Evaluating Large Language Models for the National Premedical Exam in India: Comparative Analysis of GPT-3.5, GPT-4, and Bard.

BACKGROUND: Large language models (LLMs) have revolutionized natural language processing with their ability to generate human-like text through extensive training on large data sets. These models, including Generative Pre-trained Transformers (GPT)-3.5 (OpenAI), GPT-4 (OpenAI), and Bard (Google LLC), find applications beyond natural language processing, attracting interest from academia and industry. Students are actively leveraging LLMs to enhance learning experiences and prepare for high-stakes exams, such as the National Eligibility cum Entrance Test (NEET) in India. OBJECTIVE: This comparative analysis aims to evaluate the performance of GPT-3.5, GPT-4, and Bard in answering NEET-2023 questions. METHODS: In this paper, we evaluated the performance of the 3 mainstream LLMs, namely GPT-3.5, GPT-4, and Google Bard, in answering questions related to the NEET-2023 exam. The questions of the NEET were provided to these artificial intelligence models, and the responses were recorded and compared against the correct answers from the official answer key. Consensus was used to evaluate the performance of all 3 models. RESULTS: It was evident that GPT-4 passed the entrance test with flying colors (300/700, 42.9%), showcasing exceptional performance. On the other hand, GPT-3.5 managed to meet the qualifying criteria, but with a substantially lower score (145/700, 20.7%). However, Bard (115/700, 16.4%) failed to meet the qualifying criteria and did not pass the test. GPT-4 demonstrated consistent superiority over Bard and GPT-3.5 in all 3 subjects. Specifically, GPT-4 achieved accuracy rates of 73% (29/40) in physics, 44% (16/36) in chemistry, and 51% (50/99) in biology. Conversely, GPT-3.5 attained an accuracy rate of 45% (18/40) in physics, 33% (13/26) in chemistry, and 34% (34/99) in biology. The accuracy consensus metric showed that the matching responses between GPT-4 and Bard, as well as GPT-4 and GPT-3.5, had higher incidences of being correct, at 0.56 and 0.57, respectively, compared to the matching responses between Bard and GPT-3.5, which stood at 0.42. When all 3 models were considered together, their matching responses reached the highest accuracy consensus of 0.59. CONCLUSIONS: The study's findings provide valuable insights into the performance of GPT-3.5, GPT-4, and Bard in answering NEET-2023 questions. GPT-4 emerged as the most accurate model, highlighting its potential for educational applications. Cross-checking responses across models may result in confusion as the compared models (as duos or a trio) tend to agree on only a little over half of the correct responses. Using GPT-4 as one of the compared models will result in higher accuracy consensus. The results underscore the suitability of LLMs for high-stakes exams and their positive impact on education. Additionally, the study establishes a benchmark for evaluating and enhancing LLMs' performance in educational tasks, promoting responsible and informed use of these models in diverse learning environments.

ChatGPT and Vaccines: Can AI Chatbots Boost Awareness and Uptake?

The global COVID-19 pandemic has affected all spheres of human life, resulting in millions of deaths and overwhelming medical facilities. Moreover, the world has witnessed great financial hardship because of job losses resulting in economic havoc. Many sections of society have contributed in different ways to slow the spread of the virus and protect public health. For example, medical scientists are praised for their efforts to develop COVID-19 vaccines. Clinical trials have shown that the COVID-19 vaccines are highly effective in preventing symptomatic COVID-19 infections. However, many people around the world have been hesitant to get vaccinated. Vaccine misconceptions have emerged and increased due to a combination of factors, including the availability of information on the Internet and the influence of celebrities and opinion leaders. In this context, we have analyzed ChatGPT responses to relevant queries on vaccine misconceptions. The positive responses and supportive opinions provided by the AI chatbot could be instrumental in shaping people's perceptions of vaccines and in encouraging users to get vaccinated and reduce misconceptions.

ChatGPT as a Complementary Mental Health Resource: A Boon or a Bane.

The launch of Open AI's chatbot, ChatGPT, has generated a lot of attention and discussion among professionals in several fields. Many concerns and challenges have been brought up by researchers from various fields, particularly in relation to the harm that using these tools for medical diagnosis and treatment recommendations can cause. In addition, it has been debated if ChatGPT is dependable, efficient, and helpful for clinicians and medical professionals. Therefore, in this study, we assess ChatGPT's effectiveness in providing mental health support, particularly for issues related to anxiety and depression, based on the chatbot's responses and cross-questioning. The findings indicate that there are significant inconsistencies and that ChatGPT's reliability is low in this specific domain. As a result, care must be used when using ChatGPT as a complementary mental health resource.

