The health system is launching a project with IBM Research to identify clinical signatures using audio-visual interviews and digital health data from patients 15-30 years old.
As healthcare organizations explore how to use AI to influence patient care, they’re training their sights on ambient and generative AI technology that can sift through data and point providers in the right direction.
The latest to embrace this strategy is Mount Sinai Health Care, whose care teams want to identify young people in need of mental health services and give providers the information to improve care.
The New York-based health system is partnering with IBM Research on what it’s calling the Phenotypes Reimagined to Define Clinical Treatment and Outcome Research (PREDiCTOR) study. The research will use AI tools to comb through not only audio and video interviews but a wide range of digital health data to identify predictive markers that would allow care providers to identify and arrange treatment more quickly and effectively.
“Every clinical visit provides a wealth of untapped behavioral data that includes spoken language, eye contact, and facial expressions from both the patient and clinician,” Cheryl Corcoran, MD, an associate professor of psychiatry at Mount Sinai’s Icahn School of Medicine and co-leader of the research project, said in a press release.
“With advancements in computational approaches, these behaviors can be operationalized and quantified through analysis of audiovisual data obtained from the recording of clinical interviews,” she said. “Coupled with valid behavioral data derived from smartphones that track physical activity metrics like step count and distance traveled, geolocation, social interactions like text messages and phone calls, sleep patterns, and audio data from diaries, we can develop clinical signatures that are indicative of key outcomes.”
The $20 million project, funded by a grant from the National Institute of Mental Health (NIMH), will include researchers from Harvard, Johns Hopkins, Columbia and Carnegie Mellon Universities and use ambient tools developed by Deliberate AI.
The project aims to focus AI on one of the more pressing healthcare issues in the U.S.: the soaring rate of mental and behavioral health concerns. Often the onus of diagnosing these concerns falls on providers who don’t have the background to detect subtle clues.
The research team is focusing on patients between the ages of 15 and 30 who are seeking treatment at one of six Mount Sinai Health outpatient mental health clinics. Researchers say that age range “represents a developmental window during which many disturbances of thought, emotion, and behavior emerge and when diagnoses and prognoses are often still unclear.”
The researchers will combine digital health data with audio and visual recordings of the patients’ visits over a year. They’ll then develop clinical signatures that characterize what those patients present when seeking help, which providers can then use to fine-tune care management.
“Our goal is to gain a better understanding of what predicts whether young people stay in mental health treatment or drop out, and what predicts whether their symptoms worsen such that they need acute care in an emergency crisis center or hospital,” Guillermo Cecchi, PhD, director of the computational psychiatry and neuroimaging groups at IBM Research, said in the press release. “We have shown in our research that artificial intelligence can be used to predict some outcomes in controlled experimental settings, but we believe that current advancements are powerful enough to be applied in the context of usual clinical practice.”
While many say the technology will help clinicians improve care, the workforce shortage and other pressures may prompt healthcare leaders to use AI when they can’t find or afford providers. And consumers may even prefer that.
One of the enduring concerns with AI in healthcare is that it may someday replace the doctor or nurse. And while many experts say the technology is designed to help clinicians improve patient care, there may come a time when that prediction is true.
“We can’t hire our way out of the problem right now,” says Brian Anderson, MD, co-founder and CEO for the Coalition for Health AI (CHAI), who warns that health systems won’t be able to find the doctors and nurses they need to keep pace with increased demand for services, especially from a growing senior population.
The reality is that the healthcare workforce shortage isn’t going to improve any time soon, and healthcare leaders will have to make some hard decisions over how and when care is provided, even as new technologies and strategies create opportunities for care outside the hospital, clinic, and doctor’s office. Healthcare sites are shutting down at an alarming pace because they can’t be staffed, while consumers are demanding access when and where they need it.
And if they can’t see a real doctor, maybe an AI program will do the job.
“We ultimately need to begin grappling with where is the appropriate place where providers aren't in the loop” and AI can be used in their place, he says. “I think that's going to be one of the real challenges.”
In some health systems, nurses are worried their jobs may be negatively affected by AI, and have lobbied for assurances from management.
At the recent HIMSS AI in Healthcare Forum in Boston, Lee Schwamm, MD, SVP and chief digital health officer at the Yale New Haven Health System and associate dean of digital strategy and transformation at the Yale School of Medicine, said healthcare leaders may soon have to include AI in contract negotiations, especially in rural regions where the workforce shortage is particularly acute.
