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!

Predicting Readmissions, Longitudinal Record, and Physicians’ Time

Posted on May 12, 2017 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.

Here’s a quick look around the Twittersphere and a few topics that stood out to me that I think might be of interest to you.


I’ve been following algorithms like this for a while and they’re really starting to come into their own. This type of predictive technology or predictive analytics if you prefer is going to really change how we manage patients in a hospital. If done right, it can help us become proactive instead of reactive. This will require us to change a lot of processes though.


Is a longitudinal health record possible in any format? I’m beginning to think that it’s a pipe dream that will never happen. At least not with our current documentation requirements.

I find time studies like these very interesting. However, the thing I hate about them is that we don’t have a time study from before implementing EHR software so we could compare how a physician used their time before EHR and after. No doubt over 50% of their time being spent on documentation and not face-to-face with the patient feels bad. However, how far off was this from where we were in the paper world?

Looking at the chart, prescription refills can be faster in an EHR. Secure messages can be faster with an EHR since you’re not playing phone tag which was the process before secure messages. Telephone encounters were likely the same. That leaves just the progress notes as the one thing that could be more time consuming in an EHR than the paper chart. How much more is the real question. Paper chart progress notes weren’t all that fast either. That’s why stacks of paper charts that weren’t completed were always sitting on physicians’ desks.

I guess the core question I would ask is, “Are EHRs the reason doctors hate medicine, or are the ongoing regulations and requirements that have been heaped on doctors the real problem?” My guess is that all this documentation overheard that’s being required of doctors was a problem in the paper world, but has been exacerbated in the EHR world. What do you think?

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.

Value-Based Lawn Care – Life Imitating Healthcare

Posted on March 28, 2016 I Written By

Colin Hung is the co-founder of the #hcldr (healthcare leadership) tweetchat one of the most popular and active healthcare social media communities on Twitter. Colin is a true believer in #HealthIT, social media and empowered patients. Colin speaks, tweets and blogs regularly about healthcare, technology, marketing and leadership. He currently leads the marketing efforts for @PatientPrompt, a Stericycle product. Colin’s Twitter handle is: @Colin_Hung

Ah, spring. Warmer weather, budding trees and the return of that big ball of light in the sky. The clearest sign of spring? The arrival of lawn-care flyers in my neighborhood. It’s only been a week of spring and already I have received over 15 flyers.

Normally I just throw these flyers out – taking care of my lawn is a responsibility I prefer not to outsource – but this year one company’s flyer caught my eye. Instead of the pay-as-you-mow or weekly visit programs offered by their competitors, this particular company was offering a program that guaranteed a green lawn until the start of fall. For a set price they would aerate, weed, spray, fertilize, cut and trim your lawn as needed.

“Have a healthy, weed-free lawn all summer. Let us do all the preventative and maintenance work. You just enjoy your weekends.”

Here was a company that was eschewing the industry’s volume-based standard practice and opting for a value-based offering instead. This company smartly recognized that homeowners do not want someone to come and care for their lawn on a regular basis but rather a healthy green lawn. The process to get that healthy lawn makes no difference, just the outcome. Funny how no government penalty system or legislation was need to pressure lawn-care providers into adopting a value-based model.

I must admit I never thought that the lawn care industry in my neighborhood would be going through the same volume-vs-value challenge as we are in healthcare.

I wouldn’t have made this connection had it not been for the excellent post by Sarah Bennight, Director of Marketing at eMedApps. She wrote about the four key requirements she believes are necessary for transitioning to value-based care:

  1. Strong quality measures
  2. Comprehensive population health
  3. Predictive analytics and trending in the clinical setting
  4. Breaking down silos

The lawn-care industry doesn’t have any comparable challenges (or consequences) like those mentioned by Bennight. I can’t imagine that competing landscaping companies are all that interested in sharing data or breaking down industry silos. However, I do think that healthcare can look to other industries for inspiration and ideas to address our own transition to a value-based world.

Better go seed my lawn now.

Big Data, Predictive Analytics Priorities For Healthcare Organizations

Posted on August 16, 2013 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.

Leveraging big data and healthcare analytics are key initiatives for C-suite healthcare executives, but barriers to making progress still remain, according to an item in iHealthBeat.

According to a survey by the eHealth Initiative and the College of Health Information Management Executives, about 80 percent of CIOs and other C-suite healthcare executives see big data and predictive analytics use as important goals for their organizations, iHealthBeat reports.

But it won’t come easy. In fact, 84 percent of respondents said that implementing these strategies and tools are a challenge for their organization. And only 45 percent said they had a plan in place to manage the growing volume of electronic data.

The survey, which questioned 102 executives in May and June, found that 90 percent of respondents used analytics for quality improvement, 90 percent used analytics for revenue cycle management, and 66 percent used analytics for fraud prevention. Also, 82 percent of survey respondents said that population health management is important to their analytic strategy.

Meanwhile, 82 percent of those responding said that health information exchange is important, according to iHealthBeat.

As for data sources, administrative- and claims-based data were most used, at 77 percent and 75 percent respectively. Eighteen percent of respondents’ staff were trained to handle the data, and 16 percent used third-party organizations to overcome staff shortages for data analysis.

Despite execs’ enthusiasm for big data/predictive analytics use, however, significant obstacles remain to rolling out such programs, iHealthBeat reports.  According to a separate CIC Advisory survey, budget strain and lack of needed skills is delaying the use of analytics at many healthcare organizations.

According to that survey, building an enterprise analytics system is held back by the difficulty of integrating different analytic systems. Moreover, most organizations don’t have a dedicated analytics or business intelligence team, and many rely on outside analytics consultants.

All of that being said, it seems guaranteed that hospitals and other healthcare organizations will eventually find a way to leverage big data. Healthcare organizations expect to keep ramping up their spending on data discovery and predictive analytics in coming months and years, research suggests.

In the mean time, however, there’s a ton of work to do, staff to be hired and trained and integration to be done. It’s going to be an uphill battle.

Healthcare Big Data Trends Leading To Analytics Spending

Posted on March 26, 2013 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.

Ready to exploit big data? So are your competitors, and they’re preparing to spend big bucks in areas where they’ve historically been weak, such as predictive analytics and data discovery, reports  HealthcareITNews.

Technology vendor Lavastorm Analytics recently surveyed more than 600 technology professionals in healtlhcare and other industries about their IT investment plans for this ear.

Right now, researchers found, three-quarters of respondents still routinely use Excel for self-service analytics processes, and 35 percent use the R programming language.  Of the remaining 24 self-service analytics tools listed by the survey, 17 of them were used by less than 10 percent of the audience. In other words, once you get past R and Excel for analytics, there’s little agreement as to what works best.

But the coming months should bring some big changes in this landscape, Lavastorm’s research suggests. As the desire to exploit big data grows, providers are planning investments that will allow them to exploit it. Nearly 60 percent of respondents plan to increase their investments in areas where their capacity is limited.

Those areas include gleaning insights from data (25 percent), accessing data (22 percent) and having the ability to integrate and manipulate data (19 percent), HealthcareITNews says.

To meet those goals, providers intend to invest in predictive analytics (51 percent), big data (35 percent), dashboards (32 percent), reporting (31 percent) and data exploration and discovery (30 percent). At the same time, 27 percent said that they’d invest in advanced visualization tools and 24 percent self-service analytics tools for business users.

All this being said, my hunch that providers probably aren’t particularly sure where they’re headed with this technology yet.  I’d like to have seen Lavastorm ask which clinical or business goals, specifically, they hoped to meet by making these investments, wouldn’t you?