Free Hospital EMR and EHR Newsletter Want to receive the latest news on EMR, Meaningful Use, ARRA and Healthcare IT sent straight to your email? Join thousands of healthcare pros who subscribe to Hospital EMR and EHR for FREE!

When Hospitals Leak Money

Posted on October 20, 2017 I Written By

Anne Zieger is veteran healthcare editor and analyst with 25 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

A couple of weeks ago I was skimming healthcare business headlines and stumbled across this guaranteed showstopper: You’re probably leaving $22 million on the table. That headline is from a column by Jim Lazarus, who works in the Advisory Board’s Revenue Cycle Solutions division. In his column, he named four ways in which hospitals could recapture some of this lost revenue.

In the article, Lazarus notes that hospitals aren’t following best practices in four key areas, namely denial write-offs, bad debt, cost to collect and contract yield.  Unsurprisingly, Advisory Board benchmarks also demonstrate that median performing organizations are having trouble reducing net days in accounts receivable. The Advisory Board has also found that the overall average cost to collect has worsened by 70 points of net patient revenue from 2011 to 2015.

To turn the stats around, he suggests, hospitals should focus on four critical issues in revenue cycle management. They include:

  • Preventing denials rather than responding to them. “Hospitals are losing, on average, five percentage points of their margin to underpayments, denials and suboptimal contract negotiations,” Lazarus writes.
  • Collecting more from patients by improving their financial experience. According to Lazarus, between 2008 and 2015 the portion of patient obligations being written off as bad debt has climbed from 0.9% to 4.4%. To boost patient collections, hospitals must offer price estimates, convenient payment methods and a positive care encounter, he says.
  • Being sure not to take a hit on MACRA compliance. See that doctors, including those coming on board as employed physicians, get up to speed on documentation performance standards as quickly as possible.
  • Building the value of merged RCM departments. If multiple RCM organizations are being integrated as part of consolidation, look at ways to improve the value they deliver collectively. One approach is to create a shared services organization providing a common business intelligence platform across entities and service lines systemwide.

If you’re an IT leader reading this, it’s probably pretty clear that you have a substantial role in meeting these goals.

For example, if your hospital wants to lower its rate of claims denials, having the right applications in place to assist is critical. Do your coding and billing managers have the visibility they need into these processes? Does senior management?

Also, if the hospital wants to improve patient payment experiences, it takes far more than offering a credit card processing interface to make things work. You’ll want to create a payment system which includes multiple consumer touch points and financing options, which is integrated with other data to offer sophisticated analyses of patient payment patterns.

Of course, the ideas shared by Lazarus are just the beginning. While all organizations leave some money on the table, they have their own quirks as to why this happens. The important thing is to identify them. Regardless, whether you are in RCM, operations or IT, it never hurts to assume you’re losing money and work backward from there.

Poll: Providers Struggle To Roll Out Big Data Analytics

Posted on April 10, 2017 I Written By

Anne Zieger is veteran healthcare editor and analyst with 25 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

A new poll by a health IT publication has concluded that while healthcare organizations would like to roll out big data analytics projects, they lack many of the resources they need to proceed.

The online poll, conducted by HealthITAnalytics.com, found that half of respondents are hoping to recruit data science experts to serve as the backbone of their big analytics efforts. However, many are finding it very difficult to find the right staffers.

What’s more, such hires don’t come cheaply. In fact, one study found that data scientist salaries will range from $116,000 to $163,500 in 2017, a 6.4 percent increase over last year’s levels. (Other research concludes that a data scientist in management leading a team of 10 or more can draw up to $250,000 per year.) And even if the pricetag isn’t an issue, providers are competing for data science talent in a seller’s market, not only against other healthcare providers but also hungry employers in other industries.

Without having the right talent in place, many of providers’ efforts have been stalled, the publication reports. Roughly 31 percent of poll respondents said that without a data science team in place, they didn’t know how to begin implementing data analytics initiatives.