COVID-19 and beyond: leveraging artificial intelligence for enhanced outbreak control.

COVID-19 has brought significant changes to our political, social, and technological landscape. This paper explores the emergence and global spread of the disease and focuses on the role of Artificial Intelligence (AI) in containing its transmission. To the best of our knowledge, there has been no scientific presentation of the early pictorial representation of the disease's spread. Additionally, we outline various domains where AI has made a significant impact during the pandemic. Our methodology involves searching relevant articles on COVID-19 and AI in leading databases such as PubMed and Scopus to identify the ways AI has addressed pandemic-related challenges and its potential for further assistance. While research suggests that AI has not fully realized its potential against COVID-19, likely due to data quality and diversity limitations, we review and identify key areas where AI has been crucial in preparing the fight against any sudden outbreak of the pandemic. We also propose ways to maximize the utilization of AI's capabilities in this regard.

Multi-criteria decision making-based waste management: A bibliometric analysis.

Waste management is a complex research domain. While the domain is challenging in terms of content, it is also a diverse and cross-disciplinary research subject. One of its important components includes efficient decision-making at various levels and stages. Therefore, Multi-criteria decision-making (MCDM) techniques have found decent applications in this domain. The field of MCDM techniques-based waste management has been examined using bibliometric analysis in this paper in order to report a systematic overview of the trends and advancements in this area of study. The Scopus database provided 216 publications on the aforementioned subject written between 1992 and 2022. The 216 articles include 56 countries, 158 institutions, and 160 authors. Furthermore, Asian countries, including India, Iran, and China, dominate this field of study. The geographical disparity in the output of publications is visible. Journal of cleaner production, Waste Management and Waste Management and Research are the major journals publishing on MCDM techniques-based waste management research. Given that majority of the articles include multiple authors, it can be said that there is a lot of collaborative research in this area. Overall, the current study provides a thorough analysis of the development in the domain of waste management using MCDM techniques. The trend suggests that it will continue to be a focus of research for academicians, environmentalists and policymakers in the future.

Antimicrobial resistance and machine learning: past, present, and future.

Machine learning has become ubiquitous across all industries, including the relatively new application of predicting antimicrobial resistance. As the first bibliometric review in this field, we expect it to inspire further research in this area. The review employs standard bibliometric indicators such as article count, citation count, and the Hirsch index (H-index) to evaluate the relevance and impact of the leading countries, organizations, journals, and authors in this field. VOSviewer and Biblioshiny programs are utilized to analyze citation and co-citation networks, collaboration networks, keyword co-occurrence, and trend analysis. The United States has the highest contribution with 254 articles, accounting for over 37.57% of the total corpus, followed by China (103) and the United Kingdom (78). Among 58 publishers, the top four publishers account for 45% of the publications, with Elsevier leading with 15% of the publications, followed by Springer Nature (12%), MDPI, and Frontiers Media SA with 9% each. Frontiers in Microbiology is the most frequent publication source (33 articles), followed by Scientific Reports (29 articles), PLoS One (17 articles), and Antibiotics (16 articles). The study reveals a substantial increase in research and publications on the use of machine learning to predict antibiotic resistance. Recent research has focused on developing advanced machine learning algorithms that can accurately forecast antibiotic resistance, and a range of algorithms are now being used to address this issue.

Characterization of Monoamine Oxidase-A in tropical liver fluke, Fasciola gigantica.

