As you probably know, machine learning refers to the process through which a system can use a programmed process to "learn" and become more accurate over time. It's different from the way most of us think of a robot or a computer program because in this case, the programming changes based on the results it gets and new inputs available.

Experts say that the extensive use of machine learning in healthcare is inevitable. But how might that affect healthcare and what will the consequences of it be?

Machine learning is not a new field -- in fact, it was described by Arthur Samuel in 1959 as, “the field of study that gives computers the ability to learn without being explicitly programmed.” But exponential improvements in computing, plus innovations in AI and technology in general, have meant that the field has started burgeoning over the last few years.

Machine learning is used in applications from cyber security to healthcare to, well, the movies that Netflix suggests you watch after a long week. In medicine, we're seeing applications in everything from cancer prediction and prognosis, to diagnosis in medical imaging, to treatment suggestions.

For instance, when you search for, say, peach pie recipe on Google, you'll see search results based on what Google thinks matches those words. That's a regular computer algorithm. Machine learning comes into play, however, in that Google also "watches" (actually a computer collecting data) which search results you click on, and how much time you spend on the pages you visit, to re-rank and re-sort the search results it gives the next person searching for peach pie recipe.

There is a lot that is scary and even threatening about this new world of technology. It's disturbing to think that the best doctors are sometimes worse diagnosticians than computers. And it's true that, as this JAMA paper identifies, "comparative studies on the effectiveness of machine learning–based decision support systems (ML-DSS) in medicine are lacking, especially regarding the effects on health outcomes."

The JAMA paper looks at several potential unintended consequences of the use of machine learning in medicine, for instance:

• Reducing the skills of physicians
  For instance, a study of 30 internal medicine residents showed that the residents exhibited a decrease in diagnostic accuracy (from 57% to 48%) when electrocardiograms were annotated with inaccurate computer-aided diagnoses."
• Overreliance on text.
  The JAMA paper reports that machine learning "could lead to reduced interest in and decreased ability to perform holistic evaluations of patients, with loss of valuable and irreducible aspects of the human experience such as psychological, relational, social, and organizational issues."

Ultimately, machine learning is like any other technology in medicine -- the scalpel, anesthesia, or telehealth. These tools are powerful, and come with almost inalterable impacts on how we practice medicine. They're also in our control, we're supposed to wield responsibly and manage the negative consequences. 

In the field of telemedicine, we at ClickCare are determined advocates for healthcare providers to be thoughtful about what technology they use for telehealth, and how they use it.

We advocate for healthcare providers to do 2 key things when it comes to technology in telehealth and telemedicine:

• Be open to new technology even as you're discerning about what to use.
  Of course, technology comes with unintended consequences and challenges. But it can also enrich and enhance the practice of medicine. We advocate for providers to be proactive in selecting technology that really works for them -- neither a "bury your head in the sand" approach, nor a "take whatever comes along" approach. You know what's best for you and your patients.
  
  
• Be open to redefining some aspects of your role as a medical provider.
  As technology shifts, we have the opportunity and responsibility of shifting our roles as providers, too. Machine learning may create the ability for providers to focus less on the mechanics of medicine and more on the human art of it. Telemedicine based medical collaboration allows providers to step out of their silos and treat patients as a true team. We believe that the most successful, happiest providers are those that are willing to find new ways of working as our tools change.

We believe the same principles apply to our adoption and use of machine learning in medicine. And we look forward to being on that journey with you. 

Want to get all the information before making a telehealth or telemedicine decision? Get our free summary of hybrid store-and-forward telemedicine so you can be informed:

Photo by Samuel Zeller on Unsplash

We are in an age when data matters more than ever. It affects how much physicians earn, how much hospitals make (or lose) and whether treatment plans evolve based on efficacy.

Accountable Care Organizations (ACOs) are under increasing pressure to make the data work out. Whether in managing EHRs/EMRs, doing analysis of big data, working with the Medicare Shared Savings program, or handling fee-for-performance models, hospitals must be more sophisticated than ever before.

It is an almost impossible challenge for hospital administrators to manage all of these intricacies and also keep the common sense and fundamentals of "good medicine" alive. So we were inspired by some recent comments by Joel Vengco, vice president and CIO of Baystate Health in Massachusetts.

To give you a sense, Baystate Health is huge. It is a six-hospital health system with 80 medical groups, serving 900,000 patients across four counties.

