A key objective of any health care system is not only to overcome illnesses as it happens, but to be able to predict the early on-set of illness. The proposed research will develop and extend the current study into Frailty encompassing not only clinical factors, but economic, environmental and social factors. Current estimates suggest that 7% of the population over 65 years of age exhibit signs of frailty.
This research aims to create a new paradigm in understanding, predicting and controlling the major contributing factors of frailty. Current quantificational assessment "accumulation of deficit" encapsulates the severity as a single metric known as the Frailty Index. The index method is inadequate for prediction and does not provide any detail into the underlying causes of the frailty condition once the index is compiled.
A proposed "Frailty Framework" extends the ability of clinicians and social care to engage patients identified at risk using medical & socioeconomic factors and provides predictive and preventative interventions, controlling the major contributory conditions that lead to frailty.
The work addresses the research aim by applying a wide range of risk assessors for Frailty, in order to determine the critical point at which someone is becoming ill, and put in-place intervention plans. The collaboration with CM2000 and SAS will apply predictive analytics and Big Data techniques to identify the factors which affect the Frailty outcome.
Researching Big Data, Cloud Processing and integrating mobile in a community health care setting.