Date created: | Last Updated:

Category: Project

Description: This protocol outlines a scoping review aiming to map existing evidence on the use of machine learning (ML) for occupational risk communication with healthcare workers. Background: The rapid growth of ML necessitates exploring best practices for using it to communicate and manage occupational risks faced by healthcare workers. Methods: The review will search ten major academic databases (PUBMED, MEDLINE, etc.) focusing on studies published between 2019 and 2023. Inclusion criteria specify studies involving healthcare workers, ML use in communication, and occupational risk management strategies. Excluded are studies on other populations, non-ML communication tools, and non-occupational risk communication contexts. Analysis: The review follows PRISMA-ScR and JBI guidelines. Data extraction will use an adapted JBI form in Microsoft Excel, and a narrative synthesis will summarize key findings. Results will be published in a peer-reviewed journal. Strengths: ML offers potential benefits in: • Enhancing risk analysis accuracy for healthcare workers. • Predicting future risks and enabling proactive measures. • Customizing risk communication to improve awareness and adherence to safety standards. Limitations: Potential limitations include: • Data quality affecting prediction effectiveness. • Ethical, legal, and privacy considerations surrounding ML implementation in healthcare being a recent development. Keywords: Machine Learning, risk communication, occupational health and safety, healthcare workers.