Using simulated patients to mimic 9 established noncommunicable and infectious diseases, we assessed ChatGPT\'s performance in treatment recommendations for common diseases in low- and middle-income countries. ChatGPT had a high level of accuracy in both correct diagnoses (20/27, 74%) and medication prescriptions (22/27, 82%) but a concerning level of unnecessary or harmful medications (23/27, 85%) even with correct diagnoses. ChatGPT performed better in managing noncommunicable diseases than infectious ones. These results highlight the need for cautious AI integration in health care systems to ensure quality and safety.

暂无摘要。

Generative AI tools exemplified by ChatGPT are becoming a new reality. This study is motivated by the premise that \"AI generated content may exhibit a distinctive behavior that can be separated from scientific articles\". In this study, we show how articles can be generated using means of prompt engineering for various diseases and conditions. We then show how we tested this premise in two phases and prove its validity. Subsequently, we introduce xFakeSci, a novel learning algorithm, that is capable of distinguishing ChatGPT-generated articles from publications produced by scientists. The algorithm is trained using network models driven from both sources. To mitigate overfitting issues, we incorporated a calibration step that is built upon data-driven heuristics, including proximity and ratios. Specifically, from a total of a 3952 fake articles for three different medical conditions, the algorithm was trained using only 100 articles, but calibrated using folds of 100 articles. As for the classification step, it was performed using 300 articles per condition. The actual label steps took place against an equal mix of 50 generated articles and 50 authentic PubMed abstracts. The testing also spanned publication periods from 2010 to 2024 and encompassed research on three distinct diseases: cancer, depression, and Alzheimer\'s. Further, we evaluated the accuracy of the xFakeSci algorithm against some of the classical data mining algorithms (e.g., Support Vector Machines, Regression, and Naive Bayes). The xFakeSci algorithm achieved F1 scores ranging from 80 to 94%, outperforming common data mining algorithms, which scored F1 values between 38 and 52%. We attribute the noticeable difference to the introduction of calibration and a proximity distance heuristic, which underscores this promising performance. Indeed, the prediction of fake science generated by ChatGPT presents a considerable challenge. Nonetheless, the introduction of the xFakeSci algorithm is a significant step on the way to combating fake science.

A smarter city should be a safer city. Nighttime safety in metropolitan areas has long been a global concern, particularly for large cities with diverse demographics and intricate urban forms, whose citizens are often threatened by higher street-level crime rates. However, due to the lack of night-time urban appearance data, prior studies based on street view imagery (SVI) rarely addressed the perceived night-time safety issue, which can generate important implications for crime prevention. This study hypothesizes that night-time SVI can be effectively generated from widely existing daytime SVIs using generative AI (GenAI). To test the hypothesis, this study first collects pairwise day-and-night SVIs across four cities diverged in urban landscapes to construct a comprehensive day-and-night SVI dataset. It then trains and validates a day-to-night (D2N) model with fine-tuned brightness adjustment, effectively transforming daytime SVIs to nighttime ones for distinct urban forms tailored for urban scene perception studies. Our findings indicate that: (1) the performance of D2N transformation varies significantly by urban-scape variations related to urban density; (2) the proportion of building and sky views are important determinants of transformation accuracy; (3) within prevailed models, CycleGAN maintains the consistency of D2N scene conversion, but requires abundant data. Pix2Pix achieves considerable accuracy when pairwise day-and-night-night SVIs are available and are sensitive to data quality. StableDiffusion yields high-quality images with expensive training costs. Therefore, CycleGAN is most effective in balancing the accuracy, data requirement, and cost. This study contributes to urban scene studies by constructing a first-of-its-kind D2N dataset consisting of pairwise day-and-night SVIs across various urban forms. The D2N generator will provide a cornerstone for future urban studies that heavily utilize SVIs to audit urban environments.

The increasing interest in the potential applications of generative artificial intelligence (AI) models like ChatGPT in health care has prompted numerous studies to explore its performance in various medical contexts. However, evaluating ChatGPT poses unique challenges due to the inherent randomness in its responses. Unlike traditional AI models, ChatGPT generates different responses for the same input, making it imperative to assess its stability through repetition. This commentary highlights the importance of including repetition in the evaluation of ChatGPT to ensure the reliability of conclusions drawn from its performance. Similar to biological experiments, which often require multiple repetitions for validity, we argue that assessing generative AI models like ChatGPT demands a similar approach. Failure to acknowledge the impact of repetition can lead to biased conclusions and undermine the credibility of research findings. We urge researchers to incorporate appropriate repetition in their studies from the outset and transparently report their methods to enhance the robustness and reproducibility of findings in this rapidly evolving field.

Large language models (LLMs) have the potential to transform our lives and work through the content they generate, known as AI-Generated Content (AIGC). To harness this transformation, we need to understand the limitations of LLMs. Here, we investigate the bias of AIGC produced by seven representative LLMs, including ChatGPT and LLaMA. We collect news articles from The New York Times and Reuters, both known for their dedication to provide unbiased news. We then apply each examined LLM to generate news content with headlines of these news articles as prompts, and evaluate the gender and racial biases of the AIGC produced by the LLM by comparing the AIGC and the original news articles. We further analyze the gender bias of each LLM under biased prompts by adding gender-biased messages to prompts constructed from these news headlines. Our study reveals that the AIGC produced by each examined LLM demonstrates substantial gender and racial biases. Moreover, the AIGC generated by each LLM exhibits notable discrimination against females and individuals of the Black race. Among the LLMs, the AIGC generated by ChatGPT demonstrates the lowest level of bias, and ChatGPT is the sole model capable of declining content generation when provided with biased prompts.

We deploy a prompt-augmented GPT-4 model to distill comprehensive datasets on the global application of debt-for-nature swaps (DNS), a pivotal financial tool for environmental conservation. Our analysis includes 195 nations and identifies 21 countries that have not yet used DNS before as prime candidates for DNS. A significant proportion demonstrates consistent commitments to conservation finance (0.86 accuracy as compared to historical swaps records). Conversely, 35 countries previously active in DNS before 2010 have since been identified as unsuitable. Notably, Argentina, grappling with soaring inflation and a substantial sovereign debt crisis, and Poland, which has achieved economic stability and gained access to alternative EU conservation funds, exemplify the shifting suitability landscape. The study\'s outcomes illuminate the fragility of DNS as a conservation strategy amid economic and political volatility.

暂无摘要。