He and others at the forum noted that health systems and hospitals struggling to stay open might see a benefit in using AI platforms to replace clinicians they can’t afford or even find.
At the same time, a growing number of patients are saying they’d prefer an AI doctor to a real one, especially if it improves access and convenience and is covered by insurance.
According to a recent survey of 2,000 consumers by Customertimes, almost 40% say doctors will eventually be replaced by AI.
"The truth is that quality care in the U.S. is often a luxury, available primarily to those who can afford it”, Max Votek, a former pharmacist who co-founded the digital consulting firm. He noted 83 million Americans lack access to primary care services, while new patients wait an average of 26 days just to get in front of a doctor.
“AI will enable quicker access to doctors when time is critical and help reduce costs in many cases,” added Gilbert Merariu, CIO for the pharma research company PSL Group, in the Customertimes press release on the survey. “Consider low-income individuals who may not afford a doctor's visit. With AI, they could chat with an AI that has all his historical medical info and already identify the possible next steps. Then a final review can be done by a DR (at a much lower cost and higher volume) to start his treatment. This would streamline the process and make healthcare more accessible.”
According to the survey, slightly less then half of those surveyed are optimistic about the adoption of AI in healthcare, while 17% fully trust and half somewhat trust AI-powered healthcare. Some 15% are willing to follow medical advice generated by AI, and another 25% would do so if that advice were free.
In addition, 58% said AI would ultimately benefit providers rather than patients, a nod to the belief that the technology can address many of the industry’s biggest pain points. Some 18% said AI will soon be better than humans in diagnosing and treating conditions, while 44% said that will take place “in a distant future.”
Most importantly, 57% of those surveyed said AI will lead to healthcare layoffs, while 13% said the technology will help save jobs. And 10% said AI should replace doctors in the foreseeable future—and another 28% said that will happen but shouldn’t.
Health systems like West Tennessee Healthcare are using AI platforms that can map out a patient’s predicted stay, allowing clinicians to plan discharges and even coordinate with payers on insurance coverage.
Predictive AI is starting to show its value in healthcare by helping hospitals plan patient care, from length of stay and discharge to insurance coverage.
At West Tennessee Healthcare, executives say they’ve saved more than $5 million over the past year by using an AI platform from Xsolis to review patient data, enabling them to predict when a patient will be discharged and communicate with payers on authorizations and any denials.
“Prior to this everything was a manual chart review, so the case managers were reviewing everything manually, looking through every chart, digging for a lot of information and documentation,” says Debbie Ashworth, executive director for care management for the 90-hospital network. “Now they don't have to do as much. The AI has really improved workflow processes [and] timeliness of those reviews.”
Health systems and hospitals across the country are embracing AI at a rapid pace, but the opportunities for clear and demonstrative ROI have so far been few and far between. Using the technology to sort through data from the medical record and other sources and give clinicians insight into improving patient care is one of those use cases.
The key to this particular use case is that AI isn’t affecting clinical decision-making. It’s performing administrative tasks that had previously been done by nurses, doctors and other care team members, reducing time spent in front of a computer.
At West Tennessee, the platform creates a Care Level Score for each patient, which gives clinicians an expected length of stay and discharge time based on patients with the same healthcare concerns. That score is used by utilization review, case management, and physician advisor teams to map out care management.
The platform’s link with payers takes that one step further. Ashworth says two payers are now connected to the platform, giving health system clinicians and staff the opportunity to coordinate patient care and insurance coverage more closely, reducing time-wasting delays and lengthy appeals.
“That has really improved our relationship with the payer and also the timeliness of getting the responses back,” she says, noting this cuts down on the phone calls, e-mails and faxes that often pass between provider and payer while the patient waits for care services. “The conversations we have with them are better [because] you’re both getting information that you can share.”
Ashworth says the biggest challenge to the technology has been change management. Staff and clinicians need a little time, she says, to get used to using the technology—and learning what to do with the time saved.
She also says the toll is “not 100% but very accurate,” and case managers always review the care plans and have picked up on errors.
“Just having that [data] right in front of us, to know that this patient should discharge tomorrow or … this discharge is going to be two or three days from now, [enables care teams] to prioritize a lot better and get to the appropriate level of payer,” Ashworth says. “Now they're able just to focus on what they need to do to get the patients discharged or get their insurance approved.”
A recent HIMSS forum in Boston highlighted the challenges—some new, some expected-- faced by healthcare executives in managing AI adoption.
Health system and hospital executives looking to embrace AI will need to think long and hard about how they’ll measure ROI. That may include using the technology to actually replace care providers.
