Healthcare and ECM – What’s Next Doc? (part 2 of 2)

In my last blog posting Healthcare and ECM – What’s Up Doc?, I wrote about using ECM based content analytics technology to help accelerate decision making in an industry in transition.

But why stop there … how powerful would it be to turn those new insights (from unstructured information) into action by combining content analytics with predictive analytics or other business analytics?

This is transformational … by unlocking the 80% of information not currently being leveraged (explained in part 1) we unlock new ways to use information. More compellingly, we unlock never seen before trends and patterns in both clinical and operational data.

Think about it … do we know everything we need to know about healthcare and how to identify and treat diseases? Or can we benefit from new insights? The answer is obvious.

Combining content and predictive analytics enables:

  • Accurate extraction of medical facts and relationships from unstructured data in clinical and operational sources – not easy, cost effective, or even possible in the past.
  • Never seen before trends, patterns and anomalies are revealed – connections or relationships between diseases, patients and outcomes (and even costs) are now able to be surfaced and acted upon. Think of the medical research possibilities!
  • The ability to predict future outcomes based on past and present scenarios – optimizing resource allocation and patient outcomes. One organization reduced cardiac surgery patient morbidity from 2.9% to 1.3% by doing this.
  • New insights can be surfaced to any clinical or operational knowledge based on their respective role – this could be through dashboards, case management/care coordination system, EMR, claims processing or any number of other ways – enabling better decision making and action across the organization.
  • The ability to leverage these new insights with other systems such as data warehouses, master patient data – maximizing and befitting from the use of other systems.

In my last posting, I commented that it was now an imperative to leverage clinical information and operational data in new ways … and that are obvious things to do to improve quality of care, patient satisfaction and business efficiency.

There are at least nine areas where this opportunity exists. The clinical scenarios are:

  • Diagnostic Assistance: Highly correlated symptom to health/disease analysis issues visualized with predictive guidance on diagnosis to improve treatment and outcomes … with predicted or forecasted costs.
  • Clinical Treatment Effectiveness: Examine patient-specific factors against the effectiveness of a healthcare organizations specific treatment options and protocols … including comparisons to industry wide outcomes and best practices.
  • Critical Care Intervention: Early detection of unmanageable or high risk cases in the hospital that leads to interventions to reduce costs and maintain or improve clinical conditions … including case based interventions.
  • Research for Improved Disease Management: Perform analysis and predict outcomes by extracting discreet facts from text, such as: patient smoking status, patient diet and patient exercise regime to find new and better treatment options … use a mechanism for differentiation or to secure research grants.

Operational scenarios include:

  • Claims Management: All claims involve unstructured data and manually intensive analysis. Analyze claims information documented in cases, forms and web content to understand new trends and patterns to identify areas … perfect for process improvement, cost reduction and optimal service delivery.
  • Fraud Detection and Prevention: Uncover eligibility, false assertions and fraud patterns trapped in the unstructured data to reduce risk before payments are made … usually represented by a word or combination of words in text that can’t be detected with just structured data.
  • Voice of the Patient: Include unstructured data and sentiment analysis from surveys and web forms in analysis of patient and member satisfaction … this will be key as the industry moves to a value based model.
  • Prevention of Readmissions: Discover key indicators which are indicative of readmission to alert healthcare organizations to these so that protocols can be altered to avoid readmission … this is key as new Medicare payment penalties go into effect in 2012.
  • Patient Discharge and Follow-up Care: Understand and monitor patient behavior to proactively inform preventative and follow-up care coordinators before situations get worse.

According to the New England Journal of Medicine, one in five patients suffer from preventable readmissions. This represents $17.4 billion of the current $102.6 billion Medicare budget. Beginning in 2012, hospitals will be penalized for high readmission rates with reductions in Medicare discharge payments. Seton Healthcare Family is already ahead of the game.

“IBM Content and Predictive Analytics for Healthcare uses the same type of natural language processing as IBM Watson, enabling us to leverage our unstructured information in new ways not possible before,” said Charles J. Barnett, FACHE, President/Chief Executive Officer, Seton Healthcare Family. “With this solution, we can access an integrated view of relevant clinical and operational information to drive more informed decision making. For example, by predicting readmission candidates, we can reduce costly and preventable readmissions, decrease mortality rates, and ultimately improve the quality of life for our patients.”

This week at IOD … IBM is launching a new solution specifically designed to reveal clinical and operational insights in the high impact overlap between clinical and operational use cases – enabling low cost accountable care.

IBM Content and Predictive Analytics for Healthcare, a synergistic solution to IBM Watson, helps transform healthcare clinical and operational decision making for improved outcomes by uniquely applying multiple analytics services to derive and act on new insights in ways not previously possible … which is exactly what Seton Healthcare Family is doing.  Dr. David Ramirez, Medical Director at Seton shares his perspective here.

IBM Content and Predictive Analytics for Healthcare (ICPA) is Watson Ready and is designed to complement and leverage IBM Watson for Healthcare through the ability to analyze and visualize the past, understand the present, and predict future outcomes.

