Social Prescribing Dashboard

Evidence suggests that social prescribing can lead to a range of positive health and wellbeing outcomes by supporting individuals to take greater control of their own health. However, social prescribing resources are limited and need to be targeted on those patients who would benefit most to maximise positive impact for both individuals and the healthcare system.

Arden & GEM’s Advanced Analytics Unit has designed and developed an intuitive dashboard, based on a machine learning model, which enables users to identify cohorts of patients that would benefit from social prescribing and be most likely to take up a referral so that they can be proactively targeted with an intervention.

The dashboard has been informed by a literature review and a validation of predictors with healthcare professionals to identify four high-level patient cohorts. The case finding tool then triages those patients who are most likely to be suitable for referral to a social prescribing programme.

By increasing the number of patients using targeted social prescribing services, we can widen access to primary care while reducing the demand for GP appointments and ultimately improve health outcomes.

We can work with health and care systems to develop a dashboard for their area by:

• Engaging with stakeholders to understand the social prescribing needs of patients and define objectives of the predictive model
• Data engineering and wrangling to develop the data model
• Training and validating machine learning models until satisfactory predictive accuracy is achieved
• Deploying the model onto an API to produce daily prediction scores
• Deploying the dashboard onto the preferred platform to enable visualisation of the model outputs and to provide a user-friendly interface
• User training and supporting documentation to optimise use.