Medical Home Network’s Baseball Card platform now offers physicians at-a-glance patient stats
Building on its previous success, the technolgy platform behind a Chicago-area accountable care organizaion is setting its sights on establishing a national footprint.
Medical Home Network, which manages the Medical Home Network ACO, has also implemented its new MHN Baseball Card platform to provide clinicians with at-a-glance patient data and risk scores for their patients, and is has fine-tuned its AI-powered risk stratification model to be even more predictive, says Cheryl Lulias, MHN president and CEO.
With this technology, MHN has reduced addressable social determinants of health by more than 37%, Lulias says. And it’s integrating admission, discharge, transfer, and other patient data across four different electronic health record systems for 13 health systems – including 31 hospitals in the Chicago area alone – and more than 160,000 Medicaid safety net patients.
System integrations give providers real-time alerts concerning hospital admissions and discharges and prompt providers to follow up with patients on tasks described in their discharge plans.
Clinicians can review patient histories and care plans, assess their adherence to prescription medications, and review actions taken in skilled nursing facilities and in so doing, potentially avoid unnecessary emergency hospital readmissions or other emergency room visits.
Cheryl Lulias, president and CEO of the Medical Home Network. Photo courtesy MHN.
"We start our care management process by screening on social determinants,” Lulias says. “Are you housing insecure? Are you food insecure? Do you have transportation issues? Do you feel safe? Rate your own health.”
"We've applied AI for about three years,” she adds, ”and we've created a dynamic risk stratification based on social determinants of health, and this flows through the baseball card to write the risk score."
MHN has shown that healthcare costs increase by 60% for patients affected by one social determinant of health, Lulias says, while patients facing four or five social determinants will be 200% more expensive in the future, even if they have no other medical risk factors.
During the COVID-19 pandemic, MHN was able to identify SDH risk factors in 15,500 of its 167,000 lives, and had care teams calling the day after initial treatment to connect them to the appropriate services and resources, she says.
"Our mission has been to transform care and build healthier communities in the safety net," Lulias says. "We were started to unite disparate providers, to organize them around a shared vision for really improving the health of the communities we collectively serve, but also to create a new model of care, in a much more integrated fashion, where MHN could be the convener to bring together primary care hospitals to work in service of the patient in a more organized way.”
"Our mission is national," she adds. "We want to transform care and build healthier communities in the safety net nationally."
One way of growing that national footprint is MHN's ongoing partnership with athenahealth.
"Athena is one of the EMRs that several federally qualified healthcare centers are on," Lulias says.
Last November, MHN's Baseball Card technology, which was developed internally at MHN, was deployed to eight FQHCs, part of an MHN ACO that consists of 13 such centers and three hospital systems. Rollout to other EMR systems and the clinics they serve will continue during 2022.
New MHN integrations are underway in Missouri, North Carolina, Ohio, and southern California, Lulias says.
"We're going to continue to accelerate our development," she says. "Our goal is to bring in all the digital relevant data to continue to enable a 360-degree view of the patient, and to optimize accurate and fulsome communication between members of the care team."
Exchanging real-time alerts is important, "but we think it's table stakes, to put it in context of the broader data, so you can make an intelligent assessment and prioritize what you need to do with it," she says.
Today, the ACO is at 50% risk, but over time Lulias expects that to increase.
The initial $6 million funding for the nonprofit Medical Home Network that operates the ACO came from the family of Gary Comer, founder of Land's End, in 2009. After the ACA passed, MHN received a supporting grant from the Illinois Medicaid program. Today, Lulias says, most of its revenue comes from service charges.
At this point, primary care has returned to more in-person encounters, but Lulias says virtual care is here to stay.
"There's a lot of value to virtual visits, but the key is knowing what all parts of the delivery system are doing, so you can optimize patient care coordination and care," she says.
Another key technology component is mapping all patient information to a standard enterprise master-patient index.
"It's really important, from a tech standpoint, to take all this disparate information and manage it to an individual member, no matter what the source of the data or the format of the data," Lulias says.
New services are filling in where HIEs and national EHR exchange data fall short.
Eprescribing continues to grow, and with it, healthcare IT organizations face new challenges and opportunities to share the information associated with it.
Eprescribing provider DrFirst recently announced that its iPrescribe service continues to grow steadily. In 2021, nearly 6.5 million prescriptions were processed through iPrescribe, representing more than 100% growth year-over-year. Its user base grew to more than 26,000 prescribers, an 80% jump over the previous year.
Two years ago, DrFirst hired Colin Banas, MD, as its chief medical officer. Banas had previously served as the chief medical information officer of VCU Health from 2010 to 2019. HealthLeaders spoke to Dr. Banas about the growth of eprescribing and related issues. This interview has been lightly edited for clarity and brevity.
HealthLeaders: This notion of medication history as-a-service sounds like it's something that may or may not be closely tied to the rest of the electronic health record.
Colin Banas, MD: A lot of traditional EMRs give their partners the opportunity to make a connection to an external medication history feed, and it's usually at a cost. With the big EMRs like Cerner, Epic, Allscripts, and Meditech, you can subscribe to a medication history feed. If your facility has it, and you've trained your users, the patient presents to the ER, and the clinician can click a button, which queries a database and brings back data for what the patient has gotten filled in the last three months, six months, up to a year.
The traditional medication history feed is from a company called Surescripts. And a lot of their data is adjudicated claims data. They're connected to pharmacy benefit managers. They know that I used insurance to go pick up my Lisinopril or whatnot. And they have connections to some of the big-box retail pharmacies. DrFirst has partnered with Surescripts, so we have that data feed, but also we've been an eprescribing company for 22 years. Over the course of two decades, we've made a lot of relationships, whether it's with health information exchanges (HIE), our own eprescribing data, and then, we also have connections to a lot of the smaller pharmacies, because we've made connectivity to their dispensing software systems. So right there, you've got more data coming in.
My former role was as a hospitalist and CMIO at an academic health system, and I remember how great that med history button was, because before that we didn't have anything. It was the interview or bust, or the patient brings in a giant bag of pills and you sort it out. And while that button was great, we learned quickly that it wasn't perfect in two ways.
