End-of-life decisions are inherently difficult for all concerned. Fortunately for healthcare providers, and in turn the patients they serve, increasingly robust options offer support for data-driven decisions.

Clinical technology and data analytics have tremendous potential to overcome the obstacles to effective end-of-life care, according to Srinivasa Vegi, PhD, Bethesda, Maryland-based president of data analytics and artificial intelligence for IT services provider 

Is end-of-life care the place for big data?

“Not only will these tools help doctors and patients determine whether treatment is the best course of action, but they also help to better identify appropriate patients for palliative intervention as part of their end-of-life care,” he says. “Moreover, clinical tools and analytics can help to reduce the length of stay for palliative care patients and decrease costs whether or not treatment is sought.

 In fact, data analytics-particularly machine learning solutions that use big data-are radically transforming how physicians deal with palliative care, says Sapan Desai, MD, PhD, MBA, a Chicago-based vascular surgeon and CEO of 

, a firm offering an advanced healthcare data analytics platform.

Desai says that data analytics will change how physicians approach end-of-life care. Not only can machine learning and artificial intelligence pinpoint the causes for death, but depending on how the algorithm is set up, it can even make calculations regarding which of those causes will impact the quality of life the most.

“Good analytics can help direct the conversation with a patient by targeting specific medical problems and the projected efficacy of treatment,” he says. “It can help them understand, and come to terms with, how their quality of life will look in the near future.

 For example, Desai describes an 83-year-old patient who has moderate kidney disease, poor leg circulation, and heart failure.

 “Machine learning may tell me that he is likely to suffer kidney failure leading to dialysis if I do any major intervention for his circulation problems,” Desai says. “Armed with this information, my discussion with the patient may guide him toward palliative care rather than spending his last few months on dialysis, separated from his family.”

One of the strongest arguments for the use of data analytics in this area is improved efficiency.

“Machine learning and data science can help make end-of-life care services more efficient and accessible,” says Gabriel Bianconi, founder of 

, a New York AI and advanced analytics consulting firm. He notes that these tools can increase efficiency by automatically predicting which patients could most benefit from end-of-life care, without necessarily requiring referrals, inbound interest, or manual data reviews. “Automated predictions can help healthcare professionals proactively reach out to more patients and do so at the ideal time for addressing end-of-life needs.”

Bianconi says that machine learning could help patients and professionals make more informed decisions. “For example, the tools can help give more accurate estimates of survival rates and times for different interventions,” he says. “With this information, both parties can better make a decision and plan accordingly.”

In addition, machine learning could in theory be leveraged to make more accurate end-of-life predictions, Bianconi says. He points that hybrid approaches have already outperformed healthcare professionals on a number of diagnostics tasks, and a similar approach could be applied to end-of-life situations.

How Health Systems are Using AI and Future Predictions

At the same time, these tools have the potential to give insights that are tailored specifically for the patient. Instead of giving general information about survival rates, for example, a data-driven approach could leverage the patient's medical history, and other personal data, to give more accurate survival rate predictions for different treatments or conditions, according to Bianconi.

Such applications have moved beyond the theoretical to significant real-world applications.

With better communication about advanced illness care options and end-of-life planning, physicians have the potential to make significant improvements in healthcare access, utilization, cost and outcomes, says Brentwood, Tennessee-based Kurt Merkelz, MD, senior vice president and chief medical officer of 

, a national provider of hospice, palliative and home healthcare services.  He notes that to improve communication, there needs to be a better understanding of the goals and preferences of an individual patient, and these discussions can only meaningfully occur by way of shared decision making. 

Experts Share How to Apply Big Data to Patient Care

“An informed discussion occurs when information is fully disclosed, a patient’s values, beliefs, and preferences are top of mind and a recommendation is made based on an accurate estimation of a patient’s prognosis,” Merkelz says. “However, a lack of quality prognostic markers is a potential barrier to fruitful shared decision making.”

 Thanks to advances in analytics, a productive way to address this gap is to use electronic medical record data extraction and improved predictive analytics to estimate probability outcomes. According to Merkelz, past algorithms have utilized non-clinical data and manually extracted data for calculations, limiting their usefulness. Enhanced data analytics, on the other hand, offer the opportunity to better identify patients who are at risk for hospitalization and offer other insights into a patient’s care needs. 

“This allows patients to better plan for the type of care they would like to receive throughout their health care continuum,” he says. “Having these important goals of care conversations with patients helps them access beneficial services like home health, skilled therapy, and hospice and reduce unwanted hospitalizations, procedures and treatments, creating a better quality of life for them and their families.”

