The Brandeis GPS blog

Insights on online learning, tips for finding balance, and news and updates from Brandeis GPS

Tag: medical informatics

Analytics: Not Just For Data Experts

By Ariel Garber

Analytics is useful in any profession, with the potential to increase efficiency, profitability and accuracy. From healthcare, to marketing, to even sports, analytics is becoming an essential tool in all fields. Here’s a sneak peak into how data affects more industries that you expect.

Technology is shaping a new health care economy, evident in the advances of Stethoscopemobile devices, cloud computing and analytics. “‘We need to empower consumers with the in-the-moment guidance they need,’” said Dennis Schmuland, MD, Microsoft’s chief health strategy officer, “adding that a key technological component of that on both sides of the patient-provider equation is health analytics, thus the need to ‘make analytics easy for everyone.’”

Social media Picture1and marketing analytics tools are also important as social media becomes essential in all fields. Research has shown that “the conversations your customers have among themselves drive about 13 percent of business decisions and can amplify your advertising by 15 percent.

Sports analytics are valuable to both consumers and professionals, for the way we consume sports industry through sports data is dependent upon analytics. “Sports analytics is not just a catch phrase, but an influential part of the future of sports,” said Bloomberg Sports, the leading global provider in data and analytics, “We believe sports analytics plays an integral role in the future of sport, both at a fan engagement and elite sport performance level.” Bloomberg Sports offers a variety of resources to both consumers and professionals. For professional purposes, they provide analytic tools for scouting, video analysis and “player-centric applications to assess performances and aid the preparation of upcoming games.” They also have created a predictive analytics program and use their own broadcast and TV stations to “translate analytics-rich content into broadcast tools used on-air to inform and educate viewers.” They also host their own website, StatsInsights.com, featuring analytics-rich sports articles.

Big data is becoming incorporated into all aspects of sports, from devices that can track pitches during the game, to wearable technology. Adidas’ miCoach system collects data from a device attached to the player’s jersey that shows the top performers and who is tired, as well as “real-time stats on each player, such as speed, heart rate and acceleration.” The data from these devices assists trainers, coaches, and physicians in planning better training and conditioning.

There is also a demand for data analytics specialists to translate the data from these devices in a coherent manner for the players and coaches. Moneyball, a 2003 book and 2011 movie featured the Oakland Athletics competitive baseball that utilized analytics in their data-driven strategies. This highlights a shift in sports from gut instincts to a reliance upon science. Analytics is “gaining recognition as a tried and true instrument for competitive advantage in countless industries.”

Brandeis Graduate Professional Studies offers a Strategic Analytics program that produces professionals who understand the strategic potential of big-data analytics and who can translate analysis into effective organizational decision-making, poised to lead today’s organizations to new standards of efficiency and competitiveness.

Brandeis GPS is hosting an Analytics 360 Symposium on Wednesday, April 8, 2015 from 9am-4:30pm at Hassenfeld Conference Center of Brandeis University in Waltham, Massachusetts.

360LogoALT2The day-long symposium will focus on promoting a discussion of the growing field of analytics and how organizations can leverage big data to make more strategic decisions. Panelists will engage in a conversation that places analytics in the context of big data, education, health, marketing and business.

Register here for the Analytics 360 Symposium on April 8, 2015 at Brandeis University. The cost for NERCOMP members is $135 and the cost for non-members is $265. Submit this form to learn more about special pricing available to members of the Brandeis community. For more information, email analytics360@brandeis.edu or call 781-736-8786. You can also find us on Twitter using #GPSAnalytics.

Click here to subscribe to our blog!

Footerindesign

How Predictive Analytics Can Improve Healthcare

The below is the winning essay for a Brandeis GPS’ contest written by Health and Medical Informatics student, Davis Graham. Join Brandeis GPS is a free webinar 7/17 at 7pm: Long Term CareThe Last EMRFrontier

 

“My specific interest in predictive analytics is the ability to merge the once vacant silos of health information into a model which engages a person into the maintenance of a healthier lifestyle.[1]  Genomics and health information technology has the potential to help predict disease before it becomes chronic.  Predictive analytics will allow us to change from a treatment oriented to a preventive oriented healthcare system contributing to the efficiency of healthcare.