And yet - when asked what the biggest challenge for Baystate Health as an ACO is, Mr. Vengco said:

"The first big hurdle is just really creating the necessary environment for collaboration across the continuum of care and the region... Everyone is responsible for that patient population... So it’s really back to the basics of collaboration, which is in many ways a fundamental principle, but is also sophisticated and complex with regard to an operation like that." 

This is definitely representative of our experience with hospitals that use ClickCare -- and those that don't. There is a lot of complex analysis that happens, but ultimately, success in an ACO setting comes down to excellent care coordination, superb healthcare collaboration, and healthcare providers across the continuum of care.

It's not easy work, but there are tools (like some telemedicine platforms) that can help. It's work that's done person by person, day by day.

For our best advice on creating that environment for healthcare collaboration, get our free Quick Guide:

Photo of Baystate Medical Center used under Creative Commons rights from orlandosworld on Flickr

• Insurers will be demanding "more" from providers and hospitals.
  On one hand, insurers are squeezed by higher-than-expected costs of the newly insured. Many are now requesting rate increase approval from the government. As the New York Times reports, "The rate requests, from some of the more popular health plans, suggest that insurance markets are still adjusting to shock waves set off by the Affordable Care Act." On the other hand, many insurers are merging, which gives them more leverage over hospitals and providers.  The pressure to increase revenue and cut costs, combine with increased power from mergers may well add up to more demands on providers and hospitals.
• Non-traditional care contexts are becoming the norm.
  Because of shifts in what is able to be reimbursed under the Affordable Care Act, there are new delivery mechanisms being pioneered. For instance, there is a current boom in diet clinics, due to ACA reimbursement for obesity consultations and treatment. It's likely that as care outside of doctors' offices increases (with other medical providers being the ones actually interfacing with the patient), healthcare collaboration (especially using telemedicine tools) will become more important. Collaboration will need to happen more, and across the spectrum of care, in order for patients not to fall between the cracks.
• Home care is a growing segment of medicine, and we're (mostly) not doing it well.
  Data is beginning to suggest that there are more homebound people than ever before, and they're sicker. Plus, there are more caregivers who are older family members and need support themselves. This type of dynamic means that medical providers are responding, and finding ways to provide care at home. For instance, there is a growing group of geriatrics practices that make housecalls. And if those housecalls have to be made by specialists because there is insufficient technology to allow collaboration at a distance, that's going to be unsustainable. If these trends continue, we'll need to find ways for the people providing the home care to be supported by other medical providers, in efficient and effective ways.

For decades, medical providers had the luxury of ignoring macro trends. These days, however, I think that we ignore these dynamics at the peril of ourselves, our practices, and our patients. For us to act with wisdom, sustainabily, and in service of good medicine, we must act with these things in mind.

And really, that is more of a privilege than a burden.

To learn how iClickCare can help you adapt to these shifts, click here: 

One of the things that comes most naturally to me is the simple act of collaborating with other medical providers. I've just always enjoyed the process of chatting with a nurse about a patient, or hashing out a plan on a whiteboard in the surgeon's lounge. 

But over the course of my career, I was always surprised at the amount of recognition these simple acts of collaboration received. For instance, I started an interdisciplinary group of medical providers to care for complex craniofacial patients. This Cleft and Craniofacial Team meet monthly (snacks, of course, in abundance) to discuss our current cases. The team included social workers, speech pathologists, dentists, teachers, plastic surgeons, and nurses, among many others. We were honored by the positive feedback we received about this, both in terms of the patient outcomes and in terms of the process we used.

It seemed intuitive enough to me, given the complexity of these cases, but a recent New York Times article highlights how unusual this kind of interdisciplinary healthcare collaboration really is. 

As Dr. Dhruv Khullar shares: "There is surprisingly little education on what it means to be a leader of a medical team, with its nurses, physician assistants, pharmacists, respiratory therapists, physical therapists, dieticians and case managers. There is even less discussion of how to understand one another’s roles, perspectives, frustrations and limitations… despite near-universal recognition that better care means more collaborative care, changes to health professional school curricula have been slow coming."

New payment models (with Accountable Care Organizations, changes to Medicaid and Medicare reimbursements, and a focus on performance rather than services) demands more collaboration than ever. But medical providers seem less enabled, less trained, and less able to collaborate than before. There are some initiatives that are trying to change that, including the National Center for Interprofessional Practice and Education. Mostly, however, medical organizations are slow to catch up and may be blindsided by the consequences.