 A sobering fact is that 75% of patients are unable to make some or all decisions at end of life, according to Amy Berman, RN, a senior program officer with the John A. Hartford Foundation.

“Data analytics offer the possibility of better supporting advance care planning and goal-concordant care by identifying populations at greater mortality risk at a point when advance care planning can be initiated or decisions can be reviewed,” Berman says.

In addition to helping address the concerns of individual patients, these tools offer potential for positive change on a large-scale basis.

 “We can use data analytics to root out disparities around access to palliative care, advance care planning, and the provision of unwanted care,” Berman says. “Data analytics offer the possibility of addressing what matters as our nation ages."

At the same time, another reality is that the potential for such analysis is often misunderstood, says Greg Horne, principal health analytics strategist at software and analytics provider 

“This is one of those mine fields where people are afraid that computers will one day decide whether you get to live or die,” he says. “That’s a gross mischaracterization, of course, but a real fear for many.” He says that those who express such worries are putting the emphasis in the wrong place. The real potential is not about the data or analytics but how data and analytics can inform the real human decisions that happen around end of life.

 “Doctors, patients, and families are often forced to make end-of-life decisions based on limited knowledge, guided more by gut reactions than actual evidence,” Horne says.  He suggests instead imagining an artificial intelligence-based decision support system that helps these key stakeholders understand potential options and the likely outcomes associated with each.

How Predictive Modeling, Big Data Analytics Curb Health Costs in China

Horne notes that given all the complexities involved, the primary opportunity is in the centralization and aggregation of all relevant data. Then insights extracted from that data available can be provided to key decision makers via customizable reports and dashboards.

“Effectively, analytics could provide the framework for an end-of-life care workflow and related care management coordination,” he says. Aggregated historical data could serve as a means for using analytic approaches to develop dynamic, patient-specific guidelines for recommended “paths of care.” At the same time, cost/expense insights could help guide both administrative considerations and patient and family decision-making.

Despite the advantages offered by data analytics, its application can also generate unanticipated levels of complexity. While a strength of many tools is their capacity for streamlining the process of reviewing and interpreting large volumes of information, it still takes time for healthcare providers to absorb relevant details and translate them into terms that can be readily understood by patients and their families.

Indeed, the basic functions of collecting and sharing data may generate some challenging situations, according to Manali Patel, MD, assistant professor of oncology at the Stanford University School of Medicine and staff oncologist at the 

.  While she agrees that the use of analytics can bring real value, she also points to potential challenges.  More data in itself may not be as useful as some would hope. 

“We struggle to make decisions easier with the data we have now,” she says. “I’m concerned analytics will provide more information but not knowledge that’s actionable.”

She also poses questions related to ethical concerns. Have patients consented to use of data? Who will have access? Other questions range from insurance considerations to making sure patient’s fundamental concerns are not overshadowed by numbers.

Patel points out that while analytics can support efforts to prevent unnecessary use of acute care, approximately 20% of patients with terminal illnesses would still choose aggressive treatment even if data analysis doesn’t support their decision.

The bottom line is the imperative for applying information in a meaningful way.

 “We need to make sure the data we have is going to lead to better patient care,” Patel says. “It’s all about quality care.”

In the future, the medical community can anticipate even more robust capabilities in this area, Vegi predicts.

Making sense of big data: Data projects spur progress

“Data mining algorithms successfully digest and synthesize complex data into usable information for both doctors and patients,” he says. “There’s going to be a big change in the availability of that kind of predictive information in the next few years. More systems need to be developed that can cross reference data to help empower clinicians to have these conversations with patients and their families earlier, when appropriate.”

Currently, algorithmic modeling helps to synthesize and digest complex information into usable chunks to be leveraged by doctors, patients, and families to inform decision making, Vegi says. He adds that risk-scoring based on a patient’s diagnosis, severity, clinical condition, medication, and hospitalization history can help clinicians offer objective data to families about future hospitalizations, as well as decisions to withdraw care. “Though the concept of scoring a patient’s life expectancy based on a numerical figure may not seem optimal, it actually can help doctors and medical staff compare cases to justify treatments and specific care programs,” he says.

While interpreting such numbers may seem like something out of a dreary anti-utopian film, the reality is much more promising.

“Ultimately these remain human decisions, freely chosen by the patient and family, alongside their physician,” Horne says.  He notes that exploring options customized to the patient-and rationalized by data related to end-of-life care outcomes and costs-simply provides a better starting point. “Such an evidence-based approach would certainly give families tremendous peace of mind as they face some of life’s most difficult decisions.”

Mark Rowh is a Virginia-based freelance writer whose interest areas include healthcare, business, and higher education. 

Articles

Evidence-based decisions can help guide end-of-life care.

