Assessing the suitability of generative AI for literature retrieval
Peer-Reviewed Publication
Updates every hour. Last Updated: 18-Jul-2025 11:11 ET (18-Jul-2025 15:11 GMT/UTC)
This study assesses the accuracy of ChatGPT in conducting literature reviews by prompting the AI tool to find relevant articles based on established criteria from published systematic reviews. The findings reveal a concerning rate of inaccurate citations, highlighting the limitations of current generative AI in healthcare research and emphasizing the need for human oversight to ensure accuracy and reliability.
This study investigates the effectiveness of China’s Urgently Needed Overseas Drug (UNOD) policy, which aims to expedite access to innovative drugs for patients with unmet medical needs. Analyzing data from 2012 to 2019, the research reveals that the UNOD designation did not significantly reduce launch delays for new drugs compared to the United States. This finding suggests a potential overlap in benefits with other existing policies, undermining the intended prioritization of UNOD drugs.
This study highlights China's rapid development in pharmacoeconomics over two decades, driven by policy reforms, centralized drug procurement, and innovative pricing strategies. Despite progress, gaps remain in adopting global practices like real-world evidence and AI applications. China's drug price negotiations achieved a 60% average reduction, improving medication accessibility while balancing innovation and affordability.
The article conducts an in-depth analysis of the history, key indicators and difffculties of water ecological assessments in typical countries and organization around the world. It points out the significance of water ecological assessments , and provides future implications for advancing water ecological assessment practices. Research indicates significant progresses have been made in the study and application of water ecological assessments globally. The study highlights the key to effective water ecological assessments lies in establishing a comprehensive and scientifically robust indicator system. Over time, water ecological assessments have gradually shifted from relying on single water quality metrics to adopting holistic ecosystem health assessments. The research proposes that future water ecological assessments should integrate the management of water resources, water ecology, and water environment. It improves the management of water environment in key river basins, and establishes a new framework for systematic governance.
Chinese scientists have discovered that fragile swamp forests in the Pearl River Delta (PRD) region suddenly collapsed around 2.1 thousand years ago (ka)—with human activity as the cause.
A new review paper in Engineering delves into silicon carbide (SiC)-based pressure sensors. SiC, a third-generation semiconductor, shows great potential for high-temperature applications. The report covers SiC’s material properties, key technologies in sensor development like piezoresistive effect, ohmic contact, etching, and packaging, along with future research directions.
In the realm of smart manufacturing and digital engineering, a new technology named Data-Model Fusion (DMF) is gaining traction. A review paper in Engineering details how DMF integrates model-based and data-driven methods, addresses their limitations, and finds applications across the product lifecycle. It also explores DMF’s future directions, showing its potential to reshape industrial processes.
In a recent study published in Engineering, researchers from Xi’an Jiaotong University have developed a self-adaptive core-shell dry adhesive with a “live core”. This new adhesive addresses the long-standing issue of weak adhesion under non-parallel contact in engineering operations, offering improved performance and potential applications in various fields such as robotic gripping and optical component assembly.