Guest blog by Tiffany Harman, RN, Clinical Analyst with 3M Health Information Systems
The discussion around the potential and necessity for big data analytics has reached a turning point. Many hospitals, health plans, and accountable care organizations realize that the future of healthcare and population management is going to depend on big data and are now trying to decide how to best use it. So what exactly is big data?
Big data is a buzzword, or catchphrase, used to describe a massive volume of both structured and unstructured data that is so large that it’s difficult to process using traditional database and software techniques. Big data analytics play a crucial role in the financial success of an organization and the physical health of patients it serves. There is a lot of discussion around how we can use the data and some discussion around how we are using the data. But before we use this data to treat populations, the reliability and validity of the data cannot be ignored. Everyone is racing to apply their analytics to reduce health care cost and improve patient outcomes. Organizations must comprehend all of the details of the data they are analyzing to accurately depict every aspect of the patient care performed. Continue reading
Last week, we hosted one of our Executive Council meetings up in Park City, Utah. These meetings bring together executives from many of our client sites to discuss the challenges they’re facing and ways in which 3M Health Information Systems can help them achieve their goals. It wasn’t always easy keeping the group focused on the topics instead of the view of the snow-covered mountains through the window behind me, but when the subject of analytical needs came up, I had their attention. The discussion quickly turned to the challenges they face in getting the data needed to manage regulatory requirements, reduce costs, and improve quality of care. The client executives participating voiced a number of concerns, including:
- Difficulty in getting longitudinal data across the healthcare continuum
- Inability to get data from unstructured text within their EMR
- Limitations of claims data only
- Use of data to identify “avoidable care” so they can reduce costs and improve outcomes
- Data needed to manage compliance risk Continue reading
“Big data” is a collection of data so large that common database tools cannot easily manage it. Imagine a wilderness of datasets, endless rows and columns of data points as yet unexplored and untamed.
It sounds adventurous. Google tells me that big data can help me drive outcomes and spark innovation. With the help of advanced analytics, I can harness the digital universe and unlock big data’s hidden value. The rush of metaphors makes me dizzy.
Is it big data or big hype?
I asked Jason Mark, the master black belt for the Lean Six Sigma program at 3M Health Information Systems. “There is a lot of hype,” he said. “Big data won’t solve your problems any more than cloud computing or an EHR. But it can make you better informed and give you more information to address and improve performance.” Continue reading
Echoing Paul Cerrato’s post on EHRs and Pay For Performance, which cites a study by Jonathan Weiner, et. al., at Johns Hopkins University titled New Paradigms for Measuring Clinical Performance Using Electronic Health Records, there are many shortcomings in current EHR support for a shift to Pay For Performance (P4P). Cerrato particularly calls out statistics showing very small fractions of ambulatory care encounters fully documented in EHRs and interoperable across providers – necessary to meaningfully impact quality of care across provider organizations.
There are two issues at work here: the capture and the use of data. When two provider EHRs cannot adequately share data for a single patient, this is an issue of the usage of the data. If the data cannot be effectively used across provider organizations, there is little chance of using the EHRs to drive improved quality, and thus succeeding at P4P. Continue reading
One of life’s little pleasures is that you can travel anywhere in the world, put your bank card into an ATM machine, and withdraw money in the currency of that country. It seems magical, and it sets the standard for interoperability of data. On the other hand, one of life’s frustrations is that you can’t move from state to state, from one insurance carrier to another, or even from a hospital to the one across the street, and seamlessly access your personal health record. Ever wonder why transferring health information is so much harder?
Healthcare by its very nature is much more complex than financial transactions. When clinicians are trying to determine what to do for a particular patient, the information could come from many sources. It could come from information systems in imaging services or the laboratory, from the patient history and physical exam, or from devices such as bedside monitors. These different information sources “talk” in different terms and codes, called terminologies. Continue reading
Today, 3M HIS announced it has acquired CodeRyte. As division scientist, this is exciting news from a technology perspective. Here’s my take on what it means for NLP:
The distinctive feature of CodeRyte’s technology is its strong statistical NLP capability. As I discussed in the 3M white paper, Auto-coding and Natural Language Processing, statistical machine learning systems offer the possibility of significant accuracy improvements in data-rich environments, compared to traditional rules-based approaches. A good example is in the outpatient coding environment, where data volumes are large, and CodeRyte has a history of performing very well compared to other systems.
There are multiple ways to boost the accuracy of statistical NLP, and the combination of 3M and CodeRyte will allow us to pursue several paths to the direct benefit of end users. Continue reading
Human language developed at least 100,000 years ago, and has evolved into an amazingly complex and subtle mechanism for communicating ideas.
Computers emerged on the scene a mere half-century ago. And yet, we often find ourselves trying to structure our clinical communications around “talking” to computers, rather than talking to other caregivers. The impact to quality of care is potentially large, and often ignored. Continue reading
Part 1 of this series introduced the role of standard terminologies in meaningful use (MU). Part 2 illustrates some of the challenges encountered to support the implementation of MU.
Challenge #1: Many terminologies are needed to support the EHR and MU
Currently, no one terminology or classification system contains everything that is needed for the EHR, so encoding patient data for MU requires multiple standards. The Office of the National Coordinator for Health Information Technology (ONC) has adopted an initial set of vocabulary standards to support the proposed requirements of MU, shown in Table 1. Continue reading
In last week’s blog from HIMSS, I talked about the need to go beyond the buzzwords and “look under the hood” to understand what’s driving all of these new analytics and intelligent automation solutions that are making their way to market. A lot of questions still remain about how to make the outputs of all of this analysis actionable. As healthcare slowly enters the digital age, hospital by hospital and EMR implementation by EMR implementation, the wealth of data now available to be analyzed, dissected, quantified, and modeled is spurring plenty of new ideas and solutions. Healthcare is shifting from a pay for procedure to a pay for quality/pay for performance model, which is driving the need for actionable data that can be presented to clinicians and care teams at the point of care where they can make use of that data to improve outcomes for their patients. Continue reading
By: Susan Matney
As part of The American Recovery and Reinvestment Act (ARRA), the 2009 Health Information Technology for Economic and Clinical Health (HITECH) Act has the goal of using electronic health records (EHRs) to promote patient safety and interoperability between and within healthcare systems. The initiatives outlined in the HITECH Act are known as “meaningful use” (MU), which contains three key components:
- Use of a certified EHR to meet improvement and efficiency goals
- Electronic exchange of health information to improve outcomes
- Electronic submission of clinical and quality measures
Over the past few years, as healthcare organizations and providers have focused intently on implementing or enhancing their EHRs and documenting MU, many began the process with the sense that their EHRs would handle most if not all of the MU challenges they would encounter. Other organizations assumed that implementing the necessary clinical terminology standards required for collecting and sharing patient data would also be enough to achieve their MU objectives.