One, some medications would not be on the list. Second, the instruction information (i.e., take one pill by mouth daily) can often be lacking in the data feed as well. The reason is, if it's coming from a PBM, they only care about the [national drug code (NDC)], or the drug, and the number of pills that went out the door, so the instruction data gets stripped, or never gets into the feed. So there's another source of potential error, where if you don't know the instructions, you don't know how the patient was supposed to be taking it. It can get dicey in terms of clinical care.
HL: How is medication history data updated? How do you correct errors?
Banas: We have that core feed that I described before, plus the local pharmacies that we're able to make connections with. We also have some connections, depending on geography, to health information exchanges.
We have some ability to incorporate patient-reported medications on one of our mobile applications. So if you curate a med list on the mobile app, it'll get into the feed as well. A lot of local pharmacy data is getting batch uploaded at midnight, every night. One of the first things we have to do is clean it up. We have to remove the duplicates.
Then the real game changer, and my aha moment as a CMIO and then joining DrFirst as the CMO, was this technology. Anywhere in the DrFirst lexicon you see the prefix "Smart," it means that our patented technology, the AI, is cleaning up the data, de-duplicating it, but also turning any free text back into structure, and inferring any of the missing pieces. That's how you get a more complete and safer medication history service.
HL: Do interoperability platforms such as CommonWell, Carequality, and eHealth Exchange deliver medication history as-a-service or not?
Banas: The interoperability landscape is tricky. They don't necessarily serve up med history as-a-service per se as much as they serve as a repository for those [continuity of care documents (CCD)] that get automatically transmitted after certain care events. A lot of that data can come in and allow the user to import. But again, that's only as good as what went out. It doesn't necessarily reflect what got picked up at the pharmacy or what didn't get picked up. It has the potential to be a corollary, but I wouldn't depend on it as a core medication history service. There are too many holes.
HL: Are you doing anything to promote improvement on that front? Is there something the industry as a whole can do to make that better?
Banas: One of the problems with interoperability is this notion of semantic interoperability. We're good at moving chunks of data from A to B. But we're not so good at the receiving system consum[ing] it without a lot of manual intervention. There's a couple of problems in the industry.
One, there's five different drug compendia out there. There's First Databank. There's Multum. And so the sending system might be using FDB, but the receiving system is expecting Multum. For the most part, it matches. And when it doesn't, it becomes free text. You lose all the interaction, checking on drug-drug, drug-allergy interactions. And a human has to fix it. Smart can sit in between the compendia and make sure that the NDCs are going to match no matter what.
The second thing Smart does is, we know how you've set up your nomenclature. I'll give you an example. There's a paper out of University of Michigan. They studied the most common sig [instruction] in the industry: take one tablet by mouth daily. Makes sense. They found 835 permutations of that instruction set. Some people have "tablets." Some people have "PO." Some people have "oral." We learn how you set up all of your various nomenclatures. We intercept the message, we restructure how the system expects it, and then we land it.
You're saving massive clicks and keystrokes. You're making the pharm tech, the nurse, and the clinician much more efficient. But more importantly, it's just safer. We have two papers in peer review right now showing the impact of our technology on reduction in adverse drug events and events reaching patients. But you can imagine putting that technology in front of an HIE and improving that portion of interoperability as well.
HL: According to the NIH, more than 40% of medication errors are believed to result from inadequate reconciliation in handoffs during admission, transfer, and discharge of patients. How does your platform help reduce those errors?
Banas: Part of the software also shows you the gaps that we're filling in monthly in terms of patients you were previously missing, or drugs that you were previously missing; we were able to add to the dataset. One of the reports is about dangerous medications that we were able to fill in. I sat on medication safety committees in my former role. A good example is a patient came in for a bypass surgery. It was revascularisation of the leg. The seizure medication was missed on the med history. Therefore, it didn't get reconciled and the patient never got started on it. The patient did fine.
On post-op day five, they're getting ready to get discharged. They have a seizure. Because they seized, they aspirated. They ended up on a ventilator [with a] two-week stay in the ICU. That's entirely preventable, and it's exactly what [the] NIH study alluded to, which is missing medications up front has a cascading effect throughout the continuum of care. Having a more complete data set is a huge piece of it.
The second piece is reducing the human intervention, the human tendency to introduce error into a process. Anytime I'm asking a human to re-transcribe something, or re-input something, I'm risking them making a mistake. The one becomes an 11, or the twice a day becomes four times a day because I went too fast on the scroll wheel. When you study medication errors, it's all about the Swiss cheese model, where it slips through all of the holes in the Swiss cheese, and reaches the patient. Anywhere that you can introduce automation and technology to augment the clinician experience, you're reducing error.
HL: A 2014 report by the Institute for Safe Medication Practices found that electronically transmitted medication history information, used for medication reconciliation, has potential for inaccuracy. To this day, physicians report continuing concern for some of these transmissions to introduce errors due to missing special characters, such as a decimal point, a forward slash, or a percentage in some records. How prevalent a problem are they, and what amount of patient harm or physician and pharmacist rework do problems like this introduce?
Banas: [Here] is a real-world example. There was a mistake on some of the data feeds where [the instructions say] to take a quarter tablet every day. Well, [in] 1/4, the dash would fall off, or the system would interpret it wrong. And it would be interpreted as 14 [instead]. Take 14 tablets every day. Some of the core data feeds turned off the instructions, because they knew that that error was out there.
The Smart technology has statistical and clinical guardrails around it. It's about a decade in the making, and it's processing 15 million transactions per day. There's a team of clinicians that oversees it. And we're only making these restructuring translations or inferences when it matches up with what's statistically normal and safe. In the example of one quarter becoming 14, we would know in our data that 14 tablets per day for that drug was never normal.
The AI is trained to only [bring over data] when it is statistically safe and clinically normal. And we do it with about 93% accuracy. And the 7% that we don't do is intentional. We want a human to look at it because something's off. We don't want to get this wrong.
HL: How confident are you when you remove a duplicate that it is truly a duplicate and not something that should not be removed?
Banas: 100% confident. I have 10 different data sources, but it all represents one fill event. One of them came from the PBM. One of them came from the prescribing software. One of them came because I'm connected to the local pharmacy, but it's still you picking up that Lisinopril, so I know that all 10 of those have the same timestamp. And I know I can mush them together and [know] that's one fill event, and here's the most complete data set for that fill event.