Predictive analytics gives the foundation for an individual to step onto a healthier path in life when substantial knowledge supports the first step.  There is a survival instinct which takes place in every individual when faced with the loss of health or life, giving them a fearlessness to assume responsibility to preserve their health and life.

The key element of a healthier population is engagement and implementation of a program which improves health.  For example, if a person has knowledge from predictive analytics showing they would have a 98% probability of being a candidate for colorectal cancer, then the barriers of fear currently existing in our current health care system would program-hero-strategic-analyticsinspire the patient to seek preventive care.  No one should die of colorectal cancer in this country or in the world.  Getting the patient to have a CT Colonography (CTC) would decrease the mortality rate for colorectal cancer substantially.  The cost of a CTC due to just the volume would decrease into the $250 range.  The current cost at our facility is $495; it costs us $200 to have the CTC read through teleradiology by a radiologist who reads these studies frequently.  Predictive analytics could change the whole landscape of CTC cost by pure volume.  Radiologists who are not reading CT Colonography (CTC) now would learn how to read them and would become experienced because of the increase in volume.

It is my hope that predictive analytics is steering healthcare back to the “doctor-patient relationship” of a patient driven healthcare.[2]  It is my belief that patient driven healthcare is the most efficient and effective way of providing health to a population.  With the aid of predictive analytics, the robust information gained from predictive analytics data will enable a society to engage in healthcare, which would educate the population with Stethoscopeknowledge as to how to predict their health outcomes.  Thus, the future patient population would embrace preventive health.  With patients engaged in their health, predictive analytics could reverse the current wasteful trend of 80% of healthcare expenditures being spent on 20% of the population, to one that is healthier for the economics of a country and a population.[3]  I could see in the future where 70% of the healthcare dollars is spent on 100% of the population with the remaining 30% going to research and development in healthcare and predictive analytics.

Predictive analytics would reverse the 20 to 30% of profits now going to health insurance companies into increased health dollars invested into healthcare.  A great example is William McGuire from United Health Care who earned $1.2 billion in one year.  This should be a light to the world that the $1.2 billion which William McGuire made did not go back into the healthcare system;[4]  it went into his pocket to spend and donate where his personal interests lay.  To put it in perspective, $1.2 billion could open 925 doctors’ offices each being 7,000 square foot for a cost of $1,297,400 each[5] or 4.8 million CTCs reimbursed at $250 each.

A key component to predictive analytics is the unbridled sharing of information. With quantum cryptography and the recent efforts of quantum computer (such as D-Wave), we are on the edge for sharing and processing healthcare’s “big data.” Predictive analytics in how-predictive-analytics-can-make-money-for-social-networks-46ce73d0c0the United States will be a new frontier for all health information which is electronically collected around the world. With predictive analytics, a combination of pharmaceuticals used to cure a chronic disease in one area of the world will enable population health to take steps in preventive care in advance of the chronic disease in other parts of the world.

In essence, we are embarking on a voyage into a new land of opportunity to process big data to predict solutions into the future. Healthcare is a team effort and aligns with Ernest Shackleton and his eclectic team, all of whom survived the harshest environment of being beset in the Antarctica.  Our healthcare system needs such a team to drive through the storms of economic pressure and the current healthcare system into one which perseveres.  Predictive analytics is the system which will not only benefit the United States, but predictive analytics in healthcare also has the potential to benefit the health of the world in a way healthcare has yet to be seen.”

About the Author: 

photoDavis Graham is currently earning his M.S. in Health and Medical Informatics with Brandeis University, Graduate Professional Studies. Davis is the Executive Director & CFO at the Manatee Diagnostic Center in Florida.  This essay won a contest for free entry into Eric Siegel’s Predictive Analytics World Conference.

Click here to subscribe to our blog!