The Impact of Big Data on Medical Decisions

The U.S. biosimilars market gained momentum over 2018, as more of the agents were submitted for FDA review and more regulatory approvals were granted, including additional immunosuppressive and cancer-treatment biosimilars.

Sandoz’s biosimilar adalimumab, Hyrimoz (adalimumab-adaz) injection was approved in October 2018, and Celltrion’s Truxima (rituximab-abbs), the first biosimilar to be approved in the U.S. for non-Hodgkin lymphoma and the first approved biosimilar to Rituxan, was approved in November 2018.

“We’re just seeing the cusp or initial wave of these cancer-treating biosimilars,” says Gary H. Lyman, MD, MPH, FASCO, FRCP, professor of medical oncology at the University of Washington School of Medicine, in Seattle. Lyman also serves as chair of the American Society of Clinical Oncology (ASCO) Biosimilars Work Group.

In May 2018, the FDA approved a biosimilar version of epoetin alfa (Epogen/Procrit), called Retacrit (epoetin alfa-epbx), for treatment of chemotherapy- and kidney disease-associated anemia, as well as for anemia resulting from zidovudine among HIV-positive patients. In June, the FDA approved Mylan and Biocon’s application for Fulfila (pegfilgrastim-jmdb), the first biosimilar to Neulasta (pegfilgrastim) for reducing infection risk in some patients with non-myeloid cancers who are administered myelosuppressive chemotherapy.

There are now 15 FDA-approved biosimilar products, up from nine in 2017. Of the four oncology biosimilars approved in 2018, three have already gone to market, says Rick Lozano, vice president of biosimilars and integrated business development, AmerisourceBergen. 

Additional biosimilars approvals are coming in 2019 and more applications will be submitted, as more brand-name biologics’ patent protection periods expire.

“The regulatory framework is pretty well settled now,” Lyman says. “We’re still waiting for the final rules for some of the other aspects of biosimilar approval, such as substitution and interchangeability.”

Biosimilars do not have to be declared interchangeable with their reference brand-name biologics to be prescribed, but an interchangeability determination would allow substitution by pharmacists.

“While it will take time for us to fully benefit from recent regulatory updates, the changes and communications we saw coming from policy makers in 2018 were incredibly promising and present great opportunities for 2019,” Lozano says. “Looking ahead, policy makers are seriously exploring the interchangeability between biosimilars and their reference products as part of the blueprint for lowering drug prices.”

Congress and the FDA made it clear in 2018 that biosimilars “will be part of the solution” for controlling healthcare costs, Lozano says. “That alignment is starting to better pave the way for more products to come to market, as evidenced by this year’s uptick in approvals.”

The FDA is also preparing new guidelines on biosimilar product labels, which Lozano hopes will create a “more level playing field” between biosimilars and biologics by helping to reassure healthcare providers that biosimilars are safe and effective.

Lozano expects to see continued momentum in 2019, with more approvals and increasing acceptance of biosimilars as a viable treatment option.

“We are confident that the U.S. market will continue to evolve in the direction of the European biosimilar market, as more and more obstacles, such as patent challenges and litigation, are reduced,” he

The U.S. has lagged behind Europe on biosimilars approvals and uptake, and some analysts have pointed to uncertainty about anticipated cost savings, regulatory and legal issues, contracting mechanisms, and physician unfamiliarity with biosimilars as potential barriers to uptake.

Because biosimilars are “highly similar” but not identical, on a molecular level, to originator biosimilars, some clinicians have had concerns about the idea of switching patients from well-known biologics to less familiar biosimilars. Patients have been switched to biosimilars in most cases only after brand-name biologics lost efficacy or brought intolerable toxicities.

“Europe has been ahead of the United States on biosimilar approvals for years but the good news is this: none of them have been withdrawn from the [European] market or seen red flags with major safety or efficacy issues,” Lyman says. “Nevertheless, recently, a submission for a biosimilar for rituximab for lymphoma was turned down by the FDA, for reasons they know and I don’t, and the company has decided not to challenge or resubmit.”

“Over the past year, for the first time, we have had a number of oncology biosimilars FDA-approved for cancer treatments as opposed to supportive care agents like growth factors,” Lyman says, citing approvals since September 2017 for the biosimilars Mvasi (bevacizumab-awwb), Ogivri (trastuzumab-dkst), Ixifi (infliximab-qbtx), Hyrimoz, and Truxima.

The first biosimilar approval was for Zarxio (filgrastim-sndz), a biosimilar G-CSF myeloid growth factor used in supportive cancer care, which was approved back in March 2015. In 2018, three more filgrastim and pegfilgrastim biosimilar products were approved.

