The Pittsburgh health system is using technology to extract clinical notes and more quickly qualify participants.
Technology in use at UPMC is accelerating the speed with which the Pittsburgh-based health system can identify and qualify participants in a clinical trial targeting colorectal cancer prevention.
A technology platform that combines natural language processing and artificial intelligence is more efficient than traditional patient identification methods, which are often manual, time-consuming, and costly for clinical trial sites.
"In this case, the trial is about people who have a particular kind of polyp," says Robert Schoen, MD, MPH, chief of the Division of Gastroenterology, Hepatology, and Nutrition at UPMC and a professor of medicine and epidemiology at the University of Pittsburgh. "Then you would go through all those colonoscopy exams and pathology manually, and select them one by one. It's an effective way to do it, but it's very inefficient."
Schoen is principal investigator for FORTE, a study led by NRG Oncology, part of the National Clinical Trials Network, sponsored by the National Cancer Institute.
Robert Schoen, MD, MPH, chief of the Division of Gastroenterology, Hepatology, and Nutrition at UPMC.
"This time saved allows FORTE sites to increase recruitment efforts and continue to build their FORTE referral networks, and also make the overall study more likely to hit its participant recruitment goals," Schoen says.
The primary goal of FORTE is to compare the colorectal cancer rates between the two study groups (repeat colonoscopy at five and 10 years vs. repeat colonoscopy at 10 years) to see if the rates are equivalent. Each study group had one or two small benign polyps removed during a previous colonoscopy.
If those rates are equivalent, the study could prove that a five-year exam isn't necessary, and that clinicians can focus on recommending an exam every 10 years. Participants will be asked to donate blood and stool samples and will be followed annually.
The study organizers expect to enroll 9,500 participants, which requires finding and engaging a sufficient number of eligible participants from sites across the country.
"We want to query the medical record for the six to eight criteria that we know are important, and Pieces helps us do that," Schoen says.
According to a 2015 study, as many as 86% of clinical trials do not meet recruitment goals within their proposed time periods. This often makes clinical trials more expensive and time-consuming, which in turn can affect results and clinical outcomes.
Pieces Predict is the enabling technology in the screening process. Developed by Pieces Inc., a Texas-based AI company, Pieces Predict expedites this trial recruitment process by scanning hundreds of thousands of colonoscopy notes in a secure manner at selected study sites to identify participants who have a high probability of meeting the study's eligibility criteria.
The technology won't eliminate all the steps to validate potential participants.
"We may have to ask the patient some questions that aren't contained in the record, and of course, the patient has to decide if they want to participate in the study," Schoen says. "It's purely voluntary. But just going from 10,000 [prospects] to 1,500 is an enormous time saver."
This kind of technology assistance is not common in federal national studies, so researchers are hoping that FORTE can serve as a potential model for future studies, Schoen says. NRG Oncology alone has hundreds of studies ongoing, enrolling patients in cancer treatment trials, he says.
At this point, Schoen is unable to predict precisely how much faster the technology will be able to find the desired 9,500 patients.
"We know that we have an instrument that does what we want it to do well, and we will let it do its thing," he says.
The FORTE study is also being publicized through social media and other previously used methods of attracting participants, but by zeroing in on patient records at UPMC, study leaders can identify a pool of patients more quickly, Schoen says.
"It would be a very different thing to say I'm going to look through all the EMRs at Aetna Insurance, but we don't have permission for that," he says. "We only have permission if the patient has granted us permission, or if we have an accepted license to review their medical information."
On the plus side, communities of patients gathered by organizations such as the National Clinical Trials Network are also effective ways of finding participants.
"The question is, can we marry the technology to the administrative and legal structure of how you conduct these trials at these different sites?" says Ruben Amarsingham, chief executive officer of Pieces, Inc. "That was the first question Dr. Schoen asked. The more that organizations like ours can do that, I think we can make more progress."
"Individual sites can be large academic centers, or GI practices, that have multiple providers and take care of thousands of patients," Schoen says. "It can manifest in a lot of different ways."
Although the trial will take place over a longer time span, within a year or two, FORTE leaders will complete analyses looking at how well the technology has worked at some sites, in terms of records analyzed and patients identified, Schoen says.
The NCI Division of Cancer Prevention leads the NCI Community Oncology Research Program (NCORP). While NRG Oncology is leading the FORTE study, other network organizations participating include the Alliance for Clinical Trials in Oncology, ECOG-ACRIN Cancer Research Group, and SWOG Cancer Research Network.
At Franciscan Health, Chief Medical Officer Albert Tomchaney, MD, has spent more than a dozen years exploring how technology can be used to gather the right data to help clinicians make the right decisions.
Albert Tomchaney, MD, became the first chief medical officer of the Indiana-based Franciscan Alliance, which operates as Franciscan Health, in 2008. He has managed the physician practices for a time and overseen hospital operations such as pharmacy and care management. But throughout, and especially now, his focus has been on population health activities.
"If it's pop health related, or value related, I'll probably touch it somewhere along the way," Tomchaney says.
In this conversation with HealthLeaders, Tomchaney describes some of the technology that the Franciscan Alliance is using to promote those objectives. This transcript has been lightly edited for clarity and brevity.
HL: What's an example of the transformative power of this information, whether it be patient engagement, or just bending the cost curve?
Tomchaney: Patients still strongly adhere to their right to choose what they want to choose. Sometimes they still do it with no real feedback from their primary care physician. So they're making independent decisions, which is fine, but your only way to have a line of sight to the totality of that patient's care is having a real broad data feed across clinical, claims, and quality. If you can get those three pieces together, merged into a single set of data resources, it can give us a better picture of the patients, marrying costs and outcomes together to know that, yeah, it really does make a difference to use implant A versus implant B, or whatever is the clinical decision you're making. That has been totally transformative to care delivery platforms.
