AI Medical Compendium

Energy- and Area-Efficient Ionic-Switch Activation Neuron for Monolithic 3D Neural Network Architectures.

ACS nano May 4, 2026

To overcome the bottleneck inherent in the von Neumann architecture and advance hardware-oriented neural network design, this study conceptually proposes a monolithic three-dimensional, vertically integrated neural network architecture that supports ... read more

CypGEM: A Geometry-Aware and Edge-Enhanced Graph Transformer Model for Predicting Sites of Metabolism Mediated by Cytochromes P450.

Journal of chemical information and modeling May 4, 2026

Accurate prediction of a compound's site(s) of metabolism (SoMs) mediated by cytochromes P450 (CYP450) is advantageous in the early stage of drug discovery. However, existing computational methods often struggle to explicitly capture the microscopic ... read more

Machine learning assisted prediction of the compressive response of porous metallic bio-metamaterials.

Computer methods in biomechanics and biomedical engineering May 4, 2026

This study leverages deep feed-forward neural networks (DNNs) to develop a predictive model for estimating the compressive behavior of porous metallic bio-metamaterials based on their geometric and material characteristics. A DNN architecture compris... read more

Protocol for cerebrospinal fluid analysis using enrichment-enhanced surface-enhanced Raman spectroscopy and transformer-enabled spectral classification.

STAR protocols May 4, 2026

The rapid detection and precise classification of cerebrospinal fluid in acute leukemia patients constitute a crucial clinical imperative. Here, we present a protocol for cerebrospinal fluid analysis deep learning with enrichment-enhanced surface-enh... read more

CADS: A Causal Inference Framework for Identifying Essential Genes to Enhance Drug Synergy Prediction.

Bioinformatics (Oxford, England) May 4, 2026

MOTIVATION: Drug synergy is crucial for developing effective combination therapies, but traditional screening methods suffer from inefficiency and high costs. While deep learning shows promise for predicting drug synergy, current approaches using Tra... read more

Neutrophil extracellular traps-related biomarkers in idiopathic pulmonary arterial hypertension: A machine learning-based identification and experimental validation study.

Molecular immunology May 4, 2026

Neutrophil extracellular traps (NETs) are increasingly recognized as critical mediators in vascular inflammation and remodeling, yet their molecular mechanisms in idiopathic pulmonary arterial hypertension (IPAH) pathogenesis remain largely unexplore... read more

High-precision stress prediction using deep energy network enhanced by stress equilibrium with Delaunay integration on refined grid.

Cell reports methods May 4, 2026

We present the deep energy method enhanced by stress equilibrium (DEM-SE), a physics-informed neural network (PINN) architecture for high-precision prediction of complex stress fields in elastic plates. The method calculates total potential energy vi... read more

Development and validation of a risk stratification model for sarcopenia in patients with chronic lung disease: a cross-sectional study based on CHARLS data.

BMJ open respiratory research May 4, 2026

OBJECTIVE: The aim of this study was to develop a machine learning-based stratification model to identify high-risk individuals for sarcopenia among patients with chronic lung disease (CLD), thereby facilitating early personalised management of this ... read more

Multi-omics-based machine learning model predicts response and guides treatment in Crohn disease: a case study in nutritional therapy.

Inflammatory bowel diseases May 4, 2026

BACKGROUND: Biomarkers are needed to predict treatment response and guide therapeutic decisions in Crohn disease (CD). We aimed to develop and validate a multi-omics machine learning (ML) model to predict response to nutritional therapy in pediatric ... read more

3D Freehand Ultrasound Reconstruction of the Carotid Artery.

Ultrasound in medicine & biology May 4, 2026

OBJECTIVE: Sensorless alignment of two-dimensional (2D) freehand ultrasound scans for three-dimensional US (3DUS) reconstruction offers significant advantages due to its ease of use. Prior approaches have used transducers with motion sensors, which a... read more

Artificial Intelligence Medical Compendium