From Free Text Clinical Documentation to Data-rich Actionable Information

Hey healthcare providers! Yeah you the “little guy”, the rural community hospital; or you the “average Joe”, the few-hundred bed hub hospital with outpatient clinics, an ED, and some sub-paper-pilespecialties; or you the “behemoth”, the one with the health plan, physician group, outpatient, inpatient, and multi-discipline, multi-care setting institution. Is your EMR really just an electronic filing cabinet? Do nursing and physician notes, standard lab and imaging orders, registration and other critical documents just get scanned into a central system that can’t be referenced later on to meet your analytic needs? Don’t worry, you’re not alone…

Recently, I blogged about some of the advantages of Microsoft’s new Amalga platform; I want to emphasize a capability of Amalga Life Sciences that I hope finds its way into the range of healthcare provider organizations mentioned above, and quick! That is, the ability to create adoctor microscope standard ontology for displaying and navigating the unstructured information collected by providers across care settings and patient visits (see my response to a comment about Amalga Life Science utilization of UMLS for a model of standardized terminology). I don’t have to make this case to the huge group of clinicians already too familiar with this process in hospitals across the country; but the argument (and likely ROI) clearly needs to be articulated for those individuals responsible for transitioning from paper to digital records at the organizations who are dragging their feet (>90%). The question I have for these individuals is, “why is this taking so long? Why haven’t you been able to identify the clear cut benefits from moving from paper-laden manual processes to automated, digital interfaces and streamlined workflows?” These folks should ask the Corporate Executives at hospitals in New Orleans after Hurricane Katrina whether they had hoped to have this debate long before their entire patient population medical records’ drowned; just one reason why “all paper” is a strategy of the past.   

Let’s take one example most provider organizations can conceptualize: a pneumonia patient flow through the Emergency Department. There are numerous points throughout this process that could be considered “data collection points”. These, collectively and over time, paint a vivid picture of the patient experience from registration to triage to physical exam and diagnostic testing to possible admission or discharge. With this data you can do things like real or near-real time clinical alerting that would improve patient outcomes and compliance with regulations like CMS Core Measures; you can identify weak points or bottlenecks in the process to allocate additional resources; you can model best practices identified over time to improve clinical and operational efficiencies. Individually, though, with this data written on a piece of paper (and remember 1 piece of paper for registration, a separate piece for the “Core Measure Checklist”, another for the physician exam, another for the lab/X-ray report, etc.) and maybe scanned into a central system, this information tells you very little. You are also, then, at the mercy of the ability to actually read a physicians handwriting and analyze scanned documents of information vs. delineated data fields that can be trended over time, summarized, visualized, drilled down to, and so on.11-3 hc analytics

Vulnerabilities and Liabilities from Poor Documentation

Relying on poor documentation like illegible penmanship, incomplete charting and unapproved abbreviations burdens nurses and creates a huge liability. With all of the requirements and suggestions for the proper way to document, it’s no wonder why this area is so prone to errors. There are a variety of consequences from performing patient care based on “best guesses” when reading clinical documentation. Fortunately, improving documentation directly correlates with reduced medical errors. The value proposition for improved data collection and standardized terminology for that data makes sense operationally, financially, and clinically.   

So Let’s Get On With It, Shall We?

Advancing clinical care through the use of technology is seemingly one component of the larger healthcare debate in this country centered on “how do we improve the system?” Unfortunately, too many providers want to sprint before they can crawl. Moving off of paper helps you crawl first; it is a valuable, achievable goal across that the majority of organizations burdened with manual processes and their costs and if done properly, the ROI can be realized in a short amount of time with manageable effort. Having said this, the question quickly then becomes, “are we prepared to do what it takes to actually make the system improve?” Are you?

The Microsoft Clinical Information Feedback Loop

Microsoft recently purchased Rosetta Biosoftware from Merck & Co. for its Amalga Life Science platform; with this move, Microsoft is starting to differentiate itself from its competition by offering its integrated information solutions, which include HealthVault, Amalga UIS and Amalga Life Sciences, to both providers and producers. In its crosshairs are huge budgets available from Pharma for infrastructure solutions for drug R&D and clinical trials. Microsoft is posed to attract a whole new audience of customers from Pharma to integrated health systems that have their own research entities. If done correctly, Microsoft’s new strategy could become a model for improving the efficiency of clinical research, by drastically reducing the most costly resource needed for clinical trials, time.

The current Amalga UIS is fundamentally what I like to call a PDA (no not Public Display of Affection, rather a Patient Data Aggregator). There are three core components that include:

  1. Data Aggregation and Distribution Engine (DADE) – sits on top of healthcare provider sources and listens for HL7 messages; then puts them through transformation and parsing scripts in preparation to be stored in Amalga and sends them to a data store;
  2. Data Store – receives the messages from DADE; is a basic core storage engine and is a database with a set of tables specific to segments within the HL7 messages; and
  3. Front End – a web-based presentation layer that was originally designed for patient level data viewing and has plug in capability to provide more appropriate tools for analysis.

The current needs of data integration seem to be met by this solution, and the high degree of customization that can accommodate an implementation makes it even more attractive. Microsoft’s footprint in healthcare is getting bigger; they must understand, though, that this space has many stakeholders. While addressing all their needs is nearly impossible (just ask our hard working politicians’ trying to pass healthcare reform legislation), the last people they want to alienate are those they’ve already convinced that Amalga is the healthcare platform of the future, most notably some high profile integrated health systems across the country.

