All stories

1289 published stories · page 14 of 86

SportsEvidence-backed gain

‘Like an AI agent’: Wolff hails Antonelli’s Italian GP victory in title charge

Toto Wolff has compared Kimi Antonelli to the greats of Formula One after the Mercedes driver’s remarkable victory at the Italian Grand Prix where he came back to take the flag from 19th place on the grid. The Mercedes team principal cited the win as similar to some of the best made by Lewis Hamilton, the seven-time world champion, and said that Antonelli would likely remember the race as one of the greatest of his career. Antonelli, 20 years old and in only his second season in the sport, delivered an exception…

The Guardian

Evidence-backed problem

Feeling overwhelmed by the AI doom loop? Here’s the essential reading list to make sense of it all

Evidence-backed gain

Rapid patient-specific neural networks for X-ray to volume registration

Evidence-backed gain

How to apply artificial intelligence (AI) to facilitate and enhance MASH trials

Evidence-backed gain

Genolator enables protein function interpretation using a multimodal large language model fusing genomic and structural interpretation with natural language interaction

Background Decoding the genetic code to unveil its genome functionality is a monumental task which would greatly advance the understanding of disease mechanisms and development of targeted treatments. Although large language models (LLMs) have transformed natural language processing across diverse domains, translating the complex language of DNA into human-readable form remains challenging due to genomic data complexity and unexplored regions of the human genome. Current language models either are capable of pro…

Evidence-backed gain

Development and validation of a machine learning clinicogenomic model to improve prognostic stratification in ER-positive/HER2-negative early breast cancer

Background Several gene expression signatures (GESs) are used for risk stratification in estrogen receptor-positive/human epidermal growth factor receptor 2-negative (ER-positive/HER2-negative) early breast cancer. Recent integrative approaches combine tumour proliferation, estrogen receptor signalling, immune activity, and clinicopathologic features, yielding gains in prognostic accuracy. We therefore developed a machine-learning-based clinicogenomic prognostic model integrating a research-grade implementation…

Both readings

Assessing the accuracy and usability of artificial intelligence-based language models in responding to common periodontal patient questions

Background Artificial intelligence-powered large language models (LLMs) are increasingly used by patients seeking quick information regarding dental and medical problems. Despite their growing popularity, concerns remain regarding the accuracy, clarity, and clinical usefulness of LLM-generated responses. This study aimed to comparatively evaluate the accuracy and usability of widely used LLMs in responding to frequently asked periodontal questions. Methods In this analytical-comparative study, 15 commonly asked…

Evidence-backed gain

Deep Learning-Powered Plasmonic Platform for Decoding Dynamic Protein Aggregation Landscapes in Parkinson's Disease Progression

In-depth characterization of pathological protein aggregate with its subcomponents is pivotal for early diagnosis and staging of neurodegenerative disorders. Here, we introduce the Protein Aggregate NanoDynamics Analyzer (PANDA), a plasmonic nanotechnology-powered system that translates the supramolecular size distribution of protein aggregates into distinct scattering signatures via sterically constrained immunogold clustering. In this work, PANDA enabled the profiling of α-synuclein (α-syn) aggregates with div…

Science

Rethinking catalysis: interpretable AI and description of real-world conditions <i>via</i> materials genes

Descriptors link basic physicochemical parameters that characterize the materials and the environment to the catalytic performance. Traditionally, descriptors are rooted in mechanistic understanding of elementary surface reactions gained from surface science and atomistic simulations on well-defined surfaces and under vacuum. However, real-world catalysis operates under elevated pressures and temperatures, where an intricate interplay of multiple physical processes, including significant materials' restructuring…

Health

Development of an Explainable Machine Learning Model for Predicting Reflux Esophagitis Among Candidates for Metabolic Bariatric Surgery

Background Reflux esophagitis (RE) is a common gastroesophageal disorder among candidates for metabolic bariatric surgery (MBS). This study aimed to develop and internally validate an explainable machine learning (ML) model for predicting preoperative RE risk among patients undergoing MBS. Methods This retrospective study included 1,068 MBS candidates who were randomly divided into training and internal test cohorts (7:3). Feature selection was performed using correlation analysis, multicollinearity assessment,…

Health

Why aren't we using AI in eye clinics? A systematic review of barriers and solutions in AI-based fundus image diagnostics for ocular diseases

Artificial intelligence (AI) has shown remarkable accuracy in the diagnosis of common ocular diseases such as diabetic retinopathy (DR), glaucoma, retinopathy of prematurity (ROP), and age-related macular degeneration (AMD), often matching or even outperforming expert clinicians. Despite these advancements, AI adoption in clinical settings remains limited due to key barriers. This systematic review evaluates 34 studies (2018-2025) highlighting AI's diagnostic performance (often >90% accuracy) while pointing out…

Crime

AI models ‘most potent cyber weapon’ ever created: Cohere CEO

Cybersecurity concerns are feeding a broader AI safety debate, with industry leaders calling for measures to slow frontier AI development.

Policy

Europe Proposes a New Test for Big Tech: Prove Children Are Safe by Design

Europe wants child safety built into digital platforms and the biggest providers to prove it. The proposed EU KIDS Act would combine a minimum age of 15 for independent social media accounts with curbs on addictive features and AI companions that create emotional dependency, putting platform design at the heart of online child protection.

Media & Arts

Artists boycotted this portrait prize over AI entries. Now they’re back to take them on

Poised above the lady in the red dress is a claw. Its metallic fingers grasp to pluck its prize from a jumble of other women while she looks dreamily upward, as if to say “Who, me?” The woman in the red dress is Australian comedian Alice Fraser, as photographed on stage. The other women – generic superheroes and 1950s housewives – were created using the generative AI software Krea. “It is the human being chosen over the AI element,” artist Jackie Ryan says. “But is being chosen a good thing?” Ryan’s work The Cat…

Health

Constructing Legal Knowledge Graphs and Tracing Bias in Medical Artificial Intelligence Based on Graph Neural Networks

In medical artificial intelligence (AI) legal compliance analysis, this paper addresses the ambiguity in liability determination caused by the semantic fragmentation of multi-source heterogeneous legal texts and difficulties in tracing algorithmic biases. It constructs a knowledge graph construction and bias propagation path detection method based on graph neural networks. Four types of heterogeneous nodes-legal clauses, medical behaviors, algorithm modules, and responsible parties-are structured and encoded, an…