"There is a metric that we call time outside of scheduled hours, which is simply how much time physicians are spending in the EHR outside of the patient schedule. Our physicians are scheduled to see patients from 8 a.m. to 4:30 p.m.," Weiner says. "The other euphemism for this is 'pajama time,' which is the time physicians spend at night finishing up documentation, answering patient inquiries, and refilling medications."
Physicians working in the EHR during their time off, particularly pajama time, is also a concern at Ardent Health, according to the Nashville, Tennessee-based health system's CMIO, Bradley Hoyt, MD.
"It happens all the time," Hoyt says. "It's just the way things are. I did it for years."
There is a primary consequence of physicians working in the EHR during their time off, Hoyt explains.
Recent research found that a significant percentage of primary care physicians work in the electronic health record during vacations.
In this episode of HL Shorts, we hear from Sam Weiner, CMO at Virtua Medical Group, about ways to reduce the amount of time that physicians spend working in the electronic health record. To view the episode, click on the video below.
John Phipps' goals for strategic clinical growth include improving access to primary and specialty care.
The inaugural chief clinical officer of UF Health is looking forward to defining and building out the new position.
John Phipps, MD, begins working as UF Health’s chief clinical officer on April 14. Prior to taking on his new role, he was chief care transformation officer at Inova health system. Phipps also held several leadership roles at Novant Health, including president of Novant Health Medical Group.
Phipps has several aspirations for UF Health, including taking the existing structure and high-performing clinicians as well as leaders and creating a more integrated approach so that everyone is working more collaboratively across the UF Health geography.
"We also want to turn up the volume on clinical outcomes such as safety and quality," Phipps says. "In addition, UF Health wants to use the chief clinical officer position to help strategic clinical growth opportunities."
Phipps has initial goals for strategic clinical growth opportunities.
"At a high level, I will be trying to improve access to primary and specialty care as well as seamlessness in clinical operations," Phipps says. "I consider access to be a quality measure. I will try to take some of the friction out of navigating the health system."
Although the chief clinical officer role has yet to be fully defined, Phipps says he wants to help coordinate, integrate, orchestrate, and advance delivering clinical excellence and care transformation across the health system.
"Some of it is as straightforward as having a unified approach to quality and safety," Phipps says. "Other aspects are as nebulous as being a go between among various stakeholders to advance the health system's priorities."
John Phipps, MD, is chief clinical officer of UF Health. Photo courtesy of UF Health.
Implementing patient safety and quality initiatives
Phipps says there are several elements of launching successful patient safety and quality initiatives.
"The biggest key to success in any system-wide initiative such as safety and quality is a strong commitment from the leadership of the organization," Phipps says. "There must be an organizational priority from the board of directors, the CEO, and other leaders."
There must be an understanding about organizational attributes that promote safety, according to Phipps.
"You need to be a high-reliability organization, including elements such as culture, psychological safety, and reducing variation," Phipps says.
Fostering psychological safety, which promotes the reporting of adverse events by staff members, involves messaging and modeling by a health system's leadership, Phipps explains.
"It's the things that you talk about and the behaviors that you exhibit," Phipps says. "If patient safety and psychological safety for staff are important, you need to talk about those things. People need to see that the behaviors that leaders are endorsing are the behaviors that they exhibit."
Reducing unwarranted variation in clinical care is hard work, and there are primary steps to follow, Phipps explains.
"First, you must believe that reducing variation is important," Phipps says. "We know that reducing unwarranted variation reduces waste, improves safety, improves outcomes, and improves the experience of caregivers and patients."
Health system leaders such as CMOs should get caregivers aligned around reducing variation, which requires cultural and technical work, according to Phipps.
"Culturally, you need to get people to understand that reducing variation is a pathway to excellence," Phipps says. "Technical work can include getting everyone on the same electronic health record, sharing information, and aligning around order sets for common conditions."
Leadership, vision, culture, and measuring outcomes are all important in promoting quality, according to Phipps, who adds that a factor that is often overlooked is that quality and clinical outcomes are best expressed by patients.
"An important aspect of a successful quality program includes involving patients and families, understanding their goals and values of care, understanding the outcomes that matter the most to them, and helping them to participate in setting the agenda for what you are trying to accomplish," Phipps says.