But Lyman cautions that biosimilars are still in their early days.

“Biosimilar trastuzumab and bevacizumab were approved in December 2017, but both of these met with delays and even now they are just beginning to enter the marketplace, so we really don’t yet have data on their uptake,” he says.

Oncology biosimilars have been “mainly a good-news story,” Lyman says.

“We have multiple new approvals and the approval process seems to be going smoothly-with perhaps one glitch that was part of the growing pains of a new process,” he says.

As the FDA weighs the evidence for a new approval, the agency often asks an oncology drug advisory committee to review that evidence and make a recommendation, Lyman explains.

“Usually the FDA decision is in line with the recommendation of the advisory committee,” Lyman says. “There’s public comment, a whole transparency process.”

But the agency recently skipped that step in 2018 when approving Fulphila (pegfilgrastim-jmdb), a biosimilar long-acting growth factor used in the supportive care of cancer patients, Lyman says.

“They chose not to do that this time, probably because they felt this is just another growth factor and they’ve done this before,” he says. “So, there was no public display of the evidence.”

That move might well slow its uptake, Lyman says.

“You have the issue of integration of biosimilars into clinical practice, into clinical practice guidelines or simply for uptake in health systems and clinical practices or clinics,” Lyman says. “So, this biosimilar was approved but when it came to a decision to recommend this form of growth factor biosimilar in a clinical guideline, the guideline review committee had no data available on which to base a decision because they had no data from the FDA and the company had not yet published its results from its studies.”

That episode goes to show that FDA approval is “necessary but not necessarily sufficient” for integration into clinical practice, Lyman says.

Oncologists and other clinicians-and guidelines panels-want access to all of the evidence the FDA reviewed at the time of approval, Lyman says. “Clinicians want to see trial data and results and to come to their own conclusions.”

“Hopefully this was a one-off,” Lyman says. “Whether or not the data behind these drugs are given to a drug review committee, the companies and the FDA need to make these results available to clinicians and professional organizations, and payers presumably as well want to review these data to make sure patients are being served.”

Will biosimilars deliver on cost-savings expectations?

Lyman and Lozano agree that as FDA biosimilars approvals accumulate, they should increase competition between biosimilar products to bring down cost.

“Pfizer most recently launched Retacrit at a substantial discount to the reference product Epogen,” Lozano says.

A second Neupogen biosimilar, Pfizer’s Nivestym (filgrastim-aafi), is now on the market, for example.

“Pfizer launched Nivestym at a wholesale acquisition cost [WAC) that is 30.3% lower than that of the reference product and is 20.3% lower than that of Sandoz’s Neupogen biosimilar,” says Lozano. The introduction of second entrants for a reference product, like Nivestym, within the U.S. market will give patients and their healthcare providers improved access to a high-quality, potentially lower-cost treatment option.”

“As of 2018, we have multiple supportive care biosimilar growth factors, which bring competition to that space that has for decades been dominated by the originator or innovator products, which are very costly,” Lyman says. “At the same time, the predominant growth factor used in the U.S. has been a long-acting product that requires only a single injection with each treatment cycle, and the brand-name has dominated the horizon for a couple of decades but now we will have biosimilar competition there too, in the near future.”

Biosimilar filgrastim is on the market at 10% less than the brand-name originator, Lyman says. “That’s with very early data and very little competition,” he says. “With time, we’d like to see that become 20% or 30% price reduction. It’s never going to be 80% like with generics. These are more complex molecules. But it seems to be an early trend toward a reduction in pricing.”

As biologic products’ patents continue to expire and patent litigation is resolved, 2019 should see quick approvals and market launches of more biosimilars.

“In 2019, we’re hoping to see the oncology biosimilars that haven’t launched yet due to pending patent expirations and litigation-such as [biosimilar] bevacizumab-come to market as quickly and efficiently as possible,” Lozano says. “We will also continue to watch [biosimilar] pegfilgrastim and neupogen products, which are currently filing for FDA approvals.”

But there are still headwinds that will likely slow the widespread adoption of oncology biosimilars. Chief among these are concerns about reimbursement under the current “buy and bill” payment system, Lozano says.

“It’s also important to keep in mind that oncologists’ familiarity with and confidence in using biosimilars is critical to a successful formulary,” Lozano says. “As more oncology biosimilars come to market, physician education will continue to be a critical component of a product’s launch strategy, and it must start well before a therapy is in market and can be supplemented by partners throughout the supply chain. Our group purchasing organization, ION Solutions, is in the process of developing educational resources and programs that will help oncologists include biosimilars in their prescribing, specifically addressing concerns about interchangeability questions. This will be an important step in promoting biosimilar use in the coming years.”