HL: You've talked about clinical, claims, and quality as a single set of data resources. It's often called the single source of truth. Has technology made a big difference?
Tomchaney: You need those three redundant sources of information to really be sure you capture the truth about the patient. With the redundancy, you have a greater likelihood of capturing all the realms and data elements that you need. Those tools help us understand how to put together a comprehensive care plan that's coordinated. It's still a work in progress because we still have to be able to refine and define quality more discretely than probably what we do today. And it allows the doctors to have a more educated, informed decision on how they make referrals and how they use the resources going forward.
Albert Tomchaney, MD, chief medical officer of the Franciscan Alliance. Photo courtesy Franciscan Alliance.
It's pretty impactful for the doctors when they see it in real time and it's our patients. That's the big game-changer: you take full ownership of those patients, because now there's mostly nothing you don't know about the patients [whereas], in the past, you made assumptions based on others' thoughts, feelings, comments, and issues that they had no control over that were brought to the table by whomever. Now, it's their data. So I think it's made a big impact.
HL: You've been using Cedar Gate analytics technology to unearth these insights for a number of years now. Right before the pandemic, you announced that you had improved your ACO performance by $44 million back in 2018. With the pandemic having now happened, have you seen a continuation of that kind of cost savings?
Tomchaney: Tools like Cedar Gate give us some better clarity about what was the COVID impact on patient care. Patients clearly did less care during COVID, for lots of reasons. The tool can help us quantify and understand where there may be pent-up demand and medical needs for patients that have been left unmet. It helps us understand where we may see surges in utilization. It lets us understand where there's still a vulnerable population.
COVID was a basically a two-year phenomenon that. when you talk to any of the actuaries, threw all their assumptions aside, and now you have to factor in these unknowns. COVID was an event that changed the pattern of utilization across the population, mostly to the detriment. We're picking up from that and trying to bring back the resources we need to close the gaps on things that weren't closed during COVID.
The Medicare population didn't do as much prevention, so we're playing a lot of catch-up with outreach. The data systems really helped us understand where that vulnerability was in the population we needed to treat. It helped us stay closer to being on track to where we were prior to COVID. We're still going to see some shared savings. Our quality scores, which is the measure, when we had our MSSP [Managed Security Service Provider] reconciliation for 2020, we got 100%. It's not official from [the Centers for Medicare & Medicaid Services] yet, but I can tell you we matched that score for 2021.
HL: What role do payers play in this transformation?
Tomchaney: When you talk about that single source of truth, there's numbers that we get from our claims pool that we run through Cedar Gate, so we have all that claims information. And then you have the periodic information that comes back from a particular payer. They don't match. I've talked to the payers, saying let's try to come together so that your data, my data, and the world's data is all the same, as imperfect as it may be.
I would love to see more confluence of data between the payers and the providers. Sometimes small differences mean a lot. There's also still a lot of activities that payers do along the lines of risk assessments that fit into some of their proprietary products. We don't have as much line of sight to that. But we're all going to be in risk together. We want transparency in healthcare.
The focus today is on the providers. We need to do a much better job supplying the patients and the public with better transparency. There's nothing that secret I could imagine, in terms of how you calculate it. Honestly, some of the payers don't have the solutions or the sophistication that some of the providers have.
HL: There is also an effort to expand the traditional role of health information exchanges to encompass claims data. Indiana kind of wrote the book on information health exchanges. Is there a glimmer of hope for getting around proprietary silos that payers possess?
Tomchaney: The good news is we're having discussions about it. In the past, you wouldn't even be able to really talk about that. The less-than-optimistic news is that nothing's really been done to change that. In Indiana, most of the healthcare is through employers. We're told 70% have self-funded plans. It'll take a while. The employer base in Indiana is very, very focused on hospital costs and why are they higher than other parts of the country.
HL: If there's a knock against AI, it's that it's filled with black boxes. People are trusting that the tech is doing what it says it's doing, but maybe not always being able to verify that.
Tomchaney: For most of the cases, it's going to be still up to the clinician to make that clinical decision. We keep telling the docs AI doesn't replace your brain. The thing I really get frightened of over the variety of systems I've seen is the willingness to accept a solution, from a technological standpoint, that's the easiest. It's a one-button push, as opposed to a solution that maybe takes two buttons. I've told the docs, you all understand in medicine that we live by the 80/20 rule. Whether it's through our pattern recognition, when we make a diagnosis, or whatever the experience is, 80% of the patients can go down one of those algorithms that you talked about, but the skill in this new era is identifying that 20% who don't fit that.
If you look at places like Geisinger, that has ProvenCare, they do a remarkable job on making sure that the person fits the ProvenCare solution before they even put them in there, but you have to continue to reinforce "patient-first." And while yes, 80% will fit the solution, you've got to take probably more time and effort to identify that 20% that doesn't, make sure there's checks and balances, and reasons for the clinicians to pause and not push whatever's the easy button.
CHRISTUS Health is looking to make a difference beyond the hospital walls by using technology to understand the social determinants of health and lived experiences of both patients and employees.
As system vice president of community benefit, health equity, diversity, and inclusion at CHRISTUS Health, an international Catholic health system headquartered in Irving, Texas, Marcos Pesquera sees techology as an inflection point in the health of his community and employees.
And an innovative, systemwide, community needs survey is helping the health system leverage data to understand the needs, assets, and lived realities of patients and employees to accelerate progress on health equity.
