The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; 6 of the 24 sources its claims cite were checked for support.
Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study
Open accessAbstract
BACKGROUND: The nursing process is a systematic, patient-centered framework essential for clinical reasoning and decision-making in nursing education. It is commonly operationalized through the ADPIE (Assessment, Diagnosis, Planning, Implementation, and Evaluation) model, which guides nurses in identifying patient needs, developing care plans, implementing interventions, and evaluating outcomes in a structured and iterative manner. Although the nursing process is fundamental to nursing education and practice, some students may experience difficulties in applying ADPIE effectively, particularly the aspects of clinical reasoning and reflective practice. METHODS: This was a quasi-experimental study conducted to compare the effects of a Generative Artificial Intelligence (GenAI)-assisted nursing process approach with traditional instruction on nursing students' evidence-based critical thinking, learning self-efficacy, and self-reported clinical reasoning. Moreover, the study integrated the intervention into a second-year nursing course (i.e., nursing process via obstetric nursing internship) as part of formal curriculum activities. RESULTS: Students who participated in the GenAI-assisted nursing process approach demonstrated higher levels of evidence-based critical thinking, improved learning self-efficacy, and enhanced self-reported clinical reasoning ability compared with those in the traditional instruction group. The GenAI system provided adaptive feedback, real-time scaffolding, and iterative case refinement beyond traditional case-based learning. CONCLUSIONS: Integrating GenAI into the ADPIE framework within nursing education may enhance students' critical thinking, learning self-efficacy, and self-reported clinical reasoning by supporting structured and reflective learning processes, offering a promising pedagogical approach for nursing education.
Overview
CoChat Summary
TL;DR
This quasi-experimental study compared a generative AI-assisted nursing process (GAANS) approach with traditional instruction in a second-year nursing course. The GAANS group showed significantly higher posttest critical thinking, learning self-efficacy, and self-reported clinical reasoning after controlling for pretest scores.
Key findings
- Critical thinking was higher in the GAANS group than the control group: adjusted means 4.74 vs. 4.26, F(1, 39) = 11.48, p < .01, partial η² = 0.227.
- Learning self-efficacy was higher in the GAANS group: adjusted means 4.55 vs. 4.24, F(1, 39) = 6.70, p < .05, partial η² = 0.147.
- Self-reported clinical reasoning was higher in the GAANS group: adjusted means 4.68 vs. 4.26, F(1, 39) = 8.13, p < .01, partial η² = 0.172.
- The intervention used GenAI for adaptive feedback, real-time scaffolding, and iterative case refinement within the ADPIE framework.
Methods
- Quasi-experimental design in a required second-year undergraduate nursing course, “nursing process via obstetric nursing internship,” at a university in Taiwan; two intact cohorts were assigned to experimental (n = 21) and control (n = 21) groups.
- Of 52 eligible students, 42 participated and completed the study (80.8%); both groups received comparable clinical exposure, content, materials, objectives, and instructor.
- The GAANS intervention ran over 4 weeks with one 120-minute session per week using the Edcafe AI platform and a Pregnancy-Induced Hypertension maternal scenario; outcomes were measured with pretest/posttest questionnaires and analyzed using ANCOVA with pretest as covariate.
Limitations
- The paper states a relatively small sample size, lack of randomization, potential instructor effect, possible ceiling effects from high posttest scores, self-report/social desirability bias, no objective performance-based assessments such as OSCEs, inability to isolate the independent effect of GenAI from other instructional components, limited transparency about the GenAI architecture and prompting strategies, and no confidence intervals for effect size estimates.
- The paper also notes that findings may reflect perceived competence rather than objectively verified clinical reasoning and that large effect sizes should not be interpreted as necessarily indicating strong practical or clinical significance.
- Evident from the text: the study used a convenience sample from one course/university, a short 4-week intervention, and intact class cohorts, which further limits generalizability and causal inference.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
4 Valid · 2 Not valid · 11 Not checked · 46 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Moreover, many students struggle to determine whether the medical or patient-related evidence they retrieve is sufficiently relevant and reliable to support clinical decision-making [3].”
§ Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study > Introduction
What the sources say
- Could not verifycites [3] Hants L, Bail K, Paterson C. Clinical decision-making and the nursing process in digital health systems: An integrated systematic review. J Clin Nurs. 2023;32(19–20):7010–35. https://doi.org/10.1111/jocn.16823. sourceExperimental — accuracy not yet measured
The eligibility criteria (Section 3.2; page unavailable) focus the review on registered nurses using digital health systems and exclude nursing students. Searches for students’ difficulty judging the relevance or reliability of retrieved evidence found no passage addressing that claim. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Students who participated in the GenAI-assisted nursing process approach demonstrated higher levels of evidence-based critical thinking, improved learning self-efficacy, and enhanced self-reported clinical reasoning ability compared with those in the traditional instruction group.”
§ Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study > Abstract > Results
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Students who participated in the GenAI-assisted nursing process approach demonstrated higher levels of evidence-based critical thinking, improved learning self-efficacy, and enhanced self-reported clinical reasoning ability compared with those in the traditional instruction group.”
§ Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study > Abstract > Results
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Students who participated in the GenAI-assisted nursing process approach demonstrated higher levels of evidence-based critical thinking, improved learning self-efficacy, and enhanced self-reported clinical reasoning ability compared with those in the traditional instruction group.”
§ Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study > Abstract > Results
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Findings revealed that students in the experimental group using the GAANS approach demonstrated higher learning self-efficacy than those in the control group, F(1, 39) = 6.70, p < .05, with a partial η² of 0.147, indicating a moderate effect size.”
§ Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study > Results > Learning self-efficacy
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
18 more claims
Create a free account to see all 63 claims and to verify the 3 references still open.
- It may state two separate claims as one. 23
- Probably not a substantial claim. 25
Statistics recomputed
Every reported test result, recomputed from its test statistic and degrees of freedom. A result shows as not adding up only once an independent check has confirmed it.
- ConsistentF(1, 40) = 0.83reported p = .369 · recomputed p = .368
“F(1, 40) = 0.83, p = .369”
- ConsistentF(1, 39) = 11.48reported p < .01 · recomputed p = .002
“F(1, 39) = 11.48, p < .01”
- ConsistentF(1, 40) = 0.84reported p = .37 · recomputed p = .365
“F(1, 40) = 0.84, p = .37”
- ConsistentF(1, 39) = 6.7reported p < .05 · recomputed p = .013
“F(1, 39) = 6.70, p < .05”
- ConsistentF(1, 40) = 0.11reported p = .74 · recomputed p = .742
“F(1, 40) = 0.11, p = .74”
1 more recomputed test
Create a free account to see every test the Stats check recomputed.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Self-check results appear here once an independent check has confirmed them.
Citations
Cites
Self-efficacy: Toward a unifying theory of behavioral change
Bandura, A. (1977) · Psychological Review · doi:10.1037/0033-295x.84.2.191 · Cited by 43,925
AI-based learning style detection in adaptive learning systems: a systematic literature review
Ezzaim, A., Dahbi, A., Aqqal, A., & Haidine, A. (2025) · Journal of Computers in Education · doi:10.1007/s40692-024-00328-9 · Cited by 109 · cited 1×
“GenAI can provide real-time feedback, generate patient scenarios, and support learners in synthesizing complex clinical information, thereby facilitating deeper cognitive engagement and active learning [38].”
Bressington, D. T., Wong, W.-K., Lam, K. K. C., & Chien, W. T. (2018) · Nurse Education Today · doi:10.1016/j.nedt.2017.09.019 · Cited by 105 · cited 1×
“…operationalizing clinical reasoning in a stepwise and cognitively transparent manner [11–13], expanding their medical knowledge [14], and strengthening their critical thinking [15] as well as self-efficacy [16], communication, and interpersonal collaboration within patient care contexts [17].”
Liou, S., Liu, H., Tsai, H., Tsai, Y., Lin, Y., Chang, C., & Cheng, C. (2016) · Journal of Advanced Nursing · doi:10.1111/jan.12831 · Cited by 104 · cited 1×
“Clinical reasoning was measured using the Nurses’ Clinical Reasoning Scale (NCRS), a self-report questionnaire originally developed by Liou et al. [45]; its (2) Assesses the case outcomes objectively and effectively.”
Self-citationTeaching strategies of clinical reasoning in advanced nursing clinical practice: A scoping review
Giuffrida, S., Silano, V., Ramacciati, N., Prandi, C., Baldon, A., & Bianchi, M. (2023) · Nurse Education in Practice · doi:10.1016/j.nepr.2023.103548 · Cited by 87 · cited 2×
“Several previous studies have further reported the important role of critical thinking in fostering nursing knowledge [10].”
Alshehri, F. D., Jones, S., & Harrison, D. (2023) · Nurse Education Today · doi:10.1016/j.nedt.2022.105679 · Cited by 86 · cited 1×
“In real clinical settings, nurses need to employ patient-centered mental models that enable efficient cognitive shortcuts, drawing on established schemas, prior experiences, and intuitive insights to reach conclusions [29].”
