Children’s Hospital of Orange County Begins Machine Learning Journey | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

Children’s Hospital of Orange County Begins Machine Learning Journey

June 26, 2018
by David Raths
| Reprints
William Feaster, M.D., M.B.A., CHOC’s chief health information officer, describes progress on turning data into intelligence

Leveraging its enterprise data warehouse and population health platform, Children’s Hospital of Orange County (CHOC) has developed smart registries and is now working on using automation for alerts to patients with asthma. It also is working with Cerner as a development partner on HealtheDataLab, a new big-data platform using Amazon Web Services.

In a June 25 webinar sponsored by the eHealth Initiative, William Feaster, M.D., M.B.A., CHOC’s chief health information officer, described how CHOC is leveraging its investment in EHR technology, data warehouses and machine learning.

Feaster started his presentation by quoting W. Edwards Deming: “In God we trust. All others must bring data.” He said he would amend that slightly to “all others musts bring intelligence,” and his talk was a demonstration of how a provider organization can turn data into intelligence.

He spoke about how CHOC is leveraging data to advance the health of its population. It is using Cerner’s HealtheIntent population health platform, which gives it the ability to bring data from multiple sources into a big data arena based on Hadoop. The data is cleaned up, normalized and matched to patients.

That has allowed the organization to work with Cerner to develop seven specific disease-specific “smart registries,” including one on asthma. “Registry data is available right when someone is seeing a patient at the point of care,” instead of a month or three months later as is the case with claims data, he said. In addition, clinical workflow has been augmented to integrate registries into daily activities. CHOC was able to focus on local variations in care to reduce frequent ED visits and hospital admissions. It was able to track improvements in compliance with registry metrics over time. “With other specialty registries, we can choose metrics that we can measure for improvement,” he said. After the data is mapped, the registry measures are validated against source data and credibility is established with providers, Feaster added.

Webinar

Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

During the same webinar, Marc Overhage, M.D., Ph.D., chief medical informatics officer in population health for Cerner, said the company is focused on the concept of an evolving longitudinal care plan as a way to inject intelligence into the care continuum. Such a plan requires notifications and actions to be shared among a team of providers, caregivers and a patient. Cerner is analyzing which have to be human tasks and which a computer or automation can do well. A machine might be able to notify the care team of a new patient in a care management program or identify negative trends in the data in order to free up human time to do higher-value tasks, Overhage said. “We have begun to create virtual assistants,” he said. Cerner is focusing on how to translate those activities using FHIR resources into clinical and patient engagement processes that already exist. There is a lot of work to be done to standardize how intelligence is incorporated into the work flow, he added.

Here is an example from CHOC: It is building an alerting program for asthma that takes advantage of automation and machine learning. Data sources such as remote monitoring device data and environmental data and social determinants will be imported into the system. Alerts are constructed and fed into the patient portal and care management platform to preemptively alert patients and caretakers.

An example would be a poor air quality warning triggering automatic alerts to the parent of a child with asthma. The alert through the portal and texts might say that Maria has a history of problems on poor air quality days and ask her to use a peak-flow meter to measure it. The reading might put her in the yellow zone of her asthma action plan, and a care manager is alerted to help her with care, and an appointment is scheduled automatically.

After talking about some ways CHOC is applying data science to improve quality and patient satisfaction, Feaster said there are some limitations to doing data science work using discrete data in the enterprise data warehouse. “We are limited to the data we think might be appropriate, rather than letting the machine learn from much larger data sets,” he said.

CHOC is working as a development partner with Cerner on  HealtheDataLab, a big-data environment spun up in Amazon Web Services (AWS). “There is no limit to the computing resources. Our data scientist will begin in July working full time in that environment,” he said. Two early projects involve patient deterioration in the hospital and patients with no-show tendencies in primary care. The data elements are modelled on HL7 FHIR standards as applicable, and other data sets can be loaded into the same AWS “bucket” for analysis without performance and size limits, he said.

Feaster wrapped up with another quote, this one from George E.P. Box: “All models are wrong, but some are useful.”

“That is true in general, he said. “Nothing is perfectly right, but we are using data and data science to improve care.”

 

 

 


The Health IT Summits gather 250+ healthcare leaders in cities across the U.S. to present important new insights, collaborate on ideas, and to have a little fun - Find a Summit Near You!