Fasciola gigantica, responsible for the zoonotic disease fasciolosis, pose a great threat to the livestock and human health worldwide. The triclabendazole (TCBZ) has been used for decades as a broad spectrum anthelmintic to control this perilous disease but the emergence of resistance in flukes against TCBZ has prompted researchers across the world to explore for new drugs and antigenic targets. World Health Organization has strongly recommended the utilization of neurobiologically significant biomolecules as new drug/antigenic targets because of their significant role in the physiology of parasites. Monoamine Oxidase (MAO) is an important neurobiological enzyme which catabolizes aminergic neurotransmitters thus preventing prolonged excitation of neurons and in non-neuronal cells it prevents cellular toxicity due to accumulation of toxic monoamines. Owing to the important role of MAO in the survival and perpetuation of parasites, multipronged approaches were undertaken for the characterization of MAO-A in F. gigantica. The activity of MAO was found to be 1.5 times higher in the mitochondrial samples than the whole homogenate samples. The adult worms of the F. gigantica appeared to possess both the isoforms of MAO i.e., MAO-A and MAO-B. The zymographic studies revealed strong enzyme activity in its native state as assessed through prominent dark bands at 250KDa in the zymogram. The enzyme was also found to be highly immunogenic as revealed by high antibody titer at 1:6400 dilution. The immunogenicity of MAO-A enzyme was further established in the Western Blots in which a strong band of 50KDa was distinctly evident. Despite ubiquitous presence of MAO in F. gigantica some regions like tegumental surface and intestinal caecae displayed strong immunofluorescence as compared to other regions. The detection of MAO-A in the F. gigantica samples in Dot-Blot assay indicate a great potential of this molecule for the immunodiagnostics of fasciolosis, particularly in the field conditions. The enzyme activity was sensitive to the specific inhibitor clorgyline in a concentration dependant manner, particularly in the late incubation period. The zymographic results also exhibited similar trend. The strong intensity of spots in Dot-blots indicate high immunogenicity of the MAO protein. The intensity of bands/spots in the samples of worms treated with clorgyline also declined, clearly indicating that the tropical liver fluke possesses prominent MAO-A activity.

Clinostomum complanatum: Anthelmintic potential of curcumin on the infective progenetic metacercarial stage.

The emerging resistance against commonly used antiparasitic drugs has driven investigators to explore alternative approaches using plant-derived active ingredients. These compounds have been tested for antiviral, antibacterial, and anthelmintic properties, particularly against adult worms. However, their effects on larval forms have been neglected. Curcumin is a polyphenol that is a significant constituent of the rhizome of Curcuma longa and possesses various biological activities, including antioxidant, anti-inflammatory, anti-infectious, and anti-carcinogenic. In the present study, the anthelmintic potential of curcumin was tested in vitro for its efficacy against the zoonotically important larval form, the progenetic metacercariae of Clinostomum complanatum, which were procured from the forage fish, Trichogaster fasciatus. Curcumin produced time and concentration-dependent inhibition in the motility of treated metacercarial worms, with the maximum inhibition of motility reported at 60 µM along with a significant increase of (36-92%) in ROS and (57-112%) in GSH levels at the end of a period of 6 h. In contrast, curcumin at the highest concentration significantly inhibited the activities of the antioxidant and detoxification enzymes SOD (36%) and GST (16%), respectively, in addition to altering the polypeptide profile and inhibiting cysteine proteases. The tegumental surface appeared to be highly disrupted in curcumin-treated worms, exhibiting severe blebbing, shearing of the tegument, and spine erosion. Such changes would affect the tegumental functions and survival of worms in the hostile microenvironment. This would render worms more susceptible to host-mediated rejection responses. Based on the results of the present study, it is inferred that C. complanatum could serve as an excellent model for screening novel anthelmintic drugs against larval trematodes of great economic significance. Furthermore, we conclude that curcumin could be exploited as an excellent phytotherapeutic agent against the virulent larval form under investigation.

Affinity purification, identification, and biochemical characterization of Gamma-glutamyl transpeptidase, a membrane anchored enzyme of Gigantocotyle explanatum.

Gamma-glutamyl transpeptidase is an enzyme that facilitates the transfer of glutamyl groups from glutamyl peptides to other peptides or water. Additionally, it also participates in important processes such as amino acid transport, cellular redox control, drug detoxification, apoptosis, and DNA fragmentation in a various organism. In the present study, GGT activity in Gigantocotyle explanatum was examined in order to characterize the enzyme in the helminth system. GGT is isolated using membrane solubilization and purified through affinity column chromatography (Con-A Sepharose column). Km and Vmax values, as well as the optimal pH, optimal temperature, and incubation period, are also determined using enzyme kinetics. The hetero-dimeric property of the enzyme is demonstrated by the purified GGT, which yielded two subunits of 65.5 and 55 kDa. The optimal pH and temperature are found to be 8.0 and 37 °C, respectively. While assessing the optimal incubation time of the enzyme, it was observed that the purified GGT not only retained its functional integrity up to 15 min but also reflected considerable thermostability at higher temperatures, by retaining 78% and 25% of its initial activities at 50 °C and 60 °C, respectively. One millimolar concentration of 6-Diazo-5-Oxo Nor-isoleucine (DON), a specific inhibitor of GGT, completely abolished GGT activity. These results suggest that GGT in these worms is a catalytically active enzyme with distinguishing characteristics that can be used for further study to comprehend its function in amphistome biology and in host-parasite relationships, especially since the potential therapeutic candidacy of the GGT enzyme has already been indicated in these groups of organisms.

