Evaluation of the Reliability and Quality of Nursing Care Plans Produced by Artificial Intelligence Models for Patients Experiencing Anaphylactic Shock: A Methodological and Exploratory Investigation.
- 1Kahramanmaraş Sütçü İmam University, Health Services Vocational School, Kahramanmaraş, Türkiye.
- 2Department of Nursing, Kahramanmaraş Sütçü İmam University Faculty of Health Sciences, Kahramanmaraş, Türkiye.
Abstract
Aim
This study aimed to develop and validate a ChatGPT 4.0 and DeepSeek V3 model-supported nursing care plan for patients with anaphylactic shock.Methods
The type of study is methodological and exploratory research. The research consists of three phases and six steps. Phase 1: Patient Scenario Development: (1) literature review and (2) scenario creation. Phase 2: Nursing Care Plan Development: (3) identification of patient care needs and (4) generation of a scenario-based nursing care plan by AI. Phase 3: Validation of the Nursing Care Plan: (5) expert review and validation of the AI-generated nursing care plan and (6) assessment of the nursing care plan's readability. ChatGPT 4.0 and DeepSeek V3 were employed to create nursing care plans. The Grading of Recommendations Assessment, Development, and Evaluation scale was utilized to evaluate the quality of nursing care plans. The intraclass correlation coefficient was utilized to assess the inter-rater reliability of the evaluation tool. The analysis of readability was conducted utilizing the Ateşman, the Flesch-Kincaid Grade Level, the Gunning Fog Index, and the Simple Measure of Gobbledygook formula.Results
A notable difference emerged between the models in the Nursing Assessment section, as experts assigned higher scores to ChatGPT 4.0 (p < .005). No significant differences were found among the artificial intelligence models in other sections (p > .05). DeepSeek V3 exhibited an elevated readability level, indicated by a Flesch-Kincaid Grade Level of 13.19, a Gunning Fog Index of 17.20, and an Simple Measure of Gobbledygook score of 9.91.Conclusion
Nursing care plans designed with artificial intelligence support are sufficiently readable and applicable for nurses. Cite this article as: Soylu, A., & Soylu, D. (2026). Evaluation of the reliability and quality of nursing care plans produced by artificial intelligence models for patients experiencing anaphylactic shock: a methodological and exploratory investigation. Florence Nightingale Journal of Nursing, 34, 0162, doi: 10.5152/FNJN.2026.25162.
Related
- Multi-model LLM assessment of Quality Control Circle methodological quality: a designed-anchor reliability study
- Pantoprazole-induced anaphylactic asthma and Type I Kounis syndrome: a case report and literature review
- AdaSwitch3D: Reliability-Aware Human-in-the-Loop Artificial Intelligence for Breast Tumor Segmentation in Dynamic Contrast-Enhanced MRI Across Unseen Centers
- Artificial intelligence for women’s reproductive health: A scoping review of global diagnostic trends, methodological gaps, and a translational research agenda for low-resource settings
- Emergency management and nursing care of a patient with moxifloxacin-induced anaphylactic shock complicated with Takotsubo syndrome.
BibTeX
@article{soylu2026evaluation,
title = {{Evaluation of the Reliability and Quality of Nursing Care Plans Produced by Artificial Intelligence Models for Patients Experiencing Anaphylactic Shock: A Methodological and Exploratory Investigation.}},
author = {Ayşe Soylu and Dilek Soylu},
journal = {Florence Nightingale journal of nursing},
year = {2026},
month = sep,
doi = {10.5152/fnjn.2026.25162},
url = {https://europepmc.org/article/MED/42851040},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Evaluation of the Reliability and Quality of Nursing Care Plans Produced by Artificial Intelligence Models for Patients Experiencing Anaphylactic Shock: A Methodological and Exploratory Investigation.
AU - Ayşe Soylu
AU - Dilek Soylu
PY - 2026
DA - 2026/09/29
JO - Florence Nightingale journal of nursing
DO - 10.5152/fnjn.2026.25162
UR - https://europepmc.org/article/MED/42851040
AB - Aim This study aimed to develop and validate a ChatGPT 4.0 and DeepSeek V3 model-supported nursing care plan for patients with anaphylactic shock.Methods The type of study is methodological and exploratory research. The research consists of three phases and six steps. Phase 1: Patient Scenario Development: (1) literature review and (2) scenario creation. Phase 2: Nursing Care Plan Development: (3) identification of patient care needs and (4) generation of a scenario-based nursing care plan by AI. Phase 3: Validation of the Nursing Care Plan: (5) expert review and validation of the AI-generated nursing care plan and (6) assessment of the nursing care plan's readability. ChatGPT 4.0 and DeepSeek V3 were employed to create nursing care plans. The Grading of Recommendations Assessment, Development, and Evaluation scale was utilized to evaluate the quality of nursing care plans. The intraclass correlation coefficient was utilized to assess the inter-rater reliability of the evaluation tool. The analysis of readability was conducted utilizing the Ateşman, the Flesch-Kincaid Grade Level, the Gunning Fog Index, and the Simple Measure of Gobbledygook formula.Results A notable difference emerged between the models in the Nursing Assessment section, as experts assigned higher scores to ChatGPT 4.0 (p < .005). No significant differences were found among the artificial intelligence models in other sections (p > .05). DeepSeek V3 exhibited an elevated readability level, indicated by a Flesch-Kincaid Grade Level of 13.19, a Gunning Fog Index of 17.20, and an Simple Measure of Gobbledygook score of 9.91.Conclusion Nursing care plans designed with artificial intelligence support are sufficiently readable and applicable for nurses. Cite this article as: Soylu, A., & Soylu, D. (2026). Evaluation of the reliability and quality of nursing care plans produced by artificial intelligence models for patients experiencing anaphylactic shock: a methodological and exploratory investigation. Florence Nightingale Journal of Nursing, 34, 0162, doi: 10.5152/FNJN.2026.25162.
SN - 2687-6442
ER -