/article/analytics/children-s-hospital-orange-county-begins-machine-learning-journey
/article/analytics/vcu-health-motto-god-we-trust-everyone-else-must-bring-data

VCU Health Motto: ‘In God We Trust; Everyone Else Must Bring Data’

October 19, 2018
by David Raths, Contributing Editor
| Reprints
CMIO Colin Banas, M.D., talks about winning 2018 HIMSS Davies Enterprise Award

VCU Health System in Virginia was recently named a 2018 HIMSS Davies Enterprise Award recipient for leveraging health IT to improve outcomes. Colin Banas, M.D., the health system’s chief medical information officer, said the organization prides itself on using data to improve patient outcomes. “I am reminded of a quote from one of our senior leaders,” he said. “She even puts it at the bottom of her meeting minutes. It says, ‘In God we trust. Everyone else must bring data.’”

HIMSS cited three use cases that demonstrate VCU Health’s commitment to using data and technology to improve outcomes. The first is an Enhanced Recovery after Surgery (ERAS) protocol that improved colorectal surgery outcomes.

As VCU redesigns processes such as this, technology is always one of the last steps.   “When you sit in on these meetings, they are not going to talk about tech solutions for the first two months,” Banas said. “We stress the mantra of people, process and then technology. In a 7-stage flow chart, you don’t see technology until stage six and seven.” Once a team is identified and a standard of care is spelled out, then they turn back to IT and figure out how to hard-wire the changes into the electronic health record.

Because the VCU mascot is a ram, Banas said, the “ninja swat team” that works on process improvement projects is called the RAM Care team. RAM stands for reliable, appropriate and measurable. “We try to remind people that the RAM Care team is not just implementing order sets,” he said. There are five stages of people and processes first and then technology, including decision support and dashboards. “The way to drive variation out of a lot of these care processes is to be data-driven and consensus-driven,” he said. “That is what RAM Care really does – it is all about reducing variation.”

The other efforts HIMSS highlighted involved new tools that streamlined the patient discharge process and automated documentation tools that reduced catheter-associated urinary tract infections (UTIs).

Banas says it is an exciting time to be a CMIO. “We are getting out of the doldrums of regulatory reform and meaningful use, and ICD-10 sucking up all the oxygen, and we are starting to get better tools and better interoperability platforms to start doing innovative things,” he said.  He pointed to SMART on FHIR and open APIs as allowing users to do new things.

VCU Health is a client of Cerner, which has an Ignite API engine. “We have one SMART on FHIR app, Visual DX, and we have just signed the paper to allow the Apple health record beta for VCU Health, so our patients will be able to link their portal data to the native Apple experience,” he said. Cerner is creating its own app store. “Some are free and others have a cost, but it is exciting,” Banas said. “A lot of these people are solving things that have really bugged us and Cerner for quite some time, and they have done it way better. Kudos to Cerner for opening up and allowing other people in this space. They openly acknowledge that some of the things people are developing are in direct competition to core functionality they try to sell to their clients. Competition is good.”

 

 


More From Healthcare Informatics

/article/analytics/how-data-driven-approach-can-bolster-fight-against-opioid-abuse

How a Data-Driven Approach Can Bolster the Fight Against Opioid Abuse

October 12, 2018
by Steve Bennett, Ph.D., Industry Voice
| Reprints

I want to tell you about Andy. Andy’s mom, Pam, is a colleague of mine. Growing up an only child, Andy was a happy kid. He was a straight-A student, loved to play the violin, and spent a year as an exchange student in Europe. Andy had two loving parents. But Andy suffered an injury in college, and needed to have some minor surgery performed to repair his sinuses. Following that surgery, his doctor prescribed opioid pain medication for him, to which he became addicted. Despite several years of effort, Andy was unable to shake the addiction, and tragically lost his life to a heroin overdose two years after his surgery. This was a normal kid with a normal family, like mine, and like yours.

Andy’s story is an important story. The opioid epidemic has led to the deadliest drug overdose crisis in the history of the United States, killing more than 64,000 people in 2016 alone – the last year numbers were available. This is a true national epidemic, and one that continues to get worse. For the first time in nearly 60 years, life expectancy for Americans has dropped for two years in a row due to the opioid epidemic.

The opioid crisis has been so difficult to curtail, in part, because of the inability to integrate data from various stakeholders and systems. With so many players and data sources, today’s information is partial, fragmented, and often not actionable.

While this disconnect applies directly to the opioid epidemic it is a systematic problem that affects the healthcare community at large. Better data and analytics can help develop better treatment protocols for a wide array of medical and public health challenges that affect the general public. For opioids, that could be to develop better pain management programs or for better, more-targeted remediation and rehabilitation for those that become dependent on drugs.

A Data-Driven Healthcare Approach: Making Information Real

Webinar

Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

Ample data has been collected on the opioid epidemic, but disparate sources are not communicating with one another. Addressing this disconnect and lack of communication is something that can provide researchers, lawmakers and the public with improved insights.

