AI and Measurement-Based Care with Dr. Dylan Ross

welcome to Mental Health Evolution, a podcast about what's changing in mental health and why it matters. I'm your host, Rachel Harrison, inviting you into honest conversations with people from all perspectives in the field. Clinicians, tech founders, investors, insurance companies, and all the folks in between. Let's explore what's working, what's not, and what's next. All right everyone, welcome back to the Mental Health Evolution Podcast where we explore the latest trends and strategies shaping behavioral healthcare. Today we are joined by Dr. Dylan Ross, head of clinical at Blueprint AI. Dr. Ross brings extensive expertise in value based care measurement based care, and he has applied this expertise to Blueprint AI to help shape tools that support clinicians in outpatient behavioral health settings. At Blueprint, he leads initiatives to ensure AI assisted tools like automated session notes, treatment plan suggestions and outcome tracking are aligned with evidence based practices and outcome measurement, supporting both clinician workflow and client outcomes. Today we are going to dive into some topics that intersect with our guest experience as well as current topics for the mental health industry. We will go where the conversation takes us, but we will look at things like measurement based care, value based care, and potentially touching on the ethics of AI a bit. Before we dive into the conversation, I want to highlight a few articles that you can dig into as you get your bearing on the topics that Dylan and I are going to be having a conversation about. First is an article called Value Based what It Is and why It's Needed. I thought this was a great sort of foundational piece by Commonwealth Fund and this article explains the core principles of value based care, including how it shifts reimbursement from volume to outcomes. If you're not familiar, value based care means that providers are paid based on results more so than based on just their time. That's kind of the big shift that's happening in value based care. There's a lot of it already happening in the healthcare industry. Mental health is still kind of something that payers are figuring out how to get into, how to best measure and decide how to do value based care. But this article discusses the benefits for patients and providers and why adopting it is increasingly critical in healthcare, including behavioral health. And then the second article is called Getting on Board with Implementing Measurement Informed Mental Health Care and this is from the Institute for Healthcare Improvement and this guide provides practical strategies for implementing measurement informed care in behavioral health settings. It includes how clinicians can standardize assessments to look at outcomes to inform treatment decisions and improve client engagement. This is a big piece of where Blueprint started and I think you still offer this Dylan, if I'm not mistaken. So I'm excited to talk a little bit about that. And lastly, I want to highlight an article that our guest wrote titled AI in Behavioral Health Ethical Considerations for Mental Health Clinicians. In this article, our guest here outlines Blueprint's approach to integrating AI into behavioral health documentation while maintaining ethical standards, clinical accuracy and patient privacy. He discusses how AI can support clinicians without replacing their judgment and how the these tools can complement measurement based care. This article is going to be a great launching point for our discussion as well, so I encourage you to look at the show notes and go ahead and click on that so that you can read more in depth about what Dr. Ross has had to say about that. So with all of that background Dylan, I'd love to dive into talking about where you are coming from. So maybe a little bit about your journey in the mental health industry. Kind of where you've been, places you've worked, what you've seen and kind of your background.

You bet. Well, thinking back to the beginning of my career and while there's a couple chapters that precede this, I stepped into the managed care arena in behavioral health in the early 2000s working for Kaiser Permanente in Northern California. In that role served as a psychotherapist working in a substance use disorder treatment setting and in the lead up to the Affordable Care act found myself in increasingly drawn towards more system level, structural and policy level influences that were shaping how healthcare in America behavioral health was working or not. Ultimately went back and got a PhD as an organizational psychologist. Also duly licensed as an MFT LPC and left direct care in 2013 and moved to a consulting role at Kaiser Permanente in their national program offices. And at the time the charge was to reimagine how we might 1 address and expand access for those with unmet behavioral health needs but two looking at how we could early in a more early fashion identify those unmet needs in primary care, women's health, pediatrics, upstream. So we were ultimately designing for the system, both collaborative and integrated care models and through that work in partnerships with the Department of Defense, the Veterans Administration National Health Service in the uk learned a great deal around what models ultimately support earlier Identification and Engagement act with Kaiser brought me to overseeing behavioral health quality for the health plan as well as later addiction treatment and recovery services as both the market operator in Colorado. And that was the big jump into big Q quality within behavioral health to fast forward the rest Left Kaiser after 12 years joined Optum Behavioral Health where I oversaw high performing networks team had a portfolio of multiple initiatives but the marquee one is really setting the strategy for Optum around as they refer to it measurement informed care which today sits foundational to their value based care offerings. Really missed care delivery. After four years with Optum went to Rogers Behavioral Health led digital strategy as the vice president of clinical innovation through the peak of COVID which was no small task and then ultimately went off did some consulting for a while and I also chair the American Psychological Association's national advisory committee for measurement based care and in that capacity was introduced to Danny Fried, our CEO and founder of Blueprint and so today serve as the head of clinical for Blueprint. Blueprint started off in 2019 as a single product offering offering up technology and tools to make the right thing easy to do. And in this case it was measurement based care. And we identified a handful of challenges in terms of selling that technology in marketing. And some of these themes I think will ring true for the rest of our conversation. But one, we don't have appropriate reimbursement behind activities that are key to measurement based care. Thus we see lower adoption and use across the industry when it comes to that. But the second, which leads us to another big innovation here at Blueprint was that we were competing with time or lack thereof. And so whether it was time at the clinician level or capacity at the organizational level, we ultimately found that the amount of documentation and administrative tasks was ultimately getting in the way of organizations and clinicians within those orgs ultimately doing the things that really matter most when it comes to advancing quality and outcomes. And so we built out an AI scribe for behavioral health clinicians. Today, using our technology set, we are saving anywhere between 7 to 10 hours of documentation time per week, depending on caseload. And with this advent of AI, we also saw an important opportunity in the market to bring in actionable insights before, during and after every visit using AI anchored on both transcription data and patient reported outcome data. So now we're ultimately preparing clinicians to feel more prepared, more confident, but also with those suggestions that can help them deliver the best care possible.

