A hybrid predictive and prescriptive modelling framework for long-term mental healthcare workforce planning

Over the past decade, there has been a severe staffing shortage in mental healthcare, exacerbated by increased demand for mental health services due to COVID-19. This demand is projected to increase over the next decade or so, necessitating proactive workforce planning to ensure sufficient staffing for ongoing service delivery. Despite the subject's critical significance, the present literature lacks thorough research dedicated to developing a model that addresses the long-term workforce needs required for efficient mental healthcare planning. Furthermore, our interactions with mental health practitioners within the United Kingdom's National Health Service (NHS) revealed the practical need for such a model. To address this gap, we aim to develop a hybrid predictive and prescriptive modelling framework, which combines long-term probabilistic forecasting with an analytical stock-flow model, designed specifically for mental health workforce planning. Given the vital role of nurses, who account for one-third of the total mental health workforce, we focus on modelling the headcount of nurses, but the proposed model can be generalised to other types of workforce planning in the healthcare sector. Using statistical and machine learning approaches and real-world data from NHS, we first identify factors contributing to variations in workforce requirements, then develop a long-term forecasting model to estimate future workforce needs, and finally integrate it into an analytical stock-flow method to provide policy analysis. Our findings highlight the unsustainable nature of present staffing plans, showing a growing nursing shortage. Furthermore, the policy analysis demonstrates the ineffectiveness of blanket remedies, highlighting the need for regional-level policy developments.