1.2 million customers, 15 hospitals, 185 clinics, more than 80 community pharmacies, over 30,000 employees including over 6,300 registered nurses, and nearly 1,500 employed physician create a vast amount of data. The not-for-profit Aurora Health Care system has decided to put that wealth of data to use in order to improve decision-making and make the organisation more information-centric.
Aurora just completed Smart Chart, a $200 million records system that accumulated all data collected in the past 10 years into a single data warehouse. It all started in an effort to get nationally recognized measures of our clinical performance by scoring them against national standards explains Phil Loftus, Chief Information Officer of the health group, on Forbes.
In other words, they wanted to integrate nation-wide data to benchmark results and to establish a national reputation for quality. The used clinical data and data-mining tools to analyse the large amounts of data to gain better insights.
In order to achieve this, Aurora created a hybrid Business Intelligence ecosystem combining a message-centric ETL methodology, using a RDBMS to perform all dimension and fact table processing, with a big data platform. This SQL-MapReduce and nPath enabled analytics platform powers all traditional Business Intelligence reporting as well as next-generation big data analytics.
They have 18 different primary streams of data that are processed in near real-time. It is financial data, lab data, pharmacy data and procedure data. Aurora aims to utilize all that data in a highly secured and effective manner. The tasks are computed with a massive parallel processing system using multiple inexpensive microprocessors, giving it a 20 to 30 times more computing power than a traditional data warehouse. This allowed Aurora to look differently at the data as well as change the analytics from looking at individual patient to groups of patients that have the same diseases such as diabetes or heart failures. This reveals new trends and insights as well as help researchers to easier find the right patients for medicine testing.
In addition, the Aurora computer system keeps detailed records of the patients history. This data is accessible to doctors, nurses and caregivers throughout they system, which ensures that the patients receive the best treatments and diagnoses based on their personal information. Aurora also treats more patients at home. At the moment nurses equipped with laptops treat around 2.300 patients at home. Via secure wireless data cards, these nurses can reach the computer system and have access to all relevant patient information.
Using all available data and the near real-time data analytics, Aurora is able to predict and improve patient outcomes and treatments. Using the different data streams they already have been able to reduce patient readmissions with 10%, meaning a total saving of $ 6 million. Data is now helping doctors lowering the cost of care for patients by analysing outcomes and even recommending different procedures.
Aurora also decided to join and participate in the development of the Oracle Health Sciences Network, an information-sharing platform in the cloud that aims to enable cooperation among life sciences institutes, researchers and healthcare providers. Aurora wanted to join this network, as it will help to improve the healthcare patients receive through drug-trial participation.
The results of the big data endeavour by Aurora Health Care system are interesting. In addition to the savings achieved by reducing patient readmissions, they reduced query time, improved data insights and saved 42% on treatment costs.
In the future they also want to optimize the supply chain, as at the moment that is 25% of the cost. They want to store and analyse data from the purchase order, the inventory process and the actual utilization of a product with a patient. Aurora just started discovering all possibilities and improvements that can be achieved with applying big data in the health care industry and it is expected that the results will only improve in coming years.
