Rong Zhang

Dec 5, 2024 | nature.com | Yao Ma |Rong Zhang |Yanhua Chen |Mengyao Xu |Su Rina |Ke Ma | +1 more

Artificial intelligence (AI), particularly large language models like GPT-4o, holds promise for enhancing diagnostic accuracy in healthcare. This study evaluates the diagnostic performance of GPT-4o compared to human ophthalmologists in glaucoma cases. A prospective, observational study was conducted at a tertiary care ophthalmology center. Twenty-six glaucoma cases, including both primary and secondary types, were selected from publicly available databases and institutional records. The cases were analyzed by GPT-4o and three ophthalmologists with varying levels of experience. The accuracy and completeness of primary and differential diagnoses were assessed using 10-point and 6-point Likert scales, respectively. Statistical analyses were performed using nonparametric methods, including the Kruskal–Wallis and Mann–Whitney U tests. GPT-4o was significantly less accurate in primary diagnosis compared to human ophthalmologists. Specifically, GPT-4o achieved a mean score of 5.500 (p < 0.001) compared to Doctor C, who had the highest score of 8.038 (p < 0.001). Completeness scores for GPT-4o 3.077 (p < 0.001) were also lower than Doctor B, who had the lowest score of 3.615 (p < 0.001) among human ophthalmologists. However, for differential diagnosis, GPT-4o (7.577) showed comparable accuracy to Doctor A (7.615) and Doctor C (7.673) (p < 0.0001) while achieving the highest completeness score (4.096), outperforming Doctor C (3.846), Doctor A (2.923), and Doctor B (2.808) (p < 0.0001). AI, including GPT-4o, is currently not an acceptable standalone method for diagnosing glaucoma due to its lower accuracy compared to human clinicians. These findings suggest that GPT-4o could serve as a valuable adjunct in clinical practice, particularly in complex cases, but should not replace human expertise, especially for initial diagnoses. Future improvements in AI models could enhance their utility in ophthalmology.

Apr 23, 2024 | nature.com | Feng Li |Jia Cao |Yayun Gu |Yuan Lin |Yankai Xia |Lin Ao | +16 more

Exposure to PM2.5, a harmful type of air pollution, has been associated with compromised male reproductive health; however, it remains unclear whether such exposure can elicit transgenerational effects on male fertility. Here, we aim to examine the effect of paternal exposure to real-world PM2.5 on the reproductive health of male offspring. We have observed that paternal exposure to real-world PM2.5 can lead to transgenerational primary hypogonadism in a sex-selective manner, and we have also confirmed this phenotype by using an external model. Mechanically, we have identified small RNAs (sRNAs) that play a critical role in mediating these transgenerational effects. Specifically, miR6240 and piR016061, which are present in F0 PM sperm, regulate intergenerational transmission by targeting Lhcgr and Nsd1, respectively. We have also uncovered that piR033435 and piR006695 indirectly regulate F1 PM sperm methylation by binding to the 3′-untranslated region of Tet1 mRNA. The reduced expression of Tet1 resulted in hypermethylation of several testosterone synthesis genes, including Lhcgr and Gnas, impaired Leydig cell function and ultimately led to transgenerational primary hypogonadism. Our findings provide insights into the mechanisms underlying the transgenerational effects of paternal PM2.5 exposure on reproductive health, highlighting the crucial role played by sRNAs in mediating these effects. The findings underscore the significance of paternal pre-conception interventions in alleviating the adverse effects of environmental pollutants on reproductive health.