Successful physician engagement
Phipps says he learned several lessons about physician engagement during his work as president of Novant Health Medical Group, where there is a rapidly growing, high-performing, largely community-based physician practice.
"Our approach to physician engagement was that physicians were our partners and leaders," Phipps says. "As you would with any other partner or fellow leader, we had to give our physicians a voice in the organization and to understand what was important to them."
There were several other elements of physician engagement at the medical group, Phipps explains.
"We needed to understand what solutions physicians had and to cultivate an environment of ongoing dialogue, mutual respect, honest communication, and alignment around a shared vision of providing great care to the community," Phipps says.
A significant percentage of primary care physicians are working in the EHR during their vacations, according to new research.
Many physicians are working in the EHR during their time off, according to a new study, and their CMOs need to take steps to stop that.
Research published in JAMA Network Open found that primary care physicians commonly worked in the EHR during their vacations. The article, which collected data from 56 primary care physicians, had several key findings.
The median time in the EHR per day off was 16.1 minutes, with 19% of physicians experiencing more than 30 minutes per day.
Longer durations of days off were associated with less time spent in the EHR. Physicians spent a median of 50% of short vacation days and 18% of long vacation days with some EHR use.
Physicians spent more time in the EHR at the beginning and end of vacations. They spent a median of 57% of first days and 63.5% of last days in the EHR, compared to a median of 29% of middle days in the EHR.
Electronic in-basket work was a common EHR task, with physicians spending a median of 39.5% of total EHR time performing inbox-related tasks.
"There is a metric that we call time outside of scheduled hours, which is simply how much time physicians are spending in the EHR outside of the patient schedule,” he says. “Our physicians are scheduled to see patients from 8 a.m. to 4:30 p.m.”
"The other euphemism for this is 'pajama time,' which is the time physicians spend at night finishing up documentation, answering patient inquiries, and refilling medications," Weiner adds.
Weiner says the problem is particularly acute with short periods of time off, as opposed to longer vacations.
"When we try to take a four-day weekend, forget it, we are in the EHR the whole time," Weiner says. "It is only when physicians can take a week or sometimes two weeks off that we truly get that sense of being able to breathe a sigh of relief and finally feel disconnected. That is when physicians can recharge. Unfortunately, those opportunities are few and far between."
This is also a concern at Ardent Health, according to the Nashville, Tennessee-based health system's CMIO, Bradley Hoyt, MD.
"It happens all the time," Hoyt says. "It's just the way things are. I did it for years."
Hoyt says this habit is contributing to physician burnout.
Bradley Hoyt, MD, is CMIO of Ardent Health. Photo courtesy of Ardent Health.
Helping physicians curb their off-hours EHR use
Virtua Medical Group has launched several interventions to help physicians cut back on accessing EHRs during time off, particularly for tasks associated with electronic in-basket messaging.
"We have more than two dozen primary care practices, and some of those practices have a coverage system in place for when physicians go out on vacation," Weiner says. "They have a structured way for the physicians who remain in the practice to cover for the physician who is on vacation. When a physician is out, they can feel confident that their patients will be taken care of."
Virtua Medical Group also has a strategy that the medical group calls "taming the in-basket."
"We take a lot of the messages that come in to physicians on a daily basis and screen them to make sure they go to the appropriate staff member," Weiner says. "Not every message has to go to the doctor—many of them can be fulfilled and completed by other staff members in the office."
Virtua also hires nurse practitioners to serve as "in-basketologists."
"Their role throughout the day is to mine the in-baskets of the other clinicians in the practice and take out everything that a doctor does not need to see and handle those messages," Weiner says.
Nurse practitioners, who are licensed and trained clinicians, can answer clinical questions in a way that medical assistants and even registered nurses sometimes cannot answer, according to Weiner.
"This has been shown to significantly reduce the amount of time that our physicians spend in the EHR outside of their scheduled hours," Weiner says.
Ardent Health is using AI to tackle the problem. The health system is deploying an ambient AI tool, called Ambience, to capture the doctor-patient conversation and reduce the time providers need to spend in the EHR.
"No provider likes to write notes," Hoyt says. "It is the bane of our existence. We love talking with patients—we love connecting with them. Having to leave the examine room, then dictate the note before seeing the next patient is a huge weight on the physician's shoulders."
