Regenstrief Institute won a new five-year, $1.7 million grant from the Agency for Healthcare Research and Quality for development and testing of automated patient identification approaches. 

Regenstrief’s Center for Biomedical Informatics will use the funding to build on more than 15 years of work in matching patient records, officials said.

Researchers will also work with the Indiana Network for Patient Care, the largest inter-organizational clinical data repository in the country, to develop and test new approaches in a real-world patient care network.

[Also: IU, Regenstrief score $2.5 million from NIA to test new care model for patients over 50]

"Matching the correct individual to his or her health data is critical to their medical care," Shaun Grannis, MD, principal investigator for the new grant at Regenstrief, said in a statement. "Statistics show that up to one in five patient records are not accurately matched even within the same healthcare system. As many as half of patient records are mismatched when data is transferred between healthcare systems.”

Regenstrief is not the first to take on the patient ID conundrum. Industry associations including AHIMA, CHIME and HIMSS have worked toward solutions. 

Recommendations on how to solve the patient identification problem have been proposed in the past, but they haven't been backed up by evidence, according to Grannis.

[Also: Health Catalyst, Regenstrief partner to commercialize natural language processing technology]

Linking patient information to the correct patient is complex for many reasons including similar "looking" patients. Many surnames are common, for example, and one in 20 Americans have the last name Smith, Johnson, Williams, Jones, Brown, Davis, Miller or Wilson.

Then, there are typographical errors, missing information, such as middle name or date of birth, and potentially identity theft. Also adding to the patient identity management problem are differing formats used by individual healthcare systems to electronically share data. 

[Also: Regenstrief scientist extols open source tool for consolidating patient data from multiple medical records]

"Before you can gather clinical data, you must know exactly which patient you are talking about," he said. "Our work will help electronic medical record systems better and more accurately bring together a patient's information.”

Twitter: @Bernie_HITN
Email the writer: bernie.monegain@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

CHICAGO -- As hospitals and health systems leverage information technology, healthcare executives must advocate for caregivers to improve provider satisfaction, be prepared for a telehealth explosion, embrace machine learning and artificial intelligence, incorporate the Internet of Things, and prepare for more cyber-attacks, said Thomas Zenty, CEO of University Hospitals of Cleveland.

Zenty delivered today’s keynote address at Allscripts Client Experience, the EHR vendor’s user conference here. 

The wellness of providers, the degree to which they are satisfied with their jobs, is key to operating a hospital or health system. 

“Physician satisfaction is at an all-time low,” Zenty said. “The things we now have to do with our EHRs. We have to do more work at home than ever before. The promises of efficiencies and effectiveness and time savings are not being realized. So we have to advocate for our caregivers. Do everything we can for those physicians and other caregivers.”

Collection, aggregation and interpretation of data is critically important, Zenty added. But provider wellness cannot be overlooked. “We can’t just assume because we have an EHR it’s going to be automatically adopted,” he said.

Telemedicine is an area of health IT that has been around for quite some time, and is starting to see a growth spurt. More providers are embracing the technology and more insurers are paying for telehealth services.

“Tele-, virtual-, digital health, are things critically important to the work we are doing,” Zenty said. “History will prove me right on that. And policy follows money. Once we begin to get paid for telehealth, tele-psychiatry, tele-stroke, we will see an explosion in this part of information technology.”

Machine learning and artificial intelligence are other technologies that are sparking interest in healthcare. They enable computers to handle greater amounts of work than human beings can undertake and will become increasingly important in the era of consumerization. 

“We’re in the early stage of a big wave,” he said. “How do we answer phones, how do we engage people through digital means with ML and AI will be so critical to the work we do. We know through best performances what people will need to be doing to serve patients, and the more accurate we can be with AI will be important.”

Zenty added that it’s only a matter of time before voice technologies like Siri and Alexa will play a role in hospitals.

The Internet of Things is another area healthcare executives must prepare for. Zenty said in 2015 there were 15 billion installed things on the IoT, and that in the next five years the number of devices on the IoT will grow to 51 billion.

“When we think about the number of things, this will be critically important to the work we do,” he said. “It’s far more than just remote monitoring. We can expect this will be a major growth area.”

And with the IoT comes more cybersecurity issues. The threat level is high already. Imagine what will happen with 51 billion connected devices.

“We all have read about ransomware, we read about it all the time, that is only going to increase,” Zenty said. “Think about ransomware in the context of the Internet of Things. If we have 51 billion things, people will be able to access our systems. We are going to be a bigger target than ever before.”

Twitter: @SiwickiHealthIT
Email the writer: bill.siwicki@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

Wolters Kluwer Health is integrating its ProVation Order Sets with Epic software, in a move that aims to help hospitals streamline workflows for information governance and improve clinical decision support.

"Integration has taken on greater importance as the healthcare industry continues its evolution toward quality- and value-based care," said David Del Toro, president and CEO of Clinical Software Solutions at Wolters Kluwer. 

The integration uses new order set import functionality to enable more seamless transfer of Wolters Kluwer's Panels, Smart Groups and SmartSets between systems, allowing clinicians to import order sets from Epic into ProVation, and also export them directly to Epic.

[Also: Mayo Clinic kicks off massive Epic EHR go-live]

That functionality will help hospitals with clinical content management and order set governance, preserving the details of orders from the electronic health record to support consistent terminology and structure across the care setting, officials said. This bidirectional information exchange can help hospitals broaden their evidence-based practices for clinical quality improvement.

“Having worked with ProVation Order Sets in the past, we recognized right away how beneficial integration with our new Epic EHR would be,” said Brian Churchill, director of clinical content and decision support at PeaceHealth, a 10-hospital health system operating across the Pacific Northwest.

Churchill added that one of the big benefits will be an electronic repository of order sets that resides outside the EHR and can be available even during EHR downtime. 