The Centers for Medicare & Medicaid Services requires all nonprofit hospitals to do a community health needs assessment (CHNA) every three years. These hospitals subsequently create community health improvement plans.
"This year, we're in the middle of that process," Pesquera says.
Marcos Pesquera, system vice president of community benefit, health equity, diversity, and inclusion at CHRISTUS Health. Photo courtesy CHRISTUS Health.
Anonymous responses to the survey are revealing realities to a degree that previous demographic data, gathered laboriously from multiple sources, including focus groups, failed to illuminate, he says.
The survey gathering and analysis process is being facilitated by Metopio, a cloud-based data analysis platform that is able to view visualizations of layers of data, including the survey responses, to highlight health disparities.
Six months in, the survey has exceeded expectations, with 6,000 responses received through three phases, double the number of responses that were expected by now, Pesquera says.
By including employee voices in the CHNA process, CHRISTUS Health has been able to better understand alignment and divergence between the needs of its 30,000 associates – employees and contractors – and the broader community.
Using the principles of the societal factors that influence health, with a specific focus on social determinants of health such as education level, income level, health insurance coverage, food security, unemployment rate, and life expectancy, the health system has identified zip codes with historically marginalized populations. They're now monitoring these zip codes closely during the CHNA process, to ensure that the needs of these areas were adequately addressed.
The assessment process also captures demographic data mirroring data captured clinically, such as race, ethnicity, age, preferred language, veteran status, sexual orientation, and gender identity, as well as payer and disability status.
The analysis also brings in hospital data, such as emergency room utilization, and analyzes it through an equity lens, Pesquera says. Through special permissions, the analysis also draws upon anonymized EHR records.
"This is very much going to give hospitals the public health eyes that hospitals have been missing for a thousand years," he says.
Survey respondents are also asked to describe such social determinants as inability to pay for housing or utility bills, Pesquera says.
As a result of community improvement plans, CHRISTUS Health has issued more than 30 small grants, of between $50,000 and $100,000, to institutions such as food banks to address issues such as food insecurity.
"We're not asking them for anything in return other than just let us give your phone number and address to our patients that are in need," Pesquera says.
Survey results also serve as a conduit to invite employees to volunteer their skills and share their interests with the community.
"We consider our hospitals as anchor institutions, and we have all these nonprofits," Pesquera says. Strengthening the health equity agenda may involve introducing those nonprofits to employees and patients.
Following such introductions, both may then volunteer their skills to those nonprofits, he adds.
In certain circumstances, results from the CHNA also help public health departments in the communities served by CHRISTUS Health hospitals and clinics.
The analytics software permits extensive geomapping of data across service areas, to identify resources ranging from federally qualified health centers to internet service providers, he says.
This CHRISTUS Health system initiative includes 40 hospitals in Texas, Louisiana, New Mexico, and Arkansas. CHRISTUS Health also operates hospitals in Mexico, Chile, and Colombia, although this initiative is not focused outside the US at this time, Pesquera says.
"We ask them to do community health needs assessments and be responsive to those needs that they find, but it's not as structured as it is in the US," he says.
The anchor organization designation does not mean that CHRISTUS Health is leading the initiative among all stakeholders.
"We want to make sure that as hospitals, we're not viewed as leading anything," he says. "We want to just be at a circular table, a member of a coalition. We recognize that in many of our communities, we're the largest employer, and also a consumer of goods and transportation. There's a commitment to just be part of the community, and get outside of the four walls of the hospital to help."
Pesquera hopes to finish collecting surveys by the end of July, giving CHRISTUS Health through October to finalize results and priorities and publish the CHNAs on its web sites, as required by CMS.
The cost of conducting the assessments with the technology assist compares to the previous cost of hiring consultants to gather a subset of the demographic data collected this time, Pesquera says.
"I'm very encouraged by people's willingness to share with us their lived experiences, their challenges, but also, I'm also very encouraged to see that there are so many people and organizations ready and willing to meet the needs," Pesquera says. "For whatever reason, as crazy as the world is, I see a huge heart and desire for people to really care for others in ways that I have not seen before."
A new resource developed by the two groups can be customized to help patients guard their data on third-party health sites.
With third-party applications gaining more access to patients' health information, the College of Healthcare Information Management Executives (CHIME) and the Workgroup for Electronic Data Interchange (WEDI) have announced the launch of the “THINK BEFORE YOU CLICK” campaign.
The organizations are endorsing a seamless flow of data to these applications to enhance access and improve better health outcomes. Consumers must mitigate their risk, however, and the groups are offering five-step checklist designed to educate and empower consumers to take the necessary precautions before they transmit their health information to third-party apps.
This checklist is non-branded and is made available for free to any organization seeking to educate and protect its members.
“With new federal regulations allowing patients to direct providers and health plans to share their health information to a third-party app, there is concern that unintended disclosures of sensitive data could occur,” Russell Branzell, president and CEO of CHIME, said in a press release “Providing consumers with this simple-to-use checklist with recommended actions they can take before transmitting their data is a service we feel will help consumers protect themselves and their personal information.”
“We hope that critical consumer and patient organizations personalize this resource with their brand, widely disseminate it to their members and strongly encourage its use,” added Charles Stellar, WEDI's president and CEO. “The 'THINK BEFORE YOU CLICK' checklist will be made freely available on the CHIME and WEDI websites. We urge providers, health plans and health care vendors to leverage their communication channels to distribute this collateral directly to consumers.”
The latest KLAS Arch Collaborative survey finds that healthcare organizations with the highest number of clinicians satisfied with their electronic health record experience are employing superusers.
A new report from the KLAS Arch Collaborative, which addresses how healthcare organizations build trust with clinicians to ultimately improve their electronic health record experience, shows a vast gap between those who are satisfied and those who aren't.
