Generative artificial intelligence (AI) models can create entirely new text and images, offering a new avenue for efficient fashion design. Understanding how to integrate ChatGPT and AI image generators like DALL-E 3 effectively into creative fashion design is important. Recently, researchers explored the use of DALL-E 3 to visualize fashion trends according to season and generate new fashion collections. The study highlights how AI can be improved for successful fashion design implementation.

Scientists have used AI to re-analyse a clinical trial for an Alzheimer’s medicine, and identified a group of patients who responded to treatment. The work demonstrates that AI can inform the design of future clinical trials to make them more effective and efficient, accelerating the search for new medicines.

Researchers have created an alloy that maintains its special ability to act as a sort of temperature-activated memory foam at temperatures as low as -200°C – making it highly suitable for space equipment regularly exposed to these challenging, cold environments.

This review summarizes recent advances in wind speed forecasting using artificial intelligence. It systematically analyzes multi-scale signal decomposition methods and intelligent model fusion strategies, highlighting their effectiveness in addressing the challenges of nonstationary and multiscale wind data. By identifying key methodological patterns and gaps, the review offers actionable insights for designing more accurate, efficient, and robust AI-based wind forecasting systems.

Objective

Deep venous thrombosis (DVT), a potentially life-threatening condition with a high clinical incidence, represents a significant healthcare burden in China. This study aims to investigate the prevalence of protein C (PROC) p.Lys193del mutation and promoter polymorphisms in patients with DVT in Shanghai, China.

Methods

A total of 180 patients diagnosed with DVT and 103 healthy controls underwent polymerase chain reaction amplification targeting two specific regions of the PROC gene for genetic analysis of the p.Lys193del mutation and promoter polymorphisms.

Results

The p.Lys193del mutation was significantly more prevalent in the DVT group, with 13 carriers identified (7.2​%, 13/180), compared to only one carrier in the control group (0.97%, 1/103; P<0.05). Genetic analysis of PROC promoter polymorphisms revealed distinct allele distribution patterns between the groups, with significantly different frequencies for the −1654 ​C,−1641 ​G and −1476 ​T alleles in DVT group versus control group (P<0.05). Corresponding genotype analysis showed significant intergroup differences in the three homozygous variants: −1654C/C, −1641G/G and −1476T/T, all of which exhibited significantly higher frequencies in the DVT group compared to control group (11.1% vs. 1.9%, P<0.01).

Conclusions

The PROC p.Lys193del mutation, an established genetic risk factor for DVT, accounts for about 7.2% of DVT cases. Furthermore, three promoter polymorphisms (−1654C/C, −1641G/G, −1476T/T) were present as homozygous genotypes in 6.1% (11/180) of DVT group, demonstrating statistically significant association with thrombotic risk compared to healthy controls (P<0.05). These findings position both the p.Lys193del mutation and the promoter haplotype variants as independent genetic risk factors for venous thromboembolism in the studied population.

Radiopharmaceuticals have become indispensable tools in precision medicine, revolutionizing diagnostic imaging and targeted therapeutic strategies. This manuscript provides an overview of advancements globally and in China, focusing on the classification and clinical applications of radiopharmaceuticals, particularly in oncology and neurology. Recent progress includes PET/SPECT diagnostic agents and therapeutic radionuclides that provide precise treatment while limiting damage to healthy tissues. Emerging technologies, such as artificial intelligence, novel ligands, advanced radionuclides, and combination therapies, present promising avenues to further enhance the efficacy and accessibility of the field. Despite these achievements, challenges remain in production, regulatory, and costs, underscoring the need for ongoing innovation and international collaboration to fully realize the potential of radiopharmaceuticals in personalized healthcare and optimize patient outcomes.

At the forefront of discovery, where cutting-edge scientific questions are tackled, we often don’t have much data. Conversely, successful machine learning (ML) tends to rely on large, high quality data sets for training. So how can researchers harness AI effectively to support their investigations? Published in Physical Review Research, scientists describe an approach for working with ML to tackle complex questions in condensed matter physics. Their method tackles hard problems which were previously unsolvable by physicist simulations or by ML algorithms alone.