"Additionally, utilizing the extract process of Epic to ProVation significantly decreases that effort,” Churchill added. “Our order set governance involves 24 different cross-disciplinary and cross-specialty stakeholder review boards, so streamlining and automating order set review, updates, approval and deployment will make our content teams more efficient.
 

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

More underserved patients could soon benefit from expanded access to specialists, as several top medical societies pledged a long-term partnership with the Human Diagnosis Project, which plans to scale up to close gaps in care for as many as 30 million Americans.

The Human Diagnosis Project, or Human Dx, is an open, online platform that deploys machine learning algorithms to help providers to find specialty treatment for their patients, connecting them with curated expertise from other physicians worldwide.

The system enables primary care docs at smaller or remote practices to tap into that collected wisdom and gain access to tests, opinions or diagnoses that they wouldn't have otherwise.

[Register Now: Upcoming HIMSS Pop Health Forum]

Along with the American Medical Association – which will encourage its vast physician membership to volunteer on the Human Dx project – other groups have also signed on to support the initiative, including the American Board of Internal Medicine, American Board of Medical Specialties, Association of American Medical Colleges, Association of Clinicians for the Underserved, National Association of Community Health Centers and the Dartmouth Institute for Health Policy and Clinical Practice.

"We look forward to working with Human Dx as part of this important Alliance to help more uninsured and underinsured patients gain access to the specialty care they need," said AMA President David O. Barbe, MD.

[Also: Big wave of artificial intelligence and machine learning coming to healthcare, University Hospitals of Cleveland CEO says]

Human Dx also has ongoing research collaborations with Harvard Medical School, Johns Hopkins University School of Medicine and UC San Francisco Medical Center.

That broad commitment will help the Human Dx Alliance grow over the next five years, expanding the system to help connect the safety net population with specialty care more urban patients might take for granted. In the years ahead, the hope is to expand Human Dx globally, said its founder, Jayanth Komarneni.

"Millions in this country and more than a billion people worldwide lack access to the health care they need, so they choose between paying for it themselves and being forced into poverty, or not getting it and becoming sicker or dying as a result," said Komarneni. "Thousands of doctors from over 70 countries are tired of this and have come together to build a solution. By contributing to Human Dx doctors will expand access to help people get the care they need, beginning with the underserved: first here in America, and ultimately worldwide."

Closing gaps in care

Uninsured safety net patients at the 1,300 or so community health centers and free clinics in the U.S. are able get basic medical treatment, but don't have timely and affordable access to specialists such as cardiologists or oncologists. Gaining access to their expertise requires long waits and large out-of-pocket costs.

But sometimes getting the right care doesn't depend on expansive and expensive treatment, just the right expertise at the right time. By amassing specialists' medical knowledge in an open and widely accessible system, technology can help deliver that, according to Komarneni.

Human Dx enables doctors get electronic consults for their patients, accessing targeted knowledge from specialists. A primary care doc can just log a patient's background and medical findings into the platform, which are then posted for specialists around the world to review and offer recommendations for tests or diagnoses.

"Generally, doctors can diagnose better than computers. But doctors supported by technology like the Human Dx system could help improve the accuracy of clinical decisions across the board," said David Bates, MD, professor of health policy and management at Harvard's T.H. Chan School of Public Health.

The system is built upon the insights, amassed over the past three years, of more than 6,000 physicians – representing more than 40 medical specialties – at more than 500 institutions in some 70 countries, according to Human Dx.

It uses machine learning tools to analyze that specialist input – in tandem with patient's symptoms, exam results, medical history, imaging, labs and more – to help the physician make a more informed decision.

Eventually, the platform will also help with more precision treatment, incorporating genomics, epigenomics, proteomics, published medical research and more.

Margaret Nora, MD, president and CEO of American Board of Medical Specialties, which oversees U.S. physician specialty certification, recognizes that a gap exists for vulnerable populations with regard to specialty care. "Human Dx has the potential to improve the health and wellbeing of patients in this country, and ultimately across the globe," she said.

"Clinical reasoning is a fundamental skill for doctors," said Sanjay Desai, MD, director of the Osler Medical Training Program at the Johns Hopkins School of Medicine. "However, we have no current method for measuring this skill aside from using a combination of the subjective opinions of more senior doctors and surrogate markers such as exams. Human Dx is the first tool I have seen that begins to address this unmet need."

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

HIMSS Analytics has expanded its LOGIC platform to include international data, broadening its scope to include information on the purchasing decisions of some 380,000 healthcare providers in nearly four dozen countries across the globe.

LOGIC already offers complete coverage of the approximately 5500 hospitals in the U.S. The unveiling of LOGIC International Intelligence on August 10 means vendors can gain new insights by mining health information technology market data for facilities in Europe, Asia Pacific, the Middle East and Latin America.

[Also: HIMSS Analytics launches LOGIC Google Chrome extension]

"International Intelligence not only helps to identify these potential growth areas, but also provides insight on how to best approach different markets," said Miranda Ladue, vice president, operations at HIMSS Analytics.

The expanded platform enables company researchers to explore the demographic and technological makeup of specific locations worldwide; gain insights into market share for specific IT vendors across regions; learn about HIMSS Analytics Stage 6 and 7 EMRAM organizations in the U.S. and abroad, and see specific organizations' demographic and installation data.

[Also: Learn more about the HIMSS Analytics LOGIC insights]

"Now our clients can better understand the global healthcare landscape, and identify new market opportunities for investment and expansion of their product portfolio," said Ladue.

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

Amazon appears to have put its plans to join the healthcare market on the fast track.

On the heels of creating a stealth team to focus on opportunities in the healthcare IT market, the e-commerce giant, now could be positioning itself to take the leap into pharma.