Okay, yeah, there's a lot there. I'd love to kind of start with measurement based care. How do you see that? You mentioned that there's a struggle for adopting that largely because there's not reimbursement for it or not adequate reimbursement for it. What are you seeing in terms of clinician adoption of that or the need for that or even insurance companies requiring that.

Yeah, maybe just to set the stage, putting a definition against what this thing called measurement based care is could be helpful.

Right.

So and I'm going to use the acronym MBC for ease of the conversation. Measurement based care. MBC is the routine and standardized use of patient reported outcome instruments. These are the PHQ9s and GAD7s of the world to help ultimately inform and prepare clinicians to act on the data that oftentimes is focused on symptomology, such as pHQ9 for depression or the GAD7 for anxiety. Functional measures to look at global functioning across key domains, occupational, social and beyond, as well as looking at some of the process oriented dynamics of therapy, such as the patient's perception of the quality of the working relationship between the care provider and they themselves. And so by using measurement based care as an evidence based practice, which there's over 25 years of research supporting this, bringing in data from patient reported outcome data's outcome measures, this helps serve as an additional signal to help prepare the clinician to take action sooner across a treatment episode. And I do think it's important to note that it never replaces clinical judgment again, all data being good data, this is very helpful for clinicians to act on this signal earlier. And so when we look at the research around measurement based care, not only do we see the outcomes improve by bringing in the patient voice through patient reported outcome measures, we see the therapeutic alliance, the quality of that working relationship improve between the client and the therapist. We also see something that's also that's notable is the length of treatment episodes also decreases as goals of treatment are able to be obtained earlier in that treatment episode. And the why behind that is that by having this standardized and routine use of the collection of patient reported outcome data, these data again serve as that signal that can be picked up on in a more reliable fashion earlier in the treatment episode. And thus as we see treatment episodes ultimately reduce in terms of length, goal attainment for that specific case also improve, we also see cost savings. So from an affordability standpoint, whether you're a payer or anyone else, if you see length of treatment episodes reduce, there's also that financial upside. So that's kind of a working definition of measurement based care, but high level. If we think about this in the same way, on the physical health side of healthcare, every chronic condition has a vital sign. Whether hypertension, has blood pressure, diabetes has hemoglobin A1C, whether we're looking at obesity, maybe it's BMI and weight. We don't have those same objective vital signs in the mental health arena. And while, yes, we are starting to find different biological underpinnings of certain conditions, and I do anticipate that as we move forward, technology will really help us bring additional objective data into the care process. In lieu of these vital signs, we look to the patient reported outcome measures and there's hundreds of these validated tools that are out there to serve that purpose, which I think is really important.

I see the value of it definitely. And I think in actual practice sometimes it gets a little bit difficult. For example, having patients that are willing to fill out this measure on a regular basis. What do you see in regard to that?

