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.

5 thoughts on “The Microsoft Clinical Information Feedback Loop

  1. Amalga Life Sciences features a “Concept Browser” for the Unified Medical Language System (UMLS) ontology, which enables the user to input and connect multiple concepts via their ontological relationships. The user may choose to connect via all possible connections, to select the depth of connections or to display only the shortest path. The output is displayed to the user as a visual network of concepts and relationships. Once the data is accessible and manageable, subject matter experts can then apply models and theories to data, identify the best solutions to complex problems, and predict new relationships.

    • Preeti,

      Thank you for that valuable information and insight. I believe you’ve identified one of the main reasons why Amalga Life Sciences is gaining more traction than its counterpart Amalga UIS in the provider setting, that is the application of its ontology using UMLS. The application of standard terms over user queries has drastically improved that product. If we were, for example, to apply this to nursing documentation in an acute care setting, the clinicians would be in a much better position to both document the information and retrieve it in a more logical, repeatable fashion. A great analogy I’ve heard for this construct is similar to the Dewey Decimal System in libraries to find books. Say you want to find ‘photography’ books; first you find out ‘photography’ is P804.XX; then that section is all photography and you want specifically ‘digital’ which is P804.5X; and then you get a list of all ‘digital’ ‘photography’ books. Each layer you go deeper, based on standard terms for searching and querying, the more limited the results and more importantly, the more relevant to what you’re looking for.

      Without the use of something like the UMLS in research settings, healthcare organizations are forced to undergo the extremely difficult process of standardizing their own terminology. This is accomplished through implementing a strong Data Governance framework. I’ve worked with and spoken to numerous organizations that can’t seem to gain the necessary support for a data governance initiative; yet our organization along with many others consistently identify governance as one of the most critical steps in formulating and implementing an enterprise data strategy and subsequently capitalizing on enterprise information managment.

      A great picture can be found here relating to Amalga Life Science:

      Please feel free to connect with me on LinkedIn any time ( for additional follow up or related conversation. It seems you have a wealth of knowledge about this topic, I’d be interested in hearing more.

  2. Pingback: From Free Text Clinical Documentation to Data-rich Actionable Information « Edgewater Technology Weblog

  3. The organisation and processing of clinical trials data can be very complex. maintaining complete audit trails on the data is desperately important. Does this software help?

  4. Anna,
    Thank you for your comment. Yes, Amalga does support auditing the actions of users through it’s Amalga Console. Auditing can be as detailed as, what module (e.g. Lab, Radiology Results, EKG’s) did a user look at, what patient data did they see, etc. It is configurable to an extent. This data is then packaged into an extension which provides some basic views of the audit logs.

    On top of this, Amalga has extensive control over what users see in amalga. It can be difficult to manage, but it does give administrators many options for limiting access to information/features in the Amalga Console.

    I hope this helps, if you have further questions please feel free to send them along.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s