Meanwhile, 57 percent of respondents are still struggling with a range of predictable health IT challenges, including EMR optimization and workflow issues, interoperability issues and siloed data. Not only that, for some getting buy-in is proving difficult, with 34 percent reporting that their clinical end users aren’t convinced that creating analytics tools will pay off.

Interestingly, these results suggest that providers face bigger challenges in implementing health data than last year. In last year’s study by HealthITAnalytics.com, 47 percent said interoperability was a key challenge. What’s more, just 42 percent were having trouble finding analytics staffers for their team.

But at the same time, it seems like provider executives are throwing their weight behind these initiatives. The survey found that just 17 percent faced problems with getting executive buy-in and budget constraints this year, while more than half faced these issues in last year’s survey.

This squares with research released a few months ago by IT staffing firm TEKSystems, which found that 63 percent of respondents expected to see their 2017 budgets increase this year, a big change from the 41 percent who expected to see bigger budgets last year.

Meanwhile, despite their concerns, providers are coping well with at least some health IT challenges, the survey noted. In particular, almost 90 percent of respondents reported that they are live on an EMR and 65 percent are using a business intelligence or analytics solution.

And they’re also looking at the future. Three-quarters said they were already using or expect to enhance clinical decision making, along with more than 50 percent also focusing laboratory data, data gathered from partners and socioeconomic or community data. Also, using pharmacy data, patient safety data and post-acute care records were on the horizon for about 20 percent of respondents. In addition, 62 percent said that they were interested in patient-generated health data.

Taken together, this data suggests that as providers have shifted their focus to big data analytics– and supporting population health efforts – they’ve hit more speed bumps than expected. That being said, over the next few years, I predict that the supply of data scientists and demand for their talents should fall into alignment. For providers’ sake, we’d better hope so!

Easing The Transition To Big Data

Posted on December 16, 2016 I Written By

Anne Zieger is veteran healthcare editor and analyst with 25 years of industry experience. Zieger formerly served as editor-in-chief of FierceHealthcare.com and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also contributed content to hundreds of healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or www.ziegerhealthcare.com.

Tapping the capabilities of big data has become increasingly important for healthcare organizations in recent years. But as HIT expert Adheet Gogate notes, the transition is not an easy one, forcing these organizations to migrate from legacy data management systems to new systems designed specifically for use with new types of data.

Gogate, who serves as vice president of consulting at Citius Tech, rightly points out that even when hospitals and health systems spend big bucks on new technology, they may not see any concrete benefits. But if they move through the big data rollout process correctly, their efforts are more likely to bear fruit, he suggests. And he offers four steps organizations can take to ease this transition. They include:

  • Have the right mindset:  Historically, many healthcare leaders came up through the business in environments where retrieving patient data was difficult and prone to delays, so their expectations may be low. But if they hope to lead successful big data efforts, they need to embrace the new data-rich environment, understand big data’s potential and ask insightful questions. This will help to create a data-oriented culture in their organization, Gogate writes.
  • Learn from other industries: Bear in mind that other industries have already grappled with big data models, and that many have seen significant successes already. Healthcare leaders should learn from these industries, which include civil aviation, retail and logistics, and consider adopting their approaches. In some cases, they might want to consider bringing an executive from one of these industries on board at a leadership level, Gogate suggests.
  • Employ the skills of data scientists: To tame the floods of data coming into their organization, healthcare leaders should actively recruit data scientists, whose job it is to translate the requirements of the methods, approaches and processes for developing analytics which will answer their business questions.  Once they hire such scientists, leaders should be sure that they have the active support of frontline staffers and operations leaders to make sure the analyses they provide are useful to the team, Gogate recommends.
  • Think like a startup: It helps when leaders adopt an entrepreneurial mindset toward big data rollouts. These efforts should be led by senior leaders comfortable with this space, who let key players act as their own enterprise first and invest in building critical mass in data science. Then, assign a group of core team members and frontline managers to areas where analytics capabilities are most needed. Rotate these teams across the organization to wherever business problems reside, and let them generate valuable improvement insights. Over time, these insights will help the whole organization improve its big data capabilities, Gogash says.