We, of course, created iClickCare because we believe in the power of this kind of collaboration. It's just one tool, but ultimately, the desire to collaborate lies in each medical provider's hands.

Our best suggestion? Do your best to keep collaborating, even when it seems clumsy or imperfect. That's the only way that we'll get better at it and the only way that we'll maintain these crucial links with each other.

Get our Field Guide to Medical Collaboration, including crucial tips and stores of collaboration from around the world.

Photo credit: steffen_ramsaier on Flickr, used under Creative Commons rights

Last week, the Centers for Medicare & Medicaid Services made an announcement that is really significant, but perhaps not surprising. They are launching a program that will further cement managed care and even more deeply link performance and payment -- the Next Generation ACO Model.

It is designed for ACOs that are experienced in coordinating care. The announcement notes: “It will allow these provider groups to assume higher levels of financial risk and reward than are available under the current Pioneer Model and Shared Savings Program (MSSP). The goal of the Model is to test whether strong financial incentives for ACOs, coupled with tools to support better patient engagement and care management, can improve health outcomes and lower expenditures for Original Medicare fee-for-service (FFS) beneficiaries.”

Part of the announcement is the expansion of telehealth services. This further cements the use of iClickCare, not as flourish or a "nice to have", but as a routine way of taking excellent care of patients. As the American Telemedicine Association clarified: “The decision is particularly significant because under this new model, Medicare telehealth services can be covered without regard to longstanding rural and institution restrictions, requiring a beneficiary be located in a rural area and served at a health facility. For the first time, telehealth coverage will be extended to 80 percent of Medicare beneficiaries living in metropolitan areas and from any service originating site, such as their home.”

Only 15 to 20 ACOs are expected to participate, but the message is becoming increasing clear:

Reward and risk are, increasingly, being transferred to the provider.

Are we moving back to a time before Medicare existed? Of course not but it seems that there is more recognition that the provider and the patient are part of the solution rather than part of the problem. We wonder why this is being approached in such a small way, but we also recognize that it only takes the tiniest of sparks to start a bonfire that will last the whole night.

iClickCare welcomes the opportunity to help ACOs reduce risk. More than care coordination, real risk reduction requires collaboration, which is iClickCare’s core mission. The deadline for a letter of intent for the Next Generation program is May 1, 2015, just 45 days away. If you are applying, contact us and we'll explore how we can support you. 

The benefits and savings of iClickCare have existed for decades. Now, the difference is that this type of coordination of care and strategic collaboration are indispensable -- and supported by the government. Now, more than ever, is the time.

As telemedicine becomes more important for managing risk, coordinating care, and decreasing the costs of care, you can try iClickCare for free: 

Managed Care, ACOs, and Pay for Performance systems have all been circulating in our world for years now. But for many hospital systems and long-term care facilities, adoption and management of these practices has been uneven. And research is showing that some ACOs are floundering to succeed in this new system.

That is about to change, one way or another. Managed care and pay for performance are here to stay, especially in long-term care settings.

Recent reports document that Medicare wants 30% of all payments to go through models like ACOs by the end of next year, and 50% by the end of 2018, up from about 20% now. Of course, there are already incentives and for performance in place, such as penalties for hospitals when patients get readmitted. These nudge providers to improve care, even if they’re still getting paid in a traditional fee-for-service system. The government wants 90% of all Medicare payments to include such incentives by the end of 2018. 

The government's first goal is for 30% of all Medicare provider payments to be in alternative payment models that are tied to how well providers care for their patients, instead of how much care they provide – and to do it by 2016.  Then, alternative payment models need to get to 50% by 2018. So what does this mean?

In alternative payment models, providers are accountable for the quality and cost of care for the people and populations they serve. This of course moves away from the old way of doing things, which amounted to: “the more you do, the more you get paid.” In a Patient Centered Medical Home model, instead of doctors working separately in their own silos, care coordinators oversee all the care a patient is getting.  That means patients are more likely to get the right tests and medications rather than getting duplicative tests, procedures, etc. These medical homes typically offer patients access to a doctor or other clinician 7 days a week, 24 hours a day including through extended office hours on evenings and weekends.

