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!

Mayo Clinic Creating Souped-Up Extension Of MyChart

Posted on March 19, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

As you probably know, MyChart is Epic’s patient portal. As portals go, it’s serviceable, but it’s a pretty basic tool. I’ve used it, and I’ve been underwhelmed by what its standard offering can do.

Apparently, though, it has more potential than I thought. Mayo Clinic is working with Epic to offer a souped-up version of MyChart that offers a wide range of additional services to patients.

The new version integrates Epic’s MyChart Virtual Care – a telemedicine tool – with the standard MyChart mobile app and portal. In doing so, it’s following the steps of many other health systems, including Henry Ford Health System, Allegheny Health Network and Lakeland Health.

However, Mayo is going well beyond telemedicine. In addition to offering access to standard data such as test results, it’s going to use MyChart to deliver care plans and patient-facing content. The care plans will integrate physician-vetted health information and patient education content.

The care plans, which also bring Mayo care teams into the mix, provide step-by-step directions and support. This support includes decision guidance which can include previsit, midtreatment and post-visit planning.

The app can also send care notifications and based on data provided by patients and connected devices, adapt the care plan dynamically. The care plan engine includes special content for conditions like asthma, type II diabetes chronic obstructive heart failure, orthopedic surgery and hip/knee joint replacement.

Not surprisingly, Mayo seems to be targeting high-risk patients in the hopes that the new tools can help them improve their chronic disease self-management. As with many other standard interventions related to population health, the idea here is to catch patients with small problems before the problems blossom into issues requiring emergency department visit or hospitalization.

This whole thing looks pretty neat. I do have a few questions, though. How does the care team work with the MyChart interface, and how does that affect its workflow? What type of data, specifically, triggers changes in the care plan, and does the data also include historical information from Mayo’s EMR? Does Mayo use AI technology to support care plan adaptions? Does the portal allow clinicians to track a patient’s progress, or is Mayo assuming that if patients get high high-quality educational materials and personalized care plan that the results will just come?

Regardless, it’s good to see a health system taking a more aggressive approach than simply presenting patient health data via a portal and hoping that this information will motivate the patient to better manage their health. This seems like a much more sophisticated option.

Tri-City Medical Center: Achieving a Middleware First

Posted on March 2, 2018 I Written By

The following is a guest blog post by Adam Klass, Chief Technology Officer, VigiLanz.

In the age of value-based care, it’s all about performance as hospitals continually face increased financial pressure to meet a number of different criteria related to decreasing length of stay, hospital-acquired infection rates and hospital readmissions. Today’s hospital organization must improve healthcare analytics and core measures, avoid penalties, and secure reimbursement, so it can continue to grow and thrive. This shift means hospitals must now consider cost avoidance instead of expecting direct reimbursement for patient care.

The challenge then becomes how to support and enable next-generation healthcare providers by delivering real-time results from disparate platforms and technology into any clinical workflow. It’s no surprise, then, that 62 percent of hospital CIOs identify interoperability as a top priority and 80 percent of accountable care organizations also cite integrating data as a top challenge for their IT departments.

To accomplish this goal, medical facilities like Tri-City Medical Center, a 388-bed full service, acute care hospital in Oceanside, California, require a services-oriented architecture and open application programming interface (API) capability that enables efficient aggregation, interaction and exchange of disparate data throughout the healthcare enterprise and across any of its software technologies, including EMRs and third-party single-point-solution vendors.

APIs Versus HL7

APIs fit the bill by allowing access to all of the data a digital health application and a health system would need, in real-time. Clinicians and administrators can now rapidly integrate new clinical and business information for better decision-making and, most importantly, for improved patient care with new interoperability services.

Tri-City Medical Center, which also operates a primary care clinic and employs more than 700 physicians practicing in 60 specialties, is the first VigiLanz customer site to utilize our middleware API solution, VigiLanz Connect, to convert health data from its EMR into uniform, actionable intelligence in the VigiLanz Platform. The hospital organization’s use of this solution turns its closed EMR systems into open platforms through robust services that do not rely on HL7 interfaces. Instead, our platform handles connectivity and normalizes data structures across major EMR platforms, like Cerner’s, which Tri-City Medical Center uses, to quickly unlock the data. Benefits include reduced integration time from months to days, elegant workflows, decreased maintenance costs and minimized risk.