Lee Schwamm, MD, senior vice president, chief digital health officer, and associate dean of digital strategy and transformation for the Yale New Haven Health System and Yale School of Medicine, told a busy audience at last week’s HIMSS AI in Healthcare Forum in Boston that the technology will have a profound impact on healthcare delivery. The challenge, he said, will lie in understanding that impact before it happens.
“We’re going to need better financial models to really understand the ROI,” he said, noting that healthcare organizations have so far found only three or four successful use cases for the technology.
Schwamm says the healthcare industry has become “accustomed” and “complacent” in healthcare IT, and Ai is presenting healthcare leaders with issues they haven’t encountered before. The AI evolution, he pointed out, is similar to the development of the software-as-a-service (SaaS) model, but health systems and hospitals haven’t developed the governance to regulate these tools before they’re used.
“I’ve had e-mails where [doctors] say, ‘I just really enjoy using ChatGPT while in clinic,” she said.
The challenge for hospital leaders like Schwamm and Cunningham is to get ahead of a technology that’s moving faster than anything they’ve seen before, and at a time when the industry is struggling with significant issues that AI could eventually address.
“We have to catch up to that SaaS model,” Schwamm said.
Healthcare leaders across the country are pulling their legal and compliance teams into the conversation, in some cases developing strategies based on hypothetical issues. And they’re trying to educate clinicians who might see just the good in AI and not understand the ramifications of fast adoption without governance.
AI “lowers the bar for non-technologists to use sophisticated technology,” Schwamm said.
Cunningham noted that AI tools are being tested out across the enterprise, often in small programs that show very specific, though limited ROI. Leadership has to find a way to keep track of all these programs and integrate them into a governance structure.
She said health system leadership needs to take a step back and assess the new tools and technology being pitched in healthcare. Many vendors, including those in AI, are aiming at the patient experience and engagement space, with products that promise to improve the clinician-patient relationship. But healthcare organizations are struggling with stress and burnout, to the point that a new tool that offers results “with just one more click” isn’t a good selling point, and products that aim to give clinicians time to take on more patients are just adding to the misery of overloaded workflows.
“There is no more room for one more click,” noted Zeev Neuwirth, an author, podcast host and former chief clinical executive for care transformation at Atrium Health who moderated the HIMSS panel.
Several panelists at the HIMSS forum said AI’s potential to synthesize data and take pressure off of clinicians has to be balanced with an understanding of how healthcare should manage the vast amounts of data coming into the enterprise. That may mean creating a change management strategy devoted solely to AI adoption, to give healthcare leaders an understanding of how AI will take that data and make it useful to clinicians.
AI’s potential to address workforce shortages in healthcare may also mean it can be used to replace people, especially for positions that hospitals are having problems filling. And Schwamm noted that as health systems and hospitals focus on operational factors to improve their financial standing, AI could work its way into labor negotiations.
Cunningham said the industry will eventually have to get its act together and pull all the loose AI threads into one organized strategy.
“What does it all look like five to seven years from now?” she asked. “How will all these things that we’re doing come together?”
While wearable devices have gained attention for their use in remote patient monitoring programs, hospitals are finding more value in inpatient programs
Healthcare leaders are going wireless to monitor patients in the hospital, using new technology that can track a wide variety of vital signs and give providers new insights into improving clinical outcomes.
For many health systems, the initial thought is to use wearables to monitor patients who are discharged from the hospital and into a remote patient monitoring program. But Sarah Pletcher, MD, MDHCS, Houston Methodist’s vice president and executive medical director for strategic innovation, says the inpatient setting gives hospitals an opportunity to improve a key element of care management.
“We wanted to use it in the inpatient setting because we've seen the value of continuous algorithm-based monitoring by a dedicated and highly skilled remote clinical team in the virtula ICU space,” she says. “And the idea that we could hack the way vital signs are taken in the hospital setting, which hasn't really been innovated much in the last hundred of years, was a key opportunity area.”
Houston Methodist selected BioIntelliSense's BioButton roughly one year ago, after an exhaustive process during which Pletcher even slept and showered with multiple wearables to make sure they had the form, features, and would function as intended. Pletcher says she wanted an unobtrusive, durable, medical-grade device that would track several vital signs and be scalable.
Houston Methodist is using the wearable to supplement and replace manual collection of vital signs, pushing data hourly into the EMR and continuously to a central team, who respond to algorithm alerts and then alert bedside nurses when their review data suggests something concerning.