Patients and clinicians might become more confident in biosimilars if they are granted FDA “interchangeability” status rather than only biosimilarity.

But earning that FDA designation requires biosimilars manufacturers to pay for new clinical trials, and firms have not yet pursued that option.

That could change in the 2019. Indeed, Boehringer Ingelheim is already pursuing an interchangeability trial for 

 , its candidate Humira (adalimumab) biosimilar.

Lyman believes more are likely on the way, because interchangeability could be an attractive marketing tool.

“The reason I think it will probably come is that as more of these biosimilars in a given class, like the growth factor biosimilars, all competing with one another, it’s very possible that a new one coming along will do something to distinguish themselves from the pack to give people a reason to give up using the originator,” he says. “If your patient is traveling or switching doctors or health systems, they can switch to our product because it’s interchangeable.”

As part of the federal government’s effort to address rising drug prices, the FDA is reviewing biosimilar/biologics interchangeability, Lozano says. Legislatures in 38 states have already passed bills to support the automatic substitution of biologic drugs with approved biosimilars at the pharmacy level, once the FDA starts granting interchangeability designations, he says.

While still largely a new phenomenon, biosimilars are here to stay-and this year will only bring more of them to market.

The State of Biosimilars in 2019

There are myriad factors driving interest in home health. For one, there are 46 million people who are 65 years of age and older in the United States. That number will jump to more than 

 when this age group will represent 24% of people in the United States.

Add to that the soaring cost of treating chronic conditions-Diabetes alone cost 

 in 2017. The CDC projects the cost to treat chronic obstructive pulmonary disease (COPD) will reach $50 million each year by 

Home Hospital Care Enhances Quality, Reduces Costs

Preventing hospital-acquired conditions such as sepsis is also on the mind of healthcare executives. For example, severe sepsis impacts more than 1 million Americans each year-and 15% to 30% of those people 

And all of this is taking place in a country where as much of one-third of healthcare spending may be 

Frail, sick patients increase healthcare costs

Approximately 5% of patients drive 40% of a provider’s costs, says Michael Le, MD, co-founder and chief medical officer at Huntington Beach, California-based 

, which contracts with payers to provide home health services.

Who’s helping to drive that spend? It’s older patients with mobility challenges who can’t travel to their physician’s office for follow-up appointments. These are patients, says Le, who stay home and “tough it out.” Then it gets so bad that they call 911 and get admitted to the emergency room, instead of getting care from their primary-care provider.

Repeated visits by very sick and frail patients to the emergency room are bad for continuity of care. That’s why it’s valuable to determine those patients who are frailest and in the most need of support and to bring the health system and medical procedures to patients’ homes, he adds.

Landmark Health employs a variety of clinicians, including nurse practitioners, physician assistants, and behavioral health specialists (such as psychiatrists and social workers), to provide around-the-clock home-based care to 26,000 patients on an urgent or scheduled basis. Landmark Health contracts with payers to provide this care to members.

The majority of its patients are aged 80 years or older, but Landmark Health also serves very sick patients in their 20s and 30s, says Le. On average, patients have eight chronic conditions, such as congestive heart failure, 

, and chronic kidney disease. Many of its patients are considered frail.

Most patients receive a home visit once a month and three phone calls per month; the initial visit lasts an hour and follow-up visits run about 45 minutes. That’s in addition to visits by care team members to respond to urgent medical events around the clock.

Landmark Health provides coverage-and is 100% at risk for-82,000 patients across 13 states. In some of its more established markets, the organization is engaging with 55% to 60% of covered patients. Since the company was started in 2013, it has worked with more than 30,000 patients.

Here’s how their care approach works: Care providers can test patients’ blood-glucose levels, do an inventory of their medicine cabinets, measure blood pressure, draw blood, check labs, and administer antibiotics and steroids in the home. Landmark Health partners with local imaging providers for X-rays and ultrasounds to provide imaging services within patients’ homes.

These are patients who have a medical-loss ratio of more than 100%, adds Lee. That means payers are losing money on them, largely because they’re going to the hospital so often. The patients served by Landmark Health typically have a 20% to 30% medical-loss ratio, and they have a 50% lower morality rate than patients who aren’t engaged.

One of the biggest challenges with home health is getting paid for that care. But that doesn’t mean providers aren’t working hard to figure it out.

, a suburban hospital that’s part of Boston’s Partners HealthCare. It’s piloting a program that brings clinicians into patients’ homes. The pilot is financed by the hospital.