Clinician perceptions of three key EHR stakeholders—their organization/IT leadership, their EHR vendor, and end users themselves—impact their Net EHR Experience Score (NEES). The impact is strongest with the first group, organization/IT leadership, according to the report.
The NEES uses a point scale of -100 to +100 to measure agreement or disagreement that those surveyed trust their organization/IT leadership to deliver good EHR experiences. The gap between both ends of the spectrum is vast, with 27,455 clinicians surveyed strongly agreeing that they do have such trust, and 21,058 clinicians strongly disagreeing. The NEES score between the two represents a gap of 124.1 points on the NEES scale.
Several factors determine whether clinicians trust their organization/IT leadership, including EHR satisfaction, clinician burnout, EHR training, and support.
The Arch Collaborative conducted its first survey in 2017, and since then participating organizations have seen gains in some areas and declines in others. Compared to four years ago, more clinicians are reporting feeling burned out. But the percentage of clinicians who feel their organization/IT leadership delivers well is rebounding, from 57% in 2017 to a low of 47% in 2021 but back up to 53% in the 2022 survey.
Some Arch Collaborative organizations have measured clinician satisfaction before and after completing an initiative targeting a specific department or goal. On average, these organizations see significant improvement in their NEES score, the report says.
Organizations who are successful in improving the EHR experience often leverage EHR superusers, the report says. These superusers are key to developing effective EHR education materials, and are very effective members of EHR governance boards, the survey finds.
Clinicians who feel the EHR does not support high-quality, patient-centered care tend to be much less likely to be satisfied with their EHR and their organization, the survey finds.
PopHealthCare is planning to expand from its current slate of 19 states to cover the entire country, with a strategy that includes bringing healthcare services directly into the home.
The return of the house call, combined with today's data analytics, may hold the key to managing populations and moving healthcare from fee-for-service to risk-based payments.
So says Eric Galvin, newly-appointed chief executive officer of PopHealthCare, who recently outlined his plans to leverage three decades of operations, underwriting, finance, and human resources experience to expand Emcara Health, PopHealthCare's value-based medical group, from its current 19-state footprint to all 50 states.
"We're about a 13-year-old company whose roots were in revenue analytics for health plans," he says. "That grew and evolved into more of a full-bodied risk adjustment program offering."
Emcara Health's care team visits the homes of patients and conducts health assessments, including ascertaining social determinants of health evident during the visit. In some instances, particularly in rural settings, they're the primary care provider of record.
"If that's the case, we very much are the quarterback of care, and would be interacting with specialists as needed," Galvin says.
Eric Galvin, chiief executive officer of PopHealthCare. Photo courtesy PopHealthCare.
In those cases where Emcara Health is not the primary care provider, the company interacts with the patient's primary care physician.
"We're sending data to them so they can effectively manage the other parts of the care continuum for that patient," Galvin says.
PopHealthCare also bridges the gap between patients and family members, he says, involving those family members in the care the patient is receiving or should be receiving.
While fee-for-service payment models are persistent, payers such as Jacksonville, Florida-based GuideWell, the parent company of PopHealthCare, "want to be in value-based arrangements across the board," Galvin says. "The provider community isn't always either equipped or ready to go down that path."
Galvin previously served as executive vice president and chief growth and medical cost officer of Emblem Health and president of ConnectiCare, which grew under his leadership to be a dominant provider of Affordable Care Act-driven healthcare in Connecticut.
"The whole idea was everybody in the ecosystem – hospitals, provider groups, lab companies – put all of their resources on the table," Galvin says. "There's been one consistent theme in my career, and that's about trying to make healthcare better for the consumer and for the patient."
ConnectiCare offered the first bundled payment arrangement in the state of Connecticut, focusing on orthopedics, Galvin says.
While at ConnectiCare, Galvin cofounded a 501(c)3 nonprofit, Partners for a Healthier Connecticut.
"We started it with a focus on type 2 diabetes," he says. "We said, 'Put all your resources on the table. Now forget who's doing those activities. Let's talk about who's in the best situation, the best positioned to care for the patient,' and we made some great progress."
An electronic health record customized for PopHealthCare's needs is a key enabler of this conversation, Galvin says.
"It doesn't have to be a physician standing there in someone's living room," he says. "It could be a whole host of different credentialed people that are able to interact with a patient. And you don't have to have all those people present in the home. We're able to reach more people in more and more rural locations in an efficient way because of [telemedicine] technology."
Some of PopHealthCare's customers pay a per-member-per-month fee, and in other cases the company assumes full medical risk, Galvin says.
One of his biggest challenges in his new role is to approach clients who may have purchased an individual service offered by PopHealthCare and entice them to purchase a bundle of offerings.
"There is a substantial amount of demand in the self-funded space," he says. "Geographically, there is still much white space for us, that we should be penetrating, and especially with our model, because we are so effective in rural communities."
During a previous stint at a digital health company, Galvin was able to grow the population served by a factor of 10.
"One of the secrets to that model was going to where the clients were," he says. "We would have people with a van filled with folding chairs, and we would go to the client site, and we hold health seminars."
Some methods of outreach are more challenging, however. Potential patients are no longer answering their mobile phones if the incoming call is from a number they do not recognize, Galvin notes.
The point is to overcome these challenges on behalf of all of healthcare, he says.
"We're not trying to disintermediate anyone," he says. "What we're interested in doing is bridging and also being the resource that a lot of providers can't afford to bring to bear."
Although Galvin isn't a physician, he says his skills with client engagement, patient engagement, and running an effective and efficient business complement the physician leadership at PopHealthCare.