“As we began to advance the technology across the system, we also began to redesign how we did routine vitals,” Pletcher says. “We went from every four hours for routine vitals first to every six then to every eight. And we will look for opportunities to stretch it to every 12, especially at night and for stable patients so that the patient gets more rest. The bedside teams get a bunch more time back while at the same time there's a peace of mind that even when they're not in the room with the patient doing a spot check, the technology is there gathering data every minute and flowing it to a central monitoring team that's keeping an extra eye on things.”
While the wearable detects a wide variety of vital signs, Pletcher says she’s most impressed with the value of objective, high-frequency respiratory rate.
“It turns out that changes in respiratory rate are one of the earliest things you start to see in a patient,” she says. “By the time they get to the point where their blood pressure is tanking, you're late in the game, they've likely been deteriorating for a while.”
And that’s where wearables might prove their ROI in clinical outcomes. The ability to track vital signs in real time means clinicians can identify patients in distress much earlier, rather than waiting for a nurse or doctor to come to the bedside. In many cases clinicians can intervene even before a patient shows any outward signs of distress—and with AI tools on the horizon, the opportunity to collect and analyze data in the blink of an eye offers more potential for early detection.
Pletcher sees a more immediate ROI in workflow improvements, especially for nurses.
“The ROI is solid just based on the workforce savings,” she says. "Not having to send staff wheeling that vitals cart in there for every patient every four hours no matter what, can offset the cost of using the technology. And that doesn't factor in quality/safety catches, patient experience and nursing and physician satisfaction that there's more in place helping to look after their patients. Every day there are moments where we're catching patients earlier and hopefully avoiding them needing more intensive intervention.”
She’s also noticed the ability for wearables to pick up on heart rate arrythmias, giving hospital officials new insight into whether the wearables can reduce the demand for telemetry. And she’s looking forward to the ability to monitor pulse oximetry, blood pressure, and heart function and to differentiate between surface and core body temperature.
“Sometimes it's a case of we already are getting the data,” she says. “We've never had it before, not at this frequency and scope, so we're still learning how to use it.”
Aside from teaching clinicians how to be comfortable with the wearables and understand the data coming in—a common element of change management that comes with almost any new technology—Pletcher says one the biggest issues they’re having with wearables is remembering to collect them when a patient goes home. Sometimes, she says, the small devices are forgotten and thrown away or accidentally go home with the patient.
Using Wearables to Address One Specific Care Concern
While some hospitals see wearables as a means of improving inpatient monitoring, others are starting with one use case, such as monitoring cardiac care patients or trying to reduce sepsis cases.
At Sutter Health, hospital leaders are using a wearable that attaches to the neck and takes an ultrasound of the patient’s carotid artery and jugular vein. The Flopatch Doppler ultrasound patch, developed by Flosonics Medical, enables care teams to identify signs of sepsis, hypertension/shock, and renal failure earlier and take action.
“We’re losing a lot of people [to sepsis] every year,” Kristina Kury, MD, medical director of critical care at Sutter Health’s Eden Medical Center, says of the deadly infection, which is the primary cause of death in hospitals, killing almost 40% of the 1.7 million patients each year who get sepsis.
Kury says the patch focuses on carotid artery flow time, creating a waveform that’s similar to an echocardiograph. That measurement changes when IV fluids are administered—too much fluid causes heart failure and respiratory distress, while too little fluid takes out the kidneys and other organs.
“it's extraordinarily easy and practical, and that device can stay with the patient for a week while they're in the hospital because we know things are dynamic,” she says of the patch, which is now being integrated into care pathways in four hospitals. “It's another tool that you can use to incorporate into that clinical scenario, and it's a much more accurate vital sign than heart rate.”
Kury says Sutter Health has reduced its sepsis rate to 20% through other improvements, but seems to have hit a plateau. One option was a non-invasive cardiac output monitor, which consists of a console that has to be wheeled into each patient room and electrode patches that have to be applied to the patient and which isn’t ideal for patients with structural heart disease and vascular replacements. Other options were cardiac catheters and central venous pressure monitors, both invasive and imperfect.
A wearable, Kury says, addresses a specific care gap but won’t make the patient any more uncomfortable.
“We have people at the outset who are going to be sensitive to giving any kind of intravenous volume because the heart muscle is not healthy [through] heart failure or their kidneys have failed, and they’re on dialysis,” she notes. “They have no way of intrinsically removing fluid from their body, so they quickly could get into trouble. That’s a vexing population to our clinicians, especially in the ER, where they're coming in with an undifferentiated person in shock.”
