Discover how AI code interpreters are revolutionizing data visualization, reducing chart creation time from 20 to 5 minutes while simplifying complex statistical analysis.

Objective: Our objective is to evaluate the efficacy of ChatGPT 4 in accurately and effectively delivering genetic information, building on previous findings with ChatGPT 3.5. We focus on assessing the utility, limitations, and ethical implications of using ChatGPT in medical settings. Materials and Methods: A structured questionnaire, including the Brief User Survey (BUS-15) and custom questions, was developed to assess ChatGPT 4's clinical value. An expert panel of genetic counselors and clinical geneticists independently evaluated ChatGPT 4's responses to these questions. We also involved comparative analysis with ChatGPT 3.5, utilizing descriptive statistics and using R for data analysis. Results: ChatGPT 4 demonstrated improvements over 3.5 in context recognition, relevance, and informativeness. However, performance variability and concerns about the naturalness of the output were noted. No significant difference in accuracy was found between ChatGPT 3.5 and 4.0. Notably, the efficacy of ChatGPT 4 varied significantly across different genetic conditions, with specific differences identified between responses related to BRCA1 and HFE. Discussion and Conclusion: This study highlights ChatGPT 4's potential in genomics, noting significant advancements over its predecessor. Despite these improvements, challenges remain, including the risk of outdated information and the necessity of ongoing refinement. The variability in performance across different genetic conditions underscores the need for expert oversight and continuous AI training. ChatGPT 4, while showing promise, emphasizes the importance of balancing technological innovation with ethical responsibility in healthcare information delivery. Methods Study Design This study was conducted to evaluate the performance of ChatGPT 4 (March 23rd, 2023) Model) in the context of genetic counseling and education. The evaluation involved a structured questionnaire, which included questions selected from the Brief User Survey (BUS-15) and additional custom questions designed to assess the clinical value of ChatGPT 4's responses. Questionnaire Development The questionnaire was built on Qualtrics, which comprised twelve questions: seven selected from the BUS-15 preceded by two additional questions that we designed. The initial questions focused on quality and answer relevancy: 1. The overall quality of the Chatbot’s response is: (5-point Likert: Very poor to Very Good) 2. The Chatbot delivered an answer that provided the relevant information you would include if asked the question. (5-point Likert: Strongly disagree to Strongly agree) The BUS-15 questions (7-point Likert: Strongly disagree to Strongly agree) focused on: 1. Recognition and facilitation of users’ goal and intent: Chatbot seems able to recognize the user’s intent and guide the user to its goals. 2. Relevance of information: The chatbot provides relevant and appropriate information/answer to people at each stage to make them closer to their goal. 3. Maxim of quantity: The chatbot responds in an informative way without adding too much information. 4. Resilience to failure: Chatbot seems able to find ways to respond appropriately even when it encounters situations or arguments it is not equipped to handle. 5. Understandability and politeness: The chatbot seems able to understand input and convey correct statements and answers without ambiguity and with acceptable manners. 6. Perceived conversational credibility: The chatbot responds in a credible and informative way without adding too much information. 7. Meet the neurodiverse needs: Chatbot seems able to meet needs and be used by users independently form their health conditions, well-being, age, etc. Expert Panel and Data Collection A panel of experts (two genetic counselors and two clinical geneticists) was provided with a link to the survey containing the questions. They independently evaluated the responses from ChatGPT 4 without discussing the questions or answers among themselves until after the survey submission. This approach ensured unbiased evaluation.

ObjectiveTo assess the competence of students and academic staff to use generative artificial intelligence (GenAI) as a tool in epidemiological data analyses in a randomised controlled trial (RCT).MethodsWe invited postgraduate students and academic staff at the Swiss Tropical and Public Health Institute to the RCT. Participants were randomized to analyse a simulated cross-sectional dataset using ChatGPT’s code interpreter (integrated analysis arm) vs. a statistical software (R/Stata) with ChatGPT as a support tool (distributed analysis arm). The primary outcome was the trial task score (out of 17, using an assessment rubric). Secondary outcome was the time to complete the task.ResultsWe invited 338 and randomized 31 participants equally to the two study arms and 30 participants submitted results. Overall, there was no statistically significant difference in mean task scores between the distributed analysis arm (8.5, ±4.6) and the integrated analysis arm (9.4, ±3.8), with a mean difference of 0.93 (p = 0.55). Mean task completion time was significantly shorter in the integrated analysis arm compared to the distributed analysis arm.ConclusionWhile ChatGPT offers advantages, its effective use requires a careful balance of GenAI capabilities and human expertise.

Argumentative skills are indispensable both personally and professionally to process complex information (CoI) relating to the critical reconstruction of meaning through critical thinking (CT). This remains a particularly relevant priority, especially in the age of social media and artificial intelligence-mediated information. Recently, the public dissemination of what has been called generative artificial intelligence (GenAI), with the particular example of ChatGPT (OpenAI, 2022), has made it even easier today to access and disseminate information, written or not, true or not. New tools are needed to critically address post-digital information abundance.