"Some of the best organizations that I've seen in the health space don't have a physician at the helm, but they have great physicians," he says. "Our chief medical officer is a brilliant physician and his team is amazing. So I will always yield to them when it comes to questions of medicine."
Payers also need to reduce the number of technology suppliers they work with as well, he says.
"They're showing all of the signs of saying, 'We've had these 18 different partners, [and] we now need to start consolidating those down and finding partners who could be that quarterback for us," Galvin says.
A statewide program launched in Arizona during the pandemic allowed hospitals to manage their capacity and track bed use, ensuring that transfers were handled expediently and no hospital 'ran out of space.'
The pandemic may have highlighted the shortcomings of the nation's healthcare system in shifting resources and patients to optimize care, but it also spurred the development of new technology and strategies to solve those problems. Health systems are now embracing new platforms that reduce silos and improve both care coordination and management.
HealthLeaders recently sat down to talk to Darin Vercillo, MD, a practicing board-certified hospitalist at Davis Hospital and Medical Center (owned by Steward Health Care) in Layton, Utah, and the medical director of the hospitalist division of the Physician Group of Utah. He's also co-founder and chief medical officer of ABOUT Healthcare, a digital health company that partnered with the state of Arizona during the pandemic to improve surge capacity and bed management throughout the state.
In this interview, Vercillo describes how that partnership worked, and how better technology and coordination strategy can shave days off a typical patient's hospital stay. This interview has been edited for clarity and brevity.
HealthLeaders: Does this technology bring a certain kind of order to certain kinds of chaos?
Darin Vercillo: Absolutely. There are disconnects, so many different silos, that areas of the organization operate in. If you have a patient that's needing to be transferred in, there's the silo of who controls the beds, the silo of who controls the transport, the silo of who controls the communication between providers, and even tremendous silos between physicians. If the hospitalist, the cardiologist, and the endocrinologist all have to participate in the care of the patient, who owns the admission, and who's going to say yes?
Darin Vercillo, MD, medical director of the hospitalist group for the Physician Group of Utah. Photo courtesy Physician Group of Utah.
It can be not only very chaotic, but it can be fraught with too many phone calls, clicks, information systems, and delays in patient care, of minutes to hours, in a very highly acute care transfer. Or it can even be a delay of days, like in the case of my own father, just over the Christmas holiday, where he spent 17 days waiting for a transfer from one hospital that doesn't do cardiac ablations to another hospital that did, because of the pandemic [and] beds being filled. And because it was a disjointed process, nobody looked at other nearby facilities. Once those were looked at, it was a mere 36 hours before they got everything done.
So it can be a real issue, not only for patient care, but for the cost of expensive hospitals as well, with lengths of stay.
HL: How do transfers typically work?
Vercillo: Typically, transfers [are conducted through] a clinically-oriented call center. There are varying technologies -- the EHR, bed management systems, transport systems, care management. In many cases, more than 50% of the patients that are being transferred aren't even in those systems yet, because they're coming from outside organizations. So you're talking about a patient that doesn't yet exist in your EHR.
[Technology platforms should reside] is at the nexus of all of these. First of all, [they] integrate with Epic, Cerner, Allscripts, or Meditech EHRs. [they're] exchanging information bidirectionally with them. Also with capacity management, nursing staffing, physician on call and credentialing, transportation, all these systems that are necessary to coordinate to get those transfers done, [they] connect to all of them. And then the process that surrounds that is a transfer coordinator is receiving the call from the referring physician who's saying, 'Help, I have a patient that I need to transfer to you,' getting the appropriate information quickly from that physician connecting in another physician who's going to speak with that referring doctor on the accepting side, so they can make an agreement to transfer responsibility of care.
HL: How has this process changed since the pandemic?
Vercillo: One thing has been the recognition that load balancing, and systemwide visibility, is not just a question of what's going on inside a hospital or even inside a network of hospitals. We were approached by the Department of Health in the state of Arizona because they wanted to do this same thing on a statewide basis, and coordinate COVID transfers across all of these hospital systems, from remote locations on a Native American reservation that was up on the border, into an area where there was capacity for some of their more acute cases.
During the pandemic, we set up a statewide transfer center, utilizing our technology, receiving information from the state HIE and multiple hospital systems to create statewide visibility of every bed that was available to send and receive a patient at all of the varying levels. They coordinated all COVID transfers through this one hub. They never ran out of space. Secondly, they got a tremendous amount of data that they never would have had. They were able to detect focus areas of increased need and outbreaks. They were also able to look very closely at other resources such as ventilators and ECMO machines, even nursing staffing shortages, and use that data to recruit 500 additional nurses into the state under a governor's order to make sure that they could meet all of those needs.
HL: In addition to all of the staffing challenges you mentioned, there are also great pressures on systems to control their costs. How do you justify the cost of this platform?
Vercillo: Transfers are big business. The majority of patients that are being transferred from one facility to another are moving up the level of acuity. Something has been diagnosed, and now needs a surgical or therapeutic procedure that's not offered at that hospital where they currently are. When you talk about these patients, they are going to literally run up tens of thousands, if not hundreds of thousands, of dollars in charges.
We have done a study that showed nationally that every transferred patient contributes $10,800 to the bottom line of that particular hospital, so every patient you receive is about $11,000 in profit. Now, obviously not to reduce a patient's care down to a profit line, but they're businesses and they need to be aware of this. When they're looking in competitive markets, of how do we attract the patients that our particular hospital is focused on - neurosurgery, orthopedic surgery, or trauma surgery, or cardiac or what have you - and that patient is sitting in an ER in a small community hospital that cannot meet the needs of that patient, that hospital has options as to where they're going to go to.
