I'm conducting a systematic literature review on the effectiveness of mindfulness-based interventions for anxiety in college students. Help me: 1) Develop a comprehensive search strategy for PubMed and PsycINFO, 2) Create inclusion/exclusion criteria, 3) Design a data extraction form, 4) Suggest quality assessment tools (PRISMA, Cochrane Risk of Bias)

Prompt

ChatGPTOpenAI

Certainly! Here's a detailed guide to help you with your systematic literature review on the effectiveness of mindfulness-based interventions for anxiety in college students.

1) Comprehensive Search Strategy

a) Key Concepts:

Mindfulness-based interventions

Anxiety

College students

b) Search Terms and Boolean Operators

PubMed Search Strategy:

("mindfulness"[MeSH Terms] OR mindfulness[tiab] OR "mindfulness-based"[tiab] OR "mindfulness meditation"[tiab] OR "mindfulness based stress reduction"[tiab] OR MBSR[tiab] OR "mindfulness-based cognitive therapy"[tiab] OR MBCT[tiab])
AND
("anxiety"[MeSH Terms] OR anxiety[tiab] OR "anxiety disorders"[MeSH Terms] OR "generalized anxiety disorder"[tiab] OR "social anxiety"[tiab] OR "stress, psychological"[MeSH Terms] OR stress[tiab])
AND
("students"[MeSH Terms] OR students[tiab] OR "college students"[tiab] OR "university students"[tiab] OR "undergraduate students"[tiab] OR "higher education"[tiab])

Use filters to limit to humans, English language, and publication types if necessary.

PsycINFO Search Strategy (via APA PsycNET or EBSCOhost):

(Mindfulness OR "mindfulness-based" OR "mindfulness meditation" OR MBSR OR MBCT) 
AND 
(Anxiety OR "anxiety disorder" OR "generalized anxiety" OR "social anxiety" OR stress) 
AND 
("college students" OR "university students" OR "undergraduate students" OR students OR "higher education")

Use subject headings/Thesaurus terms such as:

Mindfulness (Thesaurus term)

Anxiety (Thesaurus term)

Students (Thesaurus term), or specify "college students"

Set limits for peer-reviewed, English, empirical studies, if applicable.

2) Inclusion/Exclusion Criteria

Criteria	Include	Exclude
Population	College/university students aged 18-25	Non-college populations, children, elderly
Intervention	Mindfulness-based interventions (MBSR, MBCT, etc.)	Non-mindfulness interventions (e.g., CBT alone, pharmacotherapy)
Comparator	Control groups, waitlist, other interventions	No comparator or unclear comparator
Outcomes	Anxiety outcomes (measured by validated scales like GAD-7, STAI, BAI)	Studies not reporting anxiety outcomes
Study Design	Randomized controlled trials, quasi-experimental studies, pre-post designs	Case studies, qualitative only, reviews, protocols
Language	English	Non-English
Publication Status	Published peer-reviewed articles	Abstracts, dissertations, conference posters without full text
Time Frame	No restriction or specify recent years (e.g., last 10 years)	Studies outside chosen time frame

3) Data Extraction Form

Field	Description/Details
Study ID	Unique identifier (e.g., first author year)
Author(s)	Names of authors
Year of Publication	Year
Country	Location of study
Study Design	RCT, quasi-experimental, pre-post
Sample Size	Number of participants
Population Characteristics	Age, gender, education level, inclusion/exclusion criteria
Intervention Details	Type of mindfulness intervention, duration, frequency
Comparator	Description of control or comparison group
Outcome Measures	Anxiety scales used, timing of measurement
Results	Mean scores, effect sizes, statistical significance
Adherence/Dropout Rates	Reported attrition, adherence to intervention
Funding Source / Conflicts of Interest	Any funding or COI declarations
Notes / Comments	Additional observations

You may build this in Excel or a systematic review software (e.g., Covidence, Rayyan).

4) Quality Assessment Tools

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses):

Use PRISMA guidelines as a checklist for reporting your systematic review structure and transparency. It doesn’t assess the quality of individual studies but guides the review process.

Cochrane Risk of Bias Tool (RoB 2):

Ideal for assessing risk of bias in randomized trials. Assesses domains such as randomization, deviations from intended interventions, missing data, measurement of outcomes, and selection of reported results.

ROBINS-I Tool:

For non-randomized studies (if including quasi-experimental designs).

Other tools:

Jadad Scale (for RCT quality)

GRADE approach for assessing overall quality of evidence across studies (useful for meta-analysis conclusions)

If you want, I can also help draft the PRISMA flow diagram or suggest software for managing your review!