Investment banking firm Goldman Sachs is out with a new report indicating some preparations on the part of Amazon to seek a pharmacy partner as an initial step, reported first by CNBC.

[Also: Wait! What? Amazon and Apple eye building EHRs]

The Goldman Sachs report compiled by five analysts, suggests that Amazon could move its way into healthcare by first partnering with a pharmacy benefits manager, which is a third-party administrator of prescription drug programs.

The move might open up new opportunities for Amazon to cross-sell, according to the report.

In recent weeks, both Amazon and Apple have indicated a more than passing interest in a healthcare play, with explorations including EHRs and telemedicine. To date, the reports are based on unnamed sources.

Another scenario put forth by Goldman Sachs considers Amazon’s potential to speed up the drug delivery process – and home delivery. It would not be unlike what Amazon did with books – and the other products available on its website. Also, Amazon could build its own online pharmacy.

The ecommerce giant also has other pathways to the healthcare industry. It could move its Echo/Alexa into the clinical realm and build or buy telemedicine and remote patient monitoring technology, Goldman Sachs notes.

“There are really large companies in the tech world that are driving really significant growth,” David Solomon, president and co-chief operating officer of Goldman Sachs, notes in a video on the investment bank’s website.

Amazon grew 27 percent on $130 billion in revenue in 2016, Solomon said.

One-fifth of the S&P 500 constituents referenced Amazon on quarterly earnings calls in the past 90 days, according to investment research company Seeking Alpha, which added: “The scope and scale of the companies and industries referencing Amazon show the tremendous competitive reach of the e-commerce giant.”

Twitter: @Bernie_HITN
Email the writer: bernie.monegain@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

As HL7's FHIR standard continues to catch on across healthcare, there are ways it can be leveraged to work in tandem with the Direct protocol for better information exchange, a new report from DirectTrust shows.

Hospitals and medical practices could make progress in their interoperability initiatives by availing themselves of both approaches, according to the report, coauthored by DirectTrust CEO David Kibbe, MD, members of the DirectTrust Policy Committee and FHIR architect Grahame Grieve of HL7.

The two approaches are different, but offer synergies that bear exploration. FHIR is a standards framework created by HL7; Direct is an exchange network for easy and exchange of personal health information between providers and between provider and patients.

[Also: DirectTrust touts nearly 100,000 provider users]

The white paper, "Direct, DirectTrust, and FHIR: A Value Proposition," explores different ways  FHIR's web APIs can complement the Direct standard for more seamlessly exchanging healthcare data.

"The FHIR community’s current focus is 'perimeter interoperability' – that is, exchange of data outside the institution, either with patients/consumer directly, or between institutions," according to the report. "In the USA, most of the focus around FHIR has been consumer to business (C2B) rather than business to business (B2B). This focus is because institutions have their internal integrations and some external exchanges already in place, whereas C2B is where immediate value can be extracted and may lead to a marketplace for apps."

[Also: FHIR holds big promise for interoperability, but will need to coexist with other standards for the foreseeable future]

Meanwhile, "the primary use of the Direct protocol is for exchanging data between clinicians and support staff in institutions," the authors said. "Today, as a result of the meaningful use Program, Direct is commonly used to carry C-CDA formatted data between many institutions using version R2.1 of the C-CDA. There were over 98 million such exchanges via Direct in the DirectTrust network during 2016, and approximately 150 million transactions are expected in 2017."

Despite those very different origins and uses, however, there's big potential for harnessing the two specs together, especially across the DirectTrust network, which expect to host 150 million transitions in 2017.

"There is a perceived conflict between the current use and growth of Direct and the future use of FHIR," according to the study, "even though Direct is content agnostic, and FHIR as a resource is transport agnostic."

There are challenges to making the two standards work together – but also, potentially, big advantages.

There are two primary avenues through which Direct/DirectTrust and FHIR could work well together, the study shows. 1) FHIR resources can be pushed in Direct Messages; 2) DirectTrust framework and certificates can support FHIR’s RESTful API

The first approach could be most in cases where "each exchange information flow is unidirectional, and a Direct- based trust network like that of DirectTrust exists between the source and destination (i.e. the source knows how to deliver to the destination). Where these conditions exist, using Direct to send messages saves implementers from recreating the same distribution management system, such as certificate and policy frameworks and trust agreements."

The second strategy holds promise in that "existing work in the FHIR eco-system does not deal with establishing trust between systems," according to the white paper. "To authenticate system-to-system communication, some trust framework will be needed – either point to point agreement about certificates and other security tokens, or some mediated trust community will need to provide a framework in which these are managed. The DirectTrust community could serve this role – this would enable the 100,000+ existing DirectTrust enabled institutions and 1.5 million identity proofed addressess at those institutions to allow connections between each other without the need for point-to-point agreements."

Much more work remains to be done, and the report emphasizes the need for the DirectTrust and the FHIR communities find ways to build engagement to iron out how the technical specifications can better relate to each other and explore the implications for real-world use cases.

"Collaboration is key to getting the best out of standards," said Kibbe. "We should take every opportunity to combine the strengths of different interoperability standards, so that they enrich and support each other," said Kibbe. "No single standard, either for transport, or for content, or for trust in identity, can do everything that is needed by providers and patients wanting to securely share and exchange health information using various tools and technologies," he added.

"The existing work in the FHIR ecosystem does not standardize all aspects of establishing trust between systems,” said Grieve. "While FHIR offers SMART-on-FHIR as a way to delegate authorization, underlying trust frameworks are needed to provide a framework in which these are managed. Working with DirectTrust could potentially save the FHIR community from the costs of building a new trust framework by using one already proven to scale high identity assurance."

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

MIT Medical will install a Cerner Millennium EHR as well as the company’s integrated financial and population health management technology, the provider announced Tuesday.

