Episode 5: COVID-19 Innovations are Here to Stay

July 16, 2020

In episode 5 of Over the Counter, experts in technology and pharmacy highlight the major ways that telemedicine is rising to meet the COVID-19 pandemic.

Drug Topics®: Hi, and welcome to episode 5 of Over the Counter, the podcast from Drug Topics®. I'm Gabrielle Ientile.

In this episode, experts in telemedicine, artificial intelligence and pharmacy highlight the major ways that telehealth is taking shape to rise and meet the tide of increasing COVID-19 cases.

If you're listening to this podcast in the middle of July 2020, the United States has more than 3.5 million confirmed cases of the novel coronavirus, with most states still experiencing surges of cases.

In a world of social distancing technology is the solution to many of the challenges brought by the pandemic. Zoom links are replacing meetings, daily conversation, and birthdays, and social media is helping us stay connected while also staying spaced 6 feet apart.

Telemedicine, artificial intelligence, and other technologies have come to the frontlines amid the COVID-19 pandemic to provide care, assistant following the virus's path, and alleviate the strain being felt by our healthcare system.

Dr. Ray constantini, co-founder and CEO of Bright.md, launched Smart Exam in response to the pandemic. Constantini said to think of their company as an automation company, where care automation is applied through telehealth.

Costantini: Think about it as a virtual medical resident. So a patient is sick and they're at home or at work, on the bus, really anywhere. They can log in to Smart Exam from their health care delivery systems’ portal.

Drug Topics®: The virtual medical resident goes to work by pulling out all kinds of information from the electronic medical record.

Costantini: From chart review, calling out things like meds, allergies, problems list, visit history, demographic information, it looks at environmental and contextual information like location and seasonality – it uses all of that to drive this dynamic adaptive clinical interview, a conversational AI platform.

Drug Topics®: This AI platform interviews the patient or provider then takes all the information, digests it and gives it to the provider and frees them up from the administrative burden that comes with providing care. Instead of taking time to both interview the patient and doing administrative tasks such as documentation, order entry, prescriptions and billing -

Costantini: We streamline that process to the provider, and make it so that they're able to spend their time really at the top of license practice. They're spending about 2 minutes on diagnosis and treatment rather than spending all of that time gathering and organizing and documenting information.

Drug Topics®: And in a time of a pandemic, clinical needs will skyrocket, making it even more difficult for healthcare professionals to balance all of their tasks.

Costantini: One thing I've seen in other epidemics and outbreaks is that you have a huge increase in patient needs and clinical needs. Some of those come from the epidemic or the infectious disease itself. But a lot of them come from patient concerns. In this situation, what happens is not only do you get the increasing need from patients who are very sick with coronavirus, or the patients who had coronavirus but aren't terribly sick. You also get all of the folks, everybody who's got a cough, now he's concerned that it could be, and it’s not an inappropriate question to be asking. They're all concerned that he could be coronavirus and delivery systems have to be navigating that really massive increase in patient need.

Drug Topics®: I interviewed Dr. Constantini, in mid-March of this year, just prior to when the United States began to see huge surges in cases. Even at that point, Smart Exam was identifying high risk individuals for COVID-19 and facilitating the screening process.

Costantini: 11,000 patients in a month: a typical provider can see about a hundred patients a week in person setting. 11,000 visits in a month to take a massive number of providers and we're doing it with just a handful of providers so much, much less time because of all the efficiency that we've introduced, and that frees up that clinician to have the capacity to be able to go take care of all of these other rising needs that are out there.

Drug Topics®: Telehealth technologies themselves often incorporate artificial intelligence, or AI, to do the work of identifying high risk patients or sifting through data.

Steve Mok, PharmD, manager of pharmacy services and director of health outcomes analytics fellowship at WoltersKluwer, knows AI.

Mok: Since I joined Wolters Kluwer, I've been engaging in quite a few projects on collaborating with our data science team on how we can leverage technology to improve the delivery of pharmacist-based patient care interventions to improve and optimize patient outcomes.

So even though my background is on infectious disease and antimicrobial stewardship, a lot of hands on experience in the world of AI have been my collaboration projects with a lot the data scientists to gain experience in the past few years and seeing some of the exciting development in terms of what we can do when you put clinicians and technologists together to derive the biggest benefit for patients.

Drug Topics®: I asked Dr. Mok where we can see AI currently being used in healthcare in pharmacy, and here's what he had to say.

Mok: That is a loaded question. I will try to address that briefly. In my humble opinion, if you could look at the human body and pathophysiology the 3 major areas where we see the biggest promise is in terms of AI would be in the prevention, diagnosis and treatment of diseases.