In this context, argumentative maps (AMs), which are already used to develop argumentative skills and critical thinking, are studied for multimodal and dynamic information visualization, comprehension, and reprocessing. In this regard, the entry of generative AI into university classrooms proposes a novel scenario of multimodality and technological dynamism.

Building on the Vygotskian idea of mediation and the theory of "dual stimulation" as applied to the use of learning technologies, the idea was to complement AMs with the introduction of a second set of stimuli that would support and enhance individual activity: AI-mediated tools. With AMs, an attempt has been made to create a space for understanding, fixing, and reconstructing information, which is important for the development of argumentative skills. On the other hand, by arranging forms of critical and functional interaction with ChatGPT as an ally in understanding, reformulating, and rethinking one's argumentative perspectives, a new and comprehensive argumentative learning process has been arranged, while also cultivating a deeper understanding of the artificial agents themselves.

Our study was based on a two-group quasi-experiment with 27 students of the “Research Methods in Education” course, to explore the role of AMs in fixing and supporting multimodal information reprocessing. In addition, by predicting the use of the intelligent chatbot ChatGPT, one of the most widely used GenAI technologies, we investigated the evolution of students' perceptions of its potential role as a “study companion” in information comprehension and reprocessing activities with a path to build a good prompt.

Preliminary analyses showed that in both groups, AMs supported the increase in mean CoI and CT levels for analog and digital information. However, the group with analog texts showed more complete reprocessing.The interaction with the chatbot was analyzed quantitatively and qualitatively, and there emerged an initial positive reflection on the potential of ChatGPT and increased confidence in interacting with intelligent agents after learning the rules for constructing good prompts.

This Zenodo record follows the full analysis process with R (https://cran.r-project.org/bin/windows/base/ ) and Nvivo (https://lumivero.com/products/nvivo/) composed of the following datasets, script and results:

1. Comprehension of Text and AMs Results - Arg_G1.xlsx & Arg_G2.xlsx

2. Opinion and Critical Thinking level - Opi_G1.xlsx & Opi_G2.xlsx

3. Data for Correlation and Regression - CorRegr_G1.xlsx & CorRegr_G2.xlsx

4. Interaction with ChatGPT - GPT_G1.xlsx & GPT_G2.xlsx

5. Descriptive and Inferential Statistics Comprehension and AMs Building - Analysis_RES_Comprehension.R

6. Descriptive and Inferential Statistics Opinion and Critical Thinking level - Analysis_RES_Opinion.R

7. Correlation and Regression - Analysis_RES_CorRegr.R

8. Descriptive and Inferential Statistics Interaction with ChatGPT - Analysis_RES_ChatGPT.R

9. Sentiment Analysis - Sentiment Analysis_G1.R & Sentiment Analysis_G2.R

10. Vocabulary Frequent words - Vocabulary.csv

11. Codebook qualitative Analysis with Nvivo (Codebook.xlsx)

12. Results Nvivo Analysis G1 - Codebook - ChatGPT2 G1.docx

13. Results Nvivo Analysis G2 - Codebook - ChatGPT2 G2.docx

Any comments or improvements are welcome!

The development of argumentative text and information comprehension (CoI) skills related to the critical reconstruction of meaning (CT) is crucial in undergraduate education. Especially now in the era of social media and AI-mediated information. Generative AI aids in information creation, but its unconscious use can complicate complex information navigation. Argument maps (AM), commonly used for analyzing analog and static texts, can help visualize, understand, and rework multimodal and dynamic arguments and information.

Stemming from the Vygotskian idea, our study used a design-based research approach on the use of AMs and ChatGPT as socio-technical artifacts to stimulate and support the understanding of information (CoI) and thus the development of critical thinking (CT). The workshop introduced the multimodal element through a 3-group quasi-experiment. The first group dealt with fully analog texts, the second group used maps with multimodal textual modes, and the third group only interacted with ChatGPT. The research focused on comparing the three groups and focusing on the two experimental groups (experimental macro-focus).

The research had three main objectives: 1) to test whether AMs improved students' CoI enhancement and critical processing (CT); 2) to determine whether interaction with ChatGPT supported information reprocessing and critical construction of opinions and assessment tools; and 3) to determine whether interaction with ChatGPT alone, without AMs, still fostered greater integration of information and viewpoints.

Our preliminary analysis showed that AMs improved students' CoI and CT, especially when exposed to multimodal information. ChatGPT interaction increased critical reflection and awareness of AI's role in education. Students using only ChatGPT performed well in argumentative reworking, suggesting that interaction with the chatbot can be effective. However, integrating AMs and ChatGPT could provide optimal support for comprehension and critical thinking skills.