“An API is definitely the way to go,” explained Mark Albright, Vice President of Technology, Tri-City Medical Center. “Anytime we have a choice between an interface and an API, we always go with APIs. It’s just so much easier to install and get up and running.”

“Not only are APIs easy to use but they are a no-brainer when it comes to rapid and successful implementation,” continued Albright. “Using VigiLanz’s middleware API helped us maximize the platform in a different, modern way. Not only is it a simpler effort than using a solution like HL7 but it’s also stable and steady so it’s easy to maintain, despite the significant amount of data being pulled.”

Taking EMR Systems to the Next Level

Clinical intelligence and interoperability services complement today’s EMR systems which, on their own, may be insufficient to deliver agile, real-time intelligence services. In contrast, a middleware API can interoperate with EMR systems and is built with innovative abstract data architectures that help hospitals like Tri-City Medical Center improve patient care and operational performance.

In contrasting his organization’s middleware API experience with what would have traditionally been an HL7 integration, Albright noted, “Our hospital charged a non-programmer, non-developer, non-HL7 person with spearheading this project, something that could have not happened in an HL7 world. She would have never been able to master that.”

That “she” is Melody Peterson, a senior systems analyst, who stepped into the project post-decision, after Tri-City’s pharmacy, infection control and clinical surveillance departments had already made the decision to purchase the middleware API, separate from the organization’s IT department.

“I was tasked with making this middleware API work, without having been part of the research or purchase decision,” explained Peterson. “Because VigiLanz supports the clinical and business sides of our hospital, though, it was easy to implement this ‘plug-and-play’ integration solution, in a way that applied to all areas critical to optimizing care – from risk scoring to antimicrobial stewardship.”

A middleware architecture is often the best technological solution for addressing the problem of EHR interoperability because it facilitates the transparent, yet secure, access of patient health data, directly from the various databases where it is stored. No longer does a hospital organization like Tri-City Medical Center have to do all of the development itself, but instead can rely on off-the-shelf applications to solve problems. Middleware brings an application-agnostic approach to connecting EMRs to one another while allowing for specific development to enhance the significant investment by hospitals, health systems and physicians.

Yale New Haven Hospital Partners With Epic On Centralized Operations Center

Posted on February 5, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

Info, info, all around, and not a place to manage it all. That’s the dilemma faced by most hospitals as they work to leverage the massive data stores they’re accumulating in their health IT systems.

Yale New Haven Hospital’s solution to the problem is to create a centralized operations center which connects the right people to real-time data analytics. Its Capacity Command Center (nifty alliteration, folks!) was created by YNHH, Epic and the YNHH Clinical Redesign Initiative.

The Command Center project comes five years into YNHH’s long-term High Reliability project, which is designed to prepare the institution for future challenges. These efforts are focused not only on care quality and patient safety but also managing what YNHH says are the highest patient volumes in Connecticut. Its statement also notes that with transfers from other hospitals increasing, the hospital is seeing a growth in patient acuity, which is obviously another challenge it must address.

The Capacity Command Center’s functions are fairly straightforward, though they have to have been a beast to develop.

On the one hand, the Center offers technology which sorts through the flood of operational data generated by and stored in its Epic system, generating dashboards which change in real time and drive process changes. These dashboards present real-time metrics such as bed capacity, delays for procedures and tests and ambulatory utilization, which are made available on Center screens as well as within Epic.

In addition, YNHH has brought representatives from all of the relevant operational areas into a single physical location, including bed management, the Emergency Department, nursing staffing, environmental services and patient transport. Not only is this a good approach overall, it’s particularly helpful when patient admissions levels climb precipitously, the hospital notes.

This model is already having a positive impact on the care process, according to YNHH’s statement. For example, it notes, infection prevention staffers can now identify all patients with Foley catheters and review their charts. With this knowledge in hand, these staffers can discuss whether the patient is ready to have the catheter removed and avoid related urinary tract infections associated with prolonged use.

