Free EMR 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 EMR and HIPAA for FREE!!

Analytics Take an Unusual Turn at PeraHealth

Posted on August 17, 2017 I Written By

Andy Oram is an editor at O'Reilly Media, a highly respected book publisher and technology information provider. An employee of the company since 1992, Andy currently specializes in open source, software engineering, and health IT, but his editorial output has ranged from a legal guide covering intellectual property to a graphic novel about teenage hackers. His articles have appeared often on EMR & EHR and other blogs in the health IT space. Andy also writes often for O'Reilly's Radar site (http://oreilly.com/) and other publications on policy issues related to the Internet and on trends affecting technical innovation and its effects on society. Print publications where his work has appeared include The Economist, Communications of the ACM, Copyright World, the Journal of Information Technology & Politics, Vanguardia Dossier, and Internet Law and Business. Conferences where he has presented talks include O'Reilly's Open Source Convention, FISL (Brazil), FOSDEM, and DebConf.

Data scientists in all fields have learned to take data from unusual places. You’d think that monitoring people in a hospital for changes in their conditions would be easier than other data-driven tasks, such as tracking planets in far-off solar systems, but in all cases some creativity is needed. That’s what PeraHealth, a surveillance system for hospital patients, found out while developing alerts for clinicians.

It’s remarkably hard to identify at-risk patients in hospitals, even with so many machines and staff busy monitoring them. For instance, a nurse on each shift may note in the patient’s record that certain vital signs are within normal range, and no one might notice that the vital signs are gradually trending worse and worse–until a crisis occurs.

PeraHealth identifies at-risk patients through analytics and dashboards that doctors and nurses can pull up. They can see trends over a period of several shifts, and quickly see which patients in the ward are the most at risk. PeraHealth is a tool for both clinical surveillance and communication.

Michael Rothman, co-founder and Chief Science Officer, personally learned the dangers of insufficient monitoring in 2003 when a low-risk operation on his mother led to complications and her unfortunate death. Rothman and his brother decided to make something positive from the tragedy. They got permission from the hospital to work there for three weeks, applying Michael’s background in math and data analysis (he has worked in the AI department of IBM’s Watson research labs, among other places) and his brother’s background in data visualization. Their goal, arguably naive: to find a single number that summarizes patient risk, and expose that information in a usable way to clinicians.

Starting with 70 patients from the cardiac unit, they built a statistical model that they tested repeatedly with 1,200 patients, 6,000 patients, and finally 25,000 patients. At first they hoped to identify extra data that the nurse could enter into the record, but the chief nurse laid down, in no uncertain terms, that the staff was already too busy and that collecting more data was out of the question. It came time to get creative with data that was already being collected and stored.

The unexpected finding was that vital signs were not a reliable basis for assessing a patient’s trends. Even though they’re “hard” (supposedly objective) data, they bounce around too much.

Instead of relying on just vital signs, PeraHealth also pulls in nursing assessments–an often under-utilized source of information. On each shift, a nurse records information on a dozen different physical systems as well as essential facts such as whether a patient stopping eating or was having trouble walking. It turns out that this sort of information reliably indicates whether there’s a problem. Many of the assessments are simple, yes/no questions.

Rothman analyzed hospital data to find variables that predicted risk. For instance, he compared the heart rates of 25,000 patients before they left the hospital and checked who lived for a year longer. The results formed a U-shaped curve, showing that heart rates above a certain level or below a certain level predicted a bad outcome. It turns out that this meaure works equally well within the hospital, helping to predict admission to the ICU, readmission to the ICU, and readmission after discharge.

The PeraHealth team integrated their tool with the hospital’s EHR and started producing graphs for the clinicians in 2007. Now they can point to more than 25 peer-reviewed articles endorsing their approach, some studies comparing before-and-after outcomes, and others comparing different parts of the hospital with some using PeraHealth and others not using it. The service is now integrated with major EHR vendors.

