. 2023 May 26:1–36. Online ahead of print. doi: 10.1007/s10389-023-01936-y

Table 2.

From STROBE items/recommendation to ChatGPT questions

*Not relevant for the purposes of the present study

Question #	Original STROBE item/recommendation	STROBE item transformed into a question for ChatGPT	Answer
1	*Title and abstract. (a) Indicate the study’s design with a commonly used term in the title or the abstract	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Indicate the study’s design with a commonly used term in the title or the abstract	What are the guidelines for indicating the study design with a commonly used term in the title or abstract, according to the STROBE guidelines?
2	Title and abstract. (b) Provide in the abstract an informative and balanced summary of what was done and what was found	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Provide in the abstract an informative and balanced summary of what was done and what was found	What are the guidelines for providing an informative and balanced summary of what was done and what was found in the abstract, according to the STROBE guidelines?
Introduction
3	Background/rationale. Explain the scientific background and rationale for the investigation being reported	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Explain the scientific background and rationale for the investigation being reported	Here is a possible question for ChatGPT based on the recommendation “Explain the scientific background and rationale for the investigation being reported” from the STROBE guidelines: How can I effectively explain the scientific background and rationale for my observational study in the introduction? This question could be used to prompt ChatGPT to generate suggestions or tips for describing the scientific background and rationale for an observational study in the introduction. This might include providing a review of the relevant literature, highlighting any gaps or limitations in existing knowledge, and explaining why the research question or aim of the study is important or relevant. It is important to provide enough context and background information to allow readers to understand the scientific basis for the study, but not so much detail that the introduction becomes overly long or complicated.
4	Objectives. State specific objectives, including any prespecified hypotheses	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: State specific objectives, including any prespecified hypotheses	Here is a possible question for ChatGPT based on the recommendation “State specific objectives, including any prespecified hypotheses” from the STROBE guidelines: How can I clearly and concisely state the specific objectives and hypotheses of my observational study? This question could be used to prompt ChatGPT to generate suggestions or tips for stating the specific objectives and hypotheses of an observational study. This might include providing a clear and concise summary of the research question or aim of the study, outlining the specific outcomes or conclusions that you expect to draw from your study, and describing any prespecified hypotheses that you will be testing. It is important to clearly articulate the objectives and hypotheses of your study in order to provide a clear and focused foundation for your research and to help readers understand the purpose and focus of your study.
Methods
5	Study design. Present key elements of study design early in the paper	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Present key elements of study design early in the paper	What are the key elements of study design that should be presented early in a paper according to the STROBE guidelines?
6	Setting. Describe the setting, locations, and relevant dates, including periods of recruitment, exposure, follow-up, and data collection	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Describe the setting, locations, and relevant dates, including periods of recruitment, exposure, follow-up, and data collection	What should be described in the setting, locations, and relevant dates section of an observational study according to the STROBE guidelines, including periods of recruitment, exposure, follow-up, and data collection?
7	Participants. (a) Cohort study—Give the eligibility criteria, and the sources and methods of selection of participants. Describe methods of follow-up Case–control study—Give the eligibility criteria, and the sources and methods of case ascertainment and control selection. Give the rationale for the choice of cases and controls Cross-sectional study—Give the eligibility criteria, and the sources and methods of selection of participants	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Cohort study—Give the eligibility criteria, and the sources and methods of selection of participants. Describe methods of follow-up Case–control study—Give the eligibility criteria, and the sources and methods of case ascertainment and control selection. Give the rationale for the choice of cases and controls Cross-sectional study—Give the eligibility criteria, and the sources and methods of selection of participants	“What should be included in the report of a cohort study in order to follow the STROBE guidelines? How about a case–control study or a cross-sectional study?”
8	Participants. (b) Cohort study—For matched studies, give matching criteria and number of exposed and unexposed Case–control study—For matched studies, give matching criteria and the number of controls per case	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Cohort study—For matched studies, give matching criteria and number of exposed and unexposed Case–control study—For matched studies, give matching criteria and the number of controls per case	“What should be included in the report of a matched cohort study or case–control study according to the STROBE guidelines?”