{DateTime.UtcNow:HH:mm}

GeminiGoogle

Okay, let's break down how to conduct your systematic literature review. This is a comprehensive process, so we'll go step-by-step.

1. Comprehensive Search Strategy (PubMed & PsycINFO)

The goal here is to cast a wide net initially, then refine as you move through the screening process. A good search strategy will incorporate:

Keywords for Mindfulness:

mindfulness

mindfulness-based stress reduction (MBSR)

mindfulness-based cognitive therapy (MBCT)

mindfulness meditation

meditation, mindfulness

"acceptance and commitment therapy" OR ACT (include ACT because it often incorporates mindfulness)

Keywords for Anxiety:

anxiety

anxiety disorders

stress

generalized anxiety disorder

social anxiety

test anxiety

panic disorder

worry

Keywords for College Students:

"college students"

students

undergraduate

"higher education"

university

Here's how these might be combined in PubMed and PsycINFO. Note that syntax can vary slightly.

PubMed:

(("mindfulness"[Title/Abstract] OR "mindfulness-based stress reduction"[Title/Abstract] OR "mindfulness-based cognitive therapy"[Title/Abstract] OR "mindfulness meditation"[Title/Abstract] OR "meditation, mindfulness"[Title/Abstract] OR "acceptance and commitment therapy"[Title/Abstract] OR ACT[Title/Abstract]) AND ("anxiety"[Title/Abstract] OR "anxiety disorders"[Title/Abstract] OR "stress"[Title/Abstract] OR "generalized anxiety disorder"[Title/Abstract] OR "social anxiety"[Title/Abstract] OR "test anxiety"[Title/Abstract] OR "panic disorder"[Title/Abstract] OR "worry"[Title/Abstract])) AND ("college students"[Title/Abstract] OR "students"[Title/Abstract] OR "undergraduate"[Title/Abstract] OR "higher education"[Title/Abstract] OR "university"[Title/Abstract])

PsycINFO:

((mindfulness OR "mindfulness-based stress reduction" OR "mindfulness-based cognitive therapy" OR "mindfulness meditation" OR "meditation, mindfulness" OR "acceptance and commitment therapy" OR ACT) AND (anxiety OR "anxiety disorders" OR stress OR "generalized anxiety disorder" OR "social anxiety" OR "test anxiety" OR "panic disorder" OR worry)) AND ("college students" OR students OR undergraduate OR "higher education" OR university)

Important Considerations for Refining Your Search:

Truncation: Use truncation symbols (e.g., anxi* to capture anxiety, anxious, etc.). Check your database's specific syntax.

MeSH Terms (PubMed): Explore and use relevant MeSH terms for more precision. For example, "Mindfulness," "Anxiety Disorders," and "Students." You can combine MeSH terms with keywords. For example: MeSH:"Mindfulness" AND ("college students"[Title/Abstract] OR MeSH:"Students")

Thesaurus Terms (PsycINFO): Similar to MeSH, PsycINFO has thesaurus terms. Explore and use them.

Limits/Filters: Use filters like publication date range, language (if you only want English), and study type (e.g., randomized controlled trials). Use these cautiously at the initial search stage. It's better to screen out irrelevant studies later than to miss potentially relevant ones.

Boolean Operators: The AND and OR operators are crucial. AND narrows your search; OR broadens it.

Parentheses: Use parentheses to group similar terms together.

Run Test Searches: Before you run the full search, test it with a small set of keywords to see if it retrieves relevant articles. Adjust accordingly.

Consult a Librarian: University librarians specializing in systematic reviews can be invaluable in helping you refine your search strategy. They have expertise in database searching.

Grey Literature: Consider searching grey literature sources (e.g., ProQuest Dissertations & Theses, OpenGrey) if you want to be comprehensive.

2. Inclusion/Exclusion Criteria

These are the criteria that define which studies will be included in your review. Be explicit and specific.

Inclusion Criteria:

Population: Participants must be college students (undergraduate, graduate, or both; define the age range you're considering).

Intervention: Studies must evaluate mindfulness-based interventions (MBIs) specifically designed to reduce anxiety. Define what you consider to be an MBI. For example:

MBSR, MBCT, ACT, or other clearly defined mindfulness meditation programs.

Must have a mindfulness component.

Must be delivered in a group or individual format.

Comparison: Studies must have a comparison group (e.g., waitlist control, active control, usual care). Single-arm studies (no control group) are typically excluded in systematic reviews focused on effectiveness.

