Best practices for implementing ChatGPT, large language models, and artificial intelligence in qualitative and survey-based research

Kantor, Jonathan

doi:10.1016/j.jdin.2023.10.001

Cited by 19 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI can analyse the MRC massive data to predict clinical and treatment outcomes, improve diagnostic accuracy, and plan and improve treatment strategies. Epidemiological data analysis can support the designing and planning of mycetoma control and prevention measurements and programmes to reduce the disease burden and consequences [45][46][47][48].…”

Section: Discussionmentioning

confidence: 99%

The use of artificial intelligence to improve mycetoma management

Ali,

Elkheir,

Fahal

2024

PLoS Negl Trop Dis

View full text Add to dashboard Cite

Mycetoma is a serious, neglected tropical disease affecting the underprivileged populations in resource-constrained communities of the rural tropical and subtropical regions. It predominately affects individuals of low visibility and voice and continues to hinder and burden the poor, remote communities [1]. Furthermore, in endemic areas, the medical and health facilities are meagre and adequate treatment is lacking or inaccessible [2]. All these lead to a progressive disease with massive morbidities and serious medical, health, and socioeconomic consequences [3,4].Mycetoma is a chronic disabling subcutaneous granulomatous inflammatory disease of fungal and bacterial origin [5,6]. The inflammatory granuloma progressively spreads to affect the skin, deep tissues, and bones, leading to massive tissue damage, destruction, and serious morbidities and can be fatal [6][7][8]. A disease characteristic is the triad of subcutaneous mass, multiple sinuses discharging purulent and sero-purulent discharge frequently containing grains [9,10].The mycetoma development and the associated risk factors are still unclear. Likewise, the disease susceptibility, resistance, entry route, and incubation period are unclear [11][12][13]. Presently, the diagnosis of mycetoma is difficult and tedious [14]. The available diagnostic tests are invasive, time-consuming, of low sensitivity and specificity, and there is no point of care [15][16][17]. Furthermore, the available treatment of mycetoma is suboptimal, characterised by a low cure rate and high recurrence and follow-up rates, and the disease remains with patients for a while, if not for life [18,19].Artificial intelligence (AI) continues evolving swiftly, with ongoing research and development in various domains. It can potentially bring about significant advancements in science, technology, and society. AI has made substantial inroads into the medical and healthcare arenas, revolutionising healthcare delivery, disease diagnosis, and management. Nowadays, there are many applications for AI in medical and health practice, to mention but a few: its use in medical imaging, disease diagnosis, drug discovery, personalised medicine, data predictive analytics, electronic health records, telemedicine and virtual health assistance, robotics surgery, drug dosage, treatment recommendations, health monitoring, mental health, drug adverse event detection and healthcare operations, and resource management [20,21].Machine learning (ML) is a subset of AI that creates algorithms and models that enable computers to learn and make predictions or decisions based on data to improve performance without explicit programming. ML is essential for interpreting large datasets, automating tasks, and enhancing decision-making processes, applied across diverse domains like image and speech recognition, natural language processing, recommendation systems, autonomous PLOS NEGLECTED TROPICAL DISEASES

show abstract

Section: Discussionmentioning

confidence: 99%

The use of artificial intelligence to improve mycetoma management

Ali,

Elkheir,

Fahal

2024

PLoS Negl Trop Dis

View full text Add to dashboard Cite

show abstract

“…Furthermore, the integration of the Python-oriented Jupyter Notebook environment with ChatGPT-4 facilitates the generation of Python code from users’ natural language instructions. This simplifies programming tasks, especially for individuals not acquainted with particular libraries or data analysis techniques [ 39 ]. In contrast, direct use of Python necessitates manual coding.…”

Section: Discussionmentioning

confidence: 99%

Evaluating ChatGPT-4.0’s data analytic proficiency in epidemiological studies: A comparative analysis with SAS, SPSS, and R

