Perficient Healtchare Solutions Blog

Subscribe via Email

Subscribe to RSS feed

Archives

Follow our Healthcare Technology board on Pinterest

Posts Tagged ‘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 »

Can you predict my future? Predictive analytics at #HIMSS14

While my interest is always in the convergence of technology like the Internet of Things and healthcare IT, the role of sensors in managing health and wellness is just exploding. 

“The most popular device functionality in the wearable tech market is heart rate monitoring, with nearly 12 million such devices shipped in 2013. Pedometers and activity trackers accounted for a combined 16 million shipments over the same period.” (According to a report released Thursday by ABI Research)

- Source: New report shows smartwatches and AR glasses have their work cut out.

the role of analytics, especially healthcare analytics, should be to inform, encourage and drive healthcare consumers to improve our behaviors or decisions without being intrusive.

“The role of analytics, especially healthcare analytics, should be to inform, encourage and drive healthcare consumers to improve our behaviors or decisions without being intrusive.”

You can’t turn anywhere without reading about the latest running gadgets, fitness bands, Bluetooth blood pressure cuffs, etc.  In the inevitable rush to wearable computing, one key idea can get lost: what are we doing with all of that data? 

The data produced by these devices and sensors has to be interpreted and turned into information that is actionable.  The fitness band that looks at your goal of 10,000 steps, sees that you are at 8,000 steps right after dinner and encourages you for one final walk around the neighborhood, will ultimately win out over all others.  In order to pull off that trick, we need analytics and, sometimes, predictive analytics.

Just as the sensors are working in the background without us even taking notice, the role of analytics, especially healthcare analytics, should be to inform, encourage and drive healthcare consumers to improve our behaviors or decisions without being intrusive.  The goal of healthcare analytics or informatics should be to create an environment for the healthcare consumer that makes life better, easier and more enjoyable.

An example is when the running app sees your pace slowing down towards the end of a run, then it kicks in a song with a faster pace to help you finish strong.  Today those apps require you to recognize that situation and take action of pressing a button.  It’s all there but it’s not automated.  What we need is that invisible intelligence that recognizes the situation and then takes action to assist us.

The Role of AnalyticsAt HIMSS 2014, we will be seeing this jump in interest in predictive analytics as it applies to healthcare, especially two distinct types of predictive analytics.

  1. One type is the traditional forecasting model of advanced analytics that trends past information to predict future states.
  2. The second type of predictive analytics is statistical models that encompass multiple feeds or variables to predict a future outcome.  This modeling is rapidly moving past the arena of data scientists who create the models and is moving more within the grasp of smart business analysts.  These models can predict your longevity based on multiple factors like your BMI, blood sugar readings for diabetics and other factors from your medical history.

Of course, we want to be able to predict health outcomes, especially when faced with several choices for changing our behaviors or lifestyle.  It will be exciting to see how healthcare application vendors are addressing this important next step in analytics.

The use of predictive analytics could really change the nature of a patient engagement with your doctor.  How will we react when we see the outcome of our current lifestyle?  Will we shut off Netflix bingeing and head to the gym? See you at HIMSS 2014 to find out!  Stop by Perficient’s booth #2035 and tell us what you found out!

himss14_top

 

Reframing the ACO Analytics Problem with Malcolm Gladwell

I just finished watching a quick slideshow on the Health Data Management website, “Enterprise Analytics: Moving on Up” and as luck would have it, I also watched several sessions of the live Webcast from the Healthcare Innovation Day Conference 2014 in Washington, DC, sponsored by West Health Institute and the Office of the National Coordinator for Health Information Technology (ONC).

Malcolm Gladwell quoteWhile I was watching these, I was intrigued by the thought of how Accountable Care Organizations (ACO) can leverage existing solutions, combined with point solutions, to accomplish their reporting, analytics and beyond, and use interoperability wisely.  One of the key learning points for me from these sessions was this:  “Reframe the problem”….advice from Malcolm Gladwell’s keynote address.

How do we “reframe the problem” when it comes to ACO reporting and analytics?  There are defined metrics that are required for these organizations, so how can we leverage existing systems to create these reports and analytics?  Do we “build vs. buy”?  Depending upon the organizational size, legacy systems and IT support, the decision can be difficult.  What is good for one system may not work in another.  So where do we start?

A strategic evaluation of current state and desired future state with the development of a road map may be a logical first step.  Data Governance also needs to happen early on in the process to allow an organization to create data standards that will drive reporting and analytics.  Once these steps have occurred, an organization can feel confident that they can make an informed decision to “build or buy.”

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.”

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 »

Top 5 Technology Trends in Healthcare – September 2013

The healthcare IT field is rapidly developing and changing. Emerging technology and updated regulations put pressure on healthcare providers and health plans to stay ahead of the curve. Perficient creates a monthly list that explores some of the current topics and issues in health IT. This list examines the most talked about issues and technologies that are currently affecting the industry.

HCBlog Top5 Trends

Obamacare Defunding

Under the Affordable Care Act, or Obamacare, over 48 million uninsured Americans will be eligible for enrollment in subsidized plans through state-run health insurance exchanges, with annually increasing fines for those who go uncovered. Currently, the US government is reviewing calls to defund Obamacare while Health Insurance Exchanges are set to open on October 1st.

Google Calico

Last week, Google announced it would be reentering the e-health game with its new product, Calico. The goal of Calico is to positively impact aging and associated diseases, while focusing on health and well-being. Initially, Calico will fun aging and preventable disease research projects.

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 »