Enhancing discharge care coordination in mental health and social care: A probabilistic data-driven modelling approach

The demand for mental health services has seen a surge in recent years, an event that has been further intensified by the COVID-19 pandemic [1].

Furthermore, this issue is compounded by poor transitions from mental health services to social care including community or care home settings, resulting in adverse consequences for service users, their families, caregivers, and social service providers [2].

Inadequate coordination among mental health and social care services can lead to several challenges, including poor discharge planning and misallocation of resources [3]. To tackle these challenges, implementing innovative approaches grounded on data-driven evidence is vital.

The application of data-driven methodologies holds significant promise for yielding valuable insights [4] that can facilitate informed decision-making, efficient resource allocation, and improved coordination among managers, families, and practitioners, so enhancing the overall quality of care provided in mental health and social care.

The proposed project aims to develop novel probabilistic modelling tools [5] including AI & machine learning methods to enhance the management of care services.

The project aligns with prevailing trends and pressing challenges in the field of mental health and social care management, addressing four primary areas