Of course, taking an agile, entrepreneurial approach to big data will only work if it has widespread support, from the C-suite on down. Also, healthcare organizations will face some concrete barriers in building out big data capabilities, such as recruiting the right data scientists and identifying and paying for the right next-gen technology. Other issues include falling reimbursements and the need to personalize care, according to healthcare CIO David Chou.

But assuming these other challenges are met, embracing big data with a willing-to-learn attitude is more likely to work than treating it as just another development project. And the more you learn, the more successful you’ll be in the future.

Using NLP with Machine Learning for Predictive Analytics in Healthcare

Posted on December 12, 2016 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

There are a lot of elements involved in doing predictive analytics in healthcare effectively. In most cases I’ve seen, organizations working on predictive analytics do some but not all that’s needed to really make predictive analytics as effective as possible. This was highlighted to me when I recently talked with Frank Stearns, Executive Vice President from HBI Solutions at the Digital Health Conference in NYC.

Here’s a great overview of the HBI Solutions approach to patient risk scores:

healthcare-predictive-analytics-model

This process will look familiar to most people in the predictive analytics space. You take all the patient data you can find, put it into a machine learning engine and output a patient risk score. One of the biggest trends happening with this process is the real-time nature of this process. Plus, I also love the way the patient risk score includes the attributes that influenced a patients risk score. Both of these are incredibly important when trying to make this data actionable.

However, the thing that stood out for me in HBI Solutions’ approach is the inclusion of natural language processing (NLP) in their analysis of the unstructured patient data. I’d seen NLP being used in EHR software before, but I think the implementation of NLP is even more powerful in doing predictive analytics.

In the EHR world, you have to be absolutely precise. If you’re not precise with the way you code a visit, you won’t get paid. If you’re not precise with how the diagnosis is entered into the EHR, that can have long term consequences. This has posed a real challenge for NLP since NLP is not 100% accurate. It’s gotten astoundingly good, but still has its shortcomings that require a human review when utilizing it in an EHR.

The same isn’t true when applying NLP to unstructured data when doing predictive analytics. Predictive analytics by its very nature incorporates some modicum of variation and error. It’s understood that predictive analytics could be wrong, but is an indication of risk. Certainly a failing in NLP’s recognition of certain data could throw off a predictive analytic. That’s unfortunate, but the predictive analytics aren’t relied on the same way documentation in an EHR is relied upon. So, it’s not nearly as big of a deal.

Plus, the value that’s received from applying NLP to pull out the nuggets of information that exists in the unstructured narrative sections of healthcare data is well worth that small amount of risk of the NLP being incorrect. As Frank Stearns from HBI solutions pointed out to me, the unstructured data is often where the really valuable data about a patients’ risk score exist.

I’d be interested in having HBI Solutions do a study of the whole list of findings that are often available in the unstructured data that weren’t available otherwise. However, it’s not hard to imagine a doctor documenting patient observations in the unstructured EHR narrative that they didn’t want to include as a formal diagnosis. Not the least of these are behavioral health observations that the doctor saw, observed, and documented but didn’t want to fully diagnose. NLP can pull these out of the narrative and include them in their patient risk score.

Given this perspective, it’s hard to imagine we’ll ever be able to get away from using NLP or related technology to pull out the valuable insights in the unstructured data. Plus, it’s easy to see how predictive analytics that don’t use NLP are going to be deficient when trying to use machine learning to analyze patients. What’s amazing is that HBI Solutions has been applying machine learning to healthcare for 5 years. That’s a long time, but also explains why they’ve implemented such advanced solutions like NLP in their predictive analytics solutions.

Population Health 101: The One Where It All Starts

Posted on December 7, 2016 I Written By

The following is a guest blog post by Abhinav Shashank, CEO & Co-founder of Innovaccer.
population-health-101
Former US President Abraham Lincoln once said, “Give me six hours to chop down a tree and I’ll spend four hours sharpening the ax.”  After having a look at the efficiency of the US healthcare system, one cannot help but notice the irony. A country spending $10,345 per person on healthcare shouldn’t be on the last spot of OECD rankings for life expectancy at birth!