HL: What needs to happen next?
Banas: If your doctor writes you a prescription or a set of prescriptions, about 15 minutes later, in automatic fashion, we're going to ping you with a text message and deliver up an app-like experience. We're not going to make you go get an app. Literature shows that people respond to SMS, or at least look at them. And the app serves up education, short videos, coupon cards … or copay assist. And we've been able to show a 10% reduction in abandonment through patient engagement. My mission as CMO is, where can we insert our technology in the lifecycle of the patient journey, and specifically, the patient medication journey to make it safer, and achieve the quadruple aim?
Editor's note: This story was updated on March 18, 2022.
The Puget Sound-area health system follows in the footsteps of its corporate parent, CommonSpirit Health.
The 11-hospital Virginia Mason Franciscan Health system, serving the Puget Sound region of Washington state, recently announced a new collaboration with Contessa Health to operate Home Recovery Care, a care model that brings all the essential elements of hospital care into the comfort and convenience of patients' homes, offering a safe and effective alternative to the traditional inpatient stay.
Home Recovery Care is slated to launch at the health system's St. Joseph Medical Center in Tacoma later this year, aimed at patients with a variety of acute conditions including COVID-19, pneumonia, cellulitis, chronic obstructive pulmonary disease, congestive heart failure, and urinary tract infections. The payer mix at Virginia Mason Franciscan Health is 30% commercial insurance, 50% Medicare and Medicaid, and 20% self-pay/charity care/workers comp/TRICARE.
Ketul J. Patel, MHA, MBA, chief executive officer of Virginia Mason Franciscan Health, spoke with HealthLeaders about the new hospital at home initiative. This conversation has been lightly edited for clarity and brevity.
HealthLeaders: Is this part of the overall hospital-at-home trend?
Ketul Patel: This pandemic has driven us to be a lot more creative in terms of our approach to care. We entered this relationship with Contessa to do exactly that. When you just look at our quality outcomes, our safety scores, we're one of the best in the country, and for us to now be able to increase that level of care closer to where all of us would like to be, which is home, the better for us. And this was an opportunity for us to be able to do that.
HL: What was the timing involved that said, let's do it now?
Patel: Virginia Mason Franciscan Health has had many days that were over 100% occupancy. We want to be able to commit to finding opportunities for patients to stay out of the hospital [and] create capacity for us, so that we can take care of those who are critically in need of an inpatient stay. We decided to launch this now because we've found a partner that we think is strong and has the ability to help us scale all throughout our system.
HL: The technology involved has been evolving over the past few years. How ready is the technology to handle things, maybe even at scale?
Patel: Before 2020, we saw less than 2% of our patients on ambulatory setting virtually. At the height of our different surges, particularly in the beginning, we escalated all the way up to the mid-20s%. We're hovering in the 16%–17% range right now, in terms of virtual care. The technology has caught up to us, frankly.
HL: Why did you select St. Joseph Medical Center in Tacoma to do the initial launch?
Patel: St. Joe's has had the highest level of occupancy in our system for a number of years. It's one of our three tertiary care facilities in our system. It made the most sense for us to be able to do that, given the capacity challenges and some of the opportunities that we have in a tertiary-based hospital.
HL: Other hospital-at-home solutions have implemented their own dedicated internet connections in these cases, due to concerns about reliability of ordinary commercial internet. Do you do that also?
Patel: We have not done that yet. We're going to see if that's a need that we have. Connectivity to the internet goes into decision-making that we have in terms of identifying patients who are the right patients to have in this home recovery system.
HL: What are your goals for usage? What are the general milestones you're looking at?
Patel: I'm a big believer that we go slow to go fast. We need to have a sample size of patients that not only have gotten the right kind of treatment, but they're experiencing the kind of patient experience that we want. They feel safe. They are improving. We see readmissions rates continue to drop. So, we want to start there. Rather than forecasting numbers, in terms of what we want to see, I want to make sure that the pilot shows legitimacy around patient care, patient satisfaction, and impacting some of the metrics that we've talked about, which is slowing down readmission rates, and it's improving patient care.
HL: There are so many technologies and telehealth offerings these days. How did you narrow the selection down to Contessa?
Patel: It was a bigger question. One is, should we build it on our own? Or do we partner with a company like Contessa? So obviously, the first decision we made is we want to look for a partner. We've had history with Contessa in other parts of our system at CommonSpirit Health. And so that was, in many ways, a proof of concept for us. The biggest issue for me, though, is that we want to make sure that any partner that we have is a good partner for us in terms of our values, in terms of our focus. Our brand is so strong in terms of clinical outcomes and quality and safety, we want to ensure that the partnership that we're in is going to continue to help us elevate our performance for our patients.
HL: Does this in any way represent an alternative to building more hospital beds?
Patel: Well, I would assume that if this continues to proliferate, we all talk about moving into the value-based care segment. In the Pacific Northwest, we're still predominately fee-for-service. And we feel strongly at Virginia Mason Franciscan Health that we need to move patients outside of the hospital. It's models like this that will help us go certainly into that journey, have a little lower total cost of care for our patients in our communities, [and] be less reliant on inpatient stays on a day-to-day basis.
HL: How do you roll this out from a staff and culture point of view?
Patel: When we go through the hiring process, we want to make sure that the culture that we not only have but that Contessa has, our partnership has, is seen through the staff when they provide that level of care.
HL: So there are going to be dedicated staff, some of which are yet to be hired, that will help implement this?
Patel: Yes, so we'll have nursing staff that are going to be embedded as part of this relationship with Contessa. We're going to be using our existing physicians that are part of Virginia Mason Franciscan Health to oversee, from a physician perspective, the level of care. They also are going to have other responsibilities, but at the same time, when you're dealing with this level of care, our physicians are skilled to be able to do that. The clinical staff that are going to be in and out of homes are going to be important for us, too.
HL: Can you be more specific about the implementation timetable?
Patel: Well, the gating issue for us right now, much like anywhere else in the country, is staffing. When we have a core staff, we're going to be ready to go. In the next few months, we'll be launching this for sure.
HL: Are you at all inspired or challenged by efforts you've seen elsewhere? What's your interpretation of how it's been going elsewhere?
Patel: We've obviously done our homework. And there's nowhere else better to look than our own family, within CommonSpirit. That was a good proof of concept for us.
HL: You mentioned being predominantly fee-for-service. To what degree can this help you move toward more value-based care?
Patel: All of us feel obligated that we need to do that. And again, it's not about, as you said, increasing our bed capacity, even though we do need that in the Pacific Northwest. We have to invest in the overall continuum of care. And this to me is part of that continuum of care. It's an obligation, not just an idea. It's an obligation for us to move into value-based care. And obviously, initiatives like this are going to drive us to be able to do that.
I am proud of our entire team. We all have staff members that are incredibly fatigued but working hard. I love to see that every single day when I'm rounding.
Technology-enabled hints embedded within the EHR can deliver real-time cost information, which clinicians can then use to select less expensive alternatives for medications and labs.
A new study analyzing how subtle variations in patient care can add up to big differences in the bottom line has found that physicians become better stewards of certain costs when they’re given real-time information about cheaper alternatives during evaluation and treatment.
The physicians involved in the research were presented with technology-driven hints in the EHR, many of which pointed out cheaper alternatives when they were prescribing medicines. The technology was able to track changes in prescribing behavior, which formed the basis for the study findings.
The eight-month study by Birmingham, Alabama-based IllumiCare evaluated 287 physicians identified as hospitalist, internal medicine, or family medicine providers who placed at least 50 orders and cared for at least 15 patients.
The goal was to develop a method to directly measure behaviors that correlate with higher spending and to determine if an effective method exists to intervene on those behaviors in a way that reduces both the behaviors specifically and spending generally.
The study found that when providers are “nudged” to stop wasteful behaviors, their average spend on meds and labs goes down by an amount that exceeds the sum of the specific opportunities identified. It showed that for every $1 decrease in average savings opportunities per provider per patient, the clinician actually saves up to 1.5 times that amount per admission.
"It's amazing that when you sort of activate clinicians to become stewards, what happens is that that ethos begins to blend over to other decisions that they make, which is a beautiful thing," says G.T. LaBorde, chief executive officer at IllumiCare, which develops and markets real-time cost information technology.
The study follows years of work demonstrating that increased spending does not assure better outcomes in healthcare, LaBorde says. One Dartmouth study, he noted, showed that hip replacement costs in Texas are one-third of what they are in New England.
The new study acknowledges that health plans' higher co-pays and deductions now put more of the cost burden directly on patients, who want just enough healthcare to get well and go home, LaBorde says.
As an example, LaBorde cites cases where some physicians treating C. diff prescribe vancomycin, while others prescribe fidaxomicin, not knowing that the latter medication typically is four times the cost of the former.
"It's not like they teach physicians what things cost in medical school, and these costs change all the time," he says.
Ultimately, it’s up to the clinician to prescriibe the most appropriate medication.
"Today they're making those decisions without any knowledge of the relative cost of the choices," LaBorde says. "Our goal is to allow them to know that. But we would never second-guess a provider and say, ‘Hey, why'd you order that expensive drug?"
Companies like IllumiCare develop technology platforms that deliver real-time updates through HL7 feeds, and are often EHR-agnostic. Hospitals license the technology and are then able to tailor the alerts to their own formularies, eliminating hints that would be irrelevant or out of scope.
According to LaBorde, some 95 percent of clinicians using the technology keep it handy while dealing with patient care, and 83 percent actively check for pricing comparisons.
According to the study, the platform offers more than 1,400 opportunities to make less costly clinical decisions without compromising quality in the right clinical context. These opportunities predict 47% of the financial variation, risk-adjusted, in medication and laboratory spend in a patient’s admission.
An earlier study found savings of about $110 per admission, reducing medication, laboratory, and radiology costs by about 14%.
Payers and accountable care organizations are also using the technology to lower the cost of care by identifying providers who consistently use higher-priced alternatives, LaBorde says. And the technology doesn't interfere with other EHR alerts that may favor a more expensive medication, due to concerns such as a drug-drug interaction.
The hints disappear after briefly being displayed, unlike traditional EHR alerts, which may require a physician to type in a reason to dismiss a particular alert, LaBorde says.
The study reinforces the strategy of using technology to help clinicians become more cost-conscious.
"When you look at the clinicians who begin to attack these opportunities, and they begin lowering their wasteful behavior, they actually lower the overall cost of care more than the opportunities that have they've captured," LaBorde says.
This is true in part because the technology typically recommends a cost savings only when confidence in the data approaches 100%, he said. But it opens physicians to consider cases where the confidence in cost savings dips to 70% or 50%, and physicians are able to consider them anyway.
UpLift, which launched less than a year ago, is using an EHR tool to give patients quick and easy access to scheduling a psychiatrist appointment during a counseling session.
A modular, extendable ambulatory electronic medical record software platform has enabled a mental healthcare provider to quickly innovate to integrate psychiatry into its offerings.
UpLift, which started operations at the end of 2021, is using technology from Canvas Medical, a San Francisco-based EMR and payments company, to deliver faster, more targeted psychiatric referrals, even allowing therapists to schedule follow-up psychiatric care during their own patient encounters.
UpLift's service delivery model is based around the patient-therapist relationship and is delivered 85% virtually and 15% via in-person encounters.
"While in a video session, the therapist is able to actually look at the psychiatrist schedule, understand their profile, and actually book that encounter, send them a note, and be able to do that at the point of care," says Kyle Talcott, the organization’s co-founder and chief executive officer.
This convenience replaces the traditional therapy practice of steering patients undergoing mental health treatment to directories of psychiatrists so that they can book their own follow-up appointments, and it helps pre-quality patients for the referral by matching patients with the insurance accepted by the psychiatrists.
The in-network referrals currently connect the patients to psychiatrists employed by UpLift, but could be expanded to other psychiatrists that also accept the patient's insurance, Talcott says.
As a result of the follow-up appointment being made by UpLift-contracted therapists, "we have very low no-show rates, especially compared to [other] mental health providers," he says.
The key technology enablers are application program interfaces (APIs) included in the Canvas EMR that permit UpLift's technology team to orchestrate desired features, such as the in-session psychiatric referrals.
At a time when America faces a crisis of demand for mental health services and a shortage of qualified therapists, the UpLift playbook is to innovate in nimble ways to fill this need. The platform allows the company to reach out to the growing number of therapists who have opted out of working for large healthcare systems and networks.
"We started out really focused around solving the pain point of finding an in-network therapist," Talcott says. "So we work on both sides, both bringing therapists into our virtual group practice, and then helping them actually enroll, get credentialed with and contract with the large health plans in a given area."
UpLift contracts with close to 500 therapists, and its growth strategy is regional in nature. It now offers services in the District of Columbia, Virginia, and Maryland, Talcott says, and in March will expand into Florida.
The company also reaches out directly to consumers, working with local providers to help patients find in-network therapists.
The integration of psychiatric services adds some core capabilities that psychiatrists require beyond what therapists can do, such as e-prescribing and some EMR components.. Canvas APIs made that integration work more smoothly than any other alternatives evaluated by UpLift, Talcott says
Talcott says his history with digital health startups left him with the impression that many keep rebuilding the same components, thus slowing down innovation. The Canvas platform, he says, enabled UpLift to achieve the needed data integration and automation more quickly.
"For us, the ability to bring in some of these components, which are very complex, you could do individual integrations, but it would take a long, long time," he says. "To be able to bring them in through somewhat standardized APIs that are prepared has allowed us to speed up. We were able to launch psychiatry in close to a month."
The use cases for therapists and psychiatrists are different enough that UpLift had to optimize each use case. For example, psychiatrists need to be enrolled and credentialed into each health plan UpLift supports.
"Some take longer than others, so when somebody is looking at a schedule, it's actually the right psychiatrist for them," Talcott says.
The technology also helps match patients to the right therapist, he adds.
"As that patient journey continues, the information is shared between the two providers, which historically has not really happened in mental health," he says.
Traditionally, a patient sees a psychiatrist, who may prescribe a medication. Patients may return to see the psychiatrist as little as once a quarter, while they continue to see their therapists weekly, Talcott says.
If the therapist senses some issue or side effects with the medication prescribed by the psychiatrist, the UpLift platform is able to send that information to the psychiatrist, who may adjust the medication or dosage between psychiatric appointments, Talcott says.
Although initially offered as a fee-for-service, UpLift's model anticipates the move to value-based care.
"Our goal is to move towards shared risk over time," Talcott says. "The health plan landscape is very early, especially in broader-based mental health. We're in conversations now with various health plans around how we build a bridge towards shared risk."
The company is also considering integrating pharmacists into its care team, he says.
"Having pharmacy be able to understand the impact of all those medications is really critical," Talcott says. Such a model, he notes, may become more practical as the service moves from fee-for-service to value-based care contracts.
The Michigan-based integrated health plan is the first insurer in Michigan to implement the platform, which will allow for real-time exchange of patient health information at the point of care between Priority Health and providers. It will first set up the platform with Spectrum Health and other contracted providers using Epic, then plans to expand in the coming years.
"We understand that data from a health plan needs to be actionable at the point of care to drive effective engagement from our provider partners," says Praveen Thadani, president of Priority Health. "Because Priority Health is part of an integrated delivery system, we are uniquely positioned to excel in this space, and have the needed tools and resources for successfully implementing an advanced information sharing tool."
The Epic Payer Platform reduces what had been a three-screen care coordination process (EHRs, population health disease registries, and practice management systems) for physicians to a single screen.
Michelle Ilitch, vice president of network solutions and value-based programs at Priority Health, says that will help reduce burnout. It will also help patients communicate with their care providers when they receive services outside the network.
One example particularly relevant in Michigan is snowbird patients who may receive vaccinations in Sun Belt states. If the Sun Belt provider uses Epic, the Epic Payer Platform will notify a patient’s primary care physician back in Michigan that the Sun Belt treatment resulted in a claim paid by Priority Health, thus closing a gap in care.
Michelle Ilitch, vice president of network solutions and value-based programs at Priority Health. Photo courtesy Priority Health.
The platform offers minimally disruptive alerts in the EHR to let the primary care provider know that a claim has been paid, Ilitch says.
"Many providers are not owned by health systems," she says. "If we refer an endoscopy scope to a GI practice, how do we know the patient actually showed up for the visit at the GI doctor and got the scope? [The] Epic Payer Platform will share to us that did in fact happen, because we'll be able to see that claim actually hit the system."
Physicians are also able to query gaps in care as reported by Priority Health, not just gaps reported in their own EHRs, Ilitch says, thus improving care coordination.
"We're moving, as a society, from a world that was based in static reports to views," she says. "What a health plan can do is liberate its datasets to improve quality, reduce costs, and respond to physician burnout."
Physicians "want to see views, to log into something and see it live," Ilitch says. "We don't necessarily want to log into something and pull down a bunch of static reports and then have to go fishing to tell a story."
This, in turn, will allow payers such as Priority Health to do less work to publish gaps in care reports. "Instead of us pushing data, physicians can pull data, live in the EMR," Ilitch says.
Priority Health's investment in the Epic Payer Platform will pay for itself "in spades when we see more providers be interested in taking financial downside risk," Ilitch says. "To us, the ROI proof point is accelerating that transfer of financial risk from a health plan to physicians and acute care hospitals. Over time, we will see that ROI play itself out as more doctors say, ‘You know what, I want to partner with Priority Health because they understand how important data is for me to be able to wring out waste.’ So that ROI will come over time."
The Epic Payer Platform also provides a unique way of documentation that's important for regulations tied to risk adjustment, Ilitch says.
"The tool is going to be able to help us better understand the actual disease burden of the populations we serve," she says.
Ilitch says provider uptake "will be taking place through the course of this year, through a series of cohorts that we're going to bring on over time, as we get health systems ready to tackle this with us. We're still in a world where change is hard, and COVID is distracting."
Priority Health wants primary care specialists to adopt the Epic Payer Platform at a pace to their liking.
"That's why our rollout is going to occur throughout this year and in future years," Ilitch says. "A lot of doctors view this as a big sigh of relief, because it takes away the guessing that happens a lot when a payer provides static PDF reports."
"If there was ever something that embodied the Quadruple Aim, it would be this tool," she says. "Better care, lower costs, patient satisfaction, and bringing the joy of practice back or dealing with physician burnout."
The Epic Payer Platform also complements the work Priority Health is doing with health information exchanges, Ilitch says.
"HIEs in Michigan solve a really important gap in how we connect together entities that are involved in social determinants of health, and help solve problems related to focus areas on what quality measures we want to go after,” she says. “Those HIEs solve an important role in helping us to communicate with electronic medical records that sit outside of the Epic platform."
Former ONC chief Don Rucker and HL7 are championing a new form of healthcare IT interoperability.
Newly maturing standards for healthcare data interoperability will make providers more accountable to payers for the overall quality of care they provide.
"When we look at the big problems in American healthcare, we want value," says Rucker, now the chief strategy officer of healthcare IT company 1UpHealth.
After what he describes as a 20-year-long search for value via quality measures defined by the federal government, Rucker believes the current system is "heavily gamed" and will be replaced by a new system of bulk data sharing of patient information via the new Bulk FHIR interoperability standard.
In the spring of 2020, the ONC published a rule regulating the 21st Century Cures Act API requirement, along with protections against information blocking. One of the APIs covered in this rule is the SMART/HL7 FHIR Bulk Data Access API, or Bulk FHIR API, which enables access to patient-level data across a patient population, supporting many use cases across the healthcare ecosystem, including:
Integration of an internal clinical system with an EHR;
Biosurveillance, syndromic surveillance, and disease reporting;
Post-marketing surveillance of therapeutics and devices;
Combining claims and electronic health record data to calculate quality measures;
Building datasets to develop and tune machine-learning algorithms; and
Federated data sharing networks for multi-institutional research.
"Put simply, Bulk FHIR is a standard to enable 'push button' population health," states an informational page at the Computational Health Informatics Program of Boston Children’s Hospital, which helped develop the standard in conjunction with HL7 and the ONC. "An ACO, a researcher, or a public health authority should be able to, without special effort, extract a cohort of patient records from the EHR for further analysis."
Donald Rucker, MD, former head of the Office of the National Coordinator for Health Information Technology (ONC). Photo courtesy Donald Rucker.
Prior to Bulk FHIR, traditional quality measures adopted by the Centers for Medicare & Medicaid Services (CMS) and others were "all microscopic tranches of performance," Rucker says. "They're not integrated performance to make patients live longer or be healthier. Hemoglobin A1C is one of the most global measures, but a lot of these other [quality measures] are super narrowly defined."
As proof that traditional quality measures have failed to meet their objectives, Rucker says one only need look at the COVID-19 pandemic.
"Most state HIEs have, from the get-go of COVID, been able to answer all of the major questions that have somehow befuddled [the Centers for Disease Control and Prevention]. Who's getting affected? What is recovery? What is immunity? What are comorbidities? What things work? We have vast data stores on that, and huge statistical significance over all populations."
By contrast, Rucker says, the CDC has been unable to use huge silos of its own data to answer these questions in a timely fashion.
Too much emphasis in healthcare data interoperability has been placed on helping individual patients access their data or move it from one provider to another, he says, and not enough is placed on giving payers timely information on populations of patients so they can give providers better incentives to improve population health.
Other federal initiatives, such as adding social determinants of health to inform patient education and motivation to improve health, are falling short for other reasons, he says.
"A lot of that probably has nothing to do with the healthcare system and everything to do with the educational system," Rucker says. "If you are in an inner-city school and you can't effectively read or write, as is too often the case, [patients] are not going to be reading articles about how lipids are affected by their lifestyles."
Instead, healthcare needs a totally different kind of interoperability, based on patient populations, and intended to improve the value dialogue between payers and providers, Rucker says.
"The bulk API is going to take away most of the excuses for providers, exposing the data of their performance to the payers who paid for it," he says. "Americans love to shop, we want to be able to shop for good care. You're relying on your payer to get you a good deal in healthcare. With both FHIR and the U.S. Core Data for Interoperability, we finally have a standardized data set and a standardized API that makes it a lot easier to get this information."
Payers, as well as providers, require education about this new form of data interoperability, Rucker says.
"It's a totally different mode of doing business," he says. "When we have computational accountability in healthcare, it'll be a game changer."
While the data being shared could confirm previous studies that surgical prices vary widely from region to region, "shipping a patient [to lower-cost regions for surgeries] is almost the failure mode model," Rucker says. "There are a million way more economically effective interventions earlier on, if you have computable data."
1Up Health, where Rucker now works, is one of several healthcare IT vendors that such interoperability endpoints on the payer's side, Rucker says. State health information exchanges, as well as national data-sharing efforts such as Commonwell Alliance and Carequality, are other likely endpoints for this expanded interoperability, he adds.
"Some of this, I think, is inevitable, just because the availability of all of these [data analysis] tools in the entire rest of the economy," Rucker says.
The health system’s CMIO calls the conversational AI technology a 'game changer in healthcare.’
A health system in southwest Michigan is betting big on conversational AI technology to improve care and the doctor/patient experience in primary care.
University of Michigan Health-West has implemented Nuance’s Dragon Ambient eXperience (DAX) technology for its primary care physicians, and its executives believe conversational AI technology such as this to become the standard of care within a few years.
The benefits, executives say, include expediting the prior approval process for referrals, which contributes directly to the health system’s bottom line.
"We're doing a systemwide primary care roll-out of this," says Lance Owens, MD, chief medical information officer at University of Michigan Health-West.
During a pilot test of the technology with 15 primary care physicians, the health system's auditors found that DAX directly led to a 40% increase in first-time approval of prior authorizations "because the documentation is so good," Owens says. "It's a life preserver for healthcare."
Capturing the Conversation
DAX works by capturing conversations between physicians and their patients and outputting a SOAP note generated by DAX's algorithms. These notes find their way into each patient's electronic health record in an hour or less, according to Owens.
The technology addresses a major complaint that physicians have had with EHRs ever since they were implemented: Many of them feel the technology makes them more like highly-paid scribes and recordkeepers than doctors.
"It essentially eliminates that cognitive burden of having to put that information into the record," Owens says. "I can now, for just about any visit, walk into an exam room, sit down, turn on DAX, and then literally sit back, look my patients in the eye, have a meaningful conversation, be attentive, being able to synthesize that information, formulate a plan, talk about my medical decision making with the patient, and do my patient education. And knowing that all of that is somehow going to make it to the record in about an hour or less is an absolutely amazing thing."
Setting up the technology for additional physicians requires five minutes per physician to download the DAX app to their iPhones.
DAX's algorithms are able to distinguish different uses for words with more than one meaning, Owens says, such as distinguishing between a fall – as in a patient stumbling – and the fall season.
DAX also prompts physicians to enter orders and prescriptions as part of generated notes.
"If I'm talking to a patient about their X-ray, DAX just intuitively knows [to] show the X-ray" in the EHR, Owens says. "If I'm talking to a patient about starting them on hydrochlorothiazide for blood pressure, the order is queued up for me for signature. If the patient says ' My father had a heart attack since the last time we met,' DAX knows to put coronary artery disease in the family history of her father."
At present, Nuance sends each generated note to a quality data specialist, who reviews the note for accuracy and completeness. But the roadmap for the technology includes a completely automated process, according to Kenneth Harper, Nuance vice president and general manager of healthcare virtual assistants and ambient clinical intelligence. The company began testing those capabilities in December 2021.
"We can start bringing in clinical decision support into the workflow," Harper says. "We'll be able to allow the care teams to engage the patients even more productively, and make sure that the right patient outcomes are being delivered. You could just never do that with a human-based scribe type of system."
Harper says DAX currently saves providers seven minutes of documentation time per encounter.
"That typically equates to two to three hours of documentation time a week," he says.
Health systems using conversational AI technology could simply pack more patients per day into a physician's schedule, but many are using it instead to improve patient experience and working conditions for physicians, and to combat physician burnout.
"Our new vision statement is, ‘Our innovations change care and our care changes lives,’" says Josh Wilda, executive vice president and chief information officer at University of Michigan Health-West.
"Especially with the mission of healthcare being such a volatile mission these days, we got away from that message [of seeing more patients] and really made the message more about the ROI of provider well-being, of provider-patient intimacy, as well as the ongoing innovation of what this is going to bring to our team," Wilda says.
The health system turned to its charitable foundation to pay 60% of the first-year costs of the technology, Wilda says.
In terms of return on investment, Wilda says the technology gives them the ability to retain providers for many more years than might be possible without it.
"It's hard to put … a price tag on that kind of relationship," he says.
Conversational AI is Still a New Concept
Conversational AI is still in its infancy, due to the various challenges that face the clinical documentation process.
An effort to expand the use of DAX to specialists faces more challenges, in part because of the tendency of some specialists to perform "pre-charting," or carrying over written notes from previous patient visits into new patient encounters.
“I just don't think it worked well with our providers,” Owens says. “We're hopeful that as we grow this out, our specialists are just going to go, ‘Wow, when do I get that?’ There is no question in my mind this technology is going to be universal throughout the world."
"I wish from an industry standpoint, there was a golden standard for documentation, because actually, the AI would be able to learn that much faster," Harper adds.
Oklahoma State UMC’s telemedicine program has attracted rural critical access hospitals as customers during the pandemic
As the first wave of COVID-19 hit Oklahoma, 20 rural sites were able to connect within 120 days to a newly-built statewide network for telemedicine and hospitalist-based services through the Oklahoma State University Medical Center, part of OSU Medicine.
"We were working in close concert with 20 critical access hospitals across the state and embedding a hospitalist service that allowed them to expand their clinical capabilities and their clinical expertise for the purposes of providing an enhanced level of care locally, up to and including the care and treatment of COVID patients in their community, when and where appropriate," says Rhett Stover, MHA, FACHE, OSU Medicine's chief executive officer.
As part of the telehospitalist program, OSU Medicine deployed AGNES Connect, a cart-based platform from AMD Global Telemedicine that enables OSU Medicine-contracted hospitalists to connect through video conferencing to the on-site clinician, and to perform a medical assessment on the patient. On-site physicians capture medical device data, including from digital stethoscopes, a 12-lead EKG, and pulse oximeters, that is streamed in real time through AGNES Connect to OSU Medicine hospitalists.
"AMD was able to get us roughly 50, 55 carts in six weeks," Stover says. "That was not a small effort. They've been a great partner" through various supply chain shortages impacting the availability of technological components.
AGNES also connects with each of the rural critical access hospital's electronic health records, expediting continuity of care as patients move from emergency departments into inpatient settings, Stover says.
The success of OSU Medicine's program also rests upon providing personalized care teams to these rural patients, Stover says. This was enabled by a partnership between OSU Medicine and TeleHealth Solution, which provided telehospitalists for rural patients with rounding, admission, and care coordination for rural healthcare markets across the state.
Rhett Stover, MHA, FACHE, chief executive officer, OSU Medicine. Photo courtesy OSU Medicine.
Rural patients meeting admission criteria, based on clinical assessments by emergency department staff, have been admitted to OSU Medicine's hospitalist service.
"Probably 60% to 70% of our services are what we call nocturnal service," Stover says. "During the day, there'll be a physician on site at that particular hospital that will be involved in organizing and providing treatment and working through their care plan."
Then, overnight, OSU Medicine's telehospitalists step in and provide continuity of service while the local physicians are home.
On other occasions, Stover says, OSU Medicine telehospitalists can perform daytime admission services and assessments and even 24/7 coverage.
Whatever the arrangement, "there's a communication loop that keeps physicians engaged in coordination of care on a day-to-day basis," he says. "Collaboration is really important to the success of the program."
In some cases, that involves a local RN or nurse practitioner, instead of a local physician, communicating with OSU telehospitalists.
"We have physicians that are assigned to particular facilities so that you're not just dialing up a physician and getting someone new," he says. "You're getting one of two or three that are completely and exclusively allocated to that local facility and working with that local facility's clinical team and care management and social workers, to the extent they have those resources available."
OSU Medicine has sought to measure the effectiveness of the program through detailed evidence, such as readmission rates and patient satisfaction. Part of the challenge is that each hospital is in a different stage of gathering that data.
"We have seen a strengthened level of performance in the form of average daily census in almost all of our markets," Stover says. "What that means is, the community had an experience with the service, that they walked away from and have confidence in, or they've had members of their family, friends, or others that have had that experience. They now feel like, well, if I need to be admitted to my hospital locally, they have an enhanced level of care that can be provided in a safe, expedient, and quality-driven manner."