The second goal is for virtually all Medicare fee-for-service payments to be tied to quality and value; at least 85% in 2016 and 90% in 2018. Most providers will be tying at least some of their payments to quality and value— even those who are not yet ready to fully transition. Providers will need to link nearly all payment to quality and value, in some way, to see that we are spending smarter. 

As Murphy-Barron's and Fitch's paper summarizes: "Provider organizations need to be aware the managed long-term care plans are funded using a capitation mechanism in which they receive a lump sum per member from which they must pay most long-term care and other ancillary expenses. The risk shifts from the Medicaid program to the plan. Running a successful managed long-term care plan therefore requires significantly more investment in risk management, financial management, and strategic planning than do fee-for-service arrangements."

We're, of course, always advocating for the use of "good old fashioned" common-sense medicine as well as savvy use of technology to support these changes. But the one thing we know for sure is that it will take all of our efforts to find the way forward. 

Take a look at this 60-second video to see why we think telemedicine can help:

There have been a lot of exciting articles recently about the advantages of replacing some in-person visits with telehealth visits.  

For instance, these stories on using telehealth services to cut costs and improve care have stood out to us as models: 

• Veterans have been getting telehealth appointments for services like therapy, enabling the VA to leverage capacity and allow some vets increased privacy and ease.
• Prisons are finding telehealth crucial in decreasing risks and cutting costs.
• This study found that telehealth visits costs $40-$50 per visit, as compared to $136-$176 for a conventional visit.

Because "telehealth services" are often defined as video conferencing, there is a gaping hole in the process. When the initial visit fails to get the expected results, it can actually end up less efficient for all parties.

I live in a beautiful rural area, which is great -- unless you are trying to grow a vegetable garden.

It seems like the country would be perfect for vegetables, but I've found that when gardening where I live, wildlife becomes a daily battle, with deer seizing upon produce with the stealthy precision of Navy SEALs. I had always seen more proficient gardeners with pro-built custom fencing solutions and felt that I obviously couldn't choose one of those. I could build that myself! It's just a little fencing and I could see what they were trying to achieve with each component. Plus, the all-in-one solution cost $600.

Anyone that's ever tried a home improvement project knows where this story is headed: $540 of materials, nine days of work, and three trips to Home Depot later, I had tried to replicate the all-in-one solution, cut myself with the fencing, had to return all the materials, and eventually just bought the all-in-one solution.

Now, the DIY version is not always worse. I make bread and cheese at home, and my wife sews. But usually the cobbled-together solution is better when you don't care as much about the outcome as the process. For instance, when you include the books, materials, and resources that I've bought to make my homemade bread, it certainly doesn't come out cheaper than the stuff from the bakery. But I love the process, so it makes sense to do.

Every day, we're under increasing pressure to cut costs while improving outcomes: more and more is demanded, with fewer and fewer resources. In that context, many people have come to us looking for ways to save money on care coordination tools, platforms, and protocols. You know that you really need an efficient solution to prevent readmission and manage care of your patients, but you don't want to waste resources.

So when is an all-in-one system worth it? And when does it make sense to create your own care coordination system?

These are some of the common functions that Accountable Care Organizations and managed care organizations tell us they need in a care coordination platform (whether telemedicine or not):

• Make your information technology network very secure and impenetrable from the outside. Be sure that files on the network cannot be seen by everyone.
• Find a way to prevent transmission of pictures or taking of pictures. (We have found this to be a frequent answer, and while secure, does little to coordinate care.)
• Use a checklist so that nothing gets dropped.
• Enable both provider-to-provider communication as well as patient-to-provider communication.
• Send secure messages between providers
• Archive unique cases for teaching to medical students and residents.
• Create a patient portal so they can understand the course of treatment and engage in options.
• Integrate with EMRs and EHRs
• Manage admissions and discharge.

These are all functions that can be handmade, homemade, or patched together using existing tools. So when hospital systems and managed care organizations come to us to ask, we always tell them the same thing: if you're excited about the process of piecing together your own care coordination / medical collaboration / telemedicine system, then go for it! But if you're looking for the most efficient and effective outcome,  you may be better off with the pro-built system (iClickCare is one option) that has it all included already. Just as I would have been with the vegetable garden fencing. 

If you've been doing cost comparisons of telemedicine systems for care coordination, maybe our guide to one all-in-one system can help:

Image courtesy of hardworkinghippy on Flickr, used under Creative Commons rights.