9	Variables. Clearly define all outcomes, exposures, predictors, potential confounders, and effect modifiers. Give diagnostic criteria, if applicable	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Clearly define all outcomes, exposures, predictors, potential confounders, and effect modifiers. Give diagnostic criteria, if applicable	What should be included in the definition of outcomes, exposures, predictors, potential confounders, and effect modifiers in an observational study, and how should diagnostic criteria be provided, if applicable, according to the STROBE guidelines?
10	Data sources/measurement. For each variable of interest, give sources of data and details of methods of assessment (measurement). Describe comparability of assessment methods if there is more than one group	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: For each variable of interest, give sources of data and details of methods of assessment (measurement). Describe comparability of assessment methods if there is more than one group	What should be included in the description of sources of data and methods of assessment for each variable of interest in an observational study, and how should comparability of assessment methods be described if there is more than one group, according to the STROBE guidelines?
11	Bias. Describe any efforts to address potential sources of bias	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Describe any efforts to address potential sources of bias	“What should be included in the report of an observational study in order to address potential sources of bias according to the STROBE guidelines?”
12	Study size. Explain how the study size was arrived at	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Explain how the study size was arrived at	“How should the study size be described in the report of an observational study according to the STROBE guidelines?”
13	Quantitative variables. Explain how quantitative variables were handled in the analyses. If applicable, describe which groupings were chosen and why	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Explain how quantitative variables were handled in the analyses. If applicable, describe which groupings were chosen and why	“How were quantitative variables handled in the analyses, and if applicable, what groupings were chosen and why?”
14	Statistical methods. (a) Describe all statistical methods, including those used to control for confounding	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Describe all statistical methods, including those used to control for confounding	What statistical methods should be described, including those used to control for confounding, according to the STROBE guidelines?
15	Statistical methods. (b) Describe any methods used to examine subgroups and interactions	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Describe any methods used to examine subgroups and interactions	What methods were used to examine subgroups and interactions in the study?
16	Statistical methods. (c) Explain how missing data were addressed	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Explain how missing data were addressed	“How should missing data be addressed in the report of an observational study according to the STROBE guidelines?”
17	Statistical methods. (d) Cohort study—If applicable, explain how loss to follow-up was addressed Case–control study—If applicable, explain how matching of cases and controls was addressed. Cross-sectional study—If applicable, describe analytical methods taking account of sampling strategy	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Cohort study—If applicable, explain how loss to follow-up was addressed. Case–control study—If applicable, explain how matching of cases and controls was addressed Cross-sectional study—If applicable, describe analytical methods taking account of sampling strategy	How was loss to follow-up addressed in a cohort study, and how was matching of cases and controls addressed in a case–control study? In a cross-sectional study, how were analytical methods taking into account the sampling strategy described?
18	Statistical methods. (e) Describe any sensitivity analyses	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Describe any sensitivity analyses	“What should be included in the report of an observational study in order to describe sensitivity analyses according to the STROBE guidelines?”
Results
19	Participants. (a) Report numbers of individuals at each stage of study—e.g., numbers potentially eligible, examined for eligibility, confirmed eligible, included in the study, completing follow-up, and analysed	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Report numbers of individuals at each stage of study—e.g., numbers potentially eligible, examined for eligibility, confirmed eligible, included in the study, completing follow-up, and analyzed	“How can the numbers of individuals at each stage of a study be reported according to the STROBE guidelines, including those potentially eligible, examined for eligibility, confirmed eligible, included in the study, completing follow-up, and analyzed?”
20	Participants. (b) Give reasons for non-participation at each stage	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Give reasons for non-participation at each stage	What are the reasons for non-participation at each stage, according to the STROBE guidelines?
21	Participants. (c) Consider use of a flow diagram	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Consider use of a flow diagram	What is the purpose of using a flow diagram in an observational study, according to the STROBE guidelines?
22	Descriptive data. (a) Give characteristics of study participants (e.g., demographic, clinical, social) and information on exposures and potential confounders	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Give characteristics of study participants (e.g., demographic, clinical, social) and information on exposures and potential confounders	What characteristics of study participants (such as demographic, clinical, and social) and information on exposures and potential confounders should be included in a study according to the STROBE guidelines?
