Perficient Healtchare Solutions Blog

Subscribe via Email

Subscribe to RSS feed

Archives

Posts Tagged ‘healthcare analytics’

Why business intelligence isn’t the end game for health analytics

A few years ago, I transplanted my family from the south to Washington DC.  I love the Capital, for its history, its influence, but we quickly realized we had left Mayberry and arrived on Jupiter.  Horns honked and people moved around briskly.  Maybe it was us – our naiveté — or maybe it was the community we had arrived in.  But we quickly realized: “If you order french fries, you get french fries.” And only french fries. Months of dining out were spent, only to find that our presumed “condiments” were not standard with our order.  We would have to ask for them and specify the quantity.  French Fries and 2 ketchups, please.

Careful.Well I clicked my heels three times and eventually moved us back to our Mayberry.  It’s been three years and my son and I will still giggle together when we order french fries and see someone going out of his or her way to offer ketchup.  And when we say “Yes, Please”, we get several packets.

Consulting in Healthcare is no different. We’ve grown accustomed to the “build to spec” approach.  You get exactly what you asked for.

I’m thankful to be a part of Perficient and the Oracle Healthcare Business Intelligence team.  We share a common philosophy – understand what the customer wants to achieve, coach and advise available options, design and deliver a solution that fulfills their NOW problem and simultaneously prepared them for the next 5 years.  It’s not just a report – it’s Healthcare Analytics. Read the rest of this post »

Database inferencing to get to trusted healthcare data

A health insurance client of mine recently embarked on an initiative to truly have “trusted data” in its Enterprise Data Warehouse so that business leaders could make decisions based on accurate data.  However, how can one truly know if your data is trustable??   In addition to having solid controls in place (e.g., unique indexes on the primary AND natural key), it is also necessary to measure how the data compares to defined quality rulesWithout this measurement, trusted data is a hope – not an assured reality. 

shutterstock_71078161To enable this measurement, I designed a repository for storing

  • configurable data quality rules,
  • metadata about data structures to be measured,
  • and the results of data quality measurements.

I experienced the need to be able to perform a degree of “inferencing” in the relational database (DB2) being used for this repository.  Normally one thinks of inferencing as the domain of semantic modeling and semantic web technologies like RDF, OWL, SPARQL, Pellet, etc. – and these are indeed very powerful technologies that I have written about elsewhere.  However, using semantic web technologies wasn’t a possibility for this system.

Read the rest of this post »

5 Reasons Big Data Improves Personalization of Medicine

I enjoyed an article today in IT Business Edge about the ways that Big Data is improving outcomes. We hear that all the time, right? But what does it really mean? Why does more (and better) patient data lead to improved healthcare for all? When business intelligence is leveraged properly to deliver insights to healthcare providers, we see the following:

  1. 5_waysLearning what we never knew before: 

    “Allowing for previously unknown factors involved in disease to be discovered and utilized as drug targets or disease biomarkers.”

  2. Comparing data points from various sources to individualize treatment plans, improving outcomes. 

    “We are able to align and compare multiple data points from various sources, tailoring individualized treatment plans for each patient.”

  3. A move from subjective interpretation to objective diagnosis.A coworker of mine said to me yesterday, “Can you imagine when our kids are older? They’ll be laughing at our stories of how doctors once said to us, ‘Based on your symptoms, I think you have [X disease].’”

    She’s right. Diagnoses vary from physician to physician based on his or her background and experience. Not any more! As this article states, we’re facing a “datafication” of patient samples.

    “A vast quantity of knowledge that can be statistically analyzed and quickly reviewed by multiple clinicians for solid diagnosis”

  4. Better – and faster – decisions about treatment as a result of more and better patient data
    “Clinicians can systematically extract more information from each patient without requiring multiple rounds of testing.”
  5.  More accurate diagnosis and more appropriate spending on treatments due to reproducible testing”Consistently reproducible test results are possible between clinicians and doctors for more accurate diagnosis and appropriate spending on therapy options.”

Swallowing Sensors Gives New Meaning to the Quanitifed Self

You’ve heard of wearables in healthcare technology, but have you considered swallowables? Swallowing a piece of electronics is something that people are actually willing to try.

