ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns

Malik Sallam

doi:10.3390/healthcare11060887

Home SearchPaper Details

ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns

Malik Sallam

Multidisciplinary Digital Publishing Institute (2023) • Volume 11, Issue 6, Pages 887-887

SynthesisSystematicReviewPDF AvailableGrade Eligible⚠️ Moderate Risk Flags

Overall Assessment

Limited Methodological Quality

Assessment created by PaperScores Medical AI v0.1.0 on Dec 14, 2025

D

43/100

Key Takeaways

•Search to 16 Feb 2023 identified 60 records on ChatGPT in healthcare.
•Benefits cited across writing, research, practice, and education; concerns dominated ethics, inaccuracy, and transparency.
•Single-author screening with no registration or risk-of-bias appraisal limits credibility.
•Counts/percentages summarised; no meta-analysis; PRISMA flow included.

Conclusion

Useful early mapping but methodologically weak as a systematic review; interpret descriptive tallies with caution.

Quick Actions

Read Full Paper

Quality Dimensions

Bias & Integrity

COI handling, outcome switching, selective reporting

C-55

Methods Rigour

Protocol clarity, sampling, controls

D-30

External Validity

Generalisability, setting, population

D45

Transparency & Reproducibility

Data/code/materials availability, preregistration

D-35

Significance & Novelty

Contribution vs prior art; context if known

C60

Statistical Validity

Models, assumptions, multiplicity, CI priority

D-35

Integrity & Transparency

Integrity checks

P-hacking risk?

?

None suspected

Signs of selective hypothesis testing or analysis choices that could inflate false positive rates.

Outcome switching?

?

Review recommended

Evidence that primary outcomes were changed during or after the study, potentially distorting results.

Conflict of interest?

?

None suspected

Authors have financial or other relationships that could bias research findings.

Data integrity issues?

?

None suspected

Concerns about the accuracy, completeness, or authenticity of the reported data.

Open science signals

Research data

?

Not shared

Raw data used in the analyses is publicly available or accessible upon request.

Analysis code

?

Not shared

Code or scripts used to analyze the data are shared for reproducibility.

Study materials

?

Not shared

Protocols, questionnaires, and other materials are publicly available.

Premise

Primary Research Question

What are the utilities and valid concerns of ChatGPT in healthcare education, research, and practice?

Hypothesis is Falsifiable

—Not specified

Descriptive mapping review; no testable hypothesis.

PICO Framework

Population✓Yes

English academic/preprint records on ChatGPT in healthcare.

Intervention—Not specified

No intervention; literature synthesis.

Comparison—Not specified

No comparator.

Outcome✓Yes

Benefits/risks categories extracted and tallied.

Literature Positioning

Literature Review Balanced

Well covered

Synthesises 60 records across formats; presents benefits and concerns.

Evidence: p. 5–13; Fig. 3–4

Research Gap Clearly Stated

Well covered

Aims to map utilities and limitations of ChatGPT in healthcare.

Evidence: p. 3 Introduction/Aims

Stated Contribution Clear

Well covered

Rapid overview of benefits/risks with counts and PRISMA flow.

Evidence: Fig. 1; p. 11–13

Study Provenance

Peer reviewed venueFunding disclosedNo conflicts declared4 affiliations listed

Authors & Affiliations

University of Jordan; Jordan University Hospital, Amman, Jordan.

Funding Statement

This research received no external funding.

Conflicts of Interest

The author declares no conflict of interest.

Peer Review

✓Healthcare (MDPI) peer-reviewed; received 20 Feb 2023, accepted 17 Mar 2023.

Evidence: p. 1 header

Methodological Assessment

Systematic Review / Meta-AnalysisPRISMASR/MA

10 applicable checklist items.

Yes 4 · No 6

Protocol & Search

✗

Protocol Registered (PROSPERO/OSF)

No registration/protocol (e.g., PROSPERO) reported.

Evidence: p. 3 Methods; none cited

✓

Search Strategy Reproducible

Exact PubMed query and Google Scholar term/timeframe reported.

Evidence: p. 3 Methods 2.1

✓

Inclusion/Exclusion Criteria Clear

Clear eligibility/exclusion criteria listed.

Evidence: p. 3 Methods 2.1

✓

PRISMA Flow Diagram Provided

PRISMA-style flow diagram provided.

Evidence: Fig. 1

✗

Duplicate Screening & Extraction

Single author screened/extracted; no duplicate processes.

Evidence: p. 16 Sec. 4.7

Quality Assessment

✗

Risk of Bias Assessed

No risk-of-bias or quality appraisal performed.