"With ambient dictation, we have cut our pajama time by 50% [and] reduced total documentation time by 41%," Hoyt says. "That is a big win for our providers. They don't have to work at home as much."
Sam Weiner, MD, is CMO of Virtua Medical Group. Photo courtesy of Virtua Health.
The Iowa City, Iowa-based health system has established stable paths for AI governance and strategy.
University of Iowa Health Care has taken a consistent approach to artificial intelligence governance over the past two years.
James Blum, MD, chief health information officer at UI Health Care and a participant in the HealthLeaders AI in Clinical Care Mastermind program, says the technology needs to be treated with the proper safeguards, but that doesn't mean separating it from all other innovative tools and processes.
Blum explained in a recent HealthLeaders podcast that AI and healthcare shouldn’t exist in a vacuum, and health systems shouldn't be acquiring AI for the sake of it.
"We should probably be looking to solve problems that people have, and if that involves AI, great," Blum said. "If it doesn't, that's probably in many ways better because it takes out display of governance and potentially a lot of additional expense."
UI Health Care has launched two AI tools for clinical care: An ambient transcription platform developed by Nabla, which roughly 1,100 of the health system's 3,000 doctors are now using, and a chart mining platform from Evidently that collects all relevant data on a patient from multiple sources to give clinicians a concise view of the patient.
Blum says both AI tools were carefully reviewed by UI Health Care through a normal process for reviewing new vendors. With AI, that includes bringing in clinicians and IT personnel who understand the nuances of the technology.
"It is with a group of individuals that are qualified to review the AI right and really understand the performance characteristics and what can be expected of the technology in addition to our typical acquisition process," Blum says.
James Blum, MD, is chief health information officer at University of Iowa Health Care. Photo courtesy of University of Iowa Health Care.
AI strategy, adoption of new tools, and measuring outcomes
Over the past year, IU Health Care has maintained a consistent AI strategy, according to Blum.
"We have continued our existing AI strategy which was extensive and democratic," Blum says. "Our implementations have been across the institution to support all of our clinicians."
The health system is planning to adopt new AI tools in two areas of clinical care.
"We will be adding AI coding and clinician draft technologies," Blum says.
Costs and adoption challenges are the biggest obstacles to growth of AI tools in clinical care at IU Health Care, according to Blum.
"Regarding adoption, many of those that can most benefit are reluctant to adopt the technology," Blum says.
IU Health Care is measuring three key outcomes related to the health system's utilization of AI tools, Blum explains.
"We measure clinician burnout, clinician after hours work, and clinician satisfaction with their electronic tools," Blum says.
The HealthLeaders Mastermind program is an exclusive series of calls and events with healthcare executives. This Mastermind series features ideas, solutions, and insights on excelling in your AI programs.
To inquire about participating in an upcoming Mastermind series or attending a HealthLeaders Exchange event, email us at exchange@healthleadersmedia.com.
WellSpan Health's Ana AI tool helps with outbound patient outreach and inbound communication.
WellSpan Health is using an AI tool to improve the health system’s interaction with patients at home.
The Ana AI tool, launched in a partnership with Hippocratic AI, is an innovative approach to engaging patients, according to Mark Kandrysawtz, MBA, SVP and Chief Innovation Officer at the York, Pennsylvania-based health system. He is among nearly a dozen executives participating in the HealthLeaders AI in Clinical Care Mastermind program.
WellSpan's Ana AI model is an AI assistant that takes the form of phone-based conversational AI.
See the infographic below. Click here to read the accompanying story.
The Ana AI tool helps with outbound patient outreach and inbound communication.
WellSpan Health is using an AI tool to improve the health system’s interaction with patients at home.
The Ana AI tool, launched in a partnership with Hippocratic AI, is an innovative approach to engaging patients, according to Mark Kandrysawtz, MBA, SVP and Chief Innovation Officer at the York, Pennsylvania-based health system. He is among nearly a dozen executives participating in the HealthLeaders AI in Clinical Care Mastermind program.
WellSpan's Ana AI model is an AI assistant that takes the form of phone-based conversational AI. The AI tool performs three functions.
