Natural Language Processing for Work-Related Stress Detection Among Health Professionals: Protocol for a Scoping...

Area of Science:

• Healthcare Informatics
• Computational Linguistics
• Occupational Health Psychology

Background:

• Growing global demand for healthcare professionals necessitates addressing high attrition rates.
• Work-related stress significantly impacts healthcare professionals' well-being and patient care quality.
• Effective stress detection methods are crucial for supporting the healthcare workforce.

Purpose of the Study:

• To conduct a scoping review identifying processes and methods for automatic detection of work-related stress in health professionals.
• To explore the application of natural language processing (NLP) and text mining techniques for stress detection.
• To identify current research gaps and future directions in this field.

Main Methods:

• Systematic scoping review following Joanna Briggs Institute Methodology and PRISMA-ScR guidelines.
• Inclusion of studies on health professionals using NLP for work-related stress detection (2013-present).
• Data extraction and synthesis using tables, graphs, and a narrative summary.

Main Results:

• Anticipated completion of the systematic scoping review by June 2024.
• Identification of NLP applications, stress criteria, and technical aspects relevant to stress detection.
• Synthesis of findings to provide a comprehensive overview of NLP's role in detecting health professional stress.

Conclusions:

• This review addresses a literature gap in automated work-related stress detection among health professionals using NLP.
• It offers insights into an innovative approach and highlights areas for future research.
• Acknowledges limitations such as methodological constraints and sample biases to refine future methodologies.