MIT Medical is an ambulatory care center that serves more than 25,000 members of MIT, including students, faculty, employees, retirees and families. It operates two locations in Massachusetts – in Cambridge and Lexington.

The technology will help care providers, frontline staff and the business office improve efficiency, which will in turn boost care, said Cecilia Stuopis, MD, medical director at MIT Medical.

[Join Your Peers at HIMSS' Pop Health Forum! Register Today]

The system will also connect electronically to other healthcare institutions, Shelagh Joyce MIT Medical’s director of information services, said in a statement. Moreover, the Cerner platform makes it possible for MIT Medical to store data on one integrated database.

“One of the most compelling things about Cerner is that their own clinicians use the software they develop,” said Joyce. “It’s very unique to find a technology provider with that kind of front-line healthcare experience.”

[Also: Carolinas HealthCare adds Cerner for population health platform]

Part of the technology package at MIT Medical includes a patient portal to connect patients with the hospital and physician practices.

MIT Medical also plans to launch video visits for some types of care.

Cerner President Zane Burke said the technology will not only support MIT Medical’s clinical processes and make patient health management easier, but it will also help clinicians provide value-based care.

On the population health management front, Cerner’s HealtheIntent platform aggregates and normalizes data from various sources in near real-time, providing clinicians data they need to identify locate gaps in care.

HealtheIntent is also engineered to engage patients beyond the hospital setting and help providers manage outcomes, to improve the overall health of the community. The technology creates a single, comprehensive view of an individual’s experiences.

Twitter: @Bernie_HITN
Email the writer: bernie.monegain@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

As Amazon's Alexa makes "herself" comfortable in more and more homes, she and similar artificial intelligence technologies could soon be having an impact on hospitals.

AI-based virtual assistants are evolving quickly, and more and more effort is being put into making them emotionally intelligent – able to pick up on subtle cues in speech, inflection or gesture to assess a person's mood and feelings.

The ways that could impact wellness and healthcare are intriguing. By reading into vocal tone, AI platforms could perhaps detect depression, or potentially even underlying chronic conditions such as heart disease.

[Also: Healthcare AI poised for explosive growth, big cost savings]

For example, a Tel Aviv-based startup called Beyond Verbal is working on analytics tools that could work with Alexa et al. to gain insight into behavioral and vocal patterns.

"In the not so far future, our aim is to add vocal biomarker analysis to our feature set enabling virtual private assistants to analyze your voice for specific health conditions," said the company's CEO Yuval Mor in June.

In the nearer term, hospitals looking to realize the benefits of AI and EI need to think hard about where and how they'll deploy the technology as it continues to mature, said Anthony Chambers, director in the life sciences practice at Chicago-based consultancy West Monroe Partners.

[Also: As AI spreads through healthcare, ethical questions arise]

The use cases for AI in healthcare are many and varied. Voice-enabled virtual assistants can help clinicians access notes or let surgeons see safety checklists. They can help with staff handle coding and transcription chores. Smart deployments of the technology hold the potential for big gains in hospital efficiency.

"Hospitals have realized they're sitting on mounds of data," said Chambers. "The past few years, they've been starting to take the next steps with narrative science, natural language generation and other machine learning technologies to give them a competitive advantage. We're seeing our clients make a lot of progress on identifying and predicting where efficiencies could be found in the patient care journey."

Lots of hospitals are now using AI and machine learning to "predict where issues are: where they can the get higher throughput, where they can see more efficiency in their care management," he said. "They can measure in real-time how they're doing, how can they gauge capacity, where is the slack in the system."

But in the years ahead it may be patients themselves who could be spending the most time with the AI platforms – and that's where emotional intelligence begins to take on more importance.

"What gets really fascinating – we have yet to see it, but we're seeing discussions of it – is potential uses around the quality of care," said Chambers. "That remains an untapped potential where the promise of emotional intelligence, in combination with AI, could play out."

Hospitals and pharmaceutical companies are starting to explore how the platforms could help clinical trial management, for example: "We already know of one client that is doing a proof of concept to support clinical trials, at the intersection point between provider and pharma," he said.

Natural language processing tools could help with gathering data and predicting outcomes, "giving almost real-time feedback to the physician and the drug company at the same time," said Chambers.

That's especially useful given how stress clinical trials can be on the patient. Offering a less intrusive way to communicate results to both provider and drug company could be a boon.

"If we could use an interactive bot, where the patient then has a point of conversation via smartphone or something, that could be a game changer because of the challenge of clinical trials being so stressful on the population, and the expense of running the trials," he said.

Chambers said he's also seeing more and more providers starting to "dip their toes into automating the bookends of the patient journey" – intake and discharge.

"Being able to potentially monitor the intake with a human in the room, but also an Alexa-type unit listening to the conversation and also hearing the stress or anger or fear in a patient's voice, that may throw up real-time prompts that the human can then put forward," he said. "That use case has been kicked around, a way to support the intake process.

"Think about facial expressions, gestures, pace and tenor of speech," he added. "If you factor those pieces into what a chatbot or robot or other interaction point with a human, that becomes an indicator or piece of data that artificial intelligence and big data algorithms could use to assess outcomes."

As hospitals increasingly look to forward-leaning implementations such as these, there are some important questions CIOs and other IT professionals should be keeping in mind, said Chambers.

For those organizations looking to use AI and EI to help with customer experience or quality of care efforts, "I think the first question hospitals or clinicians are going to have to decide is how will it support that care journey," he said.

Will it displace human interaction, or just augment it? And if it does displace it, where is it going to support the patient, and how are you going to use that communication?

"Because you really are changing the paradigm, potentially, of how you're going to interact with the patient," said Chambers. "Where on the patient journey do you see a need?"

Assuming those questions are ironed out and the implementation is complete, there another important thing to consider, he said: "What are you going to do with that data? It's patient-level data, it's real-time. Does that get then folded into an electronic health record? Do you tag it with social media? Does claims data use it? How does it get integrated?