I don’t know about you, but I was excited to read about this initiative. It sounds like YNHH is doing exactly what it should do to get more out of patient data. For example, I was glad to read that the dashboard offered real-time analytics options rather than one-off projections from old data. Bringing key operational players together in one place makes great sense as well.

Of course, not all hospitals will have the resources to pull something off something like this. YNHH is a 1,541-bed giant which had the cash to take on a command center project. Few community hospitals would have the staff or money to make such a thing happen. Still, it’s good to see somebody at the cutting edge.

Deep Learning System Triages Terminally Ill Hospital Patients

Posted on January 26, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

Researchers at Stanford have developed a new tool designed to coordinate end-of-life care for critically ill patients. While the pilot study has generated screaming newspaper headlines (“AI tool predicts when people will die!”) researchers say that the system is best thought of as a triage option which helps hospitals and hospices provide timely palliative care to those who need it. It can also help terminally ill patients — most of whom would prefer to die at home — make plans for their passing and avoid dying in their hospital bed.

According to an article in tech publication Gizmodo, the Stanford set-up combines EHR data with other sources of information such disease type, disease state and severity of admission. The information is then processed by a form of AI known as deep learning, in which a neural network “learns” by digesting large amounts of data.

To conduct the study, researchers fed 2 million records from adult and child patients admitted to either Stanford Hospital or Lucile Packard Children’s Hospital. The system then identified 200,000 patients who met the study’s criteria. In addition to clinical criteria, the system also reviewed associated case reports diagnoses, number of scans ordered, number of procedures performed and other data.

After reviewing 160,000 case reports, the deep learning system was instructed to predict the mortality of a given patient within three to 12 months of a particular date using EHR data from the previous year. The algorithm included a requirement to ignore patients who appeared to have less than three months to live, as this window was too short for providers to make preparations to offer palliative care.

Then, the AI algorithm calculated the odds of patient death in the 3 to 12-month timespan extending from the original date. Its predictions turned out to be quite accurate. For one thing, it predicted patient mortality within the 3 to 12-month window accurately in nine out of 10 cases, a performance that few clinicians could match. Meanwhile, roughly 95% of patients considered to have a low probability of dying within 12 months actually lived beyond that point.

It’s worth noting that while the deep learning tool made fairly accurate predictions of patient mortality, the system doesn’t let healthcare providers know what treatment patients need or even how it makes its predictions. Luckily, researchers say, the system allows them to get a look at individual cases to better understand its deductions.

For example, in one case the system predicted accurately that a patient with bladder and prostate cancer would die within a few months. While there were many clues that he was near death, the system weighted the fact the scans were made of his spine and a catheter used in his spinal cord heavily in its calculations. Only later did the researchers realize that an MRI of the spinal cord most likely suggested a deadly cancer of the spinal cord which was likely to metastasize.

It’s worth remembering these results were produced as part of a pilot project, and that the predictions the system makes might not be as accurate for other data sets. However, these results are an intriguing reminder of the possibilities AI offers for hospitals.

Texas Hospital Association Dashboard Offers Risk, Cost Data

Posted on January 22, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

The Texas Hospital Association has agreed to a joint venture with health IT vendor IllumiCare to roll out a new tool for physicians. The new dashboard offers an unusual but powerful mix of risk data and real-time cost information.

According to THA, physician orders represent 87% of hospital expenses, but most know little about the cost of items they order. The new dashboard, Smart Ribbon, gives doctors information on treatment costs and risk of patient harm at the point of care. THA’s assumption is that the data will cause them to order fewer and less costly tests and meds, the group says.

To my mind, the tool sounds neat. IllumiCare’s Smart Ribbon technology doesn’t need to be integrated with the hospital’s EMR. Instead, it works with existing HL-7 feeds and piggybacks onto existing user authorization schemes. In other words, it eliminates the need for creating costly interfaces to EMR data. The dashboard includes patient identification, a timer if the patient is on observational status, a tool for looking up costs and tabs providing wholesale costs for meds, labs and radiology. It also estimates iatrogenic risks resulting from physician decisions.

Unlike some clinical tools I’ve seen, Smart Ribbon doesn’t generate alerts or alarms, which makes it a different beast than many other clinical decision support tools. That doesn’t mean tools that do generate alerts are bad, but that feature does set it apart from others.