23	Descriptive data. (b) Indicate number of participants with missing data for each variable of interest	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Indicate number of participants with missing data for each variable of interest	According to the STROBE guidelines, how should the number of participants with missing data for each variable of interest be indicated in a report?
24	Descriptive data. (c) Cohort study—Summarize follow-up time (e.g., average and total amount)	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Cohort study—Summarize follow-up time (e.g., average and total amount)	According to the STROBE guidelines, how should the follow-up time be summarized in a cohort study, including the average and total amount of follow-up?
25	Outcome data. Cohort study—Report numbers of outcome events or summary measures over time	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Cohort study—Report numbers of outcome events or summary measures over time	According to the STROBE guidelines, how should the numbers of outcome events or summary measures be reported over time in a cohort study?
26	Outcome data. Case–control study—Report numbers in each exposure category, or summary measures of exposure	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Case–control study—Report numbers in each exposure category, or summary measures of exposure	According to the STROBE guidelines, how should the numbers in each exposure category or summary measures of exposure be reported in a case–control study?
27	Outcome data. Cross-sectional study—Report numbers of outcome events or summary measures	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Cross-sectional study—Report numbers of outcome events or summary measures	According to the STROBE guidelines, how should the numbers of outcome events or summary measures be reported in a cross-sectional study?
28	Main results. (a) Give unadjusted estimates and, if applicable, confounder-adjusted estimates and their precision (e.g., 95% confidence interval). Make clear which confounders were adjusted for and why they were included	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Give unadjusted estimates and, if applicable, confounder-adjusted estimates and their precision (e.g., 95% confidence interval). Make clear which confounders were adjusted for and why they were included	According to the STROBE guidelines, how should unadjusted estimates and, if applicable, confounder-adjusted estimates and their precision (such as 95% confidence intervals) be reported, and how should it be made clear which confounders were adjusted for and why they were included?
29	Main results. (b) Report category boundaries when continuous variables were categorized	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Report category boundaries when continuous variables were categorized	What are the guidelines for reporting category boundaries when continuous variables are categorized in observational studies in epidemiology?
30	Main results. (c) If relevant, consider translating estimates of relative risk into absolute risk for a meaningful time period	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: If relevant, consider translating estimates of relative risk into absolute risk for a meaningful time period	What is the STROBE recommendation for translating estimates of relative risk into absolute risk for a meaningful time period, if relevant?
31	Other analyses. Report other analyses done—e.g., analyses of subgroups and interactions, and sensitivity analyses	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Report other analyses done—e.g., analyses of subgroups and interactions, and sensitivity analyses	What are the guidelines for reporting other analyses done, such as analyses of subgroups and interactions and sensitivity analyses, according to the STROBE guidelines?
Discussion
32	Key results. Summarize key results with reference to study objectives	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Summarize key results with reference to study objectives	According to the STROBE guidelines, how should key results be summarized with reference to the study objectives?
33	Limitations. Discuss limitations of the study, taking into account sources of potential bias or imprecision. Discuss both direction and magnitude of any potential bias	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Discuss limitations of the study, taking into account sources of potential bias or imprecision. Discuss both direction and magnitude of any potential bias	According to the STROBE guidelines, how should the limitations of the study be discussed, taking into account sources of potential bias or imprecision, and considering both the direction and magnitude of any potential bias?
34	Interpretation. Give a cautious overall interpretation of results considering objectives, limitations, multiplicity of analyses, results from similar studies, and other relevant evidence	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Give a cautious overall interpretation of results considering objectives, limitations, multiplicity of analyses, results from similar studies, and other relevant evidence	According to the STROBE guidelines, how should a cautious overall interpretation of the results be given, considering the study objectives, limitations, multiplicity of analyses, results from similar studies, and other relevant evidence?
35	Generalizability. Discuss the generalizability (external validity) of the study results	Please transform the following recommendation from the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) guidelines into a question for ChatGPT. Recommendation: Discuss the generalizability (external validity) of the study results	According to the STROBE guidelines, how should the generalizability (external validity) of the study results be discussed?
Other information