Remote Patient Monitoring Gets Boost from CMS Home Health Proposal

“Proof of concept is our current goal [and] focusing on providing high-quality care while the patient is at home … as well as progress in improving total medical expense as a system,” says Louis Jenis, MD, chief medical and innovation officer.

Patients are selected for home health for two reasons: they’re “super utilizers” of the emergency room or they don’t show up for follow-up appointments with their primary care providers regularly.

The pilot, which began in April, serves 60 patients-some of whom are on their third scheduled home visit. The average patient is aged 85 years and most patients are women. It involves sending a nurse practitioner into the patient’s home. The patient’s primary care physician refers the patient to the practice’s nurse practitioner for home visits.

Its home health program is still in a pilot phase, which means cost and quality measurements are currently unavailable. But Jenis says the home care program is a fundamental part of the hospital’s primary care strategy. “Our [primary care providers] are relieved to have patients seen and chronic conditions are now being managed in the home. Our patients are extremely grateful,” he adds.

Many older patients, in particular, prefer to be home and surrounded by their families, says David Levine, MD, MPH, a physician and researcher in the division of general internal medicine at Boston’s 

, which is also part of Partners HealthCare. Thus, providing home health can translate to a better patient experience.

It also helps patients avoid adverse events such as falls or hospital acquired infections. Levine adds that there’s a finite number of beds for sick patients, and that’s why sending clinicians into patients’ homes-aided by technology-can help. In this program, a doctor and nurse team travel to the patient’s home.

When a patient is stabilized in Brigham and Women’s Hospital’s emergency room, their care team then decides-based on the patient’s needs and proximity to the hospital-that they’re a candidate for home-based visits. That entails regular monitoring and home visits between two and five times a week. Supplementing that care is VitalPatch, a patch that monitors patients’ vital signs, such as heart rate, skin temperature, fall detection, and respiratory rate. That data is shared with Brigham and Women’s Hospital’s care team.

Study: Hospital-at-Home Program Benefits Severe COPD

Here’s how that works: There’s an 85-year-old patient with the flu, who requires oxygen and antibiotics, in addition to regular monitoring. If the patient experiences a faster heart rate, it would trigger the team to adjust their treatment plan, says Levine.

His team has used this device and conducted home visits with 300 patients since 2016. A pilot study including 20 patients-nine of whom were treated at home and the remainder were treated in the hospital-was 

. The result was a 52% reduction in direct care costs while maintaining quality and patient experience. The home health program is financed through a combination of payer and internal hospital funding.

Extending best practices to the health network

Increasingly, providers are reworking pre-operative education and post-surgical recovery for joint replacement patients. Oakland, California-based Kaiser Permanente has created a playbook that allows providers in each of its different markets to select from one of three post-surgical recovery paths, based on the individual patient’s needs.

National Total Joint Replacement Initiative

 is Kate Koplan, MD, MPH, associate medical director for quality and patient safety. One of the key drivers behind getting patients home after their surgeries is patient satisfaction, she says. Other drivers are patient safety and infection risk, both of which are inherent with being in the hospital. Affordability is also important, since care provided in patients’ homes costs less.

Still, Koplan acknowledges that falls, in particular, can be an issue in patients’ homes. That’s why a safety care plan is done in patients’ homes before the surgery, to assess uneven floor surfaces that could cause falls.

Her work to provide best practices for orthopedic teams for total joint surgery started about three years ago. And the different approaches, which range from no nights in the hospital to one night to two or more nights after the surgery came from the health network’s orthopedic surgeons.

The number of nights a patient stays in the hospital after their surgery depends on a variety of factors, which include number of comorbidities, support within the home, and the home safety evaluation. The decision is ultimately the result of shared decision-making between the patient and their surgeon and the rest of the clinical team.

Demographics Most Likely to Be Rehospitalized During Home Healthcare

Koplan adds that care planning is an integral part of each of the three paths. For example, patients will need access to follow-up appointments and some patients will receive that follow-up care in their homes.

Because Kaiser Permanente operates in seven markets-each of which has access to different resources-these steps may happen differently, she says. For example, a home safety assessment may be done in person or by phone by a nursing care coordinator, who also assesses the family and social support the patient will have in the home environment.

Still, the variables that help orthopedic surgeons and their patients to choose the appropriate post-surgery path are laid out in a playbook that’s shared throughout the network. The playbook was created by a multidisciplinary team that includes orthopedic surgeons, anesthesiologists, nurses, care coordinators, physical therapists, and home health service providers, in addition to patient input.

Practices outlined in the playbook range from pre-operative care (such as patient and family health education), to perioperative care (such as blood management protocols), to post-operative care, which can include home physical therapy visits.