If you allow me briefly, I will touch on a few of these. For example, prevention. As we see learn more about different disease states, were getting better and better in understanding what are some risk factors that lead to the development of certain disease states. Nearer to my heart, a lot of infections, we have good understanding of what are some of the things that lead to an increased risk for developing some of these bacterial or viral infections. If we can leverage AI to identify these patients earlier, we may have an opportunity to remove some of those risk factors or change people's behaviors that may result in a low risk of infection, if you will.

In terms of diagnosis, I'm sure some of you have heard, even in the in the general news, a lot of the AI algorithm has now being deployed to read some of the radiology records looking at CT scans, stuff like that, to help physicians to augmented clinical decision making using an AI to see if there's a disease process that they may have missed, or to confirm some of the diagnosis that they have already made.

A similar application of AI can be used in In the world of laboratory testing. Other records that are in the patient's charts, where the technology can help identifying patients with diseases a little bit earlier. So that's kind of where we see AI being applied for the diagnosis part of human diseases being the most promising.

Finally, the last part I mentioned, treatment is another area. If we can prevent and then diagnose a patient with disease, what people are interested in is what about the treatment that can help the patients recover or manage with disease states?

I think in the world of treatment, we're seeing a lot of researchers, either academic or in the commercial setting, leveraging AI to help them with drug discovery, looking at new molecular entities and identifying targets or agents and may be of interest and promise in terms of accelerating the path into becoming a usable drug.

Closer to the pharmacists’ heart: Some of these treatments also can have side effects. We're talking a lot about precision medicine these days, I'm sure you've heard in your new line of work.

How can we leverage technology to understand a patient's specific characteristics, such as their organ content, their data genomics, and other characteristics to help identify some of those patients who may be at risk for having adverse outcomes with side effects and some of these treatments. That may change some of the prescribing decisions. A first line drug that may be good for you may not be so good for me because of the differences that are inherent between us as 2 different human beings.

I think using technology has a lot of promise. Instead of having, and I hesitated to use the term cookbook medicine to describe what are some treatment, first line treatment may look different based on the patient individual characteristics.

Drug Topics®: And as for AI use amid the pandemic, it’s proving to be one of the lead innovations with the potential to support the healthcare system and drive telehealth initiatives like contract chasing, for example.

Mok: What we're seeing with COVID-19, and I think some of the things that we're learning a lot about the disease since he was first identified at the end of 2019, we're learning the weight is impacting the human body. And then we're also learning a lot about what treatment work and what treatment doesn't work.

But I think the greatest area of interest right now is identifying patients who may have been exposed or who may have been at high risk for contracting the virus. We recognize that a significant portion of patients may be asymptomatic, and they don't even know they are carrying the virus. Yet at the same time, they can be transmitting devices or other people who may be more vulnerable or at a higher risk or having complications.

I think some of the technology that we've seen so far, using a geographical locator or Bluetooth devices on your phone, which can identify whether you have been exposed to somebody who might have been identified with a carrier, that can facilitate contract contact tracing, which is such a buzzword, it warms my heart as an ID specialist. This is a term that I know but now has become a common lingo in the in the lay community. So how can we use technology to do this very labor-intensive contact tracing, if we could have the ability to actually put in a magical number that says, “Oh, this person is diagnosed with COVID-19.” And then using the technology to roll back the 10 days, 7 days before, where that infected individual interacted with other people and then notifying them that they may have been exposed so that they can take the proper precautions as far as getting tested. That is very, very exciting and promising.

And certainly we're not just talking about proof of concept. This type of technology has to already been applied outside the United States, and we have seen that recently Europe has reopened, and they have certainly enabled some of this technology in European countries, where people can opt in to be notified as well as opt in when the diagnosis is made to notify the chain of folks that may have been exposed to the infection.

Drug Topics®: Other ways that AI can take shape during the pandemic include deriving information from search engines. Here's Dr. Mok to explain.

Mok: Some of the things that we've seen, even without diagnosis, there's certainly a possibility as people do their searches. You could have a headache, or you lost taste. We see that people often, what is the first thing you do, thinking about the symptoms, you go to an internet search engine and type in those keywords to look for those things. I think that can serve as on the on your mobile devices, using the search history, can help at the macro level for local government at better understanding how many people or how many citizens are now in our locality searching for these terms.

So even though we may not be able to contact trace 100% of US citizens for this disease, we can leverage some of those searches to help local government agencies to understand how often people are searching for these types of terms to have a better understanding of the impact of the disease in your local community.

Drug Topics®: Smartwatches and fitness trackers also have the potential to detect a user's symptoms even before they know they have any.

Mok: Some of these mobile devices, your smartwatch or your fitness tracker, many of them actually have an oxygen sensor in there that can measure your oxygen saturation. And oftentimes again, detect changes in oxygen saturation earlier before the before the onset of symptoms, or even though you may have a diagnosis, the sensors can detect that you may be going into trouble into developing a more complicated or severe case before you deal with symptomatically.