The issue of privacy alone "is a little daunting," said Chambers. "How do you manage a patient's emotional quotient? I don't know. These are problems we're grappling with. But hospitals and healthcare companies have an opportunity to lead in this space."

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Like Healthcare IT News on Facebook and LinkedIn

EHR dissatisfaction is rampant. Doctors complain about too many clicks and unusable interfaces, to name just two common gripes. Health IT pros and clinicians hear and read about these problems a lot. But the other side of the story -- physicians who say the EHR makes them better doctors -- is less-often told. 

“Yes, I love the EHR I use,” said James Legan, MD. 

Legan, an internal medicine physician in Great Falls, Montana, who credits the EHR for helping him to practice medicine more effectively, is not alone. Medical Group Management Association CEO Halee Fischer-Wright, MD, while perhaps less exuberant than Legan, said EHRs have considerable promise in the practice of medicine. And then there’s Jeffrey Cleveland, MD, a pediatrician at Carolinas HealthCare System.

[Also: Patients frustrated by lack of EHR data interoperability, Surescripts finds]

Cleveland even went so far as to say that implementing Cerner had an immediate and positive impact on his ability to care for patients. 

“I was a better doctor overnight,” Cleveland said. “Absolutely. There’s no question in my mind. I was a better doctor in March 2008 than I was in February of 2008 – because I instantly had data.” 

Jeffrey Cleveland, MD, a pediatrician at Carolinas HealthCare System

How EHR love came to Carolinas

When Cleveland started practicing medicine in 1994 at Charlotte Pediatrics Clinic in Matthews, North Carolina, there was no EHR system, and there wouldn’t be one for another 14 years.

The clinic is part of the sprawling Carolinas HealthCare System, which today operates 900 care locations in North Carolina and South Carolina.

The work of getting the health system’s Cerner EHR up and running started in 2008. Cleveland was part of the informatics team that helped launch the EHR in ambulatory clinics first, and later in acute care facilities.

[Also: Study: Two-thirds of hospitals bulk up staff to boost clinician EHR adoption]

Since then, he has become a champion of EHRs, working to help other physicians get the most out of the technology. Perhaps it’s payback of sorts for what, by his own account, the EHR has done for him – and his patients.

Cleveland paints a typical scenario he encounters.

He sees children who’ve been in the newborn intensive care nursery for two months – because they were born prematurely at 26-week gestation. They’ve been discharged on Monday, and he’s seeing them on Wednesday.

“I’ve got a two-month hospital stay that I can actually go back and look at,” Cleveland said. “All the problems are neatly categorized in a problem list. All the meds are in front of me. All the procedures are right there tabulated in one place, That’s a goldmine.”

These days, after having the EHR in place for a decade, the efforts at Carolinas HealthCare are all about optimization, better integration of tools in clinician workflow.

“One of the things I love about our EMR,” Cleveland said, “is that in the decade since we started using it, a lot of the vendors have come up with a mobile solution.”

Cleveland uses Cerner’s Power Chart Touch. It’s a mobile version of the electronic health record, which is available on Cleveland’s phone or on his iPad, and it helps him to be more productive and better engages his patients, he said. 

A screensnap of Amazing Charts EHR interface.

EHRs a boon to patients, too

EHRs are not just popular among doctors at large tech-savvy hospitals. 

In Montana, for instance, when Legan transitioned to the cloud-based Amazing Charts EHR and later added CRM from Updox, “it got even better,” he said. He now counts e-prescribing and e-faxing as vital.
 
Legan added that the technology enables quick coding after each patient visit. It’s easy to provide and easy to read. It’s much more effective than trying to find the information on the old paper superbill. 

“I couldn’t do any of this,” he said “if I had not transitioned from paper to EHR-CRM.” 

But the biggest benefit is the ability to display the patient’s record on a large screen, which Legan pointed out is an effective way to engage and coach patients at the point of care.

“Clinicians, who have figured out how to use their EHRs to build strong relationships and leverage data from their systems that intelligently inform their decision making, are role modeling the highest and best use of EHRs in a clinical setting," MGMA’s Fischer-Wright said. “Physicians who love their EHRs are those who have worked hard to make their EHRs work for them.” 

Twitter: @Bernie_HITN
Email the writer: bernie.monegain@himssmedia.com

Two new studies from MIT's Computer Science and Artificial Intelligence Laboratory shed light on ways machine learning can improve electronic health records and predictive analytics to help physicians make more informed decisions.

As doctors grapple with a profusion data across multiple systems, with charts documented in varying degrees of consistency, the challenges of putting it all to use for real-time decision-making is acute.

Teams at CSAIL have tackled a pair of projects they say could help make EHRs work better for hospital clinicians. Both models were made possible by MIMIC, an open dataset developed by the MIT Lab for Computational Physiology that has deidentified health data for 40,000 critical care patients.

[Also: MIT Medical picks Cerner for EHR, population health]

One project uses machine-learning for an approach called "ICU Intervene," which processes troves of data from the intensive-care-unit and applies deep learning processes to sift through lab results, vitals demographic information and more to help physicians make real-time predictions.

"The system could potentially be an aid for doctors in the ICU, which is a high-stress, high-demand environment," said MIT PhD student Harini Suresh, the paper's lead author. "The goal is to leverage data from medical records to improve health care and predict actionable interventions."

ICU Intervene offers hourly predictions of five different interventions that cover a wide variety of critical care needs, such as breathing assistance, improving cardiovascular function, lowering blood pressure, and fluid therapy, according to the report. The data are represented with values that indicate how far off a patient is from the average.

"Much of the previous work in clinical decision-making has focused on outcomes such as mortality, while this work predicts actionable treatments," said Suresh. "In addition, the system is able to use a single model to predict many outcomes."