Outcome: Studies must report quantitative outcome measures of anxiety. Specify which measures are acceptable (e.g., State-Trait Anxiety Inventory [STAI], Beck Anxiety Inventory [BAI], GAD-7).

Study Design: Randomized controlled trials (RCTs) are ideal. You might consider including quasi-experimental studies with control groups, but be aware of the increased risk of bias. Clearly state which study designs you will include.

Publication Type: Peer-reviewed journal articles. You may decide to include dissertations/theses.

Language: English (or other languages you can read/translate).

Publication Date: Define the time period.

Exclusion Criteria:

Population: Studies that do not focus on college students.

Intervention:

Studies where the intervention is not primarily mindfulness-based.

Interventions that are solely focused on physical activity or diet, even if mindfulness is mentioned.

Studies that only use mindfulness as a minor component of a broader intervention.

Comparison: Studies without a comparison group (single-arm studies).

Outcome: Studies that do not report quantitative measures of anxiety.

Study Design: Case studies, qualitative studies, reviews, meta-analyses (though you will screen their references).

Duplicate Publications: Remove duplicate publications.

Conference Abstracts: Unless they contain sufficient data.

Lack of Full Text: If you cannot obtain the full text of the article.

Specific Comorbidities: You might exclude studies focused on a specific comorbid condition (e.g., anxiety and depression) if you want to focus solely on anxiety. Be careful with this, as it may limit your results.

Key Considerations:

Pilot Test: Before starting the full screening process, have multiple reviewers independently screen a small subset of articles (e.g., 10-20) using your inclusion/exclusion criteria. Compare results and discuss any discrepancies to ensure a shared understanding of the criteria.

Documentation: Keep a clear record of your decisions at each stage of the screening process (e.g., reasons for excluding articles).

PRISMA Flow Diagram: Use the PRISMA flow diagram to visually represent the flow of articles through your screening process.

3. Data Extraction Form

This form will help you systematically collect relevant information from each included study. Create a spreadsheet (e.g., using Excel or Google Sheets) or use a data extraction tool like Covidence (paid).

Here's a template for your data extraction form:

Category	Variable	Description/Instructions
Study ID	Author(s), Year	Last name of first author, publication year
DOI/PMID	Digital Object Identifier (DOI) or PubMed ID (PMID)
Study Design	Study Design	(e.g., RCT, quasi-experimental)
Blinding	(e.g., single-blind, double-blind, not blinded)
Participants	Sample Size (Total, Intervention, Control)	Number of participants in each group.
Age (Mean, SD)	Mean age and standard deviation of participants.
Gender (%)	Percentage of male/female participants.
Inclusion/Exclusion Criteria (Participants)	Summarize the key inclusion/exclusion criteria for participants as reported in the study.
Recruitment Method	How participants were recruited (e.g., flyers, email, course credit).
Intervention	Intervention Type	(e.g., MBSR, MBCT, ACT, other). Provide a brief description of the intervention.
Intervention Components	Detail the specific components of the intervention (e.g., meditation practices, psychoeducation, cognitive techniques).
Dosage (Frequency, Duration, Length)	Frequency of sessions (e.g., weekly), duration of each session (e.g., 60 minutes), total length of the intervention (e.g., 8 weeks).
Delivery Method	(e.g., group, individual, online).
Provider (Profession)	Who delivered the intervention (e.g., psychologist, trained facilitator).
Control Group	Control Type	(e.g., waitlist, active control [specify what the active control was], usual care).
Control Description	Provide a brief description of the control group intervention.
Outcomes	Anxiety Measure(s)	List all anxiety measures used (e.g., STAI, BAI, GAD-7).
Time Points	List the time points at which anxiety was measured (e.g., pre-intervention, post-intervention, follow-up).
Results (Intervention Group)	Report the mean, standard deviation, and any other relevant statistics (e.g., confidence intervals) for the intervention group at each time point.
Results (Control Group)	Report the mean, standard deviation, and any other relevant statistics (e.g., confidence intervals) for the control group at each time point.
Statistical Significance	Report whether the difference between the intervention and control groups was statistically significant at each time point (p-value). Also report effect sizes (e.g., Cohen's d, Hedges' g).
Other	Adverse Events/Side Effects	Report any adverse events or side effects reported in the study.
Funding Source	Report the funding source of the study.
Conflicts of Interest	Report any conflicts of interest declared by the authors.
Quality	Risk of Bias Assessment	Results of your risk of bias assessment (see Section 4).
Notes	Notes	Any other relevant information or observations about the study.