ICPA, as the first Watson Ready offering, not only provides assurance of Watson solution interoperability but extends the value ultimately delivered to clients. For example, using input from ICPA outcomes, IBM Watson will be able to provide better diagnostic recommendation and treatment protocols as well as learn from the confidence based responses.

The press release is available here for those seeking more information. I will be doing a high level main stage demo of ICPA on Wednesday which will be streamed live. I will post the replay when available.

But it’s not just healthcare … every industry is impacted by the explosion of information and has the same opportunity to leverage the 80+ percent that is unstructured to turn insights into action.

As always, leave me your thoughts and comments here.

Healthcare and ECM – What’s Up Doc? (part 1 of 2)

This is one of those industry centric topics everyone can relate to … we all need healthcare and we’ll all use it at some point in our lives.  I plan to do a couple of postings on Healthcare and ECM … here is the first.

The healthcare industry is undergoing a major transformation.  We have a legacy health system that is fee for service based resulting in a care system that is high cost with inconsistent quality.  Healthcare provider consolidation is accelerating; competitors as well as payers/providers are merging.  Clinical transformation is already occurring … disease management, health and wellness management, and behavioral health are integrating.  The industry is moving to a more patient centric, evidence based and competitive care system where the players are held accountable and will have to compete on the value they deliver and not rely solely on quantity based reimbursements.

This transformation is driving new thinking, new business models and a restructuring of clinical and operational care models.  The expectation of value is changing and healthcare organizations have to adjust their business models to deliver value, not just volume.  This type of transformation requires innovation … the kind of innovation that improves productivity and competitive advantage … and not just advancing medical technology for technology sake. The main consideration must be for total well being and cost, and not one for the sake of the other.

As the backbone for a transformed healthcare system, leveraging clinical information and operational data in new ways are obvious things to do to improve quality of care, patient satisfaction and business efficiency.  This places a premium on making this information accessible and actionable to optimize outcomes! … and where ECM comes in!

There are many ways ECM technologies are being applied to solve problems in healthcare. Obvious ones are document capture conversion of paper based patient records and advanced case management for care coordination.  I am going to focus on content analytics and leveraging unstructured information to reveal insights currently trapped in documents, records and other content.  I believe this has significant transformative potential as an ECM based information technology.

Studies show that healthcare information is growing at 35% per year and that over 80% of information is unstructured data (or content).  The explosion of information makes accessing and leveraging it a harder task, but this is now an imperative.

Unstructured data resides in many sources:  physician notes, registration forms, discharge summaries, text messages, documents and more.  Because this content lacks structure, it is arduous for healthcare enterprises to include it in business analysis and therefore it is routinely left out.

The impact of this is staggering.  If you had a choice – would you choose to leverage all of your available information or just the 20% that is structured data and found in databases?  This is exactly the type of thing that can accelerate transformation.  We need to leverage the remaining 80% of available information.  After all … would you want your Doctor making decisions about your health on 1/5th of the available information?

It’s such a simple premise but the reality is that until recently, the technology wasn’t available to easily and accurately analyze and unlock insights contained in the unstructured information.  This is where natural language processing (NLP) and breakthrough technologies like IBM Watson and IBM Content Analytics come in.  So let’s apply this to the real world.

Smoking has long been known as a habit that contributes to poor health and diseases like Congestive Heart Failure but how accurately do the healthcare systems of today reflect the patient’s current smoking status?  To understand a patient’s smoking status … it cannot only be a yes/no checklist question found in structured data.  How can a check box know you if you quit 3 years ago … or started again last year and just recently quit again … or that you recently took up casual cigar smoking … or that you cut down from 2 packs to 1 pack a day?  A structured data field can’t understand these nuances.  This is natural language based information found only in text.  These text based descriptions are often captured in registration forms, history and physical reports, progress reports and other update reports.  Most systems have not factored in this kind of information due to the cost and time taken to manually extract it. It’s often too costly and too late. Yet it is exactly this kind of information that could be most critical in improving care.

In a recent private IBM customer data study, we found 40% of the total population of smoking patients were identified in the text of unstructured physician notes, and not the structured data.  This is huge!  Can you imagine doing research on smoking without including this kind of information? … or not including 40% of the total smoking population?

BJC Healthcare has figured out the value of leveraging unstructured data.  They found that structured data alone was not enough when doing research often resulting in the reading of documents … many many documents … one by one.  You can imagine how fun and helpful that was.  They are now using IBM Content Analytics to extract key medical facts and relationships from more than 50 million documents in medical records, speeding up research to ultimately provide better care for patients worldwide… See the recent case study.

I feel strongly that ECM technologies, and especially Content Analytics, can make a huge impact in both the clinical and operational healthcare transformation underway.  I’ll be back in two weeks with more on this topic … which is now published as Healthcare and ECM – What’s Next Doc?

As always, leave me your thoughts and comments here.