It really starts with the provider. And if a clinician is asking their patient, their client, to complete these survey based tools over and over again, yet the value isn't necessarily linked to the request of taking time out of their busy lives to complete them. The data isn't ultimately reviewed and becoming just a core part of what's discussed. In a psychotherapy visit, for example, you're going to see drop off in terms of buy in ultimately on the client side to complete these, contrasting that with, let's say one done well, this becomes an ongoing topic of conversation looking at total scores in terms of symptomology or overall global functioning, using item level scores to help inform and really kind of focus the conversation around sleep attention, whatever it might be in terms of the target of treatment. It's really important that this becomes just a part of the conversation. And there's lots of research that ultimately points to the intervention, as it were, in terms of sharing and graphing change over time with clients, that this is empowering to be able to see the mile markers of both success or even challenge in terms of progress across a treatment episode. It really helps with engaging the client in care, but also makes what can at times feel very opaque in a change process much more clear. And so ultimately, you know, lots of different models out there, some take a very treat to target focus, really using these types of tools to target the symptomology or the underlying presentation of whatever the issue might be. And this becomes one of the north stars to kind of gauge success by. But ultimately it shouldn't be the only, you know, rule ruler that is used to kind of gauge success. So why do we not see it? And just to put some numbers to this outside of large group based practices, oftentimes these kind of aggregators, the headways, Rulas Almas, you know, the growth therapies of the world we see in the wild as it were, 19% of psychiatrists, 11% of psychologists and anywhere between 3 to 5% of master's level clinicians endorsing routine use of patient reported outcome measures. If we look to those large groups again, let's just choose headway as an example. You know, 40,000 therapists in this network, we see a much larger adoption and use of these given the kind of payer requirements around value based care, which I know we're going to talk about. So even if we're being generous, you know, less than 20% of the field are using this measurement based care as an evidence based practice. And we've got a ways to go to ultimately take steps forward on that.

Yeah, yeah, definitely. There's a lot of dynamics there. But I do want to go into value based care because that is more and more going to be a requirement. I know payers that I've worked with have said this is coming, get ready all of these things. What are you seeing specifically in behavioral health care for the patterns for value based care? And I think we've defined it a little bit at the beginning, but it is basically using some sort of measurement or outcome outcome to determine payment. I know I was just actually at a conference earlier this week and it was a payers conference and they were talking about value based care as sort of a shared risk kind of piece with providers where sometimes payers feel like they are shouldering all the risk because they are paying for the service. And this is a way that providers have a shared risk or some accountability if you will, in the outcome. But I'm curious to know just some of your views of value based care.

Yeah. So let's take a moment and imagine that we're all working for a large payer and just looking, let's say at Optum. You know, Optum has over 500,000 behavioral health providers in their network. One of the teams that I led while at Optum was the high performing networks team. And the charge of this team was to try to tier the network, try to understand through data who within this exceptionally large network was delivering differentiated and exceptional outcomes. The challenge the payers face is really a lack of actionable data. Claims based data is highly blunt. You may have, you know, a location code in terms of where the care is happening, a diagnosis, you'll have CPT codes and other types of codes that map back to reimbursement and billing. But it's really hard for a payer to ultimately identify and answer a seemingly simple Question, did our member get better and if so, by how much? So that's a member client level view at the provider level, whether it's an independent clinician in private practice or a very large behavioral health organization, that same question is equally as difficult to answer. You know, to what degree does you know, provider A versus provider B move the needle where it matters most in terms of clinical effectiveness as well as clinical efficiency. And embedded within that there's obviously a cost based question. And if we look at where the kind of important interest holders within the payer arenas kind of sit, employers in particular are really critical. And it's interesting to think back in the arc of my 20 plus years, 25 years in the field where we've gone from the beginning in terms of sophistication and how informed purchasers were. And in this case we'll talk about employers compared to where we are today. And what we've seen is an evolution in terms of priority. Early days access mattered more than anything else. And because of that, payers ultimately built out exceptionally large networks. They wanted to make sure that employers and other purchasers could get their constituents, consumers into care quickly. Because we have a long history in behavioral health of delays in terms of those that raise a hand and ask for help versus those that can get in quickly to get the care they need. But then fast forward, what we're now seeing is what is being asked of from payers by the purchasers. Employers in this case is yes, table stakes are access, we expect it. But now they're asking for demonstrated outcomes. What are we getting for every dollar that we spend in terms of partnering with you payer when it comes to the quality of outcomes. And so this has put an incentive behind payers to ultimately in turn swivel their head towards their provider networks and challenge them to ultimately demonstrate effectiveness. Did this member get better? Did a population improve in terms of the care that you're providing? And it's very hard to answer these questions unless we have some sort of objectionable data. And that's where measurement based care comes in. Again, these are the vital signs for behavioral healthcare. If we're not collecting outcomes, we can't answer these seemingly simple questions. Within this, we've also seen a significant increase in terms of outpatient utilization across the payer landscape. We're seeing on average a 20% year over year increase in terms of behavioral health utilization. And, and what that looks like to the bottom line of payers is they see it as runaway outpatient behavioral health spend. Benefit expense continues to rise in this segment across their whole book of business. And so what we're seeing is a real evolution and kind of a stepping up when it comes to what providers are being asked to do if and when they're going to partner with payers and be direct in network. And where we're seeing a lot of this is in the provider aggregator space. So managed service organizations, IPAs, the headways of the world, for example, where payers are basically saying, look, if you want to continue to grow your network, you're going to need to agree to these certain terms. One, you've enjoyed premium rates of reimbursement, especially coming out of COVID when virtual care access was one of the North Star priorities. But now what they're seeing is anywhere between 20 to 30% higher rates of reimbursement have historically been aligned to these large aggregator groups. And, and what the internal evaluation in terms of both cost and quality from the payer standpoint, what they've ultimately come to realize is the quality of care happening in many of these groups is not that much better than the quality of care happening outside of those groups. And as they look to those that are again just direct in network, small mid sized group practices, even independent clinicians in private practice, they're asking themselves why would we want to pay a 20 to 30% premium for the same type of outcomes? And so it's a complex space, measurement's going to be key. And so one of the strategies in terms of frameworks that payers are putting in, you know, embedding within their networks is this alternative payment models. So value based care lives on a continuum. It goes from fee for service far left all the way to full capitated full shared risk far right, but lots of different steps in between. What we see most in terms of behavioral health, in terms of value based care is ultimately a pay for performance type model where if a provider organization hits, you know, successfully obtains certain thresholds across key metrics and many of these are process oriented, very few seem to have ultimately arrived at true outcomes, then there's an additional upside that can be paid out. And so why we haven't seen such a large shift towards value based care compared to say, you know, joint replacement or other types of physical health. Examples of value based care that have been along around for many years is really this linchpin of measurement. And so back to blueprint, we see that there is a critical need within the provider community, within the practice community, to make bringing in this evidence based practice of using standardized outcome measurement. This is really Key to not only improving care and outcomes for every client and patient served, but ultimately helping to unlock value across all level of the health system, including at the payer level, but also at a population level, policy level and beyond.