I think that is one area where we can see a lot of potential promise in terms of notifying the individual patient like, “Hey, we know that there's been a change in your oxygenation level, maybe you should get this checked out.”

Similarly, we certainly are seeing a lot of research interest for the patients who do have the diagnosis and got admitted to the hospital. You all may have heard that a significant portion of the mortality associated with COVID-19 that those who end up getting put on the ventilator in the ICU. What if, using AI, we're reading the records in the EMRs and reading those data, and then identifying patients who are about to experience these clinical demise, and pick them out earlier instead of waiting to the have developed into a full blown respiratory failure. If we can't identify those patients sooner, to do other things that may have an impact in changing the trajectory of the outcome.

We're talking here in the third week of June, I don't know when people are going to encounter this information, but earlier this week, we've seen some very positive results from the UK, talking about the use of dexamethasone, in changing the outcome or improving outcome of patients with COVID-19. Wouldn't it be nice if we can actually utilize AI to identify those patients that may benefit the most from this treatment, so that we can administer them much earlier and making sure that those patients had the best chances of surviving this illness?

Drug Topics®: So AI can also help researchers learn which drugs would work best in specific subsets of patients and can help identify side effects.

Mok: Everyone who have received some of these drugs will not have a good outcome, so what is the difference between those patients who didn't have a good outcome versus those who do have a good outcome? Then we don't indiscriminately give these special medications that have potential side effects. Some of the audience are pharmacists, so they are well aware that steroids can change your metabolism, it can have significant side effects as well. If the use of this drug is not likely to lead to a good outcome, why expose our patient their risk of having some of these side effects?

And I think that's very important work that needs to be done in the next few weeks. As we understand this disease more and more to identify who are likely to benefit and who are not.

Drug Topics®: This is what Dr. Mok had to say about the role AI has within the pharmacy.

Mok: Some of the issues related to COVID-19 is that some of the patients will inevitably develop what we call secondary bacterial infections because their body is being attacked by the virus. As a result, the immune system is weakened.

A certain subset of those patients will develop other more common bacterial pneumonia, for example, or things that we see in hospital all the time, maybe a bacteria in the blood, stuff like that. Maybe because they've been intubated for a long time that tube is bound in the throat, that can set them up for some of these infections.

I think leveraging AI and then thinking about some of the early detection systems: for example, 1 area I haven't touched on yet is called natural language processing.

Electronic Health Records contains a lot of data, including a lot of the laboratory results, vital signs and a lot of patient status. A lot of human input. For example, when the nurse sees something or a doctor sees something on the physical exam, all that data is still captured in a format that is not discrete. In other words, it's not a yes, no, it is not a number. A lot of these are just natural sentences that we will say, “this particular patient has a noted rash” or “this patient is non-responsive.” Those are things that are quite tricky for what we would call a rule-based system to pick up.

Using AI and using that natural language processing, where you can leverage AI to read some of that non-structured data, can drive very meaningful outcomes. You mentioned earlier, how can pharmacists use this type of technology improving the patient care? Well, if they have this toolbox with the natural language processing that can help them understand which of their patients are experiencing side effects or some of the treatment I mentioned earlier. Dexamethasone sometimes can have significant side effects, so if they go in some sort of central nervous system reactions, these are not things that you can capture in the laboratory result. So really, it will be dependent upon the ability of having the program algorithm to read the notes that the nurses are charting, or the doctors are recording, so that the system can pick it up and notify the pharmacist, “hey, this is a patient who may be experiencing side effects that medication and maybe we need another pair of eyes on it to see if there's an alternative treatment for that.”

But looking beyond the pandemic, how would that change the way that pharmacists would utilize technology to help their patients? I think, again, going back to the way that we think about that larger framework when we first talked about this, how can we identify patients who may potentially have some of these medication-related problems because of the genomics?

Pharmacogenomics is another area where we hear a lot of interest and activity, so how can we leverage some of this advanced technology to read very complex information in the human genome and unlock those sequences that have been correlated with particular side effects from those medications so that we can change the utilization of those drugs. Looking at the identification of the side effects once they have occurred, are there any early signals that we can leverage to identify a patient who's about to have kidney failure during the antibiotics before you can see the manifestation? Even if you can catch it 24 hours earlier, you can stop the drug earlier and stop the continual assault on the kidneys. I think those areas are very promising for pharmacists to be an advocate for the patient in managing medication.

Drug Topics®: Health in Motion’s chief strategy officer Richard Scholz, PharmD, discussed their telehealth technology called ERxDirect.

Scholz: Every business I've ever been in, everything I've done with healthcare, is that the key is the patient. Now the patient/consumer. They've got to be central to the strategy or can't be successful and it can't be sustainable.