Increasing Troubles
report from Commonwealth Fund points out how massive the US health care budget is. Various US governments have left no stone unturned in becoming the highest spender on healthcare, but have equally managed to see most of its money going down the drain!

Here are some highlights from the report:

  1. The US is 3rd when it comes to public spending on health care. The figure is $4197 per capita, but it covers only 34% of its residents. On the other hand, the UK spends only $2,802 per capita and covers 100% of the population!
  2. With $1,074, US has the 2nd highest private spending on healthcare.
  3. In 2013, US allotted 17.1% of its GDP to healthcare, which was the highest of any OECD country.   In terms of money, this was almost 50% more than the country in the 2nd spot.
  4. In the year 2013, the number of practicing physicians in the US was 2.6 per 1000 persons, which is less than the OECD median (3.2).
  5. The infant mortality rate in the US was also higher than other OECD nations.
  6. 68 percent of the population above 65 in the US is suffering from two or more chronic conditions, which is again the highest among OECD nations.

The major cause of these problems is the lack of knowledge about the population trends. The strategies in place will vibrantly work with the law only if they are designed according to the needs of the people.

population-health-trends

What is Population Health Management?
Population health management (PHM) might have been mentioned in ACA (2010), but the meaning of it is lost on many. I feel, the definition of population health, given by Richard J. Gilfillan, President and CEO of Trinity Health, is the most suitable one.

Population health refers to addressing the health status of a defined population. A population can be defined in many different ways, including demographics, clinical diagnoses, geographic location, etc. Population health management is a clinical discipline that develops, implements and continually refines operational activities that improve the measures of health status for defined populations.

The true realization of Population Health Management  (PHM) is to design a care delivery model which provides quality coordinated care in an efficient manner. Efforts in the right direction are being made, but the tools required for it are much more advanced and most providers lack the resources to own them.

Countless Possibilities
If Population Health Management is in place, technology can be leveraged to find out proactive solutions to acute episodes. Based on past episodes and outcomes, a better decision could be made.

The concept of health coaches and care managers can actually be implemented. When a patient is being discharged, care managers can confirm the compliance with health care plans. They can mitigate the possibility of readmission by keeping up with the needs and appointments of patients. Patients could be reminded about their medications. The linked health coaches could be intimated to further reduce the possibility of readmission.

Let us consider Diabetes for instance. Many times Diabetes is hereditary and preventive measures like patient engagement would play an important role in mitigating risks. Remote Glucometers, could be useful in keeping a check on patient sugar levels at home. It could also send an alert to health coaches and at-risk population could be engaged in near real-time.

Population Health Management not only keeps track of population trends but also reduces the cost of quality care. The timely engagement of at-risk population reduces the possibility of extra expenditure in the future. It also reduces the readmission rates. The whole point of population health management is to be able to offer cost effective quality-care.

The best thing to do with the past is to learn from it. If providers implement in the way Population Health Management is meant to be, then the healthcare system would be far better and patient-centric.

Success Story
A Virginia based collaborative started a health information based project in mid-2010. Since then, 11 practices have been successful in earning recognition from NCQA (National Committee for Quality Assurance). The implemented technologies have had a profound impact on organization’s performance.

  1. For the medical home patients, the 30-day readmission rate is below 2%.
  2. The patient engagement scores are at 97th percentile.
  3. With the help of the patient outreach program almost 40,000 patients have been visited as a part of preventive measures.

All this has increased the revenue by $7 million.

Barriers in the journey of Population Health Management
Currently, population health management faces a lot of challenges. The internal management and leadership quality has to be top notch so that interests remain aligned. Afterall, Population Health Management is all about team effort.

The current reimbursement model is also a concern. It has been brought forward from the 50s and now it is obsolete. Fee-for-service is anything, but cost-effective.

Patient-centric care is the heart of Population Health Management. The transition to this brings us to the biggest challenge and opportunity. Data! There is a lot of unstructured Data. True HIE can be achieved only if data are made available in a proper format. A format which doesn’t require tiring efforts from providers to get patient information. Providers should be able to gain access to health data in seconds.

