The healthcare big data revolution has only just begun. Current efforts percolating around the country primarily surround aggregation of clinical electronic health records (EHRs) & administrative healthcare claims. These healthcare big data initiatives are gaining traction and could produce exciting enhancements to the effectiveness and efficiency of the US healthcare system. They can provide much needed transparency about the cost and quality of care, enhance coordination of care efforts, provide better outcomes and mitigate overall cost of care. However, they are only the building blocks for a much larger and progressive data universe.
Our data rich world offers an exciting opportunity to leverage sources of information from all aspects of life: genomic, nanotech, social media (Facebook, Twitter, smart phone technology apps, personal medical devices, shopping, travel, weather, political, employment, and so much more). Linking this data and converging it with current clinical EHR and administrative claims initiatives could yield a truly unique 360 degree view of patients, unlike anything previously seen.
Data from other highly impactful areas such as fully sequenced DNA and socio-economic factors could really make a difference. In many cases this is the data, largely untapped in the healthcare world, which can impact our own health but is rarely factored into the coordination of care. Understanding how our health is affected, either positively or negatively, by the world around us should be of importance to us all.
Undoubtedly, there are a great many challenges which lie in the path of achieving this level of interaction between data. There are obvious political and personal privacy issues. Resolving those is essential to anything this comprehensive becoming a reality.
However, for the purpose of this blog, I will focus on the technical challenges associated with such an effort. Successful insight into healthcare cost and quality depends on the correct use of technology to extract, load, cleanse, enrich, analyze and report on these data.
In future blogs I will explore a specific use case: Me. I will use my own personal health data for use in research and analysis. I will use a variety of data sources, ranging from Clinical EHR’s, Administrative Claims, Social Media, travel, weather, mobile phone applications, and more. The data will be integrated together to make a 360 degree view of my own personal health history within a specific time series. The process of integration, matching, cleansing, and enriching will be discussed. In addition, the final integrated data set will be analyzed using data visualization, exploration and reporting technology.
The results will help to identify a number of issues such as identifying trends in co-ordination, quality and cost of care, and the potential factors which were impactful. By doing so, we will determine if there are adjustments we could make in our own lives which would enable us to enhance our health and control our healthcare.
