Skip to main content
Using predictive analytics in adult social care

A case study with Luton Adult Social Care.

Luton Council aimed to improve the communication between healthcare and adult social care.

Background

The e-frailty index is collated from primary care data including symptoms, diseases, disabilities and abnormal test values. However, for falls and other health conditions requiring a system response via the Telecare system, data are not routinely collated into the Primary Care Home (PCH) dataset. This results in siloed working as data is retained in different teams, preventing a multidisciplinary approach to intervention or targeting of the required professional support.


What the project involves

By collaborating with multiple stakeholders the Luton health and care system developed a 'Framework for Frailty'. This is in response to requests from partners for a common approach to the early recognition and identification of frailty as a long-term condition.

 

It was anticipated that by making this data available, there will be better targeted prevention and early intervention through a multi-disciplinary approach.

 

This project aimed to incorporate data received from the assistive technology system - Telecare, and have this information recorded in the social care IT system (Liquidlogic), to provide health and social care staff with a more holistic view of patients' likely health and social care needs.

Personalised prevention

Potential savings of £2.7m for hospitals

Reduced admissions to hospital

Benefits of the Framework for Fragility

Clinical staff benefit from:

  • increased knowledge allowing them to support service users more effectively
  • a reduction in non-elective admissions, leading to better utilisation of resources and associated savings
  • improved communication with social care staff
  • the ability to use data to predict and thus prevent deterioration

Bedfordshire, Luton and Milton Keynes (BLMK) County Council benefit from improved and more complete data source for BLMK population management.

Social care staff benefit from:

  • increased knowledge allowing them to support service users more effectively
  • previously unavailable data now visible and reportable to the local authority enabling trend analysis
  • information available in near real-time allowing improved prioritisation

Patients benefit from:

  • (it is hoped) improved engagement by users as needs are being addressed more fully
  • a better understanding of issues using richer data, allowing personalised preventative techniques to be used to target those most at risk and help anxiety and prevent future falls

Lessons learned so far

The Luton health and care system has learned that:

 

  • engagement with all key technical stakeholders at the outset of the project ensured that requirements were understood throughout the lifetime of the project
  • the project team were working on a range of different projects, leading to competing priorities - a dedicated project team may have advantage in the future
  • holding a weekly meeting created a useful forum to discuss emerging risks and issues, and should be continued
  • engagement with third-party suppliers needs to be carried out at an earlier stage to prevent delays with IT systems

Download the case study

Last edited: 20 January 2020 3:57 pm