The Road Ahead
We believe, the basic requirement for Population Health Management is the patient data. Everything related to a patient, such as, the outcome reports, the conditions in which the patient was born, lives, works, age and others is golden. To accurately determine the cost, activity-based costing could come in handy.

Today, the EMRs aren’t capable enough to address population health. The most basic model of population health management demands engagement on a ‘per member basis’ which can track and inform the cost of care at any point. The EMRs haven’t been designed in such a way. They just focus on the fee-for-service model.

In recent years, there has been an increased focus on population health management. Advances in the software field have been prominent and they account for the lion’s share of the expenditure on population health. I think, this could be credited to Affordable Care Act of 2010, which mandated the use of population health management solutions.

Today, the Population Health Management market is worth $14 billion and according to a report by Tractica, in five years, this value will be $31.8 billion. This is a good sign because it shows that the focus is on value-based care. There is no doubt we have miles to go, but at least now we are on the right path!

Are We Outgrowing HIM Systems?

Posted on July 15, 2016 I Written By

Erin Head is the Director of Health Information Management (HIM) and Quality for an acute care hospital in Titusville, FL. She is a renowned speaker on a variety of healthcare and social media topics and currently serves as CCHIIM Commissioner for AHIMA. She is heavily involved in many HIM and HIT initiatives such as information governance, health data analytics, and ICD-10 advocacy. She is active on social media on Twitter @ErinHead_HIM and LinkedIn. Subscribe to Erin’s latest HIM Scene posts here.

We have changed and adapted to a rapid influx of electronic medical records and data over the last several years and it’s no surprise that some systems have struggled to keep the pace. Electronic medical records (EMRs) are in a state of constant revision to make sure patient care, clinical functionality, and data security measures are keeping up with our needs. It seems there are software application solutions or enhancements to almost every task we do in healthcare and these systems are also constantly evolving.

I don’t know of any healthcare application system or workflow that has remained static year over year and because of this, it is important for us to stay on top of vendors and keep an eye on current and future needs of HIM workflows. Clinical Documentation Improvement (CDI) is one of those areas that has been evolving since it first came on the scene and it is currently undergoing yet another face-lift. We realized there were many revenue opportunities hiding within inpatient clinical documentation and found that we could maximize reimbursement with a little detective work and physician education along with sophisticated software tools. Many are exploring the idea of CDI for outpatient levels of care. This means we will need software applications, interfaces, and expanded CDI workflows to extend these opportunities to outpatient documentation. Have you thought about what you will need from your vendors to adapt or upgrade current systems and how much will need to be budgeted for?

As we work to implement computer assisted coding (CAC) programs, we see opportunities to increase coder and CDI productivity and capture even more quality documentation by using discrete EMR data to our advantage. But are these CAC systems ready to be pushed to the limits to enter unchartered waters? I personally do not have a CAC success story to tell as of yet, but I am exploring the options and hoping that these systems have matured more than when we first explored them a few years ago.

That’s the beauty of technology in healthcare; if a product does not meet your needs, there may be other options already on the market or rapidly developing new technologies on the horizon. A vast amount of data may be held hostage in our systems if we do not maximize our EMRs and applications and set our standards high in a quest for knowledge. We can’t rely 100% on technology to dictate what we do which is why we need to be the visionaries and demand more from our systems in order to accomplish new and exciting things in HIM.

If you’d like to receive future HIM posts by Erin in your inbox, you can subscribe to future HIM Scene posts here.

Operationalizing Health IT Discoveries

Posted on June 24, 2016 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

I’ve been talking a lot lately with people about how we take the health IT discoveries made at one hospital and apply them to another hospital. In a recent conversation I had with Jonathan Sheldon from Oracle, he highlighted that “Many organizations don’t care about research, but just want a product that works.”

I agree completely with this comment from Jonathan. While there are some very large healthcare organizations that do a lot of research, there are even more healthcare organizations that just want to see patients in the best way possible. They just want to implement the research that other organizations have done. They just want something that works.