PeraHealth achieved Rothman’s goal of producing a single meaningful score to rate patient risk. Each new piece of data that goes into the EHR triggers a real-time recalculation of the score and a new dot on a graph presented to the nurses. In order to save the nurses from signing into the EHR, PeraHealth put a dashboard on the nurse’s kiosk with all the patients’ graphs. Color-coding denotes which patients are sickest. PeraHealth also shows which patients to attend to first. In case no one looks at the screen, at some hospitals the system sends out text alerts to doctors about the most concerned patients.

PeraHealth is now expanding. In an experiment, they did phone interviews with people in a senior residential facility, and identified many of those who were deteriorating. So the basic techniques may be widely applicable to data-driven clinical decision support. But without analytics, one never knows which data is most useful.

More About Artificial Intelligence in Healthcare – #HITsm Chat Topic

Posted on August 8, 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.

We’re excited to share the topic and questions for this week’s #HITsm chat happening Friday, 8/11 at Noon ET (9 AM PT). This week’s chat will be hosted by Prashant Natarajan (@natarpr) on the topic of “More About Artificial Intelligence in Healthcare.” Be sure to also check out Prashant’s HIMSS best selling book Demystifying Big Data and Machine Learning for Healthcare to learn about his perspectives and insights into the topic.

Healthcare transformation requires us to continually look at new and better ways to manage insights – both within and outside the organization today. Increasingly, the ability to glean and operationalize new insights efficiently as a byproduct of an organization’s day-to-day operations is becoming vital to hospitals and health systems ability to survive and prosper. One of the long-standing challenges in healthcare informatics has been the ability to deal with the sheer variety and volume of disparate healthcare data and the increasing need to derive veracity and value out of it.

The potential for big data in healthcare – especially given the trends discussed earlier is as bright as any other industry. The benefits that big data analytics, AI, and machine learning can provide for healthier patients, happier providers, and cost-effective care are real. The future of precision medicine, population health management, clinical research, and financial performance will include an increased role for machine-analyzed insights, discoveries, and all-encompassing analytics.

This chat explores participants thoughts and feelings about the future of artificial intelligence in the healthcare industry and how healthcare organizations might leverage artificial intelligence to discover new business value, use cases, and knowledge.

Note: For purpose of this chat, “artificial intelligence” can mean predictive analytics, machine learning, big data analytics, natural language processing and contextually intelligent agents.

Reference Materials

Questions we will explore in this week’s #HITsm chat include:
T1: What words or short phrases convey your current thoughts & feelings about ‘artificial intelligence’ in the healthcare space? #HITsm #AI

T2: What are big & small steps healthcare can take to leverage big data & machine learning for population health & personalized care? #HITsm

T3: Which areas of healthcare might be most positively impacted by artificial intelligence? #HITsm #AI

T4: What are some areas within healthcare that will likely NOT be improved or replaced by artificial intelligence? #HITsm #AI

T5: What lessons learned from early days of ‘advanced analytics’ must not be forgotten as use of artificial intelligence expands? #HITsm #AI

Bonus: How is your organization preparing for the application and use of artificial intelligence in healthcare? #HITsm #AI

Upcoming #HITsm Chat Schedule
8/18 – Diversity in HIT
Hosted by Jeanmarie Loria (@JeanmarieLoria) from @advizehealth

8/25 – Consumer Data Liquidity – The Road So Far, The Road Ahead
Hosted by Greg Meyer (@Greg_Meyer93)

We look forward to learning from the #HITsm community! As always, let us know if you’d like to host a future #HITsm chat or if you know someone you think we should invite to host.

If you’re searching for the latest #HITsm chat, you can always find the latest #HITsm chat and schedule of chats here.

The Shifting Health Care IT Markets

Posted on November 5, 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.

I’m at the end of my Fall Healthcare IT Conference season (although I’m still considering attending RSNA for my first time) and besides being thankful to be done with all the travel, I’m also taking a second to think about what I’ve learned over the past couple months as I’ve traveled to a wide variety of conferences.

While the EHR market has been hot for so many years, I’m seeing a big shift in purchasing to three areas: Analytics/Population Health, Revenue Cycle Management, and Privacy/Security. This isn’t a big surprise, but the EHR market has basically matured and now even EHR vendors are looking at new ways to market their products. These are the three main areas where I see the market evolving.