Curcumin in Wound Healing-A Bibliometric Analysis.

BACKGROUND: Curcumin has been widely used to treat a variety of diseases and disorders since ancient times, most notably for the purpose of healing wounds. Despite the large number of available reviews on this topic, a bibliometric tool-based meta-analysis is missing in the literature. Scope and approach: To evaluate the influence and significance of the countries, journals, organizations and authors that have contributed the most to this topic, the popular bibliometric markers, including article count, citation count, and Hirsch index (H-index), are taken into account. Their collaborative networks and keyword co-occurrence along with the trend analysis are also sketched out using the VOSviewer software. To the best of our knowledge, this is the first bibliometric review on the topic and hence it is envisaged that it will attract researchers to explore future research dimensions in the related field. KEY FINDINGS AND CONCLUSIONS: India provided the most articles, making up more than 27.49 percent of the entire corpus. The International Journal of Biological Macromolecules published the most articles (44), and it also received the most citations (2012). The Journal of Ethnopharmacology (28 articles) and Current Pharmaceutical Design (20 articles) were the next most prolific journals with 1231 and 812 citations, respectively. The results indicate a significant increase in both research and publications on the wound-healing properties of curcumin. Recent studies have concentrated on creating novel medicine-delivery systems that use nano-curcumin to boost the effect of the curcumin molecule in therapeutic targeting. It has also been observed that genetic engineering and biotechnology have recently been employed to address the commercial implications of curcumin.

The scholarly footprint of ChatGPT: a bibliometric analysis of the early outbreak phase.

This paper presents a comprehensive analysis of the scholarly footprint of ChatGPT, an AI language model, using bibliometric and scientometric methods. The study zooms in on the early outbreak phase from when ChatGPT was launched in November 2022 to early June 2023. It aims to understand the evolution of research output, citation patterns, collaborative networks, application domains, and future research directions related to ChatGPT. By retrieving data from the Scopus database, 533 relevant articles were identified for analysis. The findings reveal the prominent publication venues, influential authors, and countries contributing to ChatGPT research. Collaborative networks among researchers and institutions are visualized, highlighting patterns of co-authorship. The application domains of ChatGPT, such as customer support and content generation, are examined. Moreover, the study identifies emerging keywords and potential research areas for future exploration. The methodology employed includes data extraction, bibliometric analysis using various indicators, and visualization techniques such as Sankey diagrams. The analysis provides valuable insights into ChatGPT's early footprint in academia and offers researchers guidance for further advancements. This study stimulates discussions, collaborations, and innovations to enhance ChatGPT's capabilities and impact across domains.

Antihelminthic effect of thymoquinone against biliary amphistome, Gigantocotyleexplanatum.

Recent research on the emergence of parasitic resistance to commonly prescribed anthelmintics has sparked a greater interest in finding novel therapeutic molecules, including those derived from plants. The use of medicinal plants and their derivatives has been viewed as an alternative source of anti-parasitic compounds and as being safe in comparison to synthetic medications due to the absence of adverse effects, ease of accessibility, and little to no expense. Consequently, in the current study, thymoquinone (TQ), an active component of Nigella sativa (Black cumin), has been tested to see their effect on the activity of some important parameters of Gigantocotyle explanatum worms, including Gamma-glutamyl Transpeptidase (GGT), glutathione (GSH), Glutathione-S-Transferase (GST), Superoxide dismutase (NO). Additionally, various other survival indicators are also used, such as assays for motility, tegument damage, and DNA fragmentation. G. explanatum adult flukes were in vitro treated to thymoquinone at various concentrations for 3 h at 37 °C. Even though all of the worms were still alive after 3 h of exposure, there was a substantial (p < 0.05) reduction in worm motility at a concentration of 90 M. There were pronounced tegumental disturbances, a loss of surface annulations, and erosion in the papillae posterior region and around the acetabulum. A significant (p < 0.05) decrease in glutathione-S-transferase and superoxide dismutase activity and reduced glutathione (GSH) level was observed. A significant inhibition of Gamma-glutamyl Transpeptidase (GGT) in thymoquinone treated worms was also evident. Thymoquinone and GGT also displayed a high interaction during in silico molecular docking, suggesting that this combination may be more effective at inhibiting the antioxidant enzymes of G. explanatum. The present findings suggest that thymoquinone would reduce the worm capacity for detoxification, while GGT inhibition would have a major impact on their ability to transport amino acids across the tegument. Thymoquinone thus seemed to be a promising anthelmintic compound for future investigations.