The problem for big companies like Oracle, SAP, Tableau, etc is that they have the technology to scale up many of these health IT discoveries, but they aren’t doing the discovery themselves. In fact, most of them never will dive into the discovery of which healthcare data really matters.

In order to solve this, I’ve seen all of these organizations working on some sort of partnership between IT companies and healthcare research organizations. The IT company provides the technology and the commercialization of the product and the healthcare research organization provides the research knowledge on the most effective techniques.

While this all sounds very simple and logical, it’s actually much harder in practice. Taking your customer and turning them into a partner is much harder than it looks. Most healthcare organizations know how to be customers. It takes a unique healthcare organization to be an effective partner. However, this is exactly what we have to do if we want to operationalize the health IT discoveries these research organizations make.

We’re going to have to make this a reality. There’s no way that one organization can discover everything they need to discover. Healthcare is too complex as it is today. Plus, we’re just getting started with things like genomic medicine and health sensors which is going to make healthcare at least an order of magnitude more complex.

Healthcare Analytics Biggest Competitor – Excel

Posted on March 16, 2016 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

This tweet highlighted an interesting observation I had after experiencing so many healthcare analytics pitches going into and at HIMSS. I’ll set aside the email comment for now (email is still very powerful if done right) and instead focus on Excel. Here’s what I discovered about healthcare analytics:

Excel is a healthcare analytics company’s biggest competitor.

It’s crazy to think about, but it’s true. When a healthcare organization is evaluating healthcare analytics platform the “legacy system” that they’re usually trying to replace is Excel. I can’t tell you how many times I heard analytics vendors say that “Hospital A was doing all of this previously on a bunch of Excel spreadsheets.” If you work at a hospital, you know that you have your own garden of Excel spreadsheets that are used to run your healthcare organization as well.

When you think about the features of Excel, it’s no wonder why it’s so popular in healthcare and why it’s a challenging competitor for most healthcare organizations. First, it’s free. Ok, it’s not technically free, but every healthcare organization has to buy it for a lot of reasons so that cost is already in their standard budget. Second, every computer in the organization has a copy of Excel on it. Third, the majority of people in healthcare are familiar with how to use Excel. Since we love to talk about healthcare IT usability, Excel is extremely usable. Fourth, Excel is surprisingly powerful. I know many healthcare analytics organizations could argue its limitations, but Excel is more powerful than most people realize.

That’s not to say that Excel doesn’t have its weaknesses. I’m sure that most organizations have experienced time wasted trying to figure out which Excel file has the accurate data or is the most up to date. No doubt you’ve experienced the multiple copy problem where 2 people are editing the same file and now you have 2 versions of the same file that need to be merged. Document management software has helped with this situation in many regards as it locks the file when someone starts to edit it and things like that. However, it’s still often a problem.

Another problem with Excel as compared with a true analytics platform is when you want to go in and slice and dice the data. What’s possible with a true analytics platform is so much more powerful when you want to really dive in and chop up the data in unique ways.

While possible in Excel, most uses of Excel are backwards facing data analysis and tracking. You can do some near real-time data analysis in Excel, but newer analytics platforms do a much better job of real time analytics using the latest data.

Of course, the biggest problem long term with Excel is that it can’t scale. Once you reach a certain amount of data points or a certain amount of complexity in the data, Excel falls on its face. However, most healthcare organizations are still working on small data, so Excel’s worked fine.

I’m sure there are many more issues. Hopefully some analytics vendors will chime in with more examples in the comments or on their own blogs. However, it’s worth acknowledging that for many organizations it’s really hard for them to find a healthcare analytics solutions that’s so much better than Excel. Plus, many of these expensive analytics solutions fail when it comes to some of the things that makes Excel great (ie. Free, Usable, Ubiquitous).