Analytics and Population Health
I could have easily added the other buzzword “patient engagement” to this category as well. There’s a whole mixture of technologies and approaches for this category of healthcare IT. In fact, it’s where I see some of the most exciting innovations in healthcare. Most of it is driven by some form of value based reimbursement or organizations efforts to prepare for the shift to value based reimbursement. However, there’s also a great interest by many organizations to try and extract value from their EHR investment. Many are betting on these tools being able to help them realize value from their EHR data.

Revenue Cycle Management
We’re seeing a whole suite of revenue cycle solutions. For many years we’ve seen solutions that optimized an organization’s relationships with payers. Those are still popular since it seems like most organizations never really fix the problem so their need for revenue cycle management is cyclical. Along with these payer solutions, we’re seeing a whole suite of products and companies that are focused on patient payment solutions. This shift has been riding the wave of high deductible plans in healthcare. As an organization’s patient pay increases, they’re looking for better ways to collect the patient portion of the bill.

Privacy and Security
There have been so many health care breaches, it’s hard to even keep up. Are we becoming numb to them? Maybe, but I still see many organizations investing in various privacy and security programs and tools whenever they hear about another breach. Plus, the meaningful use requirement to do a HIPAA Risk Assessment has built an entire industry focused on those risk assessments. You can be sure the coming HIPAA audits will accelerate those businesses even more.

What other areas are you seeing become popular in health care IT?

Analytics Integration Back to EHR Can’t Disrupt the Workflow

Posted on November 3, 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.

One of the challenges we face with healthcare analytics is getting the right information to the right care provider at the right time. In many cases that means presenting the analytics information to the doctor or nurse in the EHR at the point of care. It’s hard enough to know which data to present to which person and at what point in the care process. However, EHR vendors have made this integration even more difficult since it’s not easy to interface the healthcare analytics insights into the EHR workflow. The integrations that I’ve seen are crude at best.

That’s absolutely where we need to go though. There are very few situations where you can disrupt the healthcare providers workflow and send them to another system. I love the second screen concept as much as the next, but that’s not reasonable for most organizations.

I did recently talk to a BI Manager from a hospital who talked about the way they’ve integrated some of their analytics into the EHR workflow of their doctors. What they were doing was basic at best, but did illustrate an important point of learning: inform, don’t interrupt.

The concept of informing the doctor and not interrupting the doctor is a good one. While there are likely a few cases where you’d want to interrupt the doctor, it’s more common that you want to inform the doctor of some insight on the patient as opposed to interrupting the workflow. Doctors love having the right information at their fingertips. Interrupting their workflow (especially when it was unnecessary) causes alert fatigue.

No doubt you have to be careful with how you inform the doctor as well. The insights you offer the doctor better be actionable and useful or they’ll become blind to that as well. That’s the challenge we face with healthcare analytics. How do we take the data and make it useful to the providers? The first step is going to be creating a pathway of communication from the analytics into the EHR. Everything else will evolve from that connection.

Will Your Healthcare Analytics Solution Scale?

Posted on October 26, 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.

One of the big themes being talked about at the Healthcare IT Transformation Assembly this week and particularly during my Care Performance Transformation roundtable with Midas+ has been around healthcare analytics and the solutions that will help a hospital utilize their data for population health, value based reimbursement, and improved care. This has made for an interesting discussion for me after having attended SAP Teched last week where SAP talked about the need for the right healthcare data solution that can scale to the needs of healthcare.

At both of these events it became very clear that the future of healthcare is being built on the back of healthcare data. The quantity and quality of healthcare data is expanding rapidly. There’s a lot of healthcare data being generated within the 4 walls of every healthcare organization. There’s a lot of healthcare data being generated outside of the healthcare setting. Plus, we’re just barely getting started with all of the data that’s needed for all the -omics (Genomics and Proteomics). Getting a handle on this data and ensuring the data can be trusted is of paramount concern for healthcare leaders.