Data-driven healthcare can help provide this guidance by using available data and analytics to help create programs that can make a tangible difference on population areas that need the most help. By looking at the data, lawmakers, hospital administrators and doctors can begin to make impactful changes throughout the system.

While much can be learned from this data, most of it is not being analyzed in a way that brings true benefits. It has been put in a silo and/or it is not organized in a way that is interoperable with other data systems.

The 21st Century Cures Act, which established the Health Information Technology Advisory Committee, shows the commitment of national leaders to improving healthcare information sharing. Analytics can take this data and turn it into something real. Subsequent visualization of this analyzed data presents the information in a way that can truly tell a story, making sense of data that analysts sometimes miss. Analytics can arrange and organize data in different ways and pick up previously undetected trends or anomalies. This information can be turned into real programs that produce real outcomes for those affected.

The data management and integration process can also help us understand where our knowledge gaps are, revealing flaws in data quality and availability. Organizations may learn that they lack sufficient data in a certain area where they want to learn more, but are currently limited. They can then make changes to data collection efforts or seek out different sources to fill these larger gaps. They can resolve data quality issues across systems and arrive at a consistent, reliable version of the truth.

As organizations get better at assembling and managing the data, automating processes to generate standard reports and file exchanges can ease the burden on analysts. Streamlining the user interfaces for prescription drug monitoring programs and other systems allows analysts and medical informatics staff to spend less time working on the data itself and more time enabling and encouraging the use of predictive modeling and “what-if” scenario capabilities.

Helping to Solve a Problem

The national opioid epidemic is a terrible and complex issue. It is not something that can be solved with just one action, approach or program. It is a layered issue that will require systematic changes to how patients are treated and how the healthcare system operates. Some of the nation’s best continue to work on providing operational solutions to these problems, but as the statistics show, they need more help.

A data-driven approach can be that help. Using data analytics to find better and deeper insights into the root problems of this epidemic can help decision-makers make real change. While opioids are the focus now, there will come a day when a new problem emerges. Having data and analytic solutions in place can prepare these organizations to tackle these future challenges as well.

64,000 people died in 2016 as a result of opioid abuse. But 64,000 is more than a large number – it’s also Andy and his family. With analytics and a data-driven approach, government and healthcare leaders can make better decisions that can help people in need.

Steve Bennett, Ph.D., is the director of SAS' global government practice. He is the former director of the National Biosurveillance Integration Center within the Department of Homeland Security


Related Insights For: Analytics

/article/analytics/doj-approves-cvs-aetna-69b-merger-condition-aetna-divest-part-d-business

DOJ Approves CVS-Aetna $69B Merger, On Condition Aetna Divest Part D Business

October 10, 2018
by Heather Landi, Associate Editor
| Reprints
Click To View Gallery

The Department of Justice (DOJ) has approved a $69 billion merger between mega-pharmacy retailer CVS Health and health insurer Aetna, after Aetna entered into an agreement with the DOJ to divest is Medicare Part D prescription drug plan business.

According to a statement released by the DOJ on Wednesday, the settlement, in which Aetna will sell off its Part D business, was a condition of the merger’s approval and resolves the DOJ’s “competition concerns.”

The deal is the latest in a wave of combinations among healthcare companies, including many pharmacy benefit manager (PBM) and insurer integrations. Last month, the Justice Department approved Cigna’s $67 billion takeover of Express Scripts.

CVS Health announced in early December 2017 its intention to acquire Aetna in a $69 billion-dollar merger, marking the largest ever in the health insurance industry. Woonsocket, R.I.-based CVS operates the nation’s largest retail pharmacy chain, owns a large pharmacy benefit manager called Caremark, and is the nation’s second-largest provider of individual prescription drug plans, with approximately 4.8 million members. CVS earned revenues of approximately $185 billion in 2017. Aetna, headquartered in Hartford, Connecticut, is the nation’s third-largest health-insurance company and fourth-largest individual prescription drug plan insurer, with over two million prescription drug plan members. Aetna earned revenues of approximately $60 billion in 2017.

Following news of the deal back in December, there was speculation that antitrust regulators might not approve the deal. Back in January 2017, a federal judge blocked a merger that would have resulted in Aetna acquiring Louisville, Ky.-based insurer Humana, which at the time was the largest acquisition of its type in the history of health insurance in the U.S., reported at $37 billion. At the time, U.S. District Judge John D. Bates in Washington said that proposed deal would “violate antitrust laws by reducing competition among insurers.” Similarly, a proposed combination of two other health insurers, Anthem and Cigna, was also shot down last year.

