Big data in health care

How three organizations are using big data to improve patient care and more

By Anne-Lindsay Beall, Insights Editor

Health care may have gotten off to a slower start than some industries in taking full advantage of big data. But today, sophisticated sensors connected through the IoT are used on medical equipment and patients’ bodies, and in wearables like clothing, watches and glasses. Now many organizations in this data-rich industry are focused on using big data and analytics to make life-altering changes in patient education, treatment and more.

According to Eric Topol, MD and executive vice president of the Scripps Research Institute, we now have tools and information that we’ve never had before. We can digitize and quantify almost every aspect of human beings. Just as Google maps have a satellite view, a traffic view, a street view – we can create a “Google medical map” of a human being from external features to anatomy (by scans) to physiology (by sensors), to DNA, RNA and chemical composition. “We can quantify the environment, which we could never do before – now it’s obtainable information,” says Topol.

Organizations using big data in health care

Topol’s description shows the enormous potential in using big data to individualize medical treatment – not only saving and improving lives, but delivering better medical care with improved processes, reduced waste and so much more. Let’s look at three organizations that are leading the way.

Dignity Health: Analytics helps prevent deadly infections

Sepsis is an extreme inflammatory response to infection that can lead to tissue damage, organ damage or death. The condition moves fast, and it kills around a quarter million people in the US each year. It can be very hard to spot, particularly in hectic environments like emergency rooms.

The fifth-largest health system in the US and the largest hospital provider in California, Dignity Health uses a big data and advanced analytics platform to predict potential sepsis cases at the earliest stages, when intervention is most helpful. Using the Sepsis Bio-Surveillance Program, Dignity Health monitors 120,000 lives per month in 34 hospitals and manages 7,500 patients with potential sepsis per month. Collecting data from the electronic medical records of all patients in its facilities, the solution uses natural language processing and a rules engine to continually monitor factors that could indicate a sepsis infection. In high-probability cases, the system sends an alarm to the primary nurse or physician.

Since implementing the big data and predictive analytics system, Dignity Health has seen a significant improvement in the mortality and ICU length of stay for its sepsis patients. At 28 of Dignity Health’s hospitals that have been on the program, sepsis mortality rates have dropped an average of 5 percent. Because patients spent less time in the ICU, the program delivered cost savings as well. And that’s no small matter. Sepsis is the costliest condition billed to Medicare, the second costliest billed to Medicaid and the uninsured, and the fourth costliest billed to private insurance.

Express Scripts: Better decisions, healthier outcomes with big data

Express Scripts handles millions of prescriptions annually through home delivery and retail pharmacies. Tom Henry, Vice President of Knowledge Solutions for Express Scripts, leads a group that’s using high-powered predictive analytics to crunch big data. They’re analyzing individual patients so effectively, they’ll soon be able to alert health care workers to serious side effects before a medication is prescribed.

This could have profoundly positive consequences for health:

• A health care provider would know before writing a prescription for painkillers whether the patient is at high-risk to become dependent. A different treatment plan or more careful monitoring could be selected.
• Prescription-filling behaviors, psychosocial information and other medical data could point to the development of a chronic illness – or one that hasn’t yet been properly diagnosed.
• Adherence to medication regimens post-hospitalization can predict the potential for re-admittance within 90 days. Providers could take action to avoid the re-admittance.
  

"Through our innovative predictive models, we make it more likely to avoid unnecessary treatment costs and improve patient outcomes,” says Henry. “Big data is good to have, but it’s meaningless if you can’t put it into action. That’s what we do. By being proactive, we’re driving better decisions and healthier outcomes.”

United Healthcare: Monitoring fraud and waste, improving clinical outcomes

The largest health insurer in the US, United Healthcare is processing data inside a Hadoop big data framework using big data and advanced analytics to give them a 360-degree view of each of its 85 million members. They’re using big data and advanced analytics for clinical improvements, financial analysis and fraud and waste monitoring.

“We have data that touches every aspect of the healthcare industry: member, claims, hospital, provider, clinical, operational and financial – and we use that data to get to root-causes of problems quickly, build innovative solutions and actively adapt to the changing healthcare landscape,” says Ravi Shanbhag, United Healthcare’s director of data science, solutions and strategy.

Other opportunities for big data in health care

The promise of big data in health care is staggering. Learn about other possibilities big data and analytics have created for the health care industry.

• Episode analytics. There’s unprecedented pressure on health care providers to better manage costs and quality of care. Who is most likely to succeed? Organizations that use big data to understand how well they’re performing, where they have opportunities to improve and their capacity to redesign care delivery. Episode analytics helps health care organizations create more encompassing and flexible treatment plans for patients, payers and providers. 
• Population health analytics. Using analytics to improve quality of care and patient experience at the lowest possible cost is core to population health analytics. Read how San Bernardino County is using data management and analytics to make good decisions about the community it’s serving – improving care while addressing misconceptions about behavioral health.
• Virtual care and wearable health care technologies. The rising cost of health care has been a dilemma for years. And few could argue that better preventive care is a great way to combat the issue. Streaming data and wearables can work together to give health care providers up-to-the-minute insights about a patient’s health. 
• Project Data Sphere. SAS is playing a key role in the development of industry-wide pharmaceutical data transparency. The goal is a secure, globally accessible data and analysis environment where multiple organizations can share anonymized clinical trial information. This would help scientists learn from research more quickly, and thus speed improvements in care.