We’ve covered many other tools designed to support physicians, and as you’d probably guess, those technologies come in all sizes. For example, last year contributor Andy Oram wrote about a different type of dashboard, PeraHealth, a surveillance system targeting at-risk patients in hospitals.

PeraHealth identifies at-risk patients through analytics and displays them on a dashboard that doctors and nurses can pull up, including trends over several shifts. Its analytical processes pull in nursing assessments in addition to vital signs and other standard data sets. This approach sounds promising.

Ultimately, though, dashboard vendors are still figuring out what physicians need, and it’s hard to tell whether their market will stay alive. In fact, according to one take from Kalorama Information, this year technologies like dashboarding, blockchain and even advanced big data analytics will be integrated into EMRs.

As for me, I think Kalorama’s prediction is too aggressive. While I agree that many freestanding tools will be integrated into the EMR, I don’t think it will happen this or even next year. In the meantime, there’s certainly a place for creating dashboards that accommodate physician workflow and aren’t too intrusive. For the time being, they aren’t going away.

Roche, GE Project Brings New Spin To Clinical Decision Support

Posted on January 10, 2018 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

The clinical decision support market is certainly crowded, and what’s more, CDS solutions vary in some important ways. On the other hand, one could be forgiven for feeling like they all look the same. Sorting out these technologies is not a job for the faint of heart.

That being said, it’s possible that the following partnership might offer something distinctive. Pharmaceutical giant Roche has signed a long-term partnership deal with GE Healthcare to jointly develop and market clinical decision support technology.

In a prepared statement, the two companies said they were developing a digital platform with a difference. The platform will use analytics to fuel workflow tools and apps and support clinical decisions. The platform will integrate a wide range of data, including patient records, medical best practices and recent research outcomes.

At least at the outset of their project, Roche and GE Healthcare are targeting oncology and critical care. With a pharmaceutical company and healthcare technology firm working together, providing tools for oncology specialists in particular makes a lot of sense.

The partners say that their product will give oncology care teams with multiple specialists a common data dashboard to review, which should help them collaborate on treatment decisions. Meanwhile, they plan to offer critical care physicians a dashboard integrating data from patient’ hospital monitoring equipment with their biomarker, genomic and sequencing data.

The idea of integrating new and possibly relevant information to the CDS platform is intriguing. It’s particularly interesting to imagine physicians leveraging genetic information to make real-time decisions. I think it’s safe to say that we’d all like it if CDS systems could bring the rudiments of precision medicine to thorny day-to-day clinical problems.

But the truth is, if my interactions with doctors mean anything, that few of them like CDS systems. Some have told me flat out that they end up overriding many CDS prompts, which arguably makes these very expensive systems almost irrelevant to hospital-based clinical practice. It’s hard to tell whether they would be willing to trust a new approach.

However, if GE and Roche can pull off what they’re pitching, it might just provide enough value it might convince them. Certainly, creating a more flexible dashboard which integrates data and office workflows is a large step in the right direction. And it’s probably fair to say that nothing like this exists in the market right now (as they claim).

Again, while there’s no guaranteed way to build out useful technology, bringing a pharma giant and a health IT giant might give both sides a leg up. I wonder how many users and patients they have involved in their design process. Let’s see if they can back up their promises.

Using Geography to Combat the Opioid Crisis

Posted on 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 speaks, tweets and blogs regularly about healthcare, technology, marketing and leadership. He is currently an independent marketing consultant working with leading healthIT companies. Colin is a member of #TheWalkingGallery. His Twitter handle is: @Colin_Hung.

When it comes to the opioid crisis, the numbers aren’t good. According to the latest CDC numbers, over 66,000 Americans died from drug overdoses between May 2016 and May 2017. Unfortunately this continues the rapid upward trend over the past five years.

Credit: New York Times, The First Count of Fentanyl Deaths in 2016: Up 540% in Three Years, 2 Sept 2017,

One of the biggest drivers for this increase is the prevalence of opioids – a class of drugs that includes pain medications, heroin and fentanyl (a synthetic opioid). The opioid crisis is not the stereotypical street-drug problem. It is not confined to inner cities or to any socio-economic boundaries. It affects all neighborhoods…and therein lies one of the greatest challenges of dealing with the crisis, knowing where to deploy precious resources.