Evidence: p. 4 Methods 2.3; p. 16

✗

RoB Tool Used and Applied

No ROB tool (e.g., AMSTAR, ROBIS) described.

Evidence: p. 3–4 Methods

✗

GRADE Certainty Assessed

No GRADE/certainty assessment.

Evidence: Methods/Results absent

Synthesis & Analysis

✗

Publication Bias Assessed

No assessment of publication bias.

Evidence: Methods/Results absent

✓

Exposure of Interest Consistent

All records centred on ChatGPT in healthcare contexts.

Evidence: p. 3 Eligibility; p. 5 Results

Modules without applicable checklist items (9)

These designs were fully marked as not applicable but remain available for reference.

Abstract

ChatGPT is an artificial intelligence (AI)-based conversational large language model (LLM). The potential applications of LLMs in health care education, research, and practice could be promising if the associated valid concerns are proactively examined and addressed. The current systematic review aimed to investigate the utility of ChatGPT in health care education, research, and practice and to highlight its potential limitations. Using the PRIMSA guidelines, a systematic search was conducted to retrieve English records in PubMed/MEDLINE and Google Scholar (published research or preprints) that examined ChatGPT in the context of health care education, research, or practice. A total of 60 records were eligible for inclusion. Benefits of ChatGPT were cited in 51/60 (85.0%) records and included: (1) improved scientific writing and enhancing research equity and versatility; (2) utility in health care research (efficient analysis of datasets, code generation, literature reviews, saving time to focus on experimental design, and drug discovery and development); (3) benefits in health care practice (streamlining the workflow, cost saving, documentation, personalized medicine, and improved health literacy); and (4) benefits in health care education including improved personalized learning and the focus on critical thinking and problem-based learning. Concerns regarding ChatGPT use were stated in 58/60 (96.7%) records including ethical, copyright, transparency, and legal issues, the risk of bias, plagiarism, lack of originality, inaccurate content with risk of hallucination, limited knowledge, incorrect citations, cybersecurity issues, and risk of infodemics. The promising applications of ChatGPT can induce paradigm shifts in health care education, research, and practice. However, the embrace of this AI chatbot should be conducted with extreme caution considering its potential limitations. As it currently stands, ChatGPT does not qualify to be listed as an author in scientific articles unless the ICMJE/COPE guidelines are revised or amended. An initiative involving all stakeholders in health care education, research, and practice is urgently needed. This will help to set a code of ethics to guide the responsible use of ChatGPT among other LLMs in health care and academia.

Quick Actions

Read Full Paper

Study Overview

Study Design

Systematic Review

Primary classification used to evaluate this research.

Population

English-language records on ChatGPT in healthcare education, research, and practice.

Brief summary of who or what was studied.

Sample Size

60

Number of participants included in the study analyses.

Pre-registration

Not registered

Indicates whether the protocol or trial was registered before data collection.

Primary Outcome

Unclear whether the primary outcome was pre-specified.

Reviewer Notes

Systematic review using PRISMA of literature to 16 Feb 2023; quantitative counts only; no meta-analysis.

Publication Details

DOI

10.3390/healthcare11060887

Published

March 19, 2023

Citations

2375 citations

FWCI

124.00

External Resources

DOI Link OpenAlex

Disclaimer: This assessment is generated by AI and should not be the sole basis for clinical or research decisions. Always review the original paper and consult with domain experts.

Suggested Papers

C+

Healthcare utilization and maternal and child mortality during the COVID-19 pandemic in 18 low- and middle-income countries: An interrupted time-series analysis with mathematical modeling of administrative data

Tashrik Ahmed et al.•2022

C

The genetic and functional basis of purine nucleotide feedback-resistant phosphoribosylpyrophosphate synthetase superactivity.

Michael A. Becker et al.•1995

No Report

Deficient Regulatory T Cell Activity and Low Frequency of IL-17-Producing T Cells Correlate with the Extent of Cardiomyopathy in Human Chagas' Disease

Paulo Marcos da Matta Guedes et al.•2012

Suggested Papers

From Our Blog

The Law of Small Numbers: Don't Trust the Trend

Small sample sizes yield extreme results. This is not a pattern. It is noise.

The Hierarchy of Evidence: Not All Papers Are Equal

A case study is not the same as a clinical trial. Learn the pyramid of evidence to know which studies to trust.

Type I vs Type II Errors: False Alarms and Missed Opportunities

In science, you can be wrong in two ways. You can see a ghost that isn't there, or miss a truck that is.