The Bluetooth-enabled platform, which isn’t yet integrated into the EHR, enables clinicians to monitor six patients through one dashboard in real time.
As a doctor, Kury says, “I would want to see the data myself, the curve, the waveform, the spikes, and I would want to see that myself and then have the interpretation.”
The Rise of Connected Care
Influenced by consumer-facing technology like activity bands, smartwatches and sensor-embedded clothing and jewelry, healthcare organizations have long studied the use of wearables in RPM programs outside the hospital setting. But with more sophisticated medical-grade devices on the market and a desire to create a “hospital room of the future” that places a premium on wireless technology, healthcare executives are now interested in bringing wearables inside the hospital.
Julia Strandberg, chief business leader of connected care and monitoring for Philips, says the next three to five years will see a fundamental shift in how health systems and hospitals view patient monitoring.
“Scalable, integrated and optimized patient monitoring and management system for the hospital” will become more popular, she says, as decision-makers see the value in keeping a continuous eye on patients rather than relying on spot checks or scheduled vital signs monitoring.
The benefits are numerous. Many hospitals struggled with patient monitoring during the pandemic, when infected patients were isolated and staff and clinicians had to step into bulky PPE to see them. In addition, hospitals have long struggled with the number of wires, leads and other devices attached to the patient, hindering patient movement (a key metric for clinical improvement) and prone to tangles and trips. Add to that the stress and burnout rate for clinicians and staff and the propensity to use loud sounds to demonstrate a monitor’s effectiveness or an emergency health concern.
“Beeps and dings and alarms and alerts and are very burdensome, not only on the patient but also the care [team],” says Strandberg, who notes that wireless technology is now being developed to send data and alerts into the EHR or onto dashboards. Philips is also working on an avatar that can give clinicians a whole-patient view, using cues like a blue color to indicate the patient is cold.
The key to success for health systems and hospitals is what Strandberg calls the pitcher-catcher relationship. Healthcare leaders need to make sure the EHR is catching all the data being transmitted and connecting that information to the right providers.
“How do you synthesize all that data that we brought in and stratify it such that we can help enable more rapid clinical decision making and intervention if it's required?” she asks.
Advocates are once again lobbying the White House and Congress to extend a waiver on using telemedicine to prescribe controlled medications, while the DEA prepares a new rule that could cause even more discord.
Telehealth advocates are gearing up for yet another battle with the federal government over the use of telemedicine to prescribe controlled medications, particularly in treatments for mental health and substance use disorders.
The Alliance for Connected Care is preparing stakeholder letters to the White House and Senate and House leadership urging them to put pressure on the U.S. Drug Enforcement Administration to extend for two years a pandemic-era waiver allowing providers to use telemedicine. Extending the waiver, currently set to end this year, would give the DEA time to create a long-sought registration process for those prescriptions.
“The ongoing challenges in accessing mental health and substance use treatment services, particularly in rural and underserved areas, underscores the importance of maintaining these flexibilities,” the letter states. “Telemedicine has proven to be an effective tool in bridging the gap between patients and providers, reducing barriers to care, and supporting those most in need.”
The fight over a pathway to use virtual care dates back to 2008, when the Ryan Haight Online Pharmacy Consumer Protection Act prohibited the use of telemedicine for drug prescription unless providers completed a special registration that the DEA was supposed to set up. That hasn’t happened yet, despite pressure on the DEA from lawmakers and others to create that process.
According to telehealth advocates, the DEA hasn’t been helpful. The agency had proposed long-term guidelines for telemedicine prescriptions in 2023, but that draft was widely condemned as being too complex and restrictive. A revised draft is now awaiting White House review, but reports indicate that draft, if approved, “would be a significant blow to the telemedicine industry … and hundreds of thousands of patients who have come to rely on virtual prescribing.”
In their letter to lawmakers and the White House, stakeholders say there isn’t enough time left before the end of the year for the DEA to release its new draft, allow time for public comment, review those comments and make any changes. Hence the request for a two-year extension on the waiver.
“Under the current waiver, controlled substances have been prescribed in a clinically appropriate manner to treat a variety of conditions—always by licensed medical professions with prescribing authority,” the letter states. “Given the widespread provider shortage across medical professions and specialties, this flexibility has been essential in ensuring that patients receive timely and necessary care. Continuing these practices is vital to sustaining access to treatment and addressing the ongoing healthcare challenges in underserved areas.”
Federal officials have decided not to appeal a court order that shut down the rule, saying it exceeded HHS authority under HIPAA.