What seems to be playing out is healthcare organizations are having to choose to invest in both point solutions and larger healthcare analytics solutions. Unfortunately there doesn’t seem to be one catch all solution that will solve all of a healthcare organization’s data transformation needs. None of the current solutions scale across all types of data and solve all of the current healthcare requirements. Although, some could eventually grow into that role.

In today’s discussion in particular, a number of hospital CIOs made clear that they had no choice but to have a variety of care transformation and healthcare analytics solutions. There wasn’t one integrated solution they could purchase and be done. In many ways it reminds me of the early days of PM, HIS, LIS, and EHR purchasing. Most purchased them separately because there wasn’t one integrated solution. However, over time people moved to buying one integrated system across PM, EHR, LIS, etc as the software become integrated and mature. Will we see the same thing happen with our healthcare analytics solutions?

While we’ve seen the move to more integrated healthcare IT solutions, we’re also seeing a move away from that now as well. Every EHR vendor is working on APIs to allow third party companies to integrate new solutions with the EHR. There’s a realization that it would be nice if the EHR could do everything in one nicely integrated solution, but it won’t. It’s a cycle that we see in software. I imagine we’ll see that same cycle with healthcare analytics solutions as well.

Top 10 Healthcare CIO Budget Priorities

Posted on September 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.

For those on the email list that can’t see the image that Charles Webster, MD shared, here are the list of top technology priorities:
1. BI/Analytics
2. CRM
3. Digitalization/Digital Marketing
4. Legacy Modernization
5. Industry-Specific Applications
6. Enterprise Applications
7. Infrastructure and Data Center
8. Application Development
9. Architecture
10. BPM
11. Cloud
12. Collaboration

Sure makes the life of a CIO look pretty easy, doesn’t it? (That was my sarcasm font in case you don’t have that font installed on your computer)

As I chew on this list, I’m processing Will Weider, CIO at Ministry Health Care’s response to me asking him what would he consider the 3 key focus areas for healthcare CIO’s:

Population Health Management Infographic

Posted on August 31, 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.

I recently came across this graphic which tries to illustrate the components of population health management. I like the components they’ve listed around the outside, but I thought the center section was the most interesting. All of us in healthcare need to think about how we take population health management and incorporate it into a shared vision of what we want to accomplish. One thing is certain to me, population health management isn’t going to happen if we all stay in our silos.
Population Health Management Infographic
SOURCE: CTG Health Solutions and Clinovations. “Population Health Management: Leveraging Data and Analytics to Achieve Value.” 2012.
What do you think of the components of this graphic? Is there anything missing from it?

When Has Analytics Ever Said – “You’re Awesome”?

Posted on April 27, 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.

I was just thinking about all of these analytics vendors and healthcare analytics stories that were sent to me during HIMSS. Every story goes a bit like this. We gathered a whole bunch of data. We analyzed the data. We discovered that we sucked and so we were able to save $X million dollars and improve the quality of care we provide. Makes for a great story no?

I was thinking about this and I was trying to figure out why this story never ends differently. Every analytics implementation I’ve ever seen or heard about finds some major problems in ever healthcare organization. How come they don’t sometimes do the analysis and discover: “Wow! You’re organization is awesome. You shouldn’t change anything!”

I have two theories about why this is the case. First, no healthcare system is perfectly optimized. That means that if you look hard enough, you can always find something that can be improved. There certainly are different degrees of improvement that can be provided depending on the health system’s baseline, but there are always ways that it can be improved. I think this logically makes sense. Especially when we’re talking about something as complex as healthcare.

Second, the people doing the analytics get paid to find problems. If they discovered that everything is going better than the norm and that you have a really high functioning health system, then they wouldn’t get paid. We don’t pay people to tell us we’re doing good. We pay them to tell us where we can improve. So, we get what we pay for.

The closest I’ve seen people come to this is every once in a while I hear a story from a vendor who honestly says, “we can’t do much for you.” I’ve done it a few times here at EMR and HIPAA. Sometimes they’re looking for an audience that doesn’t really read this blog. If you want the PACS administrator, then we’re probably not a good fit. We don’t write much PACS content and so I can’t imaging many PACS admins are reading the blog. It’s just easier to be honest about it. Although, not all companies feel that way.