Koplan says her role is to extend best practices throughout Kaiser Permanente. As a result of this work, the average length of stay in the hospital for patients is trending downward, while quality and safety have been maintained. The feedback from clinicians has been “fantastic,” she says.

Getting paid for care provided in the home is a challenge. That’s why Newton-Wellesley Hospital is financing its pilot and Brigham and Women’s Hospital is sharing the payment burden with a payer.

The difficulty stems from providers getting paid less for care when it’s delivered outside the hospital. That’s according to Michael Brookshire, a Dallas-based partner at consulting firm 

. Thus, there are “odd incentives” for providers to not offer home health services to patients. Provider organizations that are successful with home health have been making investments in value-based care for a long time; that’s the case with Kaiser Permanente, he says.

Landmark Health has been successful because their model of caring for sick and frail patients in the home is paid for by the payer, he adds. “That kind of model is very difficult for a traditional hospital system to create. It’s just a very different payment structure.”

Top five strategies for managing post-acute care

Delivering home health well is another challenge. Brookshire points again to Landmark Health’s ability to build home health as its core business.

Levine acknowledges that lack of payer support for home health makes this work difficult. But he believes payers will receptive once more research is done on the cost and quality impacts of home health. For example, if an emergency room visit costs a payer $10,000 and care in the home costs $9,500, the payer may be willing to share the savings with the provider. Levine hopes to see more payers embrace home health within the next five years-or even sooner.

As the U.S. population ages into declining health, accompanied by mobility challenges in getting to healthcare providers, innovative solutions to care include bringing the health system and medical procedures to patients’ homes.

The Biggest Barrier to Home Healthcare

Experts agree that forecasting the future of healthcare technology isn’t difficult-machine learning, artificial intelligence (AI), cloud technologies that apply to clinical, workplace, and financial processes will have better and richer incorporation into the industry.

But to get there, healthcare executives need to be laying the cultural foundation today for upcoming technology changes in the next decade.

For example, investing in AI over the next five years could cost, on average, more than $30 million per organization, according to 

 of 500 healthcare executives by OptumIQ published in November 2018. However, 38% of employers and 20% of health plans believe they would see a return on that investment in four years or less. Ultimately, 94% of respondents see investments in technologies, such as AI, as the clearest route to affordable, accessible and equitable healthcare in the future.

Real-World Applications of Artificial Intelligence in Healthcare

But in order to realize those future possibilities, a culture shift needs to happen in healthcare today, says Tom Lawry, director of worldwide health for Microsoft. He adds that the future of healthcare technology relies more on the culture and framework being created by clinical and business leaders today.

“What really is going to be needed in the future is not just the breakthroughs in technology, but breakthroughs in creative thinking and the ability of leaders to think differently when redeveloping their processes to leverage the power of the technologies rather than trying to insert these new technologies into a framework,” Lawry says.

Anil Jain, MD, vice president and chief information officer for Watson Health at IBM, says that healthcare organizations will need to shake the stigma of being bureaucratic and slow to adapt in order to be agile enough to adopt future technologies.

“Healthcare organizations need to start to push the agenda that says that innovation is important to healthcare. People outside of healthcare view the industry as very conservative, very slow to adapt,” Jain says. But when you talk to people inside the industry, we all think we’re moving very, very quickly. The key is for these healthcare organizations to get involved in the national debate, at the advocacy level and advising others on what the industry needs, so that movement is made collectively.”

Although it is difficult to predict, these experts have given their insights on where healthcare technology will be the most impactful in the next decade:

1. Better cloud integration with existing technologies

Although devices collecting digital data are important to healthcare, how that data is shared is the most essential part of the equation, Lawry says.

Five healthcare technologies likely to be developed in the next 10 years

More than 90% of healthcare organizations are widely utilizing the cloud to host applications, according to a 2017 Healthcare Information and Management Systems Society (HIMSS) 

 on cloud use. However, the industry is still using the cloud for separate functions, such as clinical apps, data hosting, and backup, and not in a holistic fashion. The HIMSS survey found that though there is a high level of cloud usage at healthcare organizations, the functionality is still limited.

Use of cloud integration has allowed for data from different healthcare silos to be shared, and as more organizations continue to connect those dots, Lawry says that it will transform the industry.

“Everyone's digitizing their data, whether that's electronic medical records or X-rays. But digitizing data doesn't do anything other than that. It changes data from one form to another instance,” Lawry says. “The transformation that's brought about by the cloud and bringing that data together, allows for all kinds of interesting things. That to us is the number one transformational aspect going forward for the next few years.”

Artificial intelligence has been a part of the healthcare for years, but experts believe in the next decade it will be a regular part of the industry.  

 of 200 healthcare professionals by Intel Corporation, released in July 2018, found that 37% of respondents were using AI in limited ways, and 54% believe that there will be widespread AI adoption in the next five years.