If you're the owner of the hospital system, and you want to make sure that you're the frictionless path of least resistance for providers to refer their patients, in those situations a transfer center will absolutely be the answer to that. We have seen an average of 29% growth in those transfers in just the first year. And on average, the costs associated with setting this up are paid for in the first six months of a multiyear contract. So it generates tremendous revenue and profitability.
On the other side, on the flip side of this, when you're talking about observed vs. expected lengths of stay, when you're talking about clearing patients through in a timely manner and getting them discharged at the right time of day, so you can staff your hospital with nursing staff, open a bed back up, bring the patient out of the PACU or up from the ER, appropriately, this idea of having electronic and seamless connections to your post-acute care partners is absolutely essential. For a care coordinator to contact five different skilled nursing facilities instantaneously with a click of a button, being able to message back and forth and then electronically order the ride and get the patient there, get them taken care of and arranged in their hospital for discharge, then everything happens seamlessly.
And they free that bed up by two o'clock, which they always want to do, so they can manage their staffing and their census levels at the appropriate times. If not, if care coordinators are having to stand in front of fax machines and stuff page after page after page in there, and then make phone calls and follow up. Oftentimes, you see patients getting waited on until four or five or six o'clock in the evening. And at that point they can't transfer them, so they roll over to the next day. And now you've got a possibly avoidable day on your books for that patient, which you may or may not even get reimbursed for from the insurer.
We also see many organizations that use their transfer centers and their access orchestration strategies to build new service lines. It's a venture that more than pays for itself, and is frequently referenced by many organizations as their secret sauce, as well as one of the more important areas where they focused resources for their long-term issues.
The Pennsylvania-based health system is partnering with Amazon Web Services to move its electronic health record platform and other services into the cloud.
Geisinger recently announced it has chosen Amazon Web Services (AWS) as its strategic cloud provider. The project, one of the largest migrations of electronic health record systems to AWS, will save the Pennsylvania health system several million dollars a year, which executives say they'll use to make investments in improving the health of its patients.
Geisinger Chief Information Officer John Kravitz, MHA, CHCIO, spoke to HealthLeaders about this partnership and how it will impact innovation at Geisinger. This interview has been lightly edited for brevity and clarity.
HealthLeaders: Your move to the cloud -- why now? Why not earlier or later?
John Kravitz: For us, as an organization, the time was appropriate to start. We looked at the cloud for the last two years, did an RFP process with the three major public cloud providers, and we decided we wanted to get to the cloud, so we're doing some things like setting up an API management platform to provide better integration with APIs. The ability to move to the cloud, to be agile, to be scalable, to move our applications quickly, to deploy applications quickly, that makes sense to move our strategy for the organization forward.
In the meantime, we're looking to simplify, as much as possible, our environment, as we're starting to migrate to the cloud. We're in early stages. We've just done the design and some other things for it, and started to collaborate on some small applications. It will take us a while to get to Epic, probably 18 months to 24 months before we get to an Epic production cloud. It’s going to be a three- to four-year journey before we get there.
John Kravitz, chief information officer, Geisinger. Photo courtesy Geisinger.
There are some cost savings associated with it. But that wasn't our main driver. It was agility, disaster recovery, business recovery, all those components of it. We had two data centers, but they're just in the same region, too close together and not a good scenario. We need to be diverse, and we need to have the capability to recover our business and keep business moving forward.
HL: Regarding the 400 applications mentioned in the announcement, is that typical of an organization your size?
Kravitz: Actually, it's atypical. We have about 1500 applications. We're rationalizing about 450 applications (and) eliminating them, as we're going to move to the cloud. Our goal (is that) we'll move about 90% of our applications that we can into the cloud., There'll be some things like PACS imaging, you know, for radiology, cardiology, other things like that, that really have to sit here. The middleware to connect analyzers for laboratory and other things have to sit here and connect to devices; those obviously stay on premises in our primary data center, and then we will integrate that data right into our cloud environment.
So in actuality, it's probably going to be closer to 900 applications that will migrate to the cloud. That would be about 90% of just over 1000 when we get there. Our goal is to continue to drive down specialized applications for every little thing, really driving closer to more vendor-centric, deep relationships with our EHR vendor and some other core vendors that we utilize, to utilize their stack as much as possible and not have best-of-breed systems.
HL: Going to the cloud is really the time if you're ever going to do that.
Kravitz: Exactly. You want to clean it up before you move it, because it'll cost you a lot more to move a lot of inefficiently developed applications to the cloud. When you get to the cloud with SaaS (software as a service), or infrastructure as a service, you’ve got to be able to utilize resources appropriately, and not over-allocate, or you're paying money for wasted resources. We're looking at a complete migration, moving applications to either PaaS (platform as a service) or infrastructure as a service where possible, or rewriting applications to make sure that they're efficiently used in the cloud.
HL: How do you integrate these different services once they're in the Amazon cloud? What kind of challenges does that represent?
Kravitz: We're working through those right now, using APIs where possible, or HL7 integration to make those things work, or even EDI if they're business-related transactions. Because our organization isn't just a clinical enterprise. We have a large clinical enterprise, we have a health plan, we have a medical school and a graduate education school. I've got different platforms for like EDI transactions that work for the health plan. And that has to be on an EDI engine, Tibco in this case. We can go across the backplanes, to the clouds, to connect things back and forth without having it go out to the public cloud and back in. We're going to be doing it with that environment, working with the architects from Deloitte, as well as Amazon architects. We've already started scaling some of that.
HL: What role is Deloitte playing?