A Look At Precision Medicine Solutions Available Today

Posted on December 22, 2015 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

Personalized and Precision Medicine are all the buzz since President Obama announced the Precision Medicine Initiative. However, after the government tragedy known as meaningful use, many are reasonably skeptical of government initiatives to improve healthcare. Plus, the rhetoric around what’s possible with precision medicine and the realities that most hospitals and doctors face every day feels like a massive disconnect.

The reality is that there’s good reason to be skeptical of precision medicine. Think about the scope of the problem. The world of health data that we live in today is 10-20 times bigger that it was even a decade ago. That’s a massive increase in the amount of data available. Plus, much of that data is unstructured data. Combine the volume of data with the accessibility (or lack therof) of that data and it’s easy to see why some are skeptical of really implementing precision medicine in their hospital today.

When you look at current EHR systems, none of them are built to enable precision medicine. First, they were built as massive billing engines and not as engines designed to improve care. Second, meaningful use has hijacked their development roadmap for years and will likely continue to hijack their development teams for years to come. Finally, there’s been so much money doing what they’re doing, what motivation do the entrenched EHR companies have to go out and do more?

The unfortunate reality of EHR systems is that they’re not built for real time availability of data analytics that provides improved care and precision, personalized medicine. Some may get there eventually, but we’re unlikely to see them get there anytime soon. I’ve heard precision medicine defined as a puzzle with 3 billion pieces. We have to start looking outside of traditional EHR companies to start solving such a complex puzzle.

The good news is that even though EHR vendors are not providing precision medicine solutions, we’re starting to see other vendors providing precision medicine solutions today. You no longer need to wait for an EHR vendor to participate.

One example of precision medicine happening today is the recently announced SAP Foundation for Health (we’ll forgive them on the somewhat confusing name). At the core of the SAP Foundation for Health is the SAP Hana engine. Unlike many EHR systems, SAP Hana was designed for real time data analysis of massive amounts of data and that includes both granular and free form data. You can see this capability first hand in the work SAP is doing with ASCO (American Society of Clinical Oncology) and their CancerLinQ project.

Dr. Clifford Hudis from CancerLinQ (Created by ASCO) described how personalized medicine to his grandfather was going around and visiting each patient. Over time that practice stopped and we started seeing patients in clinics where we generally only had one data set available to us: the clinical data that we captured ourselves on a paper chart. Unfortunately, as we moved electronic, we just recreated our paper chart world in electronic form. It’s too bad we didn’t do more during our shift to going electronic. However, that still means we have the opportunity to aggregate and analyze health data for the benefit of our patients. In some ways, we’re starting to democratize access to health data in order to enable precision medicine.

As Dr. Hudis pointed out, healthcare currently really only learns from patients who take part in clinical research trials. In other words, that only amounts to about 3% of adult patients who contribute to our learning. This limits our view since most clinical research trials have a biased sample which aren’t representative of the general population. How can we create personalized medicine if we only have data on 3% of the patient population? This is the problem CancerLinQ and SAP Foundation for Health are working to solve. Can they create a platform that learns from every patient?

ASCO together with SAP’s Foundation for Health is working to aggregate and analyze data across cancer patients regardless of whether they’re part of a clinical research study or not. In the past, Dr. Hudis pointed out that cancer tracking use to track cancer populations with simple groups like “small cell cancer” versus “non-small cell cancer.” That was a start, but had limited precision when trying to treat a patient. With this relatively new world of genomics, ASCO can now identify, track, and compare a patient’s cancer by specific genomic alterations. This is a fantastic development since tumors generally contain changed DNA. We can now use these DNA abnormalities to classify and track cancer patients in a much more precise way than we’ve done in the past.

This platform enables oncologists the opportunity to see real time information about their patient that’s personalized to the patients own genetic abnormalities. Instead of calling around to their network of oncologist friends, Cancer LinQ provides real time access to other patient populations with similar genetic abnormalities and could give them insight into what treatments are working for similar patients. This can also provide benchmarking for oncologists to see how they compare against their colleagues. Plus, it can show real time data to an oncologist so they can know how thorough and consistent they are with their patient population. Instead of working in a bubble, the oncologist can leverage the network of data to provide true precision medicine for their patients.