With outbound campaign-style outreach, Ana reaches targeted groups of people to help with things such as colorectal cancer screening. These patients are typically not engaged in the digital self-service tools that WellSpan has already deployed.
With outbound integrated use cases, the health system embeds outbound outreach as a fully integrated and automatic part of care experiences. For example, when patients have a normal mammogram and do not respond to the health system's self-service messaging and notifications to get their test results, Ana makes sure people know that they had a normal result. Ana will automatically call those people who have not reviewed their test results and engage them in conversation.
With inbound communication, Ana answers the phone on the first ring for primary care practices. The AI tool performs call routing and can help answer questions. In June, Ana will be able to dynamically schedule visits.
Across the use cases and touchpoints, Ana has memory, according to Kandrysawtz.
"When you have a conversation with Ana, who is empathetic and friendly with infinite patience and time, if you share details about your life such as having grandchildren, she will bring up these details the next time you talk with her to provide a personalized relationship," he says.
The health system is seeing success scaling the technology as well.
"Prior to March, we had done about 6,300 total calls in the innovation mode, where we were experimenting and learning," Kandrysawtz says. "In March, we scaled to more than 260,000 calls and more than 12,000 hours of total call time."
Ana not only speaks several languages but also can change fluidly between languages.
"If she notices that a customer is using mixed English and Spanish, she will offer to change to Spanish if the customer is more comfortable with that language," Kandrysawtz says.
Mark Kandrysawtz, MBA, is SVP and chief innovation officer at WellSpan Health. Photo courtesy of WellSpan Health.
AI tool adoption advice
Kandrysawtz offers two pieces of advice about adopting AI tools.
First, he says transformation is achieved through an experience-based approach.
"You need to identify the problems to solve and the opportunities to pursue," Kandrysawtz says. "You need to consider how to deliver the best experience for team members and customers. In this way, you can unlock the level of transformational thinking that is necessary in healthcare."
Healthcare leadership should take an experience-based design approach to leveraging AI vs. creating an AI-first strategy, according to Kandrysawtz.
"It is a better way to drive transformation in an organization because it considers team members and customers first in the process," he says. "Technology is an enabling factor."
Second, leadership should avoid being overwhelmed when considering the organizational risks associated with AI tool adoption.
"It is important to balance the risk analysis that comes with privacy, security, and reputation with the opportunities for a new frontier of thinking in healthcare," Kandrysawtz says. "Those opportunities include data monetization, co-development and collaboration with solution companies, and recognizing that the healthcare side of the paradigm brings a tremendous amount of ingenuity that we can provide in the creation of the next generation of solutions."
The HealthLeaders Mastermind program is an exclusive series of calls and events with healthcare executives. This Mastermind series features ideas, solutions, and insights on excelling in your AI programs.
To inquire about participating in an upcoming Mastermind series or attending a HealtLeaders Exchange event, email us at exchange@healthleadersmedia.com.
Successful service lines have physician alignment, operational accountability, effective communication, robust data analytics, and a grasp of quality outcomes, this chief clinical officer says.
The new chief clinical officer of the Bon Secours Richmond market has extensive experience in managing service lines.
David Hasleton, MD, became chief clinical officer of the Bon Secours Richmond market in February. Prior to joining the health system, he served as CMO of clinical shared services at Intermountain Health. The Bon Secours Richmond market is part of Bon Secours Mercy Health.
David Hasleton, MD, is chief clinical officer of the Bon Secours Richmond market. Photo courtesy of Bon Secours Mercy Health.
There are five components to operating a successful service line, according to Hasleton.
Strong physician alignment along with clear expectations and accountability
Clear operational accountability, with physician, advanced practice provider, and operational leaders understanding their roles
The Cleveland-based health system does not shy away from taking time to ensure that an AI tool is a good investment and is the right solution for its patient population.
When it comes to AI tool adoption, The MetroHealth System has a robust validation process. Health system executives are willing to take the time to review whether the tool will work regardless of its track record.
Faced with a plethora of available AI tools. executives should be cautious when adopting these solutions, according to Yasir Tarabichi, MD, chief health AI officer at MetroHealth. He is among nearly a dozen executives participating in the HealthLeaders AI in Clinical Care Mastermind program.
