Science

A new approach combines machine learning with logic-based explanations to build confidence in predicting life-threatening events in patients with Chagas disease.

A new machine learning approach reveals subtle changes in blood flow patterns that can indicate cardiovascular disease and assess the effectiveness of heart support devices.

A new study reveals how blending traditional machine learning with the power of large language models can improve heart disease prediction and offer deeper insights into patient data.

New research reveals that the ways large language models stumble aren’t random, but instead follow predictable patterns within a complex ‘manifold of failure’.

A new AI model accurately simulates global river systems, offering improved forecasting even where data is limited.

A new forecasting system combines the power of traditional weather models with artificial intelligence to deliver more accurate tropical cyclone track predictions.

A new patient-centered system uses artificial intelligence to passively monitor for warning signs of stroke, potentially enabling faster intervention for at-risk individuals.

A new approach leveraging the mathematics of random matrices reveals hidden structures within large language models, offering insights into their behavior and potential for optimization.

A new review explores how artificial intelligence is being integrated into life cycle assessment to improve sustainability efforts.

New research details a robust framework for predicting 5-year breast cancer outcomes by integrating diverse data sources and prioritizing equitable, reliable results.