Going forward, MIT researchers plan to improve ICU Intervene to offer more individualized care and give more advanced reasoning for its decisionmaking.

A second approach, called "EHR Model Transfer" looks to facilitate the deployment of predictive models across different platforms. Researchers showed that such models can be "trained" on one EHR system and used to make predictions in another.

Most existing machine-learning models need data to be encoded in a consistent way, researchers point out; the fact that hospitals often switch EHR systems can mean problems for predictive analytics. The EHR Model Transfer approach uses natural language processing technology to identify clinical concepts that are encoded differently across systems and then mapping them to a common set of clinical concepts, enabling analytics to works across different versions of EHR platforms.

"Machine-learning models in health care often suffer from low external validity, and poor portability across sites,” said Shah. “The authors devise a nifty strategy for using prior knowledge in medical ontologies to derive a shared representation across two sites that allows models trained at one site to perform well at another site. I am excited to see such creative use of codified medical knowledge in improving portability of predictive models."

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

San Diego-based electronic health record vendor CliniComp has filed a bid protest with the U.S. Court of Federal Claims against the Department of Veterans Affairs for allegedly awarding Cerner a contract for its new EHR without conducting a competitive bidding process.

CliniComp has provided EHR systems to the U.S. Department of Defense and some VA hospitals since 2009. However, VA Secretary David Shulkin announced in June that the VA would award Cerner a sole contract to replace its legacy VistA EHR system with a Cerner EHR.

[Also: How Jared Kushner helped the VA pick Cerner... quickly]

CliniComp said it filed an agency-level protest to contest the sole source award shortly after the announcement, according to the complaint. But the VA Deputy Assistant Secretary for Acquisition denied the protest on Aug. 7. In doing so, the VA violated the Competition in Contracting Act of 1978, the company claims.

Shulkin has told Congress that the price for the EHR has not yet been negotiated. And 
CliniComp alleges that this timeframe could be used to open up competition among other vendors. Competitive bidding can also reduce costs associated with an EHR implementation.

“As shown by the nine counts set forth below, the VA’s decision to award a sole-source contract to Cerner is arbitrary, capricious, an abuse of discretion and violates the CICA and Federal Acquisition Regulations,” according to the suit.

[Also: Pew calls on VA to ensure interoperability, patient matching with Cerner EHR]

The VA has been pressed by Congress for many years to replace its outdated system with a modernized, off-the-shelf EHR. Shulkin said in the spring the VA would make its decision about its legacy system in July -- but made the announcement a month earlier.

In making the announcement, Shulkin said the agency “does not have sufficient time to allow for full and open competition.”

CliniComp said this statement “lacks a reasonable basis.”

“In the six to eight months to negotiate a sole source contract with Cerner, the VA could hold an accelerated full and open competition for the next generation of EHR,” the company claimed.

Officials from CliniComp and the VA were not immediately available for comment.

Twitter: @JessieFDavis
Email the writer: jessica.davis@himssmedia.com

The Massachusetts eHealth Institute (MeHI) at MassTech has awarded nearly $200,000 to four electronic health record vendors to build pathways for Massachusetts behavioral health providers to electronically submit reportable data to the Commonwealth’s Children’s Behavioral Health Initiative.

The EHR vendors and their grants include: eHana, $54,000; Netsmart Technologies, $54,000; PsyTech Solutions, $31,000; and Qualifacts Systems, $54,000.

The grants come from an open procurement process under MeHI’s Children’s Behavioral Health Initiative Child and Adolescent Needs and Strengths Interface Development Grant Program. They incentivize the four vendors to build new electronic interfaces and connect 12 Massachusetts behavioral health providers, allowing the providers to efficiently submit Children’s Behavioral Health Initiative reports, replacing a manual process for the roughly 40,000 reports they submit to the Commonwealth annually.

[Also: Imprivata joins CommonWell Health Alliance to push interoperability]

“These awards continue MeHI’s focus on improving access and use of technology to help behavioral health practices across Massachusetts,” said Laurance Stuntz, MeHI’s director. “Child and Adolescent Needs and Strengths reports are an important tool to help manage care for some of the state’s most vulnerable children, but the manual process took valuable provider time and distracted from patient care.”

These investments will help automate much of the reporting process, enabling providers to conserve hundreds of staff hours each month and stay focused on patient care rather than data entry, Stuntz added.

[Also: Using both Direct and FHIR standards could improve data exchange]

The grant program stemmed from stakeholder meetings sponsored by MeHI that identified inefficiencies in the workflows at behavioral health providers and recognized the role technology could play in alleviating the issue.

Based on that input, MeHI developed and launched a request for proposals in October of 2016 seeking EHR vendors that work with Massachusetts behavioral health providers to develop a new Child and Adolescent Needs and Strengths HL7 interface that will extract the child and adolescent needs and strengths data from an organization’s EHR system, compile the data according to program specifications, and then automatically submit it to the Commonwealth’s Children’s Behavioral Health Initiative Child and Adolescent Needs and Strengths system through the Mass HIway.

The Children’s Behavioral Health Initiative system is a court-mandated program in Massachusetts that requires clinicians providing behavioral health services to children under the age of 21 to submit critical patient data so that the state can accurately assess the needs of this patient population. The mission is to ensure that children under the MassHealth system who have significant behavioral, emotional and mental health needs receive the services they need to ensure success at home, school, in the community and throughout their everyday life.

Twitter: @SiwickiHealthIT
Email the writer: bill.siwicki@himssmedia.com

The most sophisticated analytics programs in the world won't matter for much if health systems staffs don't use them, or don't use them well. Technology is important, but integrating it into clinical workflows – while also fostering an enterprise-wide appreciation of data-driven decision making – is essential to making data tools work for better population health.