Kravitz: They are working with us now in the initial education and training for our staff so that we are able to do this move on our own. We have a commitment with them for a short period of time, and then the knowledge transfer is there. And we will then transition over our own people to do all this work.
HL: What does that education entail? What does the average Geisinger employee need to know or do differently?
Kravitz: It’s not the average. It would be an infrastructure person from Geisinger, from the IT team. They're learning how you do segmentation within the cloud, because there are certain things that have to be segmented away, like the health plans, and the health system has to be protected. The information has to be kept separate and distinct. They're learning that, they're learning the firewall ruling and everything else that works with it: data loss prevention, you know, CASB, some of the security tools.
HL: So many people these days think the cloud is a real inflection point for innovation.
Kravitz: Cloud providers like Amazon have done really innovative work in their own environments. It provides us an opportunity to use AI and some other tools that can leverage the data that we have that's protected through nondisclosure agreements and other business associate agreements. To be able to have access to that data to assist us in doing deeper evaluations of the data and looking at things that we can do to improve the way we provide health care to our customer or to our patients.
HL: Is it true that if you have a cloud infrastructure, you don't necessarily have to ship data around as much as you did before, which inherently can provide issues of privacy and security? Do you adhere to that frame of mind about this?
Kravitz: Conceptually, yes, that is going to be the case. In practice, we hadn't had that experience just yet. But what we've learned in discussions with Deloitte, with Amazon, that is certainly the intent as we move forward.
HL: Albert Einstein once said, 'In theory, theory and practice are the same. In practice, they are not.'
Kravitz: Well, we'll find that too. I've done it a long time. I've seen a lot of things that don't work out as planned. But this does make sense that you would have the capability to use those analytics tools, and be able to effectuate change with those. We do a lot with analytics now on premise, with big data lakes, and Hadoop environments and other things like that. But we're looking at newer tools that are really cloud enabled. An example could be Snowflake, and other tools that are available for analytics purposes.
Healthcare providers are partnering with electronic health record companies to create upgrades that make the technology platform more responsive to clinical needs.
Healthcare providers are working with electronic health record companies to “co-create” updates that improve the EHR platform and help clinicians make better use of the technology.
At Hendrick Health in Abilene, Texas, clinicians have been studying day-to-day interactions on the health system’s Sunrise EHR and using that feedback to fine-tune the software.
The EHR industry “has not been sensitive to the clinician’s input of the data, how it is stored, and how clinicians can review the data on the back end,” says Joshua Reed, DO, the health system’s medical director of case management and utilization review.
According to Reed, he has seen “a widening gap between what [technology] I would use at home and what I would use at the hospital” since 2006, when he started medical school.
“Instead of that gap shrinking the way we would expect through multiple iterations or upgrades, it almost kept getting wider,” he says.
Joshua Reed, DO, medical director of case management and utilization review, Hendrick Health. Photo courtesy Hendrick Health.
EHRs have “really highlighted kind of the brokenness of medicine,” Reed says. “We've moved away from patient-centered elements of care, and we moved purely into a regulatory means of checking boxes and things like meaningful use.”
In an effort to remedy this, Allscripts in 2020 turned to a veteran software designer, Jenna Date, an adjunct professor at the Human-Computer Interaction Institute at Carnegie-Mellon University who specializes in human-centered design. The company hired her as chief experience officer for healthcare solutions, and she remains CXO and vice president with the sale of its hospital and large physician practices business unit to Harris. The unit has now been renamed to Altera Digital Health.
“We use ethnography to be able to go in and spend hours with clinicians,” Date says. “We're focused on the bigger picture. What happens when you come in in the morning? What happens, what's the first thing that you try and get done? What happens at night? What happens on call? We look at different hospitals, not just Hendrick. It was a few hospitals that we visited. And then we look for patterns across those hospitals.”
The collaboration with Hendrick Health identified four such patterns: a drive for simplicity, helping physicians get back to basic tasks, corralling regulation-fueled triggers and alerts in the EHR, and a need to focus on patients.
“Over the course of two years, we've come back to Josh time and time again and his team at Hendrick and a multiple of other connections,” Date says.
Other healthcare leaders have echoed the importance of the human factor in modifying EHRs.
“As a former software programmer and EMR analyst turned chief information officer, I found it refreshing to see Jenna Date and her team’s innovative approach to making our EMR better,” says Andrew Watt, MD, FACEP, vice president, chief information officer, and chief medical information officer at Granite One Health and Catholic Medical Center in New Hampshire.
“She came to our health system, sat with our physicians, and watched their daily workflows,” he says. “Her team took that insight and challenged her company, which designs using programmers, to be open to ideas on what is really important for caregivers on the screen. She let our providers play with working prototypes. Her team solicited feedback and observed how our people interacted with these prototypes. She is advancing the idea that design can reveal function for the first time in our EMR.”
Reed likens most EHRs to “digital shoeboxes” that don’t bring the most relevant and useful information to clinicians’ attention. And that, he says, hinders clinicians in using the platform to improve care outcomes.
The result of the Sunrise redesign, Reed says, is an EHR that is a true digital assistant to the clinician, one that can be customized to the needs of a particular hospital or health system but not be over-personalized.
“Customization is taking a basic set of software and modifying a few of the things to make it work better for that system,” he says. “Personalization is literally taking every physician and making a template for them. And that's the wrong direction, in my opinion, because that moves away from standard of care. Instead of having one protocol, you now have hundreds of individual pseudo-protocols that become impossible to manage.”
Although modern software is often a developer collaboration based on agile software development via daily or weekly software development sprints, healthcare apps can’t exactly be built in the same agile way that consumer apps are built these days, Date says.