"How we implement our AI models is unique because we are a little slower in validating them than others and are extremely careful in validating them," Tarabichi says.
As a clinical informaticist, he focuses on the concept of the learning health system when it comes to AI tool adoption.
"You are constantly developing a huge repository of data both in terms of patients and their conditions, as well as the things we are doing in our health system," Tarabichi says. "For example, how are we communicating with patients, what are the protocols we are activating, what are the clinical pathways we are leveraging, and what are the medications we are using?"
The key is taking the learning health system concept and actualizing it, according to Tarabichi.
"There is often a gap in this area," he says. "A lot of organizations talk about being a learning health system and learning from their data. They do research. They look back and they say this worked or that did not work."
A learning health system conducts tests in real time in its patient population to identify whether a change in what they do makes a meaningful impact, Tarabichi explains.
"We need to be able to do that in an agile fashion," he says. "We need to understand whether something is working."
An example is the process that the health system used to adopt a predictive tool for sepsis.
"When we took on our AI sepsis model from a vendor, it was being used by several organizations, and everybody said it worked," Tarabichi says. "When we evaluated how others were using this AI model, we approached it with a grain of salt. We were not entirely sure that this predictive model was going to work for us."
With quality oversight and a multidisciplinary group, MetroHealth developed a quality improvement process, where patients who came into the emergency room either got to be on the AI tool's scoring system or didn't.
"We set up a response team for sepsis," Tarabichi says. "We made sure everybody knew their cues and what they needed to do in the standard practice, using clinical pharmacists as the main driver. We ran the model, and we compared the data. We wanted to know how patients who got the score did and how patients who did not get the score did."
The validation process found the AI sepsis model was effective for MetroHealth's patient population.
"By the end of the study, which was a couple of months, we found that the patients who got a score got antibiotics faster than patients who did not get a score, which is important in the treatment of sepsis," Tarabichi says. "We even showed decreased mortality in the hospital associated with that outcome."
This validation process showed that people and process are at least as important as the technology, according to Tarabichi.
"The technology was a catalyst that drove the process, but what really mattered was getting the team to think about how they would use this new information and how it would drive what they do at the point of care," he says.
The AI sepsis model is designed with clinical care teams in mind, Tarabichi says.
"Our sepsis predictive algorithm provides information about the patient's risk for sepsis in a place on the chart where emergency room providers typically look to see how a patient is doing overall," he says. "It sends an interruptive alert only to the clinical pharmacists who actually want that information. They want to be stopped in their tracks when a patient comes in who could have sepsis."
Yasir Tarabichi, MD, is chief health AI officer at The MetroHealth System. Photo courtesy of The MetroHealth System.
Understanding the AI tool life cycle
Paying attention to the life cycle of AI tool implementation is another hallmark of MetroHealth's approach to AI.
Tarabichi encourages his counterparts at other health systems and hospitals to look at the frameworks for the AI life cycle that have been set out by the Coalition for Health AI (CHAI) and the Health AI Partnership.
"Thinking about the life cycle of the solution means by the time you have launched the solution you have already figured out whether it works, whether it is biased, whether it is fair, and how you are going to use it," he says.
This includes knowing when a solution should be terminated.
"What are the criteria for success and when do you need to sunset an AI tool?" Tarabichi says. "The big thing we have found in the informatics and change management world is we have done a good job of turning things on, but we do not do a good job of turning things off."
Understanding the life cycle of an AI tool is critical, Tarabichi says.
"You need to have an offramp and to understand how you are monitoring an AI tool," he says. "Do not implement a solution if you have not thought about the life cycle."
The HealthLeaders Mastermind program is an exclusive series of calls and events with healthcare executives. This Mastermind series features ideas, solutions, and insights on excelling in your AI programs.
To inquire about participating in an upcoming Mastermind series or attending a HealtLeaders Exchange event, email us at exchange@healthleadersmedia.com.
John Phipps, MD, is chief clinical officer of UF Health. Photo courtesy of UF Health.
James Blum, MD, is chief health information officer at University of Iowa Health Care. Photo courtesy of University of Iowa Health Care.
Mark Kandrysawtz, MBA, is SVP and chief innovation officer at WellSpan Health. Photo courtesy of WellSpan Health.