I’d be interested to hear if you know of other examples where this occurs. Have you seen many times when someone has said, “Your doing great. I can’t help you more.”?

A Few Quick HIMSS15 Thoughts

Posted on April 13, 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.

Today’s been a long day packed with meetings at HIMSS 2015. I need to reach out to HIMSS to get the final numbers, but word is that there are over 40,000 people at the show. In the hallways, the exhibit hall and the taxi lines it definitely seems to be the case. I’m not sure the jump in attendees, but I saw one tweet that IBM had 400 people there. Don’t quote me on it since I can’t find the tweet, but that’s just extraordinary to even consider that many people from one company.

Of course, the reason I can’t find the tweet is that the Twitter stream has been setting new records each day. The HIMSS 2015 Twitter Tips and Tricks is valuable if you want to get value out of the #HIMSS15 Twitter stream. I also have to admit that I might be going a bit overboard on the selfies. I think I’ve got the @mandibpro selfie disease. Not sure the treatment for it since my doctor doesn’t do a telemedicine visit while I’m in Chicago.

I’ve had some amazing meetings that will inform my blog posts for weeks to come. However, my biggest takeaway from the first official day of HIMSS is that change is in the air. The forces are at work to make interoperability a reality. It’s going to be a massive civil war as the various competing parties battle it out as they set the pathway forward.

You might think that this is a bit of an exaggeration, but I think it’s pretty close to what’s happening. What’s not clear to me is whose going to win and what the final outcome will look like. There are so many competing interests that are trying to get at the data and make it valuable for the doctor and health system.

Along those lines, I’m absolutely fascinated by the real time analytics capabilities that I saw being built. A number of companies I talked to are moving beyond the standard batch loaded enterprise data warehouse approach to a real time (or as one vendor said…we all have to call it near real time) stream of data. I think this is going to drive a massive change in innovation.

I’ll be talking more about the various vendors I saw and their approaches to this in future posts after HIMSS. While I’m excited by some of the many things these companies are doing, I still feel like many of them are constrained by their inability to get to the data. A number of them were working on such small data sets. This was largely because they can’t get the other data. One vendor told me that their biggest challenge is getting an organization to turn over their data for them for analysis.

While it’s important that organizations are extremely careful with how they handle and share their data. More organizations should be working with trusted partners in order to extract more value out of the data and to more importantly make new discoveries. The discoveries we’re making today are really great, but I can only imagine how much more we could accomplish with more data to inform those discoveries.

Healthcare Data Quality and The Complexity of Healthcare Analytics

Posted on March 2, 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.

The other day I had a really great chat with Khaled El Emam, PhD, CEO and Founder of Privacy Analytics. We had a wide ranging discussion about healthcare data analytics and healthcare data privacy. These are two of the most important topics in the healthcare industry right now and no doubt will be extremely important topics at healthcare conferences happening all through the year.

In our discussion, Khaled talked about what I think are the three most important challenges with healthcare data:

  1. Data Integrity
  2. Data Security
  3. Data Quality

I thought this was a most fantastic way to frame the discussion around data and I think healthcare is lacking in all 3 areas. If we don’t get our heads around all 3 pillars of good data, we’ll never realize the benefits associated with healthcare data.

Khaled also commented to me that 80% of healthcare analytics today is simple analytics. That means that only 20% of our current analysis requires complex analytics. I’m sure he was just giving a ballpark number to illustrate the point that we’re still extremely early on in the application of analytics to healthcare.

One side of me says that maybe we’re lacking a bit of ambition when it comes to leveraging the very best analytics to benefit healthcare. However, I also realize that it means that there’s still a lot of low hanging fruit out there that can benefit healthcare with even just simple analytics. Why should we go after the complex analytics when there’s still so much value to healthcare in simple analytics.

All of this is more of a framework for discussion around analytics. I’m sure I’ll be considering every healthcare analytics I see based on the challenges of data integrity, security and quality.