Drug Topics®: Health in Motion isn't COVID-19 specific, but like many telehealth platforms, is adaptable to changing needs.

Scholz: Part of the beauty of technology is the ways to make that maze much more manageable for patients. Because if the patients, if through frustration, through lack of access, they abandon their pharmacy therapy or any of their therapy initiatives or care plans to their physicians, is then we have a failure for an outcome. And it's not necessarily because we weren't capable of getting a positive outcome, it's just that there were there was there was space between the dots that didn't get connected.

Part of telehealth, part of our initiative, is connecting those dots. What COVID has been as an accelerant to that, because not only is COVID as a disease state put pressure on health care, but it's also brought into the spotlight is the importance of chronic disease management and prevention. And the reality is that our companies were born to make healthcare more efficient, get it to people more efficiently, where they work, and where they congregate, and that goes to chronic disease management. COVID, per se, is been a true accelerant to the acceptance of the type of healthcare that we're advocating for.

Drug Topics®: Health in Motion works to supplement healthcare professionals and to enhance the portability of care.

Scholz: But our care space, what the hallmark of it is, that it's synchronous communication of medical data to the provider.

The professional clinician, they get real time heart and lung sounds. They get real time, detailed, high resolution pictures. There's a nurse at the bedside, at the at the exam table, helping with the medical devices and working with the physician for doing the hands-on care that may be needed or desired for the physician to make the proper diagnosis. It's a very, very large scope of care.

We also have the direct to consumer components, where the physician can do a virtual visit directly to the consumer on a personal device. But again, it has utility, but it doesn't have as robust diagnostic utility as does the care space. We see a place for all of that. And we see a pharmacist as part of that healthcare team, we see a pharmacist being imported into each of those different environments to bring that pharmacy knowledge to that encounter and to that patient, again, as part of that healthcare team.

Drug Topics®: In April, Health in Motion launched ERxDirect’s Telemed, which is the connectivity component for pharmacists. It's implemented in pharmacies across the country. I asked Dr. Scholz about what steps a pharmacist should take to implement Thomas services into their practice. And here's the steps he shared.

Scholz: The first piece of ERxDirect’s Telemed that we're rolling out through epic pharmacies is connectivity. And they can implement this on various devices, depending on their desired workflow.

We have some pharmacies right now, where there's a pharmacist that is actually part of the vulnerable population and chooses not to be able to come to the pharmacy and appropriately so. They do all their work on a personal device in their consultations on a personal device for their home, much like you and I are working from home offices that are atypical from our normal day. And this enables those practitioners to participate in that market equally as robustly as if they were in their pharmacy.

As far as what they have to adjust in their words, it's really easy because it's workflow. The most significant changes first of all, is they have to have a viable device with a camera, which is quite common now. We have a HIPAA compliant environment so you wouldn't want to do a consult in a public area and also is as what they I think the biggest change from a workflow standpoint for pharmacists and community pharmacists is to be able to set aside time in their day to schedule consultations. They’re so used to ad hoc consultations and on demand workflow that scheduled consultations is somewhat of a new arena for them from a workflow standpoint.

Drug Topics®: And as for changes in telehealth, this pandemic has brought to light:

Scholz: Is the fact that we have a vulnerable society, with comorbidities and some chronic diseases. I believe the spotlight that COVID has shined on those chronic disease states will have a lingering effect as to how we approach it in practice population health going forward. That's going to take implementation of a healthcare team to do that.

And what we're doing through ERxDirect’s Telemed is making sure that our pharmacists are enabled to fully participate on that team. And just to kind of give you an example of how we're using now Telemed. Urgent care providers actually have a care space or a clinic in a public school, so the school nurse becomes the enabler and the care coordinator for the student. It’s really fascinating. I think we'll see a bigger focus on this post-COVID.

Another is that 38% of adults reported taking drugs with depression as potential side effect within the past 30 days, and 23% are using drugs that are carried the risk of suicide symptoms. This is an adult population, but also a student population. There are drugs that have side effects that maybe the school nurse or the teacher, the principal, may be maybe seeing a difference in behavior.

Bringing behavior health, bringing pharmacists, bringing all these to the forefront, so you're able to assist the health care team to come to the proper analysis. And we've seen that, by bringing the team together and facilitating that collaboration, that's where the magic of increasing the access and the quality comes in. We're seeing that there's going to be a lot more focus on chronic conditions, on how the different components of the professions work together, for the betterment of that patient.

Drug Topics®: That's all for this episode of Over the Counter. Check out DrugTopics.com for full interviews and articles about technology in pharmacy amid COVID-19.

And make sure to tune in next week for insights from industry experts on the latest news trends and innovations in pharmacy. If you enjoyed this podcast, please like, write a review, and share with your pharmacy friends. Thanks for listening.