Integrated health systems (IHS) often provide a combination of services including care delivery, research, education, and even  their own health plan (think KP, John Hopkins, Geisinger, and Sentara). These entities have a unique opportunity to leverage the MS offerings by creating a continuous feedback loop of information from patient to provider to researcher that improves the quality and accuracy of the data throughout the process. Let’s start with the patient:

  • Patient information in HealthVault – As patient’s progress from being baby boomers (less tech-savvy) to Generation X & Yer’s (tech-hungry), clinical information will no longer be in the sole possession of the doctors. Rather, the demand will be for online, mobile, 24×7 access that is shared and can be updated real-time as health data is gathered by both patients and their doctors. Patients, thus, become a stand-alone data quality tool as they become more comfortable verifying, updating, and changing the information in their medical records.
  • Research information in Amalga Life Sciences – Researchers are all too familiar with the tedious, error-prone process of identifying patients with the correct diagnosis and conditions as candidates for clinical trials. As patients become more empowered with their medical records, they make the segmentation of populations a much simpler process.
  • Clinical information in Amalga UIS – Amalga UIS is a mechanism for driving continuous improvement in clinical care by integrating data across the enterprise. One way to improve care is by incorporating best practices identified through clinical research. The information learned from improved research methods are then implemented directly into the standard delivery of patient care offered by provider institutions.

Amalga feedback loop (2)

The Amalga UIS is currently operational in 12 domestic organizations. Because most of these clients are IHS’ and have research entities, they are in the best position to capitalize on the Amalga Life Sciences offering. These will also be the locations where the ROI MS is hoping will be formulated for less prestigious organizations to eventually imitate. It begs the following question, though, that some of the current customers will ask, “How can the existing components of Amalga Unified Intelligence System (UIS) be leveraged in this new offering to make it attractive to the widest audience possible and more importantly, be affordable?” Well, if you can articulate the argument above, and identify the huge benefits that can come from the Microsoft Feedback Loop, your argument might be easier to make than you think. And don’t forget, this feedback mechanism is built on the fundamental principle that all stakeholders must have the collective groups’ best interest in mind; so don’t forget to share what you find with your neighbor.

Physicians Insist, Leave No Data Behind

“I want it all.” This sentiment is shared by nearly all of the clinicians we’ve met with, from the largest integrated health systems (IHS) to the smallest physician practices, in reference to what data they want access to once an aggregation solution like a data warehouse is implemented.  From discussions with organizations throughout the country and across care settings, we understand a problem that plagues many of these solutions: the disparity between what clinical users would like and what technical support staff can provide.

For instance, when building a Surgical Data Mart, an IHS can collect standard patient demographics from a number of its transactional systems.  When asked, “which ‘patient weight’ would you like to keep, the one from your OR system (Picis), your registration system (HBOC) or your EMR (Epic)?” and sure enough, the doctors will respond, “all 3”. Unfortunately, the doctors often do not consider the cost and effort associated with providing three versions of the same data element to end consumers before answering, “I want it all”.  And therein lies our theory for accommodating this request: Leave No Data Behind. In support of this principle, we are not alone.

By now you’ve all heard that Microsoft is making a play in healthcare with its Amalga platform. MS will continue its strategy of integrating expertise through acquisition and so far, it seems to be working. MS claims an advantage of Amalga is its ability to store and manage an infinite amount of data associated with a patient encounter, across care settings and over time, for a truly horizontal and vertical view of the patient experience. Simply put, No Data Left Behind.  The other major players (GE, Siemens, Google) are shoring up their offerings through partnerships that highlight the importance of access to and management of huge volumes of clinical and patient data.

pc-with-dataWhy is the concept of No Data Left Behind important? Clinicians have stated emphatically, “we do not know what questions we’ll be expected to answer in 3-5 years, either based on new quality initiatives or regulatory compliance, and therefore we’d like all the raw and unfiltered data we can get.” Additionally, the recent popularity of using clinical dashboards and alerts (or “interventional informatics”) in clinical settings further supports this claim. While alerts can be useful and help prevent errors, decrease cost and improve quality, studies suggest that the accuracy of alerts is critical for clinician acceptance; the type of alert and its placement and integration in the clinical workflow is also very important in determining its usefulness. As mentioned above, many organizations understand the need to accommodate the “I want it all” claim, but few combine this with expertise of the aggregation, presentation, and appropriate distribution of this information for improved decision making and tangible quality, compliance, and bottom-line impacts. Fortunately, there are a few of us who’ve witnessed and collaborated with institutions to help evolve from theory to strategy to solution.

mountais-of-dataProviders must formulate a strategy to capitalize on the mountains of data that will come once the healthcare industry figures out how to integrate technology across its outdated, paper-laden landscape.  Producers and payers must implement the proper technology and processes to consume this data via enterprise performance management front-ends so that the entire value chain becomes more seamless. The emphasis on data presentation (think BI, alerting, and predictive analytics) continues to dominate the headlines and budget requests. Healthcare institutions, though, understand these kinds of advanced analytics require the appropriate clinical and technical expertise for implementation. Organizations, now more than ever, are embarking on this journey. We’ve had the opportunity to help overcome the challenges of siloed systems, latent data, and an incomplete view of the patient experience to help institutions realize the promise of an EMR, the benefits of integrated data sets, and the decision making power of consolidated, timely reporting. None of these initiatives will be successful, though, with incomplete data sets; a successful enterprise data strategy, therefore, always embraces the principle of “No Data Left Behind”.