Hmm. Yeah. So what do you think is the value add for patients in this value based model?

Well, if I were looking for a therapist for somebody that was in my family or even myself, and if we wanted to draw an analog to another health condition, imagine and unfortunately, let's say in this case, you know, a loved one was diagnosed with one of 300 different cancer types. My guess is that you would want to make sure that the oncologist that you're connecting your loved one with not only is expert in treating that subspecialty focus area in terms of that type of cancer, but that the outcomes in terms of mortality, morbidity, but also recovery rates, that those were stacked up. That that's why as from a consumer standpoint, you'd want to make sure that the right provider is getting connected to the right patient at the right time for the right condition and they have a track record of success in terms of moving, moving on outcomes. Similarly in behavioral health, while yes, in the mild moderate arenas, and given prevalence rates of depression and anxiety, there's lots of providers that are well positioned to address these things. But as we look towards perhaps serious and persistent mental illness, eating disorders, ocd, substance use disorders, it really requires a certain training and specialty type. And so back to it. But it's really important from just across the landscape that we have data that can help answer again these seemingly simple questions, but those that we've been kicking the can down the road as a system.

I love it. Yeah, I think it's important to see the benefit for all the players in the landscape. Right. For measurement based care. I know we don't have a whole lot of time left, but I want to kind of ask you about Blueprint specifically and some of your thoughts moving into AI. How does AI relate to this conversation of value based care and measurement based care?

Yeah. So as I mentioned moments ago, the thesis that we had the hypothesis ultimately was that if we could offload some of the administrative demands from clinicians and within an organization and free up capacity, some breathing room for clinicians to really do what they're best at, which is providing care, that we would see a few things. One, our hypothesis was that if we introduced an ambient scribing technology such as our Documentation Automation Solutions, our AI scribe, that we would save time and again in tune between seven to 10 hours per week, and that with that time, clinicians would do the things that they historically have had less time to do, such as measurement based care. And what we've learned as a system that when we do introduce an AI scribe, that we're seeing close to a 60% increase in adoption and use of measurement based care on our platform. That's huge.

That is huge.

And so that's important. Second, if we zoom out, we have a workforce challenge when it comes to the practice community. And by any respect, it's somewhere around 320 individual Americans in our nation who have an unmet behavioral health need could benefit from treatment. We see, depending on the data source, anywhere between one in four or one in five adults and adolescents will experience some sort of mental health issue within a given year. And so if we look at 320 individuals that could benefit from care for every one provider that's ultimately licensed and capable of providing that care. This is a real kind of supply demand mismatch. And so we need to be more efficient in terms of how we deliver care. And we also need to ultimