Conectar
Systematic reviews (SRs) require comprehensive, reproducible searches, yet developing search strategies is resource-intensive and demands specialized expertise. Generative AI offers potential to streamline this process, but empirical evaluations for GAI-assisted SR searching remain scarce. The objectives of this study are to: demonstrate a step-by-step process for developing a custom ChatGPT-based chatbot to support SR search strategy development, and evaluate its performance.
A cross-sectional evaluation study.
We used ChatGPT-4.0 to create a chatbot designed to mimic a medical librarian, generating PICO-informed searches. Its knowledge base was augmented with two methodological references. After piloting testing, we refined its instructions. For evaluation, we randomly sampled 50 Cochrane SRs published in 2024. Standardized P–I–O prompts produced database-ready queries for PUBMED and EMBASE. The primary outcome was per-review success rate, summarized by median and inter-quartile range. A sensitivity analysis was conducted.
Pilot testing achieved a retrieval rate of 41/49 (83.7%). In the main sample (1169 studies; median 13.5 studies per SR), the chatbot identified a median of 67.4% of included studies (IQR: 43.1%–88.4%). When limited to indexed studies (n = 1114), retrieval rose to 72.0% (IQR: 46.0%–92.5%). Lower performance was observed when outcomes were absent from the abstracts or interventions had many lexical variants.
A GAI-based chatbot can rapidly generate SR searches (~67%–72% identification), serving as a useful starting point but not a replacement for expert-led approaches. Integration of librarian expertise, structured prompts, and controlled vocabularies may improve performance. Further benchmarking and transparent reporting are needed to guide adoption.
The use of technology to support nurses' decision-making is increasing in response to growing healthcare demands. AI, a global trend, holds great potential to enhance nurses' daily work if implemented systematically, paving the way for a promising future in healthcare.
To identify and describe AI technologies for nurses' clinical decision-making in healthcare settings.
A systematic literature review.
CINAHL, PubMed, Scopus, ProQuest, and Medic were searched for studies with experimental design published between 2005 and 2024.
JBI guidelines guided the review. At least two researchers independently assessed the eligibility of the studies based on title, abstract, and full text, as well as the methodological quality of the studies. Narrative analysis of the study findings was performed.
Eight studies showed AI tools improved decision-making, patient care, and staff performance. A discharge support system reduced 30-day readmissions from 22.2% to 9.4% (p = 0.015); a deterioration algorithm cut time to contact senior staff (p = 0.040) and order tests (p = 0.049). Neonatal resuscitation accuracy rose to 94%–95% versus 55%–80% (p < 0.001); seizure assessment confidence improved (p = 0.01); pressure ulcer prevention (p = 0.002) and visual differentiation (p < 0.001) improved. Documentation quality increased (p < 0.001).
AI integration in nursing has the potential to optimise decision-making, improve patient care quality, and enhance workflow efficiency. Ethical considerations must address transparency, bias mitigation, data privacy, and accountability in AI-driven decisions, ensuring patient safety and trust while supporting equitable, evidence-based care delivery.
The findings underline the transformative role of AI in addressing pressing nursing challenges such as staffing shortages, workload management, and error reduction. By supporting clinical decision-making and workflow efficiency, AI can enhance patient safety, care quality, and nurses' capacity to focus on direct patient care. A stronger emphasis on research and implementation will help bridge usability and scalability gaps, ensuring sustainable integration of AI across diverse healthcare settings.
FreshRSS 