Forrester Research's version of of the famousVitruvian Man

Forrester Research’s version of of the famousVitruvian Man

Just this morning, Intel released results from a very compelling study on a range of consumer interest in electronic “wearables” and monitors. They asked people how willing they are to try:

  • Wrist monitors that can monitor things like respiration, blood pressure, heart rate and more, without a cuff – you’ve seen these in Nike Fuel Band and the FitBit Flex, among others.
  • Toilet sensors – you read that correctly.
  • Prescription bottle sensors
  • Blood pressure cuffs
  • The swallowable sensor
  • and more
Eric Dishman (@EricDishman) of Intel spoke with the Wall Street Journal today about the study by Intel. Watch the video below.
More than 80% of those surveyed said they were willing to share “de-identified data” to help further science and cures, so security of information is as important as ever.

Identity and the Internet of Things – Lessons for Healthcare

Attending Dreamforce in San Francisco last month, I was reminded of an article I read in All Things Digital about the role of Identity and the Internet of Things.  Apparently Marc Benioff, salesforce.com’s CEO, mentioned during a presentation at the Bank of America Merrill Lynch 2013 Technology Conference,  that Phillips, the electronics company long known for staple consumer products like TVs, cameras and audio equipment, was working on a new toothbrush. The toothbrush under development was not just any ordinary toothbrush but included GPS, Wi-Fi and “realtime” feedback on how a person brushes their teeth.  Voila, no more lying to your dentist – self-quantification will rat you out with your own data.

While the concept of “The Internet of Things” like the high-tech toothbrush isn’t new, salesforce.com’s forward thinking CEO was previewing a new trend — connected devices are becoming inextricably tied to identity.  Just like my registration email at Dreamforce using a barcode to speed check-in and attendance at sessions.  My identity Internet-Of-Thingswas tied to a “thing” in the Internet of Things.  Lots of my personal devices are internet-enabled as well, connecting my identity to how far I walk for exercise, where I travel, what hotels I stay at, etc.  In the world of social, devices like the smartphone, activity tracking wristbands, etc. are creating comprehensive profiles of our “real” behaviors like brushing our teeth.

It doesn’t take a big leap to understand the impact of connecting my identity and devices on managing my health or lifestyle.  You can easily imagine a healthcare plan, like Geico does on cars, offering a discounted health plan in exchange for your comprehensive lifestyle profile, or at least lower deductibles for positive behaviors, including taking your medications on time.  The challenge will be making certain that your identity is truly linked to your proper information in healthcare systems and there are clear safeguards in place.  As the article in All Things Digital states

“And to be clear, trust-based relationships with users means that privacy must be accounted for and the right controls must be in place before businesses start collecting and using this data. With the proper opt-in/out privacy controls in place, identity-defining traits like hometown, religious beliefs, relationships status, likes, activities and social graph can be available to marketers and used to drive hyper-relevant marketing campaigns.”

As the list of connected “things” in our lives grows and uses our identity to tie our behavior profile to our healthcare management, the pressure will be increased for outstanding master data management by healthcare providers and healthcare plans.  It is amazingly difficult for healthcare companies to conquer enterprise-level master patient indexes to resolve your one identity and create a combined view of your medical history.  While your smartphone revolves around your Facebook username and password, Twitter log-ins, etc. to know you, the fragmented healthcare system must piece together that you go by your middle name, use a nickname or don’t really know your actual Social Security Number.

Master Data Management and Identity Management for healthcare is literally a matter of life and death, especially for people with medication allergies, chronic conditions like diabetes and people with medical implants like pacemakers.  Dick Chaney took the extreme step of firewalling his wireless connection on his pacemaker, for example, to block terrorists from attacking him based on his device and identity.  While we enjoy the idea of our exercise wrist band taking to our smart thermostat to cool down the house after a run, we need to understand the broader implication of this degree of connectivity into our own safety as patients.

You may laugh the next time that the hospital asks you your name for the umpteenth time or marks the site of your surgery with a marker, but identity matters in healthcare and as that industry becomes more connected like your devices, make sure that your information is correct, up to date and is “real.”  It could literally save your life.

Are you really listening to your patients?

If the pressure to obtain and implement Customer Relationship Management software by healthcare organizations is any indication, decision makers are recognizing the increasing importance of consumer knowledge in the race to improve patient satisfaction scores.  Indeed, today, patient insights can lead healthcare organizations to their best opportunities for growth and restoration of profitability far more accurately than that marketing presentation in the boardroom.  The increasingly reluctant spending by healthcare consumers needs to be better understood because a healthy healthcare delivery system depends on it.  The challenge is that healthcare consumer interactions are not typically structured information that is easily analyzed to be acted upon, but are increasingly emails, phone conversations, web-based chat support and other unstructured information.

