Our approach to Population Health is driven by the distribution of analytics to whole care communities.
Traditionally this has been done using national datasets and presented in isolated dashboard driven solutions.
Our approach is to embed Population Health analytics into our applications for delivery directly to people who can utilise the output such as:
- CareCentric integrated care record for clinical and operational analytics to be used as decision support for care professionals
- myCareCentric Personal Health Record and Care Apps for patient decision support.
- CareCentric Business Intelligence: The highly configurable platform enables access to the CareCentric integrated care record data with hourly or daily data refreshes. Up to date data can be used as decision support.
- Visualisations: Embedded within CareCentric and myCareCentric to be used as part of standard workflows. New visualisations or algorithm output can easily be made available to entire care communities or patients groups via configuration.
- Collaboration is at the heart: Our approach to engagement with both the customers and academics is to enable collaboration between all three parties. Our ethos is to ensure clear communication, dissemination of knowledge and continuous assistance. This improves better understanding of the analysis and models generated, give academics access to a vast knowledge base and clear routes to implementation.
- Putting research into practice: Through our research platform and data mart we can reduce the time between new research and actionable insight. We work closely with leading universities to enable collaborative research.
- Integrated security: Ensuring secure, controlled access to the analysis and data that roles need is seamless.
- Risk stratification: Use advanced machine learning, statistical and mathematical models to actively forecast and monitor patients.
- Interoperable: The output from analytic models can be exposed via Microsoft Power BI driven visualisations or REST APIs to be consumed by applications.
- Detect, alert and optimise: The integration of our business intelligence and data science platforms with CareCentric enables effective communication of key factors, including service utilisation, performance, health outcomes and care deficits. The detection of these factors supports the shared care record area in highlighting areas for service optimisation, improving services, and reducing health inequalities.
- Whole system virtualisation: The use of historical data to understand the cause and effect of interventions allows us to enable large scale ‘what-if’ analysis to model potential outcome of new interventions.
- Stabilising care: The use of geo-spatial and characteristics analysis enables the early identification of individuals or groups of individuals who are at risk of care instabilities or the rise of care inequalities.
- Enables impactibility modelling: Application of data mining techniques to understand current health and social care delivery models and monitor the impact of service change through 'what if' scenarios and prediction analysis.