Another great example of precision medicine happening today is seen in the work of Carlos Bustamante, Professor of Genetics and Stanford University School of Medicine. Carlos is using SAP Foundation for Health to quickly identify genetic abnormalities in high performing athletes. Rather than recount the stories of Carlos’ work here, I’ll just link to this video where Carlos talks about the amazing insights they’ve found from studying the genomic abnormalties of high performing athletes. I love that his precision medicine work with high performing athletes has significant potential benefits for every patient.

Carlos is spot on in the video linked above when he says that the drop in genomic sequencing costs would be like taking a $400,000 Ferrari and now selling it for 10 cents. What originally took $13 billion and years of effort to sequence the first genome now takes $1500 and a few days. Access to every patient’s genome is going to change the types of drugs we develop, the treatment options we provide patients, our choice of drugs to treat a patient, and much much more. You can see that first hand in the work that ASCO and Stanford University School of Medicine are doing. Is there any more personalized medicine than the human genome?

Of course, the genome is just one of the many factors we’re seeing in the precision medicine revolution. We can’t forget about other variables that impact a patient’s health like environmental, behavioral, patient preference, and much more. We really are looking at a multi-billion piece puzzle and we’re just getting started. Remember that healthcare is not linear, but we’ve been treating it like it is for years. Healthcare is a complex matrices of challenges and we need our technology solutions to reflect that fact.

I see a beautiful future for precision medicine that’s already begun and builds into the future. We’re developing and targeting new drugs, devices and services that work for populations and individuals. We’re seeing new open, secure platforms that provide real-time flexible R&D analysis, genomics and other “omics” disciplines, patient cohort building and analysis, patient trial matching, and extended care collaboration solutions.

Data by itself is not valuable. However, the right engine on top of the right data is changing how we look at healthcare. We’re getting a much more precise view of each individual patient. Where have you seen precision medicine starting to take hold? What precision medicine solutions are you using in your organization?

Also, check out this infographic which looks at SAP’s view of precision medicine:
Personalized Medicine You Can Do Today

SAP is uniquely positioned to help advance personalized medicine. The SAP Foundation for Health is built on the SAP Hana platform which provides scalable cloud analytics solutions across the spectrum of healthcare. SAP is a sponsor of Influential Networks of which Healthcare Scene is a member.

New Data Driven Perspectives in Healthcare w/ @MandiBPro @Ashish_P @techguy

Posted on December 10, 2015 I Written By

John Lynn is the Founder of the HealthcareScene.com blog network which currently consists of 10 blogs containing over 8000 articles with John having written over 4000 of the articles himself. These EMR and Healthcare IT related articles have been viewed over 16 million times. John also manages Healthcare IT Central and Healthcare IT Today, the leading career Health IT job board and blog. John is co-founder of InfluentialNetworks.com and Physia.com. John is highly involved in social media, and in addition to his blogs can also be found on Twitter: @techguy and @ehrandhit and LinkedIn.

UPDATE: Here’s the recorded version of our interview (Ashish had video issues, so he joined audio only)

As part of our ongoing series of Healthcare Scene interviews (see all our past Healthcare Scene interviews on YouTube), we’re excited to announce our next interview with Mandi Bishop and Ashish Patel where we’ll be talking about New Data Driven Perspectives in Healthcare. If you’d like to watch the interview live and get your questions answered, you can join us on blab, Monday, December 13th at Noon ET (9 AM PT).

In this interviews I’m lucky to have two of the most knowledgeable people in healthcare when it comes to various healthcare data sources and how to extract value out of that data. Plus, they’ll offer ways in which data has changed their perspective on healthcare. I’m also excited to hear about the new data sources that are available for health care and how we are using and will use that data to improve healthcare as we know it.


Here are a few more details about our panelists:

You can watch our interview on Blab or in the embed below. We’ll be interviewing our panelists for the first 30-40 minutes of the blab and then we’ll open up to the audience for questions for the rest of the hour. We hope you can join us live. We’ll also share the recorded video after the event.