Huang,

Wu,

et al. 2024

J Glob Health

View full text Add to dashboard Cite

Background OpenAI’s Chat Generative Pre-trained Transformer 4.0 (ChatGPT-4), an emerging artificial intelligence (AI)-based large language model (LLM), has been receiving increasing attention from the medical research community for its innovative ‘Data Analyst’ feature. We aimed to compare the capabilities of ChatGPT-4 against traditional biostatistical software (i.e. SAS, SPSS, R) in statistically analysing epidemiological research data. Methods We used a data set from the China Health and Nutrition Survey, comprising 9317 participants and 29 variables (e.g. gender, age, educational level, marital status, income, occupation, weekly working hours, survival status). Two researchers independently evaluated the data analysis capabilities of GPT-4’s ‘Data Analyst’ feature against SAS, SPSS, and R across three commonly used epidemiological analysis methods: Descriptive statistics, intergroup analysis, and correlation analysis. We used an internally developed evaluation scale to assess and compare the consistency of results, analytical efficiency of coding or operations, user-friendliness, and overall performance between ChatGPT-4, SAS, SPSS, and R. Results In descriptive statistics, ChatGPT-4 showed high consistency of results, greater analytical efficiency of code or operations, and more intuitive user-friendliness compared to SAS, SPSS, and R. In intergroup comparisons and correlational analyses, despite minor discrepancies in statistical outcomes for certain analysis tasks with SAS, SPSS, and R, ChatGPT-4 maintained high analytical efficiency and exceptional user-friendliness. Thus, employing ChatGPT-4 can significantly lower the operational threshold for conducting epidemiological data analysis while maintaining consistency with traditional biostatistical software’s outcome, requiring only specific, clear analysis instructions without any additional operations or code writing. Conclusions We found ChatGPT-4 to be a powerful auxiliary tool for statistical analysis in epidemiological research. However, it showed limitations in result consistency and in applying more advanced statistical methods. Therefore, we advocate for the use of ChatGPT-4 in supporting researchers with intermediate experience in data analysis. With AI technologies like LLMs advancing rapidly, their integration with data analysis platforms promises to lower operational barriers, thereby enabling researchers to dedicate greater focus to the nuanced interpretation of analysis results. This development is likely to significantly advance epidemiological and medical research.

show abstract

“…At each step of the evolutionary process, there is less pressure on the researcher to know the underlying nuts and bolts of software and more opportunity to focus on the data. Researchers are only beginning to explore all the options that generative Arti cial Intelligence offers [35]. Understandably, signi cant shifts are frightening, and the generative AI revolution in the academic world is no different.…”

Section: Technological Revolutionsmentioning

confidence: 99%

Enhancing Mixed Methods Research with your generative AI assistant – A Tutorial and Evaluation for Scholars

Combrinck

2024

Preprint

View full text Add to dashboard Cite

Scholars from all disciplines can benefit from learning how to use generative Artificial Intelligence (GAI or AI) for data analysis. The current article used real data to demonstrate the analysis and synthesis of mixed methods research (MMR) data with generative AI. I also explore how reliable and valid data outputs are and how to improve the use of generative AI for research. The demonstration data used emanated from a study done in South Africa, with a quantitative sample size of 969 first-year engineering students and, for the qualitative part, 14 second-year students. In the current article, I compare my original analysis to ChatGPT results. Generative AI is a mind tool that is ideal when utilised with human insight to check the cohesion, consistency, and accuracy of the data analysis. The current content is geared towards enhancing methodological application regardless of field or discipline and includes access to a prompt library and examples of using outputs. For the qualitative analysis, I found that ChatGPT could detect similar themes but missed some, and its write-up was shallower than our human version. The quantitative analysis was accurate for the descriptive statistics, but the researcher had to use best judgment to select the correct inferential analysis. A quantitative and qualitative analysis should be conducted separately in generative AI before asking the bot for help with mixed methods research. I give guidelines and a tutorial on how to use chatbots in an ethically responsible and scientifically sound manner for research in social and human sciences.

show abstract

Best practices for implementing ChatGPT, large language models, and artificial intelligence in qualitative and survey-based research

Cited by 19 publications

References 5 publications

The use of artificial intelligence to improve mycetoma management

The use of artificial intelligence to improve mycetoma management

Evaluating ChatGPT-4.0’s data analytic proficiency in epidemiological studies: A comparative analysis with SAS, SPSS, and R

Enhancing Mixed Methods Research with your generative AI assistant – A Tutorial and Evaluation for Scholars

Contact Info

Product

Resources

About