“We have sort of like a waterfall agile, where we do our due diligence to be able to put requirements in place early, give designers the time to be able to do all of that work and usability test it, and then we have enough to go into a sprint where we say okay, development, this is what it should look like,” Date says.
Measuring the effectiveness of the redesign is the next challenge for Reed and clinicians at other Allscripts Sunrise-powered facilities, who will be going live with the Sunrise 22.1 update during June.
“Instead of hardcore metrics, my brain goes more to the anecdotes of, if I’m in the physician lounge, I’m hearing less complaining,” Reed says. “I’m seeing more time to go see patients, less burnout, and some of the indirect measures.”
The health system's new platform replaces manual processes to maximize staffed OR utilization and improve a hospital's bottom line.
A major rollout of technology designed to optimize operating room use is helping drive profits at one of the nation's largest health systems.
The technology, developed by LeanTaaS, replaces manual systems with AI-based automation at Chicago-based CommonSpirit Health, which operates 142 hospitals in 21 states. It targets workflows by providing real-time access to OR availability and scheduling, allowing schedulers and staff to manage OR use more efficiently, reduce potential transcription errors and ease stress for both providers and patients.
Dignity Health, which merged with Catholic Health Initiatives to form CommonSpirit Health, reports that 36 of its hospitals have used the technology and saw an additional contribution margin of 14.5 times the return on investment from May 2019 to December 2020, compared to previous year-over-year measurements.
The driving force behind this deployment is Brian Dawson, MSN, RN-BC, CNOR, CSSM, system vice president of perioperative services. He came to CommonSpirit Health after stints at Sutter Health and Keck Medicine of USC, as well as serving as executive assistant to and chief of staff for the surgeon general of the US Navy.
"In healthcare, I come from three different angles," he says. "One, as a clinician. Two, as a quality leader. And third, I want to grow business. Today in healthcare – and COVID proved this – we make our money from our operating rooms and other procedural areas" like the catheterization lab and interventional radiology.
Brian Dawson, MSN, RN-BC, CNOR, CSSM, system vice president of perioperative services at CommonSpirit Health. Photo courtesy CommonSpirit Health.
Everything else in the hospital "really loses us money," he says. "The longer you stay, the less money we get to keep from insurance or [the Centers for Medicare & Medicaid Services]."
When he joined Dignity Health, Dawson says, nurses were looking through OR schedules and e-mailing opportunities to surgeons in the area.
"One of our hospitals in the Bay Area, Sequoia, had already reached out to LeanTaaS about bringing that tool into their facility," Dawson says. "I had tried to bring the tool into USC when I was working there as a consultant."
Dignity's chief executive officer, Lloyd Dean, and chief operating officer, Marvin O'Quinn, supplied the budget for Dawson to deploy LeanTaaS IQ across 32 hospitals in 2019.
The platform works by prompting surgeons to release unused time, in part by suggesting automatic "release dates" timed to maximize prospects for filling as many of those unused staff operating rooms as possible. They're often marketed to surgeons in the area who haven't previously considered performing surgeries at the hospitals reaching out to them.
"I'm constantly banging on our marketing people to say, 'What are we doing to take volume away from our competitors?'" Dawson says.
The technology, he says, is able to query across all the hospitals in the CommonSpirit network in a defined regional market.
Among the results of the initial deployment: 21% of ORs released by the system ended up being filled. And Dawson says he can do better than that.
"It takes our marketing people to go out to surgeons who don't operate with us to say, 'Can you get into the hospital you operate as much as you want?"' he says. "Their answer is going to be no, right? Then I'm going to turn around and say, well, what day would you like, because I have that day available. So it's a marketing ploy."
As a result, the health system has seen a 153% increase in staffed OR blocks released by surgeons, to drive the higher utilization.
"The data truly speaks to power, sitting in front of a surgeon, going through his or her data," Dawson says. "Once they realize that the data is correct, then they fall in line. And it's the same with leadership."
It's also an important tool in communities that have only one hospital.
"We're in places where healthcare has left," Dawson says.
Dawson calculated the ROI by identifying the number of minutes of OR time the tool unlocked, and he estimated that every minute the tool filled equated to $65 in revenue.
The pandemic, which began in the middle of the rollout, depressed that $65 figure to more like $32, due to plummeting elective surgeries at hospitals nationwide. But Dawson is set to calculate the revenue again this fall, and he expects it to be close to $50 per minute.
At the same time, CommonSpirit Health is expanding the platform to more hospitals in its network.
"The tool's now in all of California, in our two hospitals in Las Vegas, our five hospitals in the Phoenix area, as well as the Pacific Northwest, Texas, Tennessee, the Midwest, and we're about to go into the Kentucky valley around Lexington, as well as four or five hospitals in Arkansas," Dawson says. "Then [we'll add] a handful of hospitals in North Dakota that are using Cerner."
There are some limitations. Small, critical access hospitals with fewer than four ORs are not a good fit yet for the technology.
"The hospitals that are in small rural areas that have less than four rooms and [where] there might be five surgeons that operate there, each of them has their own day, and so outside of collecting data, the tool's really not going to be that advantageous for them," Dawson says.
The tool also allows surgeons to be prompted to release unused dates via either texts or e-mails, he says.
"On average, we are releasing unused surgical time 26 days before the surgery date," he says. "That means that if Dr. Smith normally operates on Tuesday, 26 days before that Tuesday, if he's not going to use it, we're releasing that time to others. That's important. Prior to the tool, our average release time was two or four days. You as a doctor can't get someone ready in two days to fill the gap."
The optimal sweet spot is 14 days, Dawson says.
"But the nice part about the tool and our moving auto-release date is it's now out into the 20s. Which is great. The farther out the better."