Des Moines, Iowa-based UnityPoint Health has gained some experience in recent years in the right way to putting analytics to work. With a keen focus on encouraging a culture that embraces the value of data, and keeping attuned to the unique needs of various stakeholders, the health system managed achieved a 40 percent reduction in its risk-adjusted readmission index over three years at a pilot hospital.

Those wins have encouraged the health system to continue building out a more comprehensive care coordination initiative for readmissions reduction, fueled by descriptive and predictive analytics that have been integrated into care teams' daily workflows.

[Join Your Peers at HIMSS' Pop Health Forum! Register Today]

First things first: "We really believe it's about being practical and choosing the right use cases," said Rhiannon Harms, UnityPoint's executive director of strategic analytics. "We don't want to build models that sit on the shelf, or later realize no one is using them. We keep those people who use the tools top-of-mind, so we can build things that will actually help them drive results."

"Industry-wide, for the past three or so years, healthcare has focused so much on getting the technology right, to the point where we can gather the data, do the modeling, deploy it," added Ben Cleveland, data scientist at UnityPoint Health. "Now it feels like we're shifting away from that and getting to a point where it can be useful."

[Also: Healthcare leaders: Predictive analytics will save health systems millions]

Readmissions is an obvious place to start.

"Most folks will land on it pretty quickly due to the financial incentive involved, but it's a really rich use case for a number of reasons," said Cleveland.

"It really spans the whole care continuum," he explained. "Think of a patient going to a hospital and getting treated there, having to coordinate the follow-up care planned for their discharge once they leave the hospital, How do you facilitate that hand-off to post-acute caregivers? What information do those folks need to keep them out of the hospital? It turns into a multi-faceted problem that has decision points throughout the patient's timeline and trajectory."

At UnityPoint, the goal was to take a more holistic and forward thinking view of readmission risk, he said – moving beyond just identifying the patients most in need of more targeted interventions, but instead asking, "OK, given their high risk, now what should we do? How can we use analytics to inform the intervention after they leave? How can we assess the likelihood of success for those interventions?"

Rather than just calculating the overall risk for 30-day readmission, the analytics team at UnityPoint also tried to assess risk for every day along that 30-day post-discharge continuum.

"What we found is that some patients were at much greater risk of coming back early on after their stay, and then others tended to be more at risk later on in that 30-day timeline," said Cleveland. "Maybe their problems would compound over time, or they would miss their follow-up appointments, or they wouldn't follow directions for medication.

"So we developed a risk heat map over that 30-day timeline that visually depicts a patient's risk very quickly," he said. "You don't have to be a data scientist to interpret the output you're looking at, you can look at it quickly. For every patient we have they have their own individualized heat map that our care teams are working off of."

The program allows care teams to easily see who's at high risk for readmission. But even more importantly, forearmed with the knowledge of where on that 30-day continuum they're most at risk, it helps them know when to schedule interventions in the "heat zones" most applicable to the patient.

Another innovation was a freestanding no-show appointment model, said Cleveland.

"We incorporated it into this tool, and now what we can do is, if clinicians and care teams decide to schedule follow-ups, we'll actually compute the no-show risk," he said. "So you've identified their readmission risk over time, you've planned two follow-up appointments with their PCP – but it turns out they have a high risk of not showing up for those, so you have to augment your strategy a little more to ensure interventions actually happen."

Finally on the hospital side, "we also have a freestanding length-of-stay model that predicts how long a patient will be in the hospital," said Cleveland. "This helps folks with discharge planning, to do resource allocation. We've incorporated that into the tool."

All told, for every patient in the hospital – and for the 30 days after they're discharged – UnityPoint has "four models firing and providing individualized risk assessments in a variety of different avenues," he said.

That's hugely useful, of course, but not exactly a piece of cake to put into practice. So careful attention to care teams and clinical staff – with clear instruction about how to use the tools and clear explanation of their value – has been important to the initiative's success.

"In general, predictive analytics is pretty new to healthcare over the past few years," said Harms. "We recognize that there's training and education we need to provide as analytics professionals to our clinical and business leaders on how to use predictive analytics. It's a different way of approaching the problem than looking in the rear-view mirror with descriptive analytics. We've really tried to do some proactive work on the analytics competency and training piece.

"We've really tried to focus in on the use case and working to be a partner to our clinical and business leaders, to enable them to drive better results," she added. "It is for us about developing better solutions with the end workflow and end result in mind, and doing that in partnership with those who provide care to our patients."

Harms and Cleveland will offer a more detailed description of their predictive analytics strategies  at the HIMSS Pop Health Forum, October 2-3 in Chicago.

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

As the opioid national emergency continues, Intermountain Healthcare is promising to reduce the number of hydrocodone, oxycodone and other opioids dispensed by its 22 hospitals and 180 clinics by 40 percent by the end of 2018.

Currently, the Salt Lake City-based health system prescribes more than 5 million opioid tablets each year. As it works to get that number down to 3 million or fewer, it's rolling out an array of news policies to help its clinicians think harder about what they're giving their patients, and how many – if any – opioid pills they really need.

Intermountain has trained 2,500 of its caregivers about potential alternatives to opioids, and plans to expand its education programs across the health system.

[Also: National e-prescribing bill gains support as Trump declares opioid state of emergency]

It's also making changes to its Cerner electronic health record system to help nudge prescribers toward fewer opioid prescriptions, building in new prompts and default order sets for decision support.

"Nationwide, providers tend to write prescriptions for more opioids than patients need, and large quantities of the medications are often left over after the need for pain relief is past," said Doug Smith, MD, Intermountain's associate medical director, in a statement. "We will follow best practices in prescribing so the medications prescribed more closely match the needs of patients.”.

Smith emphasized that patients with acute or chronic pain "will still be able to get the medications they need. We will ensure patients have access to the full range of options to manage pain."