As governments and public health authorities begin to take more aggressive action, some are wisely turning to geographic information systems (GIS) in order to determine where the need is greatest. GIS (also called geospatial mapping) are designed specifically to capture, store, manage and analyze geographical data. It has been a mainstay in mining, engineering and environmental sciences since the early 1990’s. For more information about GIS, please see this excellent PBS documentary. In recent years, GIS has been applied to a number of new areas including healthcare.

Esri is one of the companies doing pioneering GIS work in healthcare and recently they have focused on applying their ArcGIS technology to help tackle the opioid crisis. “One of the basic challenges that public health authorities face is clearly defining the scope of the opioid problem in their local area.” says Estella Geraghty MD, Chief Medical Officer & Health Solutions Director at Esri. “The good news is that the information to map the extent of the problem is available, it’s just stored in disparate systems and in incompatible formats. We help bring it all together.”

Geraghty points to their work with the Tri-County Health Department (TCHD) as an example of how effective GIS can be. TCHD is one of the largest public health agencies in the US, serving 1.5 million residents in three of Denver’s metropolitan counties: Adams, Arapahoe and Douglas. Using Esri’s ArcGIS solution, TCHD created an open data site that allows internal teams and external partners to pool and share their opioid health information using a visual map of the region as a common base of reference.

According to Esri: “Since the creation of the Open Data site, there has been a dramatic increase in both the information available to the public and the community’s understanding of the opioid crisis.” You can see the Open Data site here and if you scroll down you will see six different maps available to the public. Particularly sobering is the Opioid Overdose Deaths from 2011-2016, which allows you to zoom in down to specific streets/blocks. Another interesting map is the Household Medication Take-Back Locations which seems to indicate there is a lack of coverage for the city of Denver.

Esri itself has created its own site to bring attention to the opioid crisis at a national level. Two maps in particular stand out to me. The first is the map of Opioid Prescriptions per Provider. The red zones on that map represent areas where a high number of opioid prescriptions are being made by relatively few providers. This points to potential areas where opioid abuse may be occurring.

By mapping the data in this way, some interesting insights emerge. Take Taliaferro County in Georgia for example where 2,069 claims out of a total of 29,016 were for opioids, yet the county only has 2 providers. Or Clinch County in Georgia where a whopping 10% of all claims were for opioids.

The second interesting map is Lost Loved Ones (located at the bottom of the Esri site). This is a completely open map where anyone can pay tribute to a loved one who has been lost to the opioid crisis. Each dot is a person – a stark reminder that behind each statistic is a son, daughter, mother, or father who has died from opioids. Anyone can add to the map by clicking the button at the top of the map.

There is something to be said about seeing data overlaid onto an interactive map. It takes data from abstract lines, bars or numbers on a page and transforms it into something more tangible, more “real”. I suspect that for many on the front lines of this crisis, having the opioid data visualized in this manner helps to drive home the need for additional resources.

“Esri is helping public health officials all over the country make better decisions,” continued Geraghty. “We are helping them determine if they have enough coverage for places where people can drop off expired drugs, places where Naloxone is available and mental health program coverage. We can visually present the types of drugs being dropped off by region. We can track where first responders have had to use Naloxone. We plan on continuing to collaborate closely with customers, especially with public health authorities. This opioid crisis is impacting so many neighborhoods. We can make a difference.”

Given the continued upward trend in opioid-related deaths, healthcare can use all the difference makers it can get.

Hospital Takes Step Forward Using Patient-Reported Outcome Data

Posted on December 6, 2017 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

I don’t usually summarize stories from other publications — I don’t want to bore you! — and I like to offer you a surprise or two. This time, though, I thought you might want to hear about an interesting piece appearing in Modern Healthcare. This item offers some insight into how understanding patient-generated determinants of health could improve outcomes.

The story tells the tale of the Hospital for Special Surgery, an orthopedics provider in New York City which provides elective procedures to treat joint pain and discomfort. According to the MH editor, HSS has begun collecting data on patient-reported outcomes after procedures to see not only how much pain may remain, but also how their quality of life is post-procedure.