Increasingly, outbound direct mail or telemarketing is simply not getting results for healthcare marketing departments.  The focus needs to shift to creating a great consumer experience on the inbound approach as an alternative. Doesn’t everyone enjoy doing business with a company that is easy to find and obtain what you are looking iStock_DoctorPatientfor?  You don’t have to look far for proof of this idea.  No longer able to differentiate on brand reputation, leading companies instead are focusing on the consumer experience—the all-important feelings that consumers develop about a company and its products or services across all touch points—as the key opportunity to break from their competition and regain lost revenue from programs like hospital value based purchasing. Outside of healthcare, the evidence of this new emphasis is found in the emergence of the “chief consumer officer” (CCO) role across the Fortune 1000 community.  Companies such as United Airlines, Samsung and Chrysler have all implemented chief consumer officers as part of their executive suites.  Should healthcare plans and providers consider this key competitive move too?

Read the rest of this post »

A Low Cost Big Data Integration Option?

With all of the interest in big data in healthcare, it’s easy to get drawn in by the excitement and not realize that it’s not a silver bullet that’s going to address all your data and infrastructure problems.   Unless you are able to understand and integrate your data, throwing all the data onto a platform like Hadoop or Cassandra probably won’t provide the benefit you’re looking for. Of course, there really is benefit to leveraging a big data platform for the right kinds of use cases, such as increased scalability, performance, potentially lower TCO, etc.

Of course, there are many integration tools out on the market that perform well.   However, I’d like to propose consideration of Semantic Web technologies as a low cost alternative to traditional data integration.  Many are open sourced and are based on approved standards from W3C such as RDF (Resource Description Framework) and OWL (Web Ontology Language).

How_information_is_connecting_all_types_of_healthcare_data_to_make_a_difference_LRGUsing Semantic Web technologies to enable integration, for example the Open Link Data initiative for integrating data across the internet, can (besides being less expensive) provide significant advantages for automated inferencing of new data which would previously require specialized programming to derive.  Indeed, your Semantic Web environment can serve as the knowledge base for artificial intelligence.

Read the rest of this post »

The Coming “Big Data” Storm

As a technologist raised in Kansas as a child, I am used to examining the horizon for changes in the weather.  We could watch the large thunderstorms build up during the heat of the day into 40,000 foot monsters full of hail and tornadoes.  I was reading an Ars Technica article on how pervasive computing and cloud will change the nature of IT recently, and the article pointed out the coming “big data” storm.  The article argues that like the heat of a Midwestern day growing and driving the thunderstorm, key technologies have reached a tipping point to create the perfect “big data” storm.

Just like storms, big data includes three big trends of volume, velocity and variety.  Data sets were predicted to reach 1 petabyte (1 million gigabytes) and without recent advances in hardware and software, especially virtualization and cloud storage, would be unmanageable in terms of volume.  Velocity is especially evident in healthcare data stormwhere near real-time information is not just a goal but becoming a requirement.  Velocity demands very fast processing to analyze data, potentially aggregate it, and visualize results.  Variety of data is a challenge in healthcare as well, with new and unstructured forms like video, text and sensor readings. The proliferation of medical devices and sensors alone can create data that literally overwhelm the typical healthcare organization’s ability to analyze and take action based on the information, thus creating a dangerous storm.

Read the rest of this post »

The Conceptual Data Model – Key to Integration

The importance of data integration, whether for analytics, mergers/acquisitions, outsourcing arrangements, third party interfaces, etc., is easy to understand but extremely difficult to realize.  The technical aspect of data integration is the (relatively) easy part.  The hardest part is bridging the semantic divide and agreeing on business rules – i.e., communication.  The Conceptual Data Model can be an invaluable tool to help bridge the gap.

A Conceptual Data Model is a technology, application, and (usually) business unit neutral view of key business objects (data entities) and their relationships, and should be the framework for information systems.  It is a business model, from a business object perspective, where we’re identifying what data is of interest to the business rather than how the data is used.  It is not a process model, and is stateless in nature (all states of a relationship must be expressed to provide a longitudinal perspective).   Relationships can express many business rules.  A Conceptual Data Model typically takes the form of an ERD, UML Class Diagram, or ORM diagram.