Intermountain bills itself as the first health system to pledge opioid reductions with such specificity. In addition to its efforts on the clinical side, it is also a partner on other initiatives, such as collaboration with the Utah Department of Health and other groups to provide extensive provider and patient education.

The health system's community pharmacies have also installed secure medication disposal drop boxes for unused medications – which have been filled with more than 15,000 pounds of unused medications since 2015.

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Officials from Allscripts, Cerner, Epic and two dozen other electronic health record vendors called for timeliness and clarity on requirements for MACRA’s Quality Payment Program in comments submitted to federal agencies on Wednesday.

The members of the HIMSS Electronic Health Record Association submitted the comments this to the Centers for Medicare and Medicaid Services and the Office of the National Coordinator for Health Information Technology on two crucial proposed rules: MACRA and the Trusted Exchange Framework provision in the 21st Century Cures Act.

In the first letter to CMS Administrator Seema Verma, the 30-member group thanked CMS for involving providers in the design of MACRA, and for the flexibility it has promised in various aspects of the QPP.

[Also: House budget backs Trump's drastic cuts to ONC]

But it expressed concern that "repeated delays in program implementation timelines, as we have seen over several regulatory cycles, as well as a continued lack of clarity around requirements" could discourage provider groups from adequately preparing for the performance improvements required under the Merit-based Incentive Payment System.

The group said it was reminded of similar delays in years past with meaningful use and ICD-10 rules. Such uncertainty "can condition providers to delay implementing necessary and beneficial changes in technology and its use in clinical practice," they wrote.

Healthcare providers and IT vendors have invested heavily in technology upgrades and process improvements, they said. "Being unable to realize a return on those investments because deadlines are moved creates disincentives to aggressive participation in future years. Overall, this pattern can inhibit the broader adoption of health IT, a necessary component to the transition to value-based care."

It's imperative for CMS to get it right as early as possible in the rulemaking process, the group told Verma – arguing that mid-course changes in direction only waste the time and money of providers and tech developers alike.

That said, EHRA offered several points about technology requirements for various components of the QPP.

For instance, with the new virtual groups option for reporting to MIPS in 2018 "there remains uncertainty as to how data can and should be submitted for these groups," they said. "Many providers in small practices who may opt to form virtual groups will be using different EHR systems, which will require them to combine data prior to submission."

Given those challenges in interoperability and data aggregation, the group called on CMS to set clear expectations as to how virtual groups should submit data across categories and from multiple systems while ensuring their information is aggregated and reported correctly to maximize the group’s composite performance score."

MIPS grades providers based on their performance across four categories, and the association had detailed suggestions for Verma and CMS about the requirements for how EHRs can support Improvement Activities, Advancing Care Information, Cost and Quality components.

Make interoperability framework voluntary, EHRA says

Meanwhile, in a letter to National Coordinator for Health IT Donald Rucker, MD, the EHR Association offered its thoughts on the Trusted Exchange Framework and Common Agreement – key interoperability provisions contained within the landmark 21st Century Cures Act, signed by President Barack Obama in December 2016.

Chief among EHRA's suggestions: The trust framework should be "voluntary, with future work building upon existing standards and technology approaches for interoperability."

The association also reiterated its support for secure exchange and nondiscrimination in data-sharing; urged ONC to build upon the substantial investments already made by various provider and vendor stakeholders rather of introducing disruptive mid-course changes; and pointed out that some comment areas proposed by ONC seem to go beyond specific requirements of the Cures Act, and should be classified as policy goals rather than statutory requirements.

The group also offered a long list of technical suggestions related to standardization, transparency, security, patient safety and more.

Twitter: @MikeMiliardHITN
Email the writer: mike.miliard@himssmedia.com

Deloitte and PwC headline lead a newly released list of firms that non-U.S. provider organizations are considering for health IT consulting work, according to new rankings from Klas. Deloitte is widely considered for their advisory and implementation work while PwC is looked at almost exclusively for IT advisory engagements, the report said.

KLAS said the report is its first-ever study on consulting firms for providers outside the U.S., highlighting how 89 healthcare IT consulting firms are perceived by 90 provider organizations abroad. 

[Also: GE Healthcare buys clinical outcomes consulting firm Novia Strategies]

The top 13 health IT consulting firms measured by percentage of mentions by provider organizations in the study are: Deloitte, 34 percent; PwC, 29 percent; The HCI Group, 18 percent; KPMG, 16 percent; Accenture, 15 percent; EY, 15 percent; IBM, 9 percent; NTT Data, 8 percent; McKinsey, 6 percent; Healthtech Consultants, 5 percent; Gartner, 4 percent; DXC Technology, 3 percent; and HQS Plus, 3 percent.

Other regional health IT consulting firms received a 60 percent mindshare rating while other multiregional firms scored 30 percent, the study found.

[Also: Technology consulting firm Technossus hires women for four top positions]

With electronic health records implementations outside the U.S. on the rise, many healthcare provider organizations are considering using consulting firms for help in planning for or implementing an EHR. Within healthcare organizations, resources for strategizing and implementing often are stretched thin.

The 117-page study breaks out data on health IT consulting firms in many and varied ways. For example, The HCI Group is recognized as the firm that best-combines competency and price, according to the study, entitled “Global Healthcare Consulting: Which Firms are Considered for Implementation and Advisory Work?”

According to KLAS research, of the top firms that are widely considered by health systems globally, The HCI Group stands out as being unique due to its combination of high competency and value. With its roots in healthcare, The HCI Group’s “mindshare is impressive when put in the context of the top 13 firms mentioned by providers,” the study said.

The HCI Group recently merged with Tech Mahindra.

Twitter: @SiwickiHealthIT
Email the writer: bill.siwicki@himssmedia.com