Population Health Management is an important tool that is increasingly being used by health care providers to manage and control the escalating costs. The crux of Population Health Management is to use data to improve health outcomes. Tracking, monitoring and bench marking are the three bastions of Population Health Management, aimed at improving clinical and health outcomes while managing and reducing cost.
A successful population health management initiative requires establishing a repository that can collect data from multiple sources in any and all formats, whether it be structured, semi-structured or unstructured. Furthermore, the repository needs to be able to integrate the disparate data sources, with a fast time-to-action to flexibly meet ever-evolving healthcare analytics needs. By analyzing the patient population to gain insight into its socioeconomic constitution, demographics, and overall medical condition across geospatial regions, health care providers can better understand the quality of care being provided and identify areas for improvement and cost savings. The Microsoft Azure Data Lake is one such technology that has all the capabilities required to build a population health management repository. It not only permits users to store data of any size, shape and speed, it also has the capability to conduct data processing, advanced analytics, and machine learning modeling with high scalability in a cost-effective way. Using U-SQL, R, Python and/or .NET, it allows users to run massively parallel data transformation and processing over petabytes of data. It is truly a one-stop-shop for population health reporting, advanced analytics and predictive modeling.
In this solution guide, we will be leveraging clinical and socioeconomic in-patient data (simulated) generated by the hospitals for population health reporting. Additionally, we will also be making predictions for the length of hospital stay, as an example of a machine learning application within a Population Health Management solution. Hospitals can use these results to optimize care management systems and focus their clinical resources on patients with more urgent need. Understanding the communities they serve through population health reporting can help hospitals transition from fee-for-service payments to value-based care while reducing costs and providing better care. In the deployment guide folders above, you will find instructions on how to create a Population Health Management solution using different components of the Cortana Intelligence Suite.
The snapshot below shows how we use PowerBI for Population Health reporting:
For technical audiences, we have put together a manual deployment guide as well as an automated deployment guide. The manual deployment guide is geared toward those who want to understand how to spin up the different components and how they can be connected together to build an end-to-end pipeline. The automated deployment guide is for seeing the entire solution in action without having to do all the wiring manually.
In this folder, you will find instructions on how to put together and deploy from the ground up a population Health Management solution using the Cortana Intelligence Suite. It will walk you through how to manually set up and deploy all the individual services used in this solution (e.g. Azure Event Hub, Data Lake Store, Azure Stream Analytics etc.).
There is also a deployable Population Health Management solution in the Cortana Intelligence Gallery (offering an accelerated deployment of all services required for this solution). In this folder, you will find instructions on how to monitor the progress of your automated deployment (takes about 20-40 minutes to deploy) and carry out some post-deployment steps.
For more information on how to tailor Cortana Intelligence to your needs, connect with one of our partners.