Zhang, T., Wu, X., Peng, G., Zhang, Q., Chen, L., Cai, Z., & Ou, H. (2021) · International Journal of Nursing Knowledge · doi:10.1111/2047-3095.12315 · Cited by 82 · cited 1×
“…have sufficient time to find evidence-based references to continuously refine their understanding of the nursing process for patient care decisions [4]; consequently, they may lack a comprehensive grasp of the key aspects of clinical problems, and demonstrate insufficient proficiency in patient…”
Shan, Y., Shang, J., Yan, Y., & Ye, X. (2023) · BMC Nursing · doi:10.1186/s12912-023-01209-9 · Cited by 79 · cited 1×
“…references to continuously refine their understanding of the nursing process for patient care decisions [4]; consequently, they may lack a comprehensive grasp of the key aspects of clinical problems, and demonstrate insufficient proficiency in patient history taking and physical assessment [5].”
Hants, L., Bail, K., & Paterson, C. (2023) · Journal of Clinical Nursing · doi:10.1111/jocn.16823 · Cited by 79 · cited 1×
“Moreover, many students struggle to determine whether the medical or patient-related evidence they retrieve is sufficiently relevant and reliable to support clinical decision-making [3].”
Registered nurses' clinical reasoning skills and reasoning process: A think-aloud study
Lee, J., Lee, Y. J., Bae, J., & Seo, M. (2016) · Nurse Education Today · doi:10.1016/j.nedt.2016.08.017 · Cited by 74 · cited 1×
“Lee et al. defined clinical reasoning as the cognitive processes underlying professional judgment, evaluating evidence quality, solving problems, and formulating diagnostic and management decisions [28].”
Research works printed but not linked: 7
- Saucier BL, Stevens KR, Williams GB. Critical thinking outcomes of computer-assisted instruction versus written nursing process. Nurs Health Care Perspect. 2000;21(5):240.
- Aldhaferi EAM, Alrsheidy SKD, Alshammari NMK, Alanazi MOS, Alshammari NK, Alenezi MN. Enhancing person-centered care through reflective practice: A qualitative study on the collaboration between nurse technicians and health management specialists. J Int Crisis Risk Commun Res. 2024;7(S10):2028.
- Reis da Silva TH. The nursing process in geriatric care: a comprehensive approach. Int J Biomed Res. 2024;3(5). https://doi.org/10.31579/2834-5029/064. · doi:10.31579/2834-5029/064
- Potter PA, Perry AG, Stockert PA, Hall A, Ostendorf WR. Fundamentals of nursing. St. Louis (MO): Elsevier; 2025.
- American Nurses Association. Nursing: Scope and standards of practice. 4th ed. Silver Spring (MD): American Nurses Association; 2021.
- Rakhmawati D, Fitria R. Reading classics reinvented: Development of easy create reading activities based on Edcafe AI to enhance literary comprehension. Inovish J. 2025;10(1):9–21. https://doi.org/10.35314/inovish.v10.i1.603. · doi:10.35314/inovish.v10.i1.603
- Chang CY, Kao CH, Hwang GJ. Facilitating students’ critical thinking and decision making performances. Educ Technol Soc. 2020;23(2):32–46.
Metadata
- Authors
- Dwiarini, M., Hwang, G.-J., & Chang, C.-Y.
- Affiliations
- Taipei Medical University (TW)
- National Taiwan University of Science and Technology (TW)
- Corresponding author
- Chang, Ching-Yi
- Venue
- BMC Nursing
- Published
- 2026-07-09
- Volume
- 25
- Issue
- 1
- ISSN
- 1472-6955 (ISSN-L)
- PMC
- PMC13531795
- OpenAlex
- W7167795843
- Semantic Scholar
- dea1d3251f1753a7f9c4614ba5738c7fc42985af
- Cited by
- 1
- References
- 41
- Citations by year
- 2026: 1
- FWCI
- 1.95
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc-nd
- creativecommons.org/licenses/by-nc-nd/4.0 (tdm)
- creativecommons.org/licenses/by-nc-nd/4.0 (vor, 53 d)
- Locations
- BMC Nursing (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Ministry of Science and Technology, Taiwan (NSTC 113-2410-H-038-026-MY2)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Nursing › Research and Theory › Nursing Diagnosis and Documentation
- Health Sciences › Health Professions › General Health Professions › Health Sciences Research and Education
- Keywords
- generative AI, nursing process, clinical reasoning, critical thinking, learning self-efficacy, nursing students, case-based learning, adaptive feedback, scaffolding, reflective practice
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study. https://app.cochat.ai/papers/10.1186/s12912-026-04840-4
- The paper
- Dwiarini, M., Hwang, G.-J., & Chang, C.-Y. (2026). Effects of a generative AI-assisted ADPIE Framework on critical thinking, learning self-efficacy, and clinical reasoning in nursing education: a quasi-experimental study. BMC Nursing. https://doi.org/10.1186/s12912-026-04840-4
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.