Saved in:
| Main Author: | |
|---|---|
| Format: | Artículo científico |
| Language: | en |
| Published: |
Universidad Autónoma de Bucaramanga
2024
|
| Subjects: | |
| Online Access: | https://www.redalyc.org/articulo.oa?id=71979998006 https://www.redalyc.org/journal/719/71979998006/ https://www.redalyc.org/journal/719/71979998006/html/ https://www.redalyc.org/journal/719/71979998006/71979998006.epub https://www.redalyc.org/journal/719/71979998006/movil https://doi.org/10.29375/01237047.4633 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- RNAO’s Artificial Intelligence Innovations: A Novel Strategy to Advance Evidence-Based Nursing Practice Shanoja Naik Doris Grinspun Medicina Evidence Based Nursing Machine Learning Artificial Intelligence Health Information Systems Introduction. Artificial intelligence and machine learning methodologies, such as prediction, pattern recognition, or general inference based on the data used in clinical aspects, must fit within the intended purposes of developing it. This article aims to provide high-level, non-technical details of the initiative and a comprehensive approach that has been taken to integrate AI-powered techniques in evidence- based nursing practices appropriately. Methodology. A multi-pronged phased approach was considered for developing artificial intelligence tools. This approach includes conducting a scoping review, analyzing data to identify patterns of impactful intervention, employing data triangulation, enhancing data collection based on impactful intervention strategies, and developing a prototype (pilot) for an artificial intelligence tool. The process encompasses piloting, testing and training, validation, and implementation. Results. In this early stage of piloting the tool, the primary focus was identifying patterns from various information gathered from healthcare organizations. This analysis revealed opportunities for knowledge generation, facilitated the expedited implementation of guidelines, and enhanced resource efficiency. Discussion. Focusing on a data-driven model to inform best practices for implementing guidelines and identifying the most impactful interventions is facilitated by extensive in-house data storage. The triangulation of approaches to guideline development, implementation, and evaluation contributes to developing this scientifically validated artificial intelligence and machine learning initiative. Conclusion. Any artificial intelligence technique requires extensive data. To provide healthcare organizations with the best available evidence, purposeful efforts must be made to structure data collection and ensure data quality before expanding the development of artificial intelligence tools. 2024 artículo científico 0123-7047 https://www.redalyc.org/articulo.oa?id=71979998006 https://www.redalyc.org/journal/719/71979998006/ https://www.redalyc.org/journal/719/71979998006/html/ https://www.redalyc.org/journal/719/71979998006/71979998006.epub https://www.redalyc.org/journal/719/71979998006/movil https://doi.org/10.29375/01237047.4633 en http://www.redalyc.org/revista.oa?id=719 MedUNAB application/pdf Universidad Autónoma de Bucaramanga MedUNAB (Colombia) Num.1 Vol.27