This project began by doing a check in with the patient before the procedure, during which nurses went over important information and answered any questions the patient might have. (As readers may know, this is a fairly standard approach to pre-surgical patient communication, so this was something of a warm-up.)

However, things got more interesting a few months later. For its next step, the hospital also began surveying the patients on their state of mind and health prior to the procedure, asking 10 questions drawn from the Patient-Reported Outcomes Measurement Information System, or Promis.

The questions captured not only direct medical concerns such as pain intensity and sleep patterns, but also looked at the patient’s social support system, information few hospitals capture in a formal way at present.

All of the information gathered is being collected and entered into the patient’s electronic health record. After the procedure, the hospital has worked to see that the patients fill out the Promis survey, which it makes available using Epic’s MyChart portal.

Getting to this point wasn’t easy, as IT leaders struggled to integrate the results of the Promis survey into patient EHRs. However, once the work was done, the care team was able to view information across patients, which certainly has the potential to help them improve processes and outcomes over time.

Now, the biggest challenge for HSS is collecting data after the patients leave the hospital. Since kicking off the project in April, HSS has collected 24,000 patient responses to nursing questions, but only 15% of the responses came from patients who submitted them after their procedure. The hospital has seen some success in capturing post-surgical results when doctors push patients to fill out the survey after their care, but overall, the post-surgical response rate has remained low to date.

Regardless, once the hospital improves its methods for collecting post-surgical patient responses, it seems likely that the data will prove useful and important. I hope to see other hospitals take this approach.

Amazon May Soon Announce Major Cloud Deal With Cerner

Posted on November 27, 2017 I Written By

Anne Zieger is veteran healthcare branding and communications expert with more than 25 years of industry experience. and her commentaries have appeared in dozens of international business publications, including Forbes, Business Week and Information Week. She has also worked extensively healthcare and health IT organizations, including several Fortune 500 companies. She can be reached at @ziegerhealth or

As I’ve previously noted, Amazon is making increasingly aggressive moves into the healthcare space of late. While it hasn’t been terribly public with its plans—and why should it, honestly?— there been some talk of its going into the healthcare technology space. There’s also much talk about angles from which Amazon could attack healthcare sectors, including its well-publicized interest in the pharmacy business.

Though interesting, all of this has been vaguely defined it best. However, a new deal may be in the works which could have a very concrete effect. It could change not only the future of Amazon’s healthcare industry efforts but also, potentially, have an impact on the entire health IT world.

Think I’m exaggerating? Check this out. According to a story on the CNBC site, Amazon is about to announce a “huge” deal with Cerner under which the two will work together on building a major presence in enterprise health IT for Amazon Web Services. Put that way, this sounds a bit hyperbolic, but let me lay this out a bit further.

As things stand, the online retailer’s Amazon Web Services is already generating almost $20 billion a year, boasting clients across major industries such as technology, energy and financial services. Its only stumbling point to date is that it’s had trouble cracking the healthcare market.

Apparently, at the re:Invent conference in Las Vegas next week, AWS’s CEO will announce that Amazon is teaming up with Cerner to convince senior healthcare leaders to use AWS for key initiatives like population health management.

Sources who spoke to CNBC that the partnership will initially focus on Cerner’s HealtheIntent population health product, presumably as a door into convincing hospitals shift more of the cloud-based business to AWS.

Now why, you ask, is this deal bigger than the average bear?  is it one of those vaporware partnerships that fly a flag and promise a lot but don’t really go anywhere?

Yes, I admit that’s always possible, but in this case, I don’t think it’s going to turn out that way. The fit simply seems to work too well for this to be one of those much-ballyhooed deals that fade away quietly. (In fact, I could visualize a Cerner/Amazon merger in the future, as crazy as that might sound. It’s certainly less risky than the Whole Foods deal.)

For one thing, both Amazon and Cerner have significant benefits they can realize. For example, as the story notes, Amazon hasn’t gotten far in the healthcare market, and given its talent for doing the impossible, it must be really stuck at this point. Cerner, meanwhile, will never pull together the kind of cloud options AWS can offer, and I doubt Epic could either, which gives Cerner a boost in the always next-and-neck competition with its top rival.

