Search

AIM: To assess the possibility of using different large language models (LLMs) in ocular surface diseases by selecting five different LLMS to test their accuracy in answering specialized questions related to ocular surface diseases: ChatGPT-4, ChatGPT-3.5, Claude 2, PaLM2, and SenseNova. METHODS: A group of experienced ophthalmology professors were asked to develop a 100-question single-choice question on ocular surface diseases designed to assess the performance of LLMs and human participants in answering ophthalmology specialty exam questions. The exam includes questions on the following topics: keratitis disease (20 questions), keratoconus, keratomalaciac, corneal dystrophy, corneal degeneration, erosive corneal ulcers, and corneal lesions associated with systemic diseases (20 questions), conjunctivitis disease (20 questions), trachoma, pterygoid and conjunctival tumor diseases (20 questions), and dry eye disease (20 questions). Then the total score of each LLMs and compared their mean score, mean correlation, variance, and confidence were calculated. RESULTS: GPT-4 exhibited the highest performance in terms of LLMs. Comparing the average scores of the LLMs group with the four human groups, chief physician, attending physician, regular trainee, and graduate student, it was found that except for ChatGPT-4, the total score of the rest of the LLMs is lower than that of the graduate student group, which had the lowest score in the human group. Both ChatGPT-4 and PaLM2 were more likely to give exact and correct answers, giving very little chance of an incorrect answer. ChatGPT-4 showed higher credibility when answering questions, with a success rate of 59%, but gave the wrong answer to the question 28% of the time. CONCLUSION: GPT-4 model exhibits excellent performance in both answer relevance and confidence. PaLM2 shows a positive correlation (up to 0.8) in terms of answer accuracy during the exam. In terms of answer confidence, PaLM2 is second only to GPT4 and surpasses Claude 2, SenseNova, and GPT-3.5. Despite the fact that ocular surface disease is a highly specialized discipline, GPT-4 still exhibits superior performance, suggesting that its potential and ability to be applied in this field is enormous, perhaps with the potential to be a valuable resource for medical students and clinicians in the future.

Double-stranded RNA (dsRNA) has emerged as key player in gene silencing for the past two decades. Tailor-made dsRNA is now recognized a versatile raw material, suitable for a wide range of applications in biopesticide formulations, including insect control to pesticide resistance management. The mechanism of RNA interference (RNAi) acts at the messenger RNA (mRNA) level, utilizing a sequence-dependent approach that makes it unique in term of effectiveness and specificity compared to conventional agrochemicals. Two primary categories of small RNAs, known as short interfering RNAs (siRNAs) and microRNAs (miRNAs), function in both somatic and germline lineages in a broad range of eukaryotic species to regulate endogenous genes and to defend the genome from invasive nucleic acids. Furthermore, the application of RNAi in crop protection can be achieved by employing plant-incorporated protectants through plant transformation, but also by non-transformative strategies such as the use of formulations of sprayable RNAs as direct control agents, resistance factor repressors or developmental disruptors. This review explores the agricultural applications of RNAi, delving into its successes in pest-insect control and considering its broader potential for managing plant pathogens, nematodes, and pests. Additionally, the use of RNAi as a tool for addressing pesticide-resistant weeds and insects is reviewed, along with an evaluation of production costs and environmental implications. [ABSTRACT FROM AUTHOR]