Footerindesign

Is an Average of Averages Accurate? (Hint: NO!)

by: Katherine S Rowell author of “The Best Boring Book Ever of Select Healthcare Classification Systems and Databases” available now!

Originally posted: http://ksrowell.com/blog-visualizing-data/2014/05/09/is-an-average-of-averages-accurate-hint-no/

Today a client asked me to add an “average of averages” figure to some of his performance reports. I freely admit that a nervous and audible groan escaped my lips as I felt myself at risk of tumbling helplessly into the fifth dimension of “Simpson’s Paradox”– that is, the somewhat confusing statement that averaging the averages of different populations produces the average of the combined population. (I encourage you to hang in and keep reading, because ignoring this concept is an all too common and serious hazard of reporting data, and you absolutely need to understand and steer clear of it!)

hand drawing blue arrowImagine that we’re analyzing data for several different physicians in a group. We establish a relation or correlation for each doctor to some outcome of interest (patient mortality, morbidity, client satisfaction). Simpson’s Paradox states that when we combine all of the doctors and their results, and look at the data in aggregate form, we may discover that the relation established by our previous research has reversed itself. Sometimes this results from some lurking variable(s) that we haven’t considered. Sometimes, it may be due simply to the numerical values of the data.

First, the “lurking variable” scenario. Imagine we are analyzing the following data for two surgeons:

  1. Surgeon A operated on 100 patients; 95 survived (95% survival rate).
  1. Surgeon B operated on 80 patients; 72 survived (90% survival rate).

At first glance, it would appear that Surgeon A has a better survival rate — but do these figures really provide an accurate representation of each doctor’s performance?

Deeper analysis reveals the following: of the 100 procedures performed by Surgeon A,

  • 50 were classified as high-risk; 47 of those patients survived (94% survival rate)
  • 50 procedures were classified as routine; 48 patients survived (96% survival rate)

Of the 80 procedures performed by Surgeon B,

  • 40 were classified as high-risk; 32 patients survived (80% survival rate)
  • 40 procedures were classified as routine; 40 patients survived (100% survival rate)

When we include the lurking classification variable (high-risk versus routine surgeries), the results are remarkably transformed.

Now we can see that Surgeon A has a much higher survival rate in the high-risk category (94% v. 80%), while Surgeon B has a better survival rate in the routine category (100% v. 96%).

Let’s consider the second scenario, where numerical values can change results.

First, imagine that every month, the results of a patient satisfaction survey are exactly the same (Table 1).

patient-satisfaction-survey-table1

The Table shows that calculating an average of each month’s result produces the same result (90%) as calculating a Weighted Average (90%). This congruence exists because each month, the denominator and numerator are exactly the same, contributing equally to the results.

Now consider Table 2, which also displays the number of responses received from a monthly patient-satisfaction survey, but where the number of responses and the number of patients who report being satisfied differ from month to month. In this case, taking an average of each month’s percentage allows some months to contribute to or affect the final result more than others. Here, for example, we are led to believe that 70% of patients are satisfied.

patient-satisfaction-survey-table2

All results should in fact be treated as the data-set of interest, where the denominator is Total Responses (2,565) and the numerator is Total Satisfied (1,650). This approach correctly accounts for the fact that there is a different number of values each month, weights them equally, and produces a correct satisfaction rate of 64%. That is quite a difference from our previous answer of 6% — almost 145 patients!

How we calculate averages really does matter if we are committed to understanding our data and reporting it correctly. It matters if we want to identify opportunities to improve, and are committed to taking action.

As a final thought about averages, here is a wryly amusing bit of wisdom on the topic that also has the virtue of being concise. “No matter how long he lives, a man never becomes as wise as the average woman of 48.” -H. L. Mencken.

I’d say that about sums up lurking variables and weighted averages — wouldn’t you?

– See more at: http://ksrowell.com/blog-visualizing-data/2014/05/09/is-an-average-of-averages-accurate-hint-no/#sthash.WCltUtKb.dpuf

Untitled-1

Protected by Akismet
Blog with WordPress

Welcome Guest | Login (Brandeis Members Only)