Doctor Working on a Laptop Read the rest of this post »

Chronic Disease Management through Disease Registries

Chronic diseases, those diseases lasting 3 months or more that cannot be prevented by vaccines or cured by medication1, are placing an increasing burden on our healthcare system.  Unfortunately, the United States has one of the highest rates of illness, disability and death due to chronic diseases, such as asthma, diabetes, coronary heart disease and obesity.  According to the Centers for Disease Control and Prevention (CDC), 7 out of 10 deaths among Americans each year are from chronic diseases and as a nation, 75% of our health care dollars goes to treatment of chronic diseases2.  In 2005, 133 million Americans, almost 1 out of every 2 adults, had at least one chronic illness1. Regardless of the impact of these preventable diseases, a recent survey found that only 56% of recommended care is being provided for patients with chronic illness3.  As a result, provider organizations are seeking new strategies for effectively managing these large and expensive populations4.  “There is a great need for a systematic and comprehensive approach to caring for patients with chronic diseases to help improve the quality of chronic care delivery.” 4  One such strategy is implementing disease registries to capture and track key patient information that assists care team members in proactively managing patients with chronic diseases5.

In this blog post, we will take a high-level look at the some of the key functions and limitations of a disease registry as it relates to chronic disease management.

Functions of a Disease Registry

A registry can be defined as “an organized system for the collection, storage, retrieval, analysis, and dissemination of information on individual persons exposed to specific medical intervention who have either a particular disease, a condition (e.g., a risk factor) that predisposes them to the occurrence of a health-related event, or prior exposure to substances (or circumstances) known or suspected to cause adverse health events.” 6

Read the rest of this post »

Key insights on source data for healthcare analytics & exchanges

Providers and payers need to exchange or source a lot of data, and the rate of this activity will only increase with implementation of Obamacare and other directives.  Given the poor state of metadata management (which makes data sharing much more difficult), the decision to incorporate a new data set into an Enterprise Data Warehouse or data services can be fraught with much confusion making it very difficult to estimate the level of effort and deliver on time.  It makes sense, therefore, to identify and document a list of  “what we need to know about data” so that standard policies and data dictionary templates can be crafted to serve as the foundation for the data contract (even above and beyond an XSD if you’re using XML, unless the XSD is completely expressive with restrictions on lengths, acceptable values, etc., – but of course even then it can be hard for business and data analysts to review an XSD).

The list of “what we need to know about data” must go far beyond the bare bones metadata such as the field name, datatype, length, and description.  Why?  Because someone is going to have to gather the missing information, and of course this information collection takes a significant amount of  time and effort on the part of  business analysts, data analysts, data stewards, and modelers.  If the effort to collect this information isn’t made up front then more time and money will be required during the development process with increased risks of lack of confidence in the data.

Read the rest of this post »

Harnessing Hospital Data to Improve Healthcare

In the age of ACOs and value based payments, there is a constant pressure on the healthcare industry to reduce costs without damaging the quality of care provided. While there are many factors in this balancing act, hospital readmissions and  lack of medication adherence are two issues driving up costs that can be addressed and prevented. EMRs hold the data needed to created a prevention plan, but that data is often siloed from clinical, financial and operation data also necessary for an effective plan. Business intelligence and analytics tools allow providers to view and interpret the data, but even these systems often don’t communicate with other systems.

A Forbes article recently announced that IBM and Premier health alliance are teaming up to provide better data insights across a population. Using big data, this Data Alliance Collaborative (DAC) utilizes IBM technology to predict readmissions and medication compliance issues across the Premier collaboration of 200 hospitals. With over 70 different health care systems, Premier sees great value in using shared capabilities to leverage data analytics for population health.

“Partnering with Premier and  IBM to create the integrated view of clinical, financial and operational information in one data model will allow a clearer analysis of costed outcomes and improved decision support for healthcare organizations,” said Martin Sizemore, principal, healthcare strategic advisory services at Perficient. This real-time integrated view of the data will allow hospitals to make mid-course adjustments to meet federal regulations.

Perficient will be hosting a webinar, “Going Beyond the EMR for Data-driven Insights in Healthcare,” to further explore the role of data analytics in healthcare. Join us to learn how analytics is being used to measure and monitor performance and provide service-line directors and financial administrators with reporting and analysis that enhances clinical care processes and business operations.