All stories

1288 published stories · page 3 of 86

ClimateBoth readings

Making scents: could AI help perfumers take pressure off endangered plants?

Many of the world’s most expensive perfumes begin with a wounded tree. When some Aquilaria trees are damaged, they produce a dark, fragrant resin that becomes agarwood, or oudh – an ingredient so valuable that wild trees have been illegally felled in its pursuit. The result has devastated wild Aquilaria populations. But what if perfumers could create the smell without cutting down the tree? With the help of AI, scientists are learning to predict how molecules that have never been made will smell, reconstructing…

The Guardian

Both readings

Generative AI and misinformation: a scoping review of the role of generative AI in the generation, detection, mitigation, and impact of misinformation

Evidence-backed gain

Machine Learning and Statistical Models for Genomic Selection of Phytophthora Fruit Rot Resistance in Watermelon

Both readings

Engineering smart polymeric lipid nanoparticles for breast cancer: The convergence of AI and medical personalization to enhance efficacy and safety

Both readings

Unfolding new horizons: Machine learning applications for pediatric intussusception - A systematic review and meta-analysis

Background Pediatric intussusception is among the most common surgical emergencies in early childhood. Ultrasonography is the diagnostic standard but remains operator-dependent, and no validated machine learning (ML) tools exist for triage or prognostic stratification. We systematically evaluated ML models for diagnosis and prognosis of pediatric intussusception. Methods This PROSPERO-registered systematic review and meta-analysis (CRD420251073590) included studies evaluating ML models for pediatric intussuscept…

Both readings

Guideline-augmented prompting improves comparative preference and response consistency of large language model outputs for orthopaedic anaesthesia questions: A controlled prompting study

Purpose Large language models (LLMs) are increasingly used in clinical contexts; however, performance in complex perioperative decision-making remains uncertain. Orthopaedic anaesthesia presents a demanding test case due to comorbidity burden and guideline-dependent management. Whether successive LLM generations and guideline-augmented prompting improve clinical alignment, comparative performance and response consistency was evaluated in this study. Methods In this controlled prompting study, 34 orthopaedic anae…

Evidence-backed gain

A Multiparametric in vitro Strategy for Small Molecule Drug-Induced Liver Injury Risk Mitigation in Early Drug Development

Drug-induced liver injury (DILI) remains a major cause of preclinical and clinical attrition, reflecting persistent gaps in the predictive translation of preclinical safety data to human outcomes. To address these gaps, we established a refined multiparametric framework for early DILI risk prediction using a balanced reference set of 170 drugs with established clinical outcomes. Thirty physicochemical, mechanistic endpoints and exposure-related features were systematically evaluated to identify high-specificity…

Evidence-backed problem

The Serial Mediating Roles of Repetitive Negative Thinking and Future Anxiety Between AI Competence Anxiety and Sleep Disturbance

Although artificial intelligence technologies are rapidly becoming widespread, the potential psychological risks associated with these technologies have not yet been sufficiently understood. Considering the expanding areas of use of artificial intelligence tools, examining the potential risk factors that may emerge from these technologies is considered important. Accordingly, the present study investigated the serial mediating roles of repetitive negative thinking (RNT) and future anxiety in the relationship bet…

Health

Using interpretable machine learning models to predict the occurrence of severe influenza in hospitalized children: a retrospective cohort study

Influenza, a prevalent disease, significantly threatens public health. Accurately predicting severe influenza occurrences is crucial for developing personalized prevention strategies and treatment plans. This study aimed to construct a highly interpretable model to assess the risk of severe influenza in hospitalized children, using the SHapley Additive exPlanation (SHAP) method to interpret the Random Forest (RF) model and identify risk factors for severe influenza. A retrospective cohort study was conducted, co…

Health

Development and Nationwide Multicentre Evaluation of Guideline-Grounded Large Language Model Chatbots to Support Patient Self-Management and Education in Rheumatology

Patients with rheumatic diseases have persistent information needs that are not fully addressed in routine care. We developed and evaluated guideline-grounded, large language model (LLM) chatbots to support patient self-management and education in rheumatology.Ten disease-specific chatbots based on German guidelines were co-developed and deployed through 13 rheumatology centres and six patient organisations. Chatbot users rated responses and completed a questionnaire. User questions, feedback, and response chara…

Health

Slice-Wise Quality Assessment of High b Value Breast DWI via Deep Learning-Based Artifact Detection

Diffusion-weighted imaging (DWI) can support lesion detection and characterization in breast MRI. Therefore, DWI is increasingly being incorporated into breast MRI protocols to address some of the shortcomings of routine clinical breast MRI. However, especially high b value DWI can be prone to intensity artifacts that can affect diagnostic image assessment. To detect hyper- and hypointense artifacts on high b value DWI (b = 1500 s/mm2) using deep learning, employing either a binary classification (artifact prese…

Media & Arts

Norway floats temporary but total ban on AI glasses as it investigates 'socially beneficial uses'

Officials want a temporary ban as smart glasses make it easier to photograph, film and record people without their knowledge.

Media & Arts

Sony reportedly demanded music platforms take down over 260,000 AI deepfake tracks.

According to the Financial Times, that’s nearly double the 135,000 takedown requests Sony Music had previously sent for AI tracks imitating its artists, like Harry Styles, Adele, and Britney Spears. Over the past year, Sony has also filed lawsuits against AI music platforms like Suno and Udio over copyright infringement. [Link: Sony Music steps up fight against streaming fraud | https://www.ft.com/content/51aed058-f8e0-4426-b92a-790b7863d350 | Financial Times]

Media & Arts

OpenAI has ‘work to do to rebuild trust’ in Australia, executive tells AI inquiry

OpenAI has used an appearance before a parliamentary inquiry on AI to apologise again to Australia about the hack on Medicare last month, as media and entertainment organisations argued weakening copyright law for AI model training would leave artists as “roadkill”. Meanwhile Anthropic told the inquiry it was not seeking to dictate copyright law on model training, but the current rules made it “impossible” to train AI in Australia. Tuesday morning’s hearing of the joint parliamentary inquiry on artificial intell…

Health

ChatGPT Health and ChatGPT Plus in Urogynecology: A Blinded Comparison of Response Quality, Guideline Concordance, and Safety

Introduction and hypothesis ChatGPT Health is a health-focused conversational artificial intelligence (AI) environment, but its performance in patient-oriented urogynecology has not been directly compared with standard ChatGPT using both validated quality assessment and objective guideline-based criteria. We hypothesized that ChatGPT Health would provide higher patient-facing response quality while maintaining comparable guideline concordance and safety. Methods Twenty-four guideline-informed patient queries cov…