Patients at risk of avoidable hospital-acquired conditions, such as sepsis or venous thrombosis, can be identified earlier, which enables care teams to intervene more actively and reduce the likelihood of these life-threatening complications from occurring.
Care teams and patients can be notified about gaps in care or variation from evidence-based best practice, which can reduce unnecessary variation, either due to underuse or overuse.
By adopting techniques that are widely used in other consumer-friendly industries, patients can receive highly personalized care team-directed interventions through a variety of traditional and emerging delivery channels, including smartphones and health apps, thereby improving patient engagement.
With a little ingenuity, the data we already have can be used to improve patient health while reducing organizational costs and risks. But it could be working so much harder.
Predictive analytics helps you see and plan for the future. Hindsight leads to insight and to foresight. Big data technologies let you apply analytics to vast data sources. Masses of genomic, electronic health record and claims data, as well as data from smart home sensors and wearable devices, can be brought together to reveal important insights at both the individual and population level to support better operational and medical decisions – and, ideally, bring analytic insights right to the point of care.
Imagine being able to have an intelligent safety net that provides 24x7x365 surveillance of a near-unlimited number of biological, behavioral and environmental factors that might influence a person’s health risk and experience. Or to evaluate alternative treatments by looking at factors that affect length of stay and incidence of readmission. Reveal which therapeutic regimens work best for what types of patients. Uncover disease patterns. Identify at-risk patients or assess the performance of individual physicians.
As our health care system transformation continues, analytic insights will be fundamental to economic survival. Well-informed care decisions and operational decisions become critical as we bring more of the previously uninsured onto the health care rolls and transform health care systems from a fee-for-service model to pay-for-value.
The case for cloud analytics
Much of the potential of big data analytics for health care remains untapped, and technology has been a perceived barrier. IT departments, already stretched thin, can be understandably reluctant to invest in the infrastructure. The data center will have to be engineered for peak processing loads, leaving much capacity idle (translate, inefficient) the rest of the time. It will require technical specialists to support the daily maintenance, inevitable upgrades and major surgeries – the forklift upgrades of data center hardware. It will consume months of analysts’ time to create and deploy the analytical software.
Not with cloud analytics. With cloud analytics, one or more key elements of data analysis – data sources, data models, application processing, computing power, analytic models, and sharing or storage of results – reside on shared infrastructure managed by a cloud service provider. IT departments can focus on core business initiatives instead of managing on-site technologies. Computing resources are virtualized, allocated as needed for great efficiency, and available on-demand on any device. Users get fast access to the answers they need from anywhere. All for a subscription or pay-per-use fee instead of a huge capital investment.
Hadoop is a natural for the cloud. Hadoop is an open source software framework for running applications on large clusters of commodity hardware. As such, Hadoop is a remarkably low-cost and scalable alternative to big data center servers. Need more power? Just add more off-the-shelf servers.
Hadoop brings a high-tech twist to the adage “many hands make light work.” It delivers enormous processing power with its ability to handle virtually limitless concurrent tasks and jobs across the cluster. Computationally intensive algorithms that would take hours or days to process using traditional analytical software can now run in minutes in memory.
Cloud analytics in action
Dignity Health, one of the largest health systems in the US, is working to develop a cloud-based, big data platform powered by a library of clinical, social and behavioral analytics. Over time, the platform will connect and share data across the system’s 39 hospitals and more than 9,000 affiliated providers. The goal is to help doctors, nurses and other providers better understand patients and tailor their care for better outcomes and lower costs.
For example, Dignity Health sees the following opportunities to use cloud analytics for data-driven insights to:
- Plan care for individuals and populations, including predictive disease management.
- Define and apply best practices to reduce readmission rates.
- Determine best practices for addressing congestive heart failure and sepsis.
- Predict the risk of sepsis or kidney failure, and intervene early to reduce negative outcomes.
- Better manage pharmacy costs and outcomes.
- Use performance data to drive best practices based on outcomes and value.
- Strengthen reimbursement models, with a focus on paying for outcomes.
- Create tools to improve each patient’s experience.
The analytics platform is being developed using our deep experience in medical research, health care, health insurance and pharmaceutical industries. So it starts smart, but it gets smarter over time. Algorithms in analytical models can learn interactively from the data. With every iteration, the models deliver more accurate results – faster.
Big data technologies have redefined the possibilities for using data – terabytes and petabytes of it – to dramatically improve health care costs, the care experience and patient outcomes. Cloud analytics puts it within easy reach.