If this agreement goes through, the ripples could be felt throughout the healthcare industry, if for no other reason than the impact it will have on the enterprise EHR market. This one should be fun to watch. I’m pulling out the popcorn.

AMIA17 – There’s Gold in Them EHRs!

Posted on November 13, 2017 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 speaks, tweets and blogs regularly about healthcare, technology, marketing and leadership. He is currently an independent marketing consultant working with leading healthIT companies. Colin is a member of #TheWalkingGallery. His Twitter handle is: @Colin_Hung.

If even 10% of the research presented at the 2017 American Medical Informatics Association conference (AMIA17) is adopted by mainstream healthcare, the impact on costs, quality and patient outcomes will be astounding. Real-time analysis of EHR data to determine the unique risk profile of each patient, customized remote monitoring based on patient + disease profiles, electronic progress notes using voice recognition and secondary uses of patient electronic records were all discussed at AMIA17.

Attending AMIA17 was an experience like no other. I understood less than half of the information being presented and I loved it. It felt like I was back in university – which is the only other time I have been around so many people with advanced degrees. By the time I left AMIA17, I found myself wishing I had paid more attention during my STATS302 classes.

It was especially interesting to be at AMIA17 right after attending the 3-day CHIME17 event for Hospital CIOs. CHIME17 was all about optimizing investments made in HealthIT over the past several years, especially EHRs (see this post for more details). AMIA17 was very much an expansion on the CHIME17 theme. AMIA17 was all about leveraging and getting value from the data collected by HealthIT systems over the past several years.

A prime example of this was the work presented by Michael Rothman, Ph.D of Pera Health. Rothman created a way to analyze key vital signs RELATIVE to a patient’s unique starting condition to determine whether they are in danger. Dubbed the Rothman Index, this algorithm presents clinicians and caregivers with more accurate alarms and notifications. With all the devices and systems in hospitals today, alarm fatigue is a very real and potentially deadly situation.

Missed ventilator alarms was #3 on ECRI Institute’s 2017 Top 10 Health Technology Hazards. It was #2 on the 2016 Top 10 list. According to ECRI: “Failure to recognize and respond to an actionable clinical alarm condition in a timely manner can result in serious patient injury or death”. The challenge is not the response but rather how to determine which alarms are informational and which are truly an indicator of a clinical condition that needs attention.

Comments from RNs in adverse-event reports shared in a 2016 presentation to the Association for the Advancement of Medical Instrumentation (AAMI) sums up this challenge nicely:

“Alarm fatigue is leading to significant incidents because there are so many nuisance alarms and no one even looks up when a high-priority alarm sounds. Failure to rescue should be a never event but it isn’t.”

“Too many nuisance alarms, too many patients inappropriately monitored. Continuous pulse oximetry is way overused and accounts for most of the alarms. Having everyone’s phone ring to one patient’s alarm makes you not respond to them most of the time.”

This is exactly what Rothman is trying to address with his work. Instead of using a traditional absolute-value approach to setting alarms – which are based on the mythical “average patient” – Rothman’s method uses the patient’s actual data to determine their unique baseline and sets alarms relative to that. According to Rothman, this could eliminate as much as 80% of the unnecessary alarms in hospitals.

Other notable presentations at AMIA17 included:

  • MedStartr Pitch IT winner, FHIR HIEDrant, on how to mine and aggregate clinically relevant data from HIEs and present it to clinicians within their EHRs
  • FHIR guru Joshua C Mandel’s presentation on the latest news regarding CDS Hooks and the amazing Sync-for-Science EHR data sharing for research initiative
  • Tianxi Cai of Harvard School of Public Health sharing her research on how EHR data can be used to determine the efficacy of treatments on an individual patient
  • Eric Dishman’s keynote about the open and collaborative approach to research he is championing within the NIH
  • Carol Friedman’s pioneering work in Natural Language Processing (NLP). Not only did she overcome being a woman scientist but also applying NLP to healthcare something her contemporaries viewed as a complete waste of time

The most impressive thing about AMIA17? The number of students attending the event – from high schoolers to undergraduates to PhD candidates. There were hundreds of them at the event. It was very encouraging to see so many young bright minds using their big brains to improve healthcare.

I left AMIA17 excited about the future of HealthIT.