The challenge
In the UK, the seasonal flu epidemic kills and average of 600,000 people each year, but this can fluctuate significantly, especially in pandemic years. However, capturing enough data to predict an outbreak is difficult due to the unpredictable nature of the influenza virus. Many factors can influence the length and severity of an outbreak. These can vary from what type of influenza viruses are spreading and the peak times of an outbreak, to whether scientists can offer a vaccine compatible with the right virus. Furthermore, as the influenza virus adapts and mutates, every solution must be provided on a case-by-case basis.
Since 1967, the Royal College of General Practitioners Research and Surveillance Centre (RCGP RSC) network has been actively monitoring incidents of influenza, alongside other diseases, by collecting anonymised data from around 200 volunteer GP practices. This data enables the NHS to find spikes of outbreaks during the different seasons of the year, to assess their effectiveness and support vaccination programmes.
While the quality and accuracy of the UK’s medical records is high, factors such as the structure of GP appointments and human input can lead to inconsistencies. These constraints can limit data quality in computerised records, which in turn limit the knowledge we can glean from the retrospective data.
The solution
The University of Surrey, where the RCGP RSC is based, partnered with NPL, for its data mining expertise. NPL studied the data monitored and worked to correct missing or miscoded incidents not properly tracked by the network, in particular differentiating a new incident case of an influenza-like illness from a follow-up. NPL’s algorithm helped to analyse the corrected data weekly and historical data retrospectively. This level of accuracy provided the system with a clearer and more comprehensive picture of peaks in different influenza epidemics, and allowed the RCGP RSC to include data they used to discard.
The impact
Such visibility will enable easier identification of trends over time, and ultimately improve the accuracy of epidemic early warnings. It will also provide a new perspective on the efficacy of new vaccines and other treatments and improve our ability to plan for and treat flu epidemics.
This opens many avenues in the utilisation of this data in the future. For example, there is the potential to combine current data sets with other information, such as data from social media. By improving the ability to analyse and utilise big data, such as through this partnership, we will be able to unlock new and exciting opportunities to improve and innovate healthcare in the UK.