Deep learning model predicts how individual cells influence disease outcomes

A computational method called scSurv, developed by researchers at Institute of Science Tokyo, links individual cells to patient outcomes using widely available bulk RNA sequencing data. The approach ...

New AI model predicts record high dipole moments in unexpected molecules

Chemists may soon have one less rigorous step to worry about when searching for the right molecules to accomplish their highly specific innovation needs. Scientists have now built a new machine ...
IEEE

CALM: A Copula-Augmented Lightweight Deep Learning Model for Robust Pulmonary Function Assessment from CT Imaging

Abstract: Chronic respiratory diseases (CRDs) are among the leading chronic diseases worldwide and pose a significant threat to public health and life expectancy. Pulmonary dysfunction, a core ...
Science News

AI models spot deepfake images, but people catch fake videos

AI systems are far better than people at spotting deepfake images, but when it comes to deepfake videos, humans may still have the edge. That’s the surprising twist from a new study that pits people ...
Fierce Healthcare

67% of doctors use AI daily in their practice, survey finds

Physicians are already deep into artificial intelligence adoption—67% of doctors use AI tools daily in their practice and nearly 90% use AI at least weekly. Clinicians are using AI daily for writing ...
News Medical

New AI models detect dementia with high accuracy using EEG signals

Researchers at örebro University have developed two new AI models that can analyze the brain's electrical activity and accurately distinguish between healthy individuals and patients with dementia, ...
The New York Times

Deep Beneath Helsinki, the Playgrounds Are Really Bomb Shelters

Finland has spent decades digging caves into its bedrock. Now, as Russia rears its head, nervous Finns want to know: “Where’s my shelter?” Credit... Supported by By Sally McGrane Visuals by Vesa ...
American College of Cardiology

Deep Learning Model Accurately Identifies MV Prolapse From TTEs

A deep learning model accurately identified mitral valve prolapse (MVP) from transthoracic echocardiograms (TTE), and its predictions were associated with clinical endpoints such as mitral ...
chromatographyonline

Developing Deep Learning Models to Identify More Peaks in GC–MS Chromatograms

MASSISTANT predicts molecular structures from GC-EI-MS spectra using SELFIES encoding, overcoming traditional database limitations. SELFIES encoding ensures valid molecular predictions, unlike SMILES, ...
C&EN

Deep Learning-Based Shape Classification for Hyperspectral-Imaged Microplastics

Article subjects are automatically applied from the ACS Subject Taxonomy and describe the scientific concepts and themes of the article. Figure 1 illustrates the overall workflow of the hyperspectral ...
Frontiers

VAE deep learning model with domain adaptation, transfer learning and harmonization for diagnostic classification from multi-site neuroimaging data

The acquisition sites include: CALTECH, California Institute of Technology; CMU, Carnegie Mellon University; KKI, Kennedy Krieger Institute; LEUVEN, University of Leuven; MAX, Ludwig Maximilians ...