PROCED-DST – PROactive, Collaborative and Efficient complex Discharge – Decision Support Tool

Lay Description

As of January 2023, 14,436 patients a day remained in hospital despite being well enough to leave. This is due to delays in arrangements for onward care.

Discharge delay occupies beds putting pressure on a wide-range of NHS services. Leaving hospital at the right time is also better for patients, reducing physical and mental de-conditioning and chance of hospital infections. Discharge planning involves patients, clinical teams in hospitals, community care, and local authorities. Organising care takes time considering the availability of social care services and mediation with patients and their families. An initial discharge assessment should be made within the first 24 hours of hospital admission. In practice this planning is provided for less than 50% of patients due to staff workload and inability to identify care requirements can delay assessments.

Aims: In a previous project called PROCED, we developed a machine learning (ML) model to predict onward care needs when someone is admitted to hospital. In PROCED-DST we aim to investigate how these predictions can support better discharge planning. Planning care earlier during hospital stays gives more time for patients and families to discuss care needs with care workers and to leave hospital on time.

Approach: We will consider how a decision support tool (DST) using these predictions can help clinicians organise onward care. We will organise collaborative sessions with clinicians, patients, and computer scientists to design the DST and understand how the predictions can be used. We will also understand how the model generalises to new data/site at Portsmouth Hospitals University Foundation Trust (PHUFT).

Public Benefit Statement

Reducing discharge delays are important for patients.

Firstly, patients with complex care needs (e.g., nursing at home, reablement) prior to admission have a higher risk of delay. Longer hospital stays lead to poorer patient outcomes due to increased risk of physical and cognitive deconditioning complications, increased risk of hospital acquired infections which can snowball as patients accumulate further care needs. Prompt discharge is important for health and reducing risk of negative outcomes such as readmission.

Secondly, the rationale is important for wider service delivery. Complex discharge is a significant challenge for decision makers who must ensure efficient flow of patients from hospital to ongoing community care by matching patient care needs with community care resources. The process involves several stakeholders (patients, hospital, community care providers, care and nursing homes, rehabilitation services, local authorities, brokers) who must collaborate to implement a safe discharge whilst considering the patient voice. Whilst all service providers are patient centred, struggles occur regarding discharge acuity (i.e. medically optimising too early for community care provision), distribution of responsibility and risk, and conflicts between institutional targets, interests, and resources. The wide range of community and social care services, operational structures, and funding models makes ongoing care resource planning challenging as services cannot be uniformly characterised.