This Zenodo record follows the full analysis process with R (https://cran.r-project.org/bin/windows/base/ ) and Nvivo (https://lumivero.com/products/nvivo/) composed of the following datasets, script and results:

1. Comprehension of Text and AMs Results - Arg_Map.xlsx

2. Critical Thinking level - CriThink.xlsx

3. Descriptive and Inferential Statistics Comprehension and Critical Thinking - Preliminary Analysis.R

4. Elaboration and Integration Opinion - Opi_G1.xlsx; Opi_G2.xlsx & Opi_G3.xlsx

5. Descriptive and Inferential Statistics Opinion level - Preliminary Analysis_opi.R

6. Sentiment Analysis - Sentiment Analysis.R

7. Vocabulary Frequent words - Vocabulary.csv

8. Codebook qualitative Analysis with Nvivo (Codebook.xlsx)

9. Results Nvivo Analysis G1 & G2 - Codebook-ChatGPT_G1&G2.docx

Any comments or improvements are welcome!

📹Project Video available on YouTube - https://youtu.be/WmJYHz_qn5s

🖇️Connect with me on LinkedIn - https://www.linkedin.com/in/rohit-grewal

Realistic Synthetic - AI Financial & Market Data for Gemini(Google), ChatGPT(OpenAI), Llama(Meta)

This dataset provides a synthetic, daily record of financial market activities related to companies involved in Artificial Intelligence (AI). There are key financial metrics and events that could influence a company's stock performance like launch of Llama by Meta, launch of GPT by OpenAI, launch of Gemini by Google etc. Here, we have the data about how much amount the companies are spending on R & D of their AI's Products & Services, and how much revenue these companies are generating. The data is from January 1, 2015, to December 31, 2024, and includes information for various companies : OpenAI, Google and Meta.

This data is available as a CSV file. We are going to analyze this data set using the Pandas DataFrame.

This analyse will be helpful for those working in Finance or Share Market domain.

From this dataset, we extract various insights using Python in our Project.

1) How much amount the companies spent on R & D ?

2) Revenue Earned by the companies

3) Date-wise Impact on the Stock

4) Events when Maximum Stock Impact was observed

5) AI Revenue Growth of the companies

6) Correlation between the columns

7) Expenditure vs Revenue year-by-year

8) Event Impact Analysis

9) Change in the index wrt Year & Company

These are the main Features/Columns available in the dataset :

1) Date: This column indicates the specific calendar day for which the financial and AI-related data is recorded. It allows for time-series analysis of the trends and impacts.

2) Company: This column specifies the name of the company to which the data in that particular row belongs. Examples include "OpenAI" and "Meta".

3) R&D_Spending_USD_Mn: This column represents the Research and Development (R&D) spending of the company, measured in Millions of USD. It serves as an indicator of a company's investment in innovation and future growth, particularly in the AI sector.

4) AI_Revenue_USD_Mn: This column denotes the revenue generated specifically from AI-related products or services, also measured in Millions of USD. This metric highlights the direct financial success derived from AI initiatives.

5) AI_Revenue_Growth_%: This column shows the percentage growth of AI-related revenue for the company on a daily basis. It indicates the pace at which a company's AI business is expanding or contracting.

6) Event: This column captures any significant events or announcements made by the company that could potentially influence its financial performance or market perception. Examples include "Cloud AI launch," "AI partnership deal," "AI ethics policy update," and "AI speech recognition release." These events are crucial for understanding sudden shifts in stock impact.

7) Stock_Impact_%: This column quantifies the percentage change in the company's stock price on a given day, likely in response to the recorded financial metrics or events. It serves as a direct measure of market reaction.

This folder gives the supporting data for the manuscript entitled: AI Detectors are Poor Western Blot Classifiers: A Study of Accuracy and Predictive Values. It contains:The entire prompting history used to create images.A spreadsheet (Excel) that summarises all quantitative analyses.A spreadsheet (Excel) that provides details of all sampled articles.Comma-separated values (CSV) files for each specific data set.The R codes used to analyse the data.GraphPad Prism files used to generate the figures.There were no ethical issue related to human or animal research in this project. All analyses were performed on already published historical data or images generated by ChatGPT.

This dataset comprises ChatGPT-generated nutritional recommendations and sample diet plans for 50 distinct patient profiles. Each case study represents the patient profile with sociocultural background of ethnic groups in Central Asia and provides comprehensive data on age, gender, cultural and medical history, dietary patterns, anthropometric characteristics, disease-related functional indicators, biochemical and hematological parameters, and lifestyle behaviors. The LLM outputs include general nutritional recommendations and individualized daily meal plans based on Central Asian foods for each profile. At the same time, we are providing codes for translation into local languages.In case of using our dataset, please cite our work: Adilmetova, G., Nassyrov, R., Meyerbekova, A., Karabay, A., Varol, H. A., & Chan, M. Y. (2025). Evaluating ChatGPT's Multilingual Performance in Clinical Nutrition Advice Using Synthetic Medical Text: Insights from Central Asia. The Journal of nutrition, 155(3), 729–735. https://doi.org/10.1016/j.tjnut.2024.12.018