The contribution of machine learning to the prevention of burnout among healthcare workers in Morocco

TL;DR

This paper explores how machine learning can be used to develop predictive models to prevent burnout among healthcare workers in Morocco, especially during high-stress periods like the COVID-19 pandemic.

Contribution

It introduces a modeling approach using supervised learning to predict emotional exhaustion risks among healthcare staff, filling a gap in AI applications for psychosocial risk prevention in healthcare.

Findings

Development of a predictive model for burnout risk

Potential to assist decision-makers in preventive measures

Enhancement of psychosocial risk management systems

Abstract

In recent years, and particularly during the Covid-19 pandemic, Morocco has experienced significant pressure from user demand, leading to a significant workload in public hospitals. This situation raises major questions regarding the occupational health of healthcare staff. While previous studies have focused on the role of AI in the safety and resilience of military personnel, no research has investigated its role in protecting healthcare personnel from psychosocial risks. This inadequacy leads us to formulate the following central question:What is the contribution of machine learning to the prevention of emotional exhaustion (burnout) among healthcare staff in Morocco? This work is part of a modeling approach aimed at developing a predictive model of the risks of emotional exhaustion (burn-out), the parameters of which will be estimated using supervised learning. From a scientific perspective, this work aims to contribute to the development of systems for preventing psychosocial risks affecting staff in healthcare establishments. From a managerial perspective, this research aims to equip decision-makers in healthcare establishments so that they can anticipate psychosocial disorders linked to emotional exhaustion (burn-out) and implement appropriate preventive measures.