Webinar

Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

According to the DOJ’s statement issued today on the CVS-Aetna deal, the Justice Department’s Antitrust Division had significant concerns about the anticompetitive effects of the merger with regards to the Medicare Part D businesses. CVS and Aetna are significant competitors in the sale of Medicare Part D prescription drug plans to individuals, together serving 6.8 million members nationwide, according to the DOJ.

In a press release issued today, CVS Health said, “DOJ clearance is a key milestone toward finalizing the transaction, which is also subject to state regulatory approvals, many of which have been granted.” CVS Health's acquisition of Aetna remains on track to close in the early part of Q4 2018, the company said.

“DOJ clearance is an important step toward bringing together the strengths and capabilities of our two companies to improve the consumer health care experience,” CVS Health president and CEO Larry J. Merlo, said in a statement. “We are pleased to have reached an agreement with the DOJ that maintains the strategic benefits and value creation potential of our combination with Aetna. We are now working to complete the remaining state reviews.”

Merlo also said, “CVS Health and Aetna have the opportunity to combine capabilities in technology, data and analytics to develop new ways to engage patients in their total health and wellness. Our focus will be at the local and community level, taking advantage of our thousands of locations and touchpoints throughout the country to intervene with consumers to help predict and prevent potential health problems before they occur. Together, we will help address the challenges our health care system is facing, and we'll be able to offer better care and convenience at a lower cost for patients and payors.”

Following the close of the transaction, Aetna will operate as a standalone business within the CVS Health enterprise and will be led by members of its current management team.

The American Medical Association (AMA), an industry group that has been opposed to the merger, issued a statement saying the agreement that Aetna divest its Part D business doesn't go far enough to protect patients.

"While the AMA welcomes the U.S. Department of Justice (DOJ) requiring Aetna to divest its Medicare Part D drug plan business, we are disappointed that the DOJ did not go further by blocking the CVS-Aetna merger," Barbara L. McAneny, M.D., president, American Medical Association, said in a statement. "The AMA worked tirelessly to oppose this merger and presented a wealth of expert empirical evidence to convince regulators that the merger would harm patients. We now urge the DOJ and state antitrust enforcers to monitor the post-merger effects of the Aetna acquisition by CVS Health on highly concentrated markets in pharmaceutical benefit management services, health insurance, retail pharmacy, and specialty pharmacy."

Agreement with DOJ Resolves “Competition Concerns”

Late last month, Aetna agreed to sell its Part D business to WellCare. According to a Securities and Exchange Commission (SEC) filing from WellCare Health Plans last month, WellCare entered into an asset purchase agreement with Aetna to acquire the company’s entire standalone Medicare Part D prescription drug plan business, which has 2.2 million members. According to the agreement, Aetna will provide administrative services to and retain the financial risk of the Part D business through 2019. In that filing, it states that Aetna is divesting its Part D business as part of CVS Health’s proposed acquisition of Aetna.

“Today’s settlement resolves competition concerns posed by this transaction and preserves competition in the sale of Medicare Part D prescription drug plans for individuals,” Assistant Attorney General Makan Delrahim of the Justice Department’s Antitrust Division, said in a statement. “The divestitures required here allow for the creation of an integrated pharmacy and health benefits company that has the potential to generate benefits by improving the quality and lowering the costs of the healthcare services that American consumers can obtain.”

In its statement, the DOJ referred to WellCare as “an experienced health insurer focused on government-sponsored health plans, including Medicare Part D individual prescription drug plans.”

The Department’s Antitrust Division, along with the offices of five state attorneys general, today filed a civil antitrust lawsuit in the U.S. District Court for the District of Columbia to enjoin the proposed transaction, along with a proposed settlement that, if approved by the court, would fully resolve the Department’s competitive concerns. The participating state attorneys general offices represent California, Florida, Hawaii, Mississippi, and Washington.

In a complaint filed to the U.S. District Court, DOJ attorneys argued that without the divestiture, the combination of CVS, which markets its Medicare Part D individual prescription drug plans under the “SilverScript” brand, and Aetna would cause “anticompetitive effects, including increased prices, inferior customer service, and decreased innovation in sixteen Medicare Part D regions covering twenty-two states.” DOJ attorneys also argued that the loss of competition between CVS and Aetna would result in “lower-quality services and increased costs for consumers, the federal government, and ultimately, taxpayers.”

Under the terms of the proposed settlement, Aetna must divest its individual prescription drug plan business to WellCare and allow WellCare the opportunity to hire key employees who currently operate the business.  Aetna must also assist WellCare in operating the business during the transition and in transferring the affected customers through a process regulated by the Centers for Medicare and Medicaid Services (CMS).

 


See more on Analytics

betebettipobetngsbahis