por paresUso en el mundo realThe Neural Forcing for Three-Dimensional Incompressible Navier-Stokes finite time blowup
It separates neural candidate discovery from continuum analysis, derives integrated reciprocal-vorticity criteria that imply Riccati-type growth and finite-time loss of smooth continuation, develops a validated computational-to-continuum transfer strategy, and establishes a conditional positive-probability closure for a nondegenerate neural output law.
PreprintAfirmaciones fuertes, leer con cuidadoDice ser un gran avanceSynSeq: End-to-End SYNTAX Score Prediction from Coronary Angiography Videos
Evaluated on the public CardioSyntax dataset, SynSeq significantly outperforms previous state-of-the-art methods, improving by 0.55, reducing prediction bias by 93.1% and achieving more consistent performance across annotations from three independent expert graders.
PreprintUso en el mundo realCódigo disponibleBenchmarking Off-the-Shelf Multimodal AI Models Against Dermatologists on Patient-Captured Skin Images
We evaluate AI performance relative to a panel of three certified dermatologists, who grade each image, and we present four interesting findings.
PreprintUso en el mundo realFácil de leerLearning Cardiac Features: ECG Biometrics Across Time and~Exercise
This first extensive assessment of ECG biometrics under combined physiological and temporal variability achieves an intra-session rest-to-peak EER of 1.7% and stateof-the-art 3.9% on the CYBHi dataset.
Preprint con versión publicadaUso en el mundo realPredicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information
The proposed model outperforms existing PPGR baselines using image-derived nutritional inputs and approaches the performance of methods that rely on manually reported macronutrients despite using automatically estimated nutritional information.
PreprintUso en el mundo realScalable molecular representations enabled by multimodal fusion and sequence distillation
This study integrates six complementary molecular representations into a distilled molecular string embedding, enabling scalable property prediction and prioritization of compounds that reduce DNA-damage phenotypes in yeast.
Revista con revisión por paresUso en el mundo realA Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits
In a retrospective evaluation conditioned on recorded future exposures, the model forecasts the remaining new-to-brand prescription volume through week 52 with a relative error of 2.9% from a week-4 cutoff and 0.8--2.6% from cutoffs at weeks 8--26.
PreprintUso en el mundo realTargeted Review for AI-Assisted Biodiversity Surveys: Active Continuous-Score Occupancy Modeling
We introduce Active Continuous-Score Occupancy Modeling (ACORN), a method that incorporates ML predictions into occupancy models and strategically selects samples for expert review that are maximally informative for downstream ecological analysis.
PreprintUso en el mundo realCódigo disponibleHapi: A Multivariable Land-Surface Transformer for Medium-Range Hydrological Forecasting at Continental Scale
On 2024 test data using reconstructed weather and land-surface inputs from ERA5-Land, Hapi outperformed an operational physics-based model and a state-of-the-art AI model in flood detection.
PreprintUso en el mundo realImage-Derived PM10 Estimation in Cattle Feedlot Using Machine Learning: Addressing Concentration Ranges Beyond Existing Digital Imaging Methods
These findings demonstrate the feasibility of image-based PM10 estimation across PM concentration ranges substantially exceeding those reported in prior urban studies and provide practical guidelines for future deployment in feedlot environments.
PreprintUso en el mundo realOptical microscopy predictions of focal recurrence in glioblastoma
We present an artificial intelligence (AI)–based model to predict the recurrence risk of unprocessed surgical tissues at initial resection.
Revista con revisión por paresAfirmaciones fuertes, leer con cuidadoUso en el mundo realEnSol: an environment-aware graph neural network for molecular solubility prediction
Here, we introduce EnSol, an environment-aware probabilistic framework for molecular solubility prediction.
PreprintUso en el mundo real