Measuring the Results
Some rural physicians had initially felt the service was somewhat forced on them due to COVID-19, but are now more open and accepting, Stover says.
"In some extreme examples, we've had patients tell us that telemedicine is the only way they want to interact with their physician from now on," he says. "We treat that as a positive comment, but we do not see the services that we are organizing as a replacement for the physician-patient relationship. It's always to supplement, support, and add value to the relationship."
The program was initially funded through CARES Act funds distributed to the state, but as those dollars were exhausted, OSU Medicine had to create a model that at least allowed the program to break even going forward, Stover says. Ultimately, the health system established a base fee for the service.
In one case, a rural community pays $18,000 a month for a telehospitalist to be available 24/7 to the local hospital.
"For them to accomplish that in a traditional setting would be about $350,000 a year," Stover says. "So it's an immediate savings that they're getting in that regard."
The lower cost of the telehospitalist through OSU Medicine can be recovered by enabling just a small handful of additional weekly admissions, Stover adds.
As for improving patient outcomes, Stover believes the service has elevated the health status of patients in the rural communities it is serving.
"In some cases, that enhanced level of service and that elevated and quicker attention, you could argue that yes, it's had a profound impact up to and including eliminating mortality," he says.
Longer-term prospects for continuing the program post-pandemic are a bit more of a mixed bag, Stover says.
"It is on a community by community basis," he says. "Five years from now, we'll [have] an industry with medical advances that are helping us address the workforce shortage, and precision with diagnosis, treatment, planning, and care. Hopefully, the result of that is leading to better health outcomes across the most challenging of our geographies in the United States."
A modified Greenway EHR fuels expansion of primary care clinics for the Medicare generation
Using a modified version of the Greenway electronic health record software platform, Oak Street Health has been riding a dramatic growth curve through the COVID-19 pandemic.
As of last November, the Chicago-based primary care provider operates 110 centers, up from 67 at the end of September 2020. Total revenue for the third quarter of 2021 was $388.7 million, up 78% year over year.
Co-founder and Chief Medical Officer Griffin Myers, MD, says technology serves the unique approach of Oak Street, which focuses on value-based care, spending extra time with patients, and high-quality health outcomes to maximize the clinic’s appeal.
"It’s a vulnerable group of patients," he says. "We are focused entirely on what matters to patients.”
“What patients care about tends not to be what I think most doctors think it is,” he adds. “It is not how charming you are in the exam room. It’s ‘Can’t I get an appointment when I need it? Do you make me wait? Do you keep me on hold? Can I get my questions answered? Can I get my test results?’ Things like that."
Oak Street Health Co-founder and CMO Griffin Myers, MD. Photo courtesy Oak Street Health.
Oak Street sees its patients an average of nine times a year, with the sickest 5% of patients connecting, on average, 19 times per year, Myers says.
"The average Medicare patient sees their primary care doctor three times a year,” he points out, adding that the average Medicare patient nationwide only sees his or her primary care provider three times a year. “Our visits are twice as long as the national ambulatory healthcare survey averages."
Patients interact with the same staff in their care team from visit to visit, including through 24/7 phone support, next-day visits, and telemedicine visits. Oak Street centers also offer transportation to and from patients’ homes, and each center includes a 1,500-square-foot community center facility for health education, Myers says.
Since its founding in 2012, Oak Street Health has driven an approximately 51% reduction in patient hospital admissions compared to Medicare benchmarks, a 42% reduction in 30-day readmission rates and a 51% reduction in emergency department visits, all while maintaining a net promoter score of 90 across patients, according to the company.
Technology Makes a Difference
Technology has allowed Oak Street to deliver high-quality care across the patient lifecycle as a matter of routine, Myers says.
"We have technology built to help us onboard new patients, manage their referrals and their interaction with the rest of the healthcare system, and help them through transitions when they do have to go to the hospital," he says.
"We're all really excited about the Rubicon acquisition because it means we're able to democratize specialty care in our communities in a way that's consistent with our values and built into our platform," Myers says. "We are able to bring specialty care to patients in a way that we couldn't before, reducing the need for patients to find transportation or manage medical records on their own. This is certainly better for patients, and we believe it's an important addition to the Oak Street platform as well."
Despite Oak Street’s continued growth, Myers notes that "the pandemic has been really disruptive to our patients’ lives.”
“It has made it harder and harder for people who already found it hard to engage with a primary care model to do that,” he says. “It’s reminded us at a societal level how important primary care, community health, and public health and access is. We’re definitively existed to get on the other side of this, where it’s gone."
The pandemic also disrupted Oak Street’s outreach efforts. In 2019, the company did more than 20,000 community events.
"We couldn’t do that in 2020," Myers says. "While we’ve restarted, we’re not where we’d like to be, because it’s hard to get people in groups right now safely."
A Timely Acquisition
Oak Street has also been buoyed by last fall’s announcement by the AARP as the only primary care provider to carry the AARP name. In addition, Oak Street is one of the very few groups named both times the American Medical Association’s Joy in Medicine Health System Recognition Program has been announced, in 2019 and 2021.
"Our physician burnout rates are very low compared to the rest of the country, but still not zero," Myers says. "Our turnover rates in that cohort are under half the national average. It's proof that we're doing this right. We are adding hundreds of new primary care providers every year, in an environment that is supply constrained.”
Despite that, Oak Street asks its clinicians "to do really hard work," he adds. "Unlike the rest of the healthcare system, we hold them accountable to a certain quality of care. That comes with pressure. In addition, we're doing that in communities and populations that have a very high disease burden. They witness a lot of suffering every day. And that's really, really hard. So I don't want these jobs to be easy. I want them to be meaningful, and they are meaningful."
Several times a year, Oak Street shuts down the practice to do grand rounds, including brining in guest speakers.
At present, Oak Street operates in 20 states across the U.S. "We'd like to be everywhere," Myers says. Entering new markets involves identifying communities where health equity gaps persist, with a critical mass of low-income seniors who lack primary care.
"Unfortunately, there’s a lot of places like that in our country," he adds.
"Our technology has helped us not only to grow and make the patient experience great, but it also gives us a scalable platform to care for more patients and offer a greater breadth of services to them," Myers says.