Skip to main content
Skip to footer

Taking data from big and complex to manageable and actionable

Published on 2/5/2020

Estimated read time: 4 minutes

Have you ever wished you could predict the future? In health care, accurate predictions can save time, money and, most importantly, lives. Using the massive amounts of data and intelligence tools, we can build algorithms that inform care decisions and improve outcomes.

Health care data can be messy. It's not always clear where the data comes from or if it’s been duplicated. It can be sparse and even biased to the challenge the clinical team is trying to solve. A recent study shows that data scientists spend the majority of their workday collecting, cleaning and organizing data, leaving them with little time for more meaningful tasks like refining algorithms and mining data for patterns.

The question with which the industry is grappling: How can technology empower health care systems to tackle huge volumes of data and use the information to anticipate and improve patient outcomes – at scale?

Powering predictive analytics to save patient lives

Intelligence has been part of our technology since Cerner was founded more than 40 years ago. With data and insights at the center, we are uniquely positioned to provide solutions that make it easier and quicker for users at diverse venues of care to organize vast amounts of patient data and build machine learning models at scale.

With Cerner HealtheDataLab, you can shift the data science workflow from big and complex to manageable and actionable. The technology supports the development and integration of rule-based, symbolic and machine-learned algorithms for risk prediction, modeling, identifying patient care guidelines and more. HealtheDataLab is designed to help health care organizations solve everyday business challenges. For example:

  • The Advocate Cerner Collaborative was established to accelerate innovation in population health management. With a focus on the efficient allocation of clinical resources, predictive analytics was shown to be key to identifying high-risk patients earlier.

For instance, clinicians know that patients with heart failure have a higher risk of being admitted to the hospital. But it would help clinicians to know if there’s a subset of patients who are at high risk for short-term admission, whose care could be better managed at home.

Advocate and Cerner developed a risk score and integrated it into the Advocate care management system to prioritize patients for care management outreach. A year later, the team has created additional risk scores to offer this type of program to people living with other conditions, like chronic obstructive pulmonary disease and asthma. The collaborative was able to remove the technological barrier and focus on operating efficiencies.

  • Children’s Hospital of Orange County (CHOC Children’s) also used HealtheDataLab to build risk scores. CHOC Children’s wanted to better support families with children at the highest risk of readmission. With an organized and unified data set, and advanced computation inside the solution, CHOC Children’s was able to quickly build and improve its readmission model in weeks – rather than months or years like its legacy system. The organization also tackled building 11 additional models in just a year with only a small team of data scientists.

“Previously, it would take a couple of months to develop a model, extract the data and iteratively run through the algorithm. Now it only takes us a couple of days. Since streamlining our workflow, our data science team has gained tremendous efficiency. We no longer require assistance from multiple groups for all of our activities, and we’re not constrained by hardware limits.”

- Louis Ehwerhemuepha, data scientist, CHOC Children’s

  • Amazon Web Services and Cerner created a framework to predict the onset of chronic conditions, such as congestive heart failure. With a model capable of predicting the onset of congestive heart failure months into the future, providers can implement strategies designed to reduce risk factors, such as high blood pressure, high cholesterol and diabetes. This type of model can also assist researchers in evaluating interventions that have the potential to delay or avert the development of other conditions with high mortality, morbidity rates and significant costs.

In health care, the power to accurately predict the future can save time, resources and, most importantly, lives. The industry continues to weigh how IT can empower providers to tackle huge volumes of data and use the information to anticipate and improve patient outcomes – at scale. The future of health care relies on taking data from big and complex to manageable and actionable.

HealtheDataLab can help health systems decipher their unlimited sums of data and drive the next big advancements in care. Learn more here.