John Doyle, director of business strategy for Worldwide Health Industry at Microsoft, says that moving forward we should expect to see AI infused into all aspects of clinical and operational workflow.

“We are early in the journey for cloud and AI adoption today, but we are already starting see some amazing progress being made and we expect this continue and with a broader adoption of applied AI in areas such as the clinical interpretation of complex datasets, intelligent medical images, voice integration, and real-time insight of streaming medical devices and sensors data,” Doyle says.

As a new generation of consumer-focused services aim to merge patients and consumer journeys, applied AI will disrupt how patients engage with healthcare providers today, Doyle says.

“Applied AI has the potential to reduce the complexity of how healthcare data is captured and analyzed, examples of this include how intelligent voice integration and bot technologies are being used during virtual consultations to reduce the time spent entering data by both patients and clinicians, and how pre-trained clinical knowledge can be applied at the point of care,” Doyle says.

3. Infrastructure upgrades that make healthcare more accessible

The ability for clinicians to meet with patients via web and mobile portals is essential for chronic care management, says Rhonda Collins, DNP, RN, chief nursing officer at 

, and founder of the American Nurse Project.

“A majority of this country is still rural. So, we need to rely on technology to fill gaps in human connections in healthcare-telehealth will be more important going forward, as infrastructure and technology continue to improve. Hospitals and clinics will need to prepare for a world that technology is making smaller,” Collins says.

 issued by the Federal Communications Commission found that 50% of U.S. counties house people who both have high occurrences of chronic diseases and a greater need for broadband connectivity. The commissioned coined this, “double burden,” and incidents can be as high as 60% in rural counties.

Three Strategies That Improve Access to Rural Healthcare

“That makes a remote consultation with a doctor or video chat very difficult, but the situation is improving, and over time, I think at-home, remote care will be most valuable in rural areas, where technology use is far more practical than a long drive to see a doctor,” Collins says.

As telehealth expansion continues through Medicare reimbursements, patients are still unclear about its availability and use. A 

 released by Healthline in August 2018 found that 46% of Medicare Advantage members were unsure if telehealth was an option, and 37% stated telehealth was not offered, even though it is.

Collins adds that hospitals are still lacking full-scale Wi-Fi and consistent cellular service, which impedes integration of telehealth and other mobile health offerings.

“These basic issues make it very difficult to bring technology in to provide extraordinary care and connectivity to all patients everywhere. Infrastructure upgrades are a must, and that should be the focus of many hospitals, so they can leverage great technologies that improve the lives of patients and clinicians alike,” Collins says.

Though smartphones, smart watches and other smart devices are being used by consumers, a focus on “smart” hasn’t translated to healthcare solutions, says Kal Patel, MD, MBA, president of 

, a Flex company that provides biopharma and medical technology internet platforms.

“By and large, many healthcare solutions lack meaning. They are not smart,” Patel says. “The data from them is either not collected at all or it is collected, and it stays in some type of local environment which inherently limits the value you can derive from that.”

Patel says that in the next decade drug delivery devices such as insulin pens, biologic auto injectors, inhalers, and smart packaging for pills will be commonplace to enhance both clinical and business operations in healthcare. The goal of tracking this data is to add to the landscape of behavioral insights that can help enhance patient care. Patel says that the ability to observe how patients use chronic therapies both inside clinical settings and at home or inpatient care settings is enhanced by integrated cloud and artificial intelligence use.

“Most of that technology is already there, so in the next five to 10 years it’s about unlocking that data. Once you can unlock that data, we will really be able to see progress using artificial intelligence and machine learning within those data sets,” Patel says.

Jain says that IBM Watson is currently studying concepts around prescribing digital therapies that can be powered by blockchain and artificial intelligence and be tailored to patients’ behavior.

Smart Digital Health Investments That Lead to More Engaged Patients

“Wouldn't it be really interesting if I prescribed an anti-

It’s an exciting time for healthcare technologies. Here are the ones you need to look out for in the next ten years.

Managed Healthcare Executive February 2019 Issue

The Impact of Big Data on Medical Decisions

The State of Biosimilars in 2019

The Biggest Barrier to Home Healthcare

Six Healthcare Technologies Coming in the Next 10 Years

Four Trends Health Execs Need to Follow in 2019

Featured Exec Marc Harrison: President and CEO of Intermountain Healthcare

How Three Hospitals Use Predictive Analytics to Reduce Readmissions

The 4 Biggest New Areas to Focus on in 2019

Managed Care Technology Survey 2019