Key Considerations:

Pilot Testing: Before you start extracting data from all the included studies, pilot test your data extraction form on a few studies. Revise the form as needed to ensure it captures all the necessary information clearly and consistently.

Multiple Reviewers: Have at least two reviewers independently extract data from each study. Compare the extracted data and resolve any discrepancies through discussion. This increases the accuracy and reliability of your data extraction.

Detailed Instructions: Provide clear and detailed instructions for each variable in your data extraction form to minimize ambiguity and ensure consistency across reviewers.

4. Quality Assessment Tools (Risk of Bias Assessment)

Assessing the quality of included studies is crucial for understanding the strength of the evidence. Here are some commonly used tools:

Cochrane Risk of Bias Tool (RoB 2.0): This is the recommended tool for assessing the risk of bias in randomized controlled trials (RCTs). It assesses bias across five domains:

Bias arising from the randomization process: How well was randomization implemented?

Bias due to deviations from intended interventions: Were there deviations from the intended interventions?

Bias due to missing outcome data: Was there substantial missing outcome data?

Bias in measurement of the outcome: Was the outcome assessment blinded?

Bias in selection of the reported result: Was there selective reporting of results?

Each domain is assessed as "low risk," "some concerns," or "high risk" of bias. An overall risk of bias is then assigned to the study. The RoB 2.0 tool is quite complex, so familiarize yourself with the guidance thoroughly.

Risk Of Bias In Non-randomized Studies - of Interventions (ROBINS-I): If you include quasi-experimental studies, use ROBINS-I. It's designed for non-randomized studies and is more comprehensive than older tools.

Newcastle-Ottawa Scale (NOS): Less commonly used now than RoB 2.0 or ROBINS-I, but it can be used for cohort and case-control studies (though unlikely you will include these).

Applying the Quality Assessment Tools:

Training: Ensure all reviewers are thoroughly trained in using the chosen quality assessment tool.

Independent Assessment: Have at least two reviewers independently assess the risk of bias for each included study.

Discrepancy Resolution: Resolve any disagreements through discussion or, if necessary, involve a third reviewer.

Reporting: Clearly report the results of your quality assessment in your review. You can use tables or figures to summarize the risk of bias ratings for each study.

Sensitivity Analysis: Consider conducting a sensitivity analysis to assess how the inclusion or exclusion of studies with high risk of bias affects your overall findings.

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses):

PRISMA is not a quality assessment tool. It's a reporting guideline. Use the PRISMA checklist to ensure you've reported all the essential elements of your systematic review in a clear and transparent manner. The checklist covers sections like:

Title and Abstract

Introduction

Methods (including your search strategy, inclusion/exclusion criteria, data extraction, and risk of bias assessment)

Results (including the PRISMA flow diagram)

Discussion

Funding

In summary, here's a checklist to ensure your literature review is comprehensive and rigorous:

☐ Develop a detailed and comprehensive search strategy for PubMed and PsycINFO. Test it, refine it, and consider grey literature.

☐ Create explicit and specific inclusion/exclusion criteria. Pilot test them with multiple reviewers.

☐ Design a comprehensive data extraction form. Pilot test it, ensure detailed instructions, and use multiple reviewers.

☐ Choose appropriate quality assessment tools (RoB 2.0 or ROBINS-I). Train reviewers and conduct independent assessments.

☐ Use the PRISMA checklist to guide your reporting.

☐ Document every step of the process. This is crucial for transparency and reproducibility.

By following these steps, you'll be well-equipped to conduct a high-quality systematic literature review on the effectiveness of mindfulness-based interventions for anxiety in college students. Good luck! Remember to consult with your research advisor throughout the process.

{DateTime.UtcNow:HH:mm}

GrokxAI

Error calling Grok API.

{DateTime.UtcNow:HH:mm}

Analysis

This comparison demonstrates the different approaches each AI model takes when responding to the same prompt. Here are the key differences observed:

Response Characteristics

ChatGPT: Provides a detailed response with 20 sentences.

Gemini: Provides a detailed response with 195 sentences.

Grok: Provides a concise response with 1 sentences.

Key Takeaways

Each model brings unique strengths to this type of query
Response styles vary significantly between models
Consider your specific use case when choosing between these models

Try This Comparison Yourself

Want to test these models with your own prompts? Visit SNEOS.com to compare AI responses side-by-side in real-time.

This comparison was generated using the SNEOS AI Comparison ToolPublished: October 15, 2025 | Models: ChatGPT, Gemini, Grok