Data lake technology has been named the future of big data. Unlike data warehousing techniques, data lakes offer a different type of data management better suited to handling and collaborating various forms of data in a way which doesn’t confuse systems. But how exactly do data lakes work? What are their benefits in the healthcare system?
Data lakes embrace a semantic approach to data storage, retaining enormous amounts of raw information (whether structured or unstructured) in its original state within a single centralised location. This technology, often referred to as graph databases, enables analysts to select which data to use when necessary, giving them the opportunity to reuse it when required. Analysts also have the option of combining seemingly incompatible sources of information in ways previously thought impossible with data warehousing.
Source: Data lake technology collaborates different forms of data without reconstruction
Now that data storage and technology is more affordable across several industries, companies are able to employ data scientists who have the capabilities to understand untamed data, being able to produce quality insights into a company’s particular systems or general processes. Healthcare is one such industry where the potential of data lake technology is being realised. The healthcare environment provides a number of opportunities for data lakes to make an impact, especially due to the highly variable nature of data generated by;
1. Electronic health records
2. Insurance claims
3. Medical devices
4. Internet of Things tools
5. Emerging competencies in genomics
Partners HealthCare, based in Boston, is an American healthcare system currently tapping into data lake technology to create an all-encompassing big data storage warehouse, research workbench and analytics environment. Their project, the IDEA (Integrated Data Environment for Analytics) platform, focuses on providing a safe, trustworthy and customisable epicentre for its advanced research and health IT development divisions.
The integration of data lakes in the development of the platform means that its operations will be enhanced, producing several key benefits. Data that is kept in hospital records is normally deleted once the patient is discharged, however if this same data is transferred to the data lake for archived storage it can later be used for research purposes. Data lake technology also means that clinical decision support can be used to decode the pattern of medications ordered by individual patients, making it easier to create personalised care guidelines, in addition to forecasting the length of stay available from a patient’s admission data.
The IDEA platform demonstrates how effective co-operation between machine learning and data lake technology can mean gaining otherwise inaccessible clinical knowledge, allowing clinicians to observe in-depth insights for patients with complicated needs.
Source: The IDEA platform will help to improve hospital services and enhance overall patient care
Generally speaking, the application of data lake technology in the platform will have similar fundamental benefits across the healthcare industry, making it simpler for researchers to crunch numbers, report on their findings, and take the next step into the clinical setting.
The Protogen team are enthusiastic about new and innovative ways in which we can gain data insights from big data analysis across numerous industries like healthcare. Contact us to find out more on how to enhance data processes in your company.