Federal officials have withdrawn a plan to restrict hospitals from using tracking technology to collect data from consumers visiting their web portals.
The Health and Human Services Department (HHS) has withdrawn its appeal of a district court vacating the federal rule, which was outlined in a December 2022 bulletin from the HHS Office for Civil Rights. The rule stated that entities covered by the Health Insurance Portability and Accountability Act (HIPAA) “are not permitted to use tracking technologies in a manner that would result in impermissible disclosures of PHI to tracking technology vendors or any other violations of HIPAA Rules.”
The American Hospital Association and several other groups filed suit against HHS in late 2023, charging that the federal agency exceeded its statutory authority in preventing healthcare providers from collecting the IP addresses of people visiting public-facing websites. On June 20 of this year, a federal district court in the Northern District of Texas ruled that the federal order “was promulgated in clear excess of HHS’s authority under HIPAA.”
The AHA and others had argued that the rule could have been interpreted to prevent hospitals from using common technologies, such as analytics software, video, translation and accessibility services and digital maps to access IP addresses, assess the usability of their portals and communicate with patients.
HHS’ decision to drop its appeal was hailed by the AHA.
“The American Hospital Association is pleased that the Office for Civil Rights has decided not to appeal the district court’s decision vacating the new rule adopted in its Online Tracking Technologies Bulletin,” AHA General Counsel Chad Golden said in a statement. “As the AHA repeatedly explained to OCR—both before and after OCR forced the AHA to file its lawsuit—this rule was a gross overreach by the federal government, imposed without any input from healthcare providers or the general public. Now that the Bulletin’s illegal rule has been vacated once and for all, hospitals can safely share reliable, accurate health care information with the communities they serve without the fear of federal civil and criminal penalties.”
Faced with pharmacy closures and struggling to make ends meet, health system executives are innovating pharmacy operations to cut costs, reduce waste and give the pharmacist a bigger role in care management.
For an increasing number of hospitals, the path to healthcare innovation leads through the pharmacy.
Whether it’s to keep the doors open in a rural region or address care gaps brought on by retail pharmacy closures and disruptor drawbacks, healthcare leaders are taking a closer look at hospital pharmacy operations. Some are eyeing a hub-and-spoke drug distribution model to cut costs and waste, while others are making the pharmacist a more active member of the care team.
“We’re definitely more involved in patient care,” says Jason Tipton, inpatient operations supervisor at Carle Foundation Hospital, part of the Illinois-based, eight-hospital Carle Health system. “Basically, what it boils down to is safety.”
Carle Health turned to digital health company DrFirst to improve medication management through the pharmacy. The AI-enhanced tech platform helped health system executives boost efficiency by at least 16%, cutting down on long hours spent in front of a computer or on a phone talking to doctors and retail pharmacies, searching through patient histories and matching the right prescriptions and drugs to the right patient.
Tipton says the health system has not only reduced medication errors, but identified the barriers that keep patients from filling out their prescriptions or following doctor’s orders. By integrating that platform into the EHR, pharmacists were able to work with the care team to identify the right medications, including doses and frequency, check for side effects and potential interactions, even make sure the patient fills out the prescription.
According to the health system, the technology has helped Carel Health improve medication management and reduce stress on its pharmacy staff, to the tune of roughly 1,209 acute care hours saved annually.
While the issue of pharmacy closures and deserts has hit the front pages recently, Tipton notes the problem began during the pandemic, when pharmacies were struggling to keep up with the surge and patients were looking to their providers for help. Health systems like Carle Health saw the opportunity not only to improve patient engagement then, but to plot a long-term strategy to boost that business line.
Hospital pharmacists and pharmacy technicians “have always been involved in that process,” he says, “but this was a chance to be more of a part of the care team. And physicians liked that as well. After all, if [patients] aren’t getting their medications [or they’re not following doctor’s orders], they’re going to show up in the hospital.”
Taking on Pharmacy Innovation in a Rural Hospital
In Virginia, a reimagined pharmacy was the key to the July 2021 reopening of Lee County Community Hospital, which had closed its doors in 2013.
Executives say the hospital in Pennington Gap, which is part of the Ballad Health system, reopened due to public pressure: There just weren’t that many healthcare options in the rural region dividing southeast Kentucky and southwest Virginia. But with that opening, which cost the health system roughly $15 million, came pressure to cut expenses, reduce waste and improve care delivery.
And that meant an automated virtual pharmacy.
“In pharmacy, we've really learned [that] everything that we do is expensive,” says Trish Tanner, vice president and chief pharmacy officer for the 20-hospital health system. “My people are expensive. My drugs are expensive. My equipment is expensive, [and] it's really hard to recruit here, so [we are] trying to find ways to be innovative and bring that same level of care to patients regardless of where they're located.”
Instead of having a pharmacist on site, Lee County Community Hospital has an automated drug dispensing system and a remote order entry platform, as well as a telehealth platform that includes medication management. The hospital partnered with Omnicell to automate their pharmacy management operations.
Eighteen of Ballad Health’s hospitals are now on this platform, with the last two expected to go live by January of 2025. From a central pharmacy, drivers visit each hospital to refill drug cabinets, check expiration dates, and do any other tasks needed.
“We can’t put a pharmacist in there,” Tanner says of Lee County, though she could be talking about any of the small hospitals in the health system. “We're able to redeploy the pharmacist who would be there to other tasks that aren't currently being met, our greatest one being medication reconciliation.”
Through a telehealth platform and a focus on community engagement for the providers who do work at each hospital, Ballad Health officials say they’re able to improve quality of care and keep each hospital’s doors open.
“What is [important] is that we really know our patient population and the drugs that they're typically on,” Tanner says. “And while I don't have a pharmacist physically at bedside at Lee County, we do have them virtually.”
The telehealth platform gives providers an opportunity to dig into the data on a patient’s care management needs and find ways to close care gaps, whether it’s finding a more affordable prescription or developing a routine to ensure that a patient takes their medications when expected.
“50% of the country is not following doctor’s orders right now,” Tanner points out. “That’s a huge outlier for any hospital, especially a rural hospital that is trying to watch its costs. So we've worked really hard to make pharmacy services [as] seamless as possible for our patients on their journey [and] for our physicians across the organization.”
Marvin Eichorn, Ballad Health’s vice president and chief administrative officer, says the pharmacy is the ideal use case for today’s digital health innovations.
“In today's world it's very difficult to recruit almost any position,” he says. “So if we can maybe do it [with] robots or other technology or maybe off-site somewhere, that can provide [a benefit] to the hospital. And then we can use [the money saved] to focus on other areas of care, to make care better.”
Exploring Payer Collaboration
At Baptist Health in Kentucky, officials recently cut the ribbon on a new, 102,000-square-foot central pharmacy aimed at reducing costs and clutter in the nine-hospital network and improving the supply chain. The health system took a good look at how UPS handles things to develop its central pharmacy strategy.
Baptist Health also launched a partnership with Clearway Health, a company that focuses on improving specialty pharmacy operations.
With independent and chain pharmacies struggling and patients wondering where they’ll get their next prescription, Nilesh Desai, Baptist Health’s chief pharmacy officer, says it was imperative to look at each patient’s entire pharmacy journey, not just the part that intersects with the hospital.
“It's better for them because they're coming to see our physicians, our providers, and they're like, ‘Hey, you know what? I'd rather see my own pharmacist,’” he says. “So then maybe we can answer their questions or make a phone call. It really makes it easier on all fronts.”
Key to the Clearway Health partnership is access to the payer market, which is also keeping a wary eye on the pharmacy turmoil. Desai notes that health plans are affected just as much when a member can’t or chooses not to fill a prescription.
He says it’s important for health systems and hospitals to work with payers to make sure patients/members have access to pharmacists. That includes understanding payer networks and adjusting to give hospital pharmacists and pharmacy technicians more opportunities to impact care management.
“There is a provider shortage, there is nursing shortage, [and] medication management in general has become very, very complex,” he says. “You need someone who's an expert, who understands medication all the way through. Who better than the pharmacist?”
Desai says the workforce shortage will only get worse over the next three to four years – there’s a 65% shortage in pharmacy school applications now. It’s up to the healthcare industry to address that, not only by working with medical schools to boost the pharmacy tech pipeline but to take on more pharmacy services.
“Sometimes we do the reverse,” he says. “We've called the patients at home to say, ‘Hey, how's the medication working on you? Are you having any issues?’ So, having that continuous dialogue is going to be very, very important.”
Cedars-Sinai researchers are analyzing biomarkers in the retina that identify Alzheimer’s and cognitive decline, studies which could lead to the development of new tools to diagnose the disease through a non-invasive eye test.
Could healthcare providers soon be able to diagnose Alzheimer’s disease through an eye test?
Researchers at Cedars-Sinai Medical Center are touting the results of three recent studies that indicate an eye test could be used to assess the eye-brain connection, which would allow clinicians to diagnose Alzheimer’s earlier and begin treatment.
“The retina, a layer of tissue at the back of the eye, is part of the central nervous system and is directly connected with the brain,” Maya Koronyo-Hamaoui, PhD, a professor of neurosurgery, neurology and biomedical sciences at Cedars-Sinai and senior author of all three studies, said in a press release. “It has similar cell types and vascular structures to the brain, but is not shielded by bone, so it is more accessible to noninvasive imaging. Our latest research unearths new details about the eye-brain connection.”
Healthcare leaders are looking for innovative and less-invasive strategies to diagnose Alzheimer’s disease, which affects some 5.8 million Americans; that number is expected to jump by 14 million by 2060. Alzheimer’s accounts for some 60% to 80% of dementia diagnoses, and leads to roughly $413,000 in lifetime healthcare costs per patient. Nationally, the price tag for Alzheimer’s care was estimated in 2020 to be $385 billion.
Earlier detection and treatment could reduce those costs and improve clinical outcomes.
At Cedars-Sinai, researchers launched a study to analyze tau, a protein that helps stabilize the structure of nerve cells in the brain and retina and a critical marker for Alzheimer’s. They found that higher levels of abnormal tau in the retina corresponded to brain changes related to Alzheimer’s, as well as cognitive decline.
A second study, focusing on clumps of protein called amyloid plaques, found two to three times as many plaques clustered near blood vessels in the retinas of patients diagnosed with Alzheimer’s or mild cognitive impairment. A third study focused on other Alzheimer’s biomarkers in the retina, including reduced blood flow, inflammation, nerve cell damage, damage to the barrier that prevents harmful substances from entering retinal tissue, and deposits of amyloid-beta proteins inside blood vessel walls.
“Imaging technology now being developed will allow us to see these changes in patients in clinical settings,” Keith L. Black, MD, chair of the Department of Neurosurgery and the Ruth and Lawrence Harvey Chair in Neuroscience at Cedars-Sinai and co-author of the studies, said in the press release. “This technology, which is noninvasive and affordable, allows us to see changes in the cells and blood vessels in tremendous detail.”
The EHR company put on its usually flashy show, and while groundbreaking announcements were minimal, there are signs that the industry is starting to look at the technology in a new light.
Epic’s annual User’s Group Meeting (UGM) last week was all that it promised to be: Flashy, upbeat and befitting of the nation’s biggest EHR company.
But for healthcare execs who are part of the Epic universe as well as those on the outside looking in, there wasn’t much that could be called newsworthy. The company and its powerhouse leader, Judy Faulkner, are notorious for playing things close to the vest.
That said, here are the four biggest takeaways:
The AI Hype Machine Rolls On. More than 100 AI-enabled tools are already in the Epic toolbox, according to Faulkner, and the company has an aggressive agenda to develop the technology for both providers and consumers. The announcement puts Epic smack in the middle of the AI race, alongside some of the tech titans with which it’s also collaborating. And with little more than a passing mention of working with others and developing open-source tools, it’s clear that the company is making AI its next big marketing feature.
Playing With Payers? The Epic Payer Platform isn’t revolutionary, nor is it new. But it does address a consistent concern in healthcare: How to get providers and payers to sit at the same table to trade data and tackle key pain points in connecting care with compensation. Faulkner said roughly half of the Epic health system and medical group customers and seven of the nation’s largest payers are connected to the platform, with the goal of reducing denials and improving the prior authorization process. But will payers want to play in this sandbox? And what incentives could Epic offer to get them interested?
Looking to the Little Guys. Epic has long been focused on the biggest health systems and hospitals, to the point that some competitors have changed their approach to focus on smaller providers, from rural hospitals to medical practices, even FQHCs, Rural Health Clinics and specialty practices. Faulkner’s mention of the Washington State Health Care Authority, a collaboration between the state and Epic launched several years ago to support EHR adoption for smaller providers, may be an indication that the company has its sights set on expanding its reach.
Paying Attention to the Patient. From plans to make MyChart a more interactive tool for patients to the grand designs for Cosmos, it’s clear that Epic wants to get more involved with patient-centered care. Cynics will say they’re giving patients that same opportunity to experience the frustration with technology that doctors experienced a few decades back, but this strategy may be the most impactful of all to come out of the UGM. It recognizes that the EHR, for all its perceived faults, has evolved. If patients can draw as much value as clinicians from this platform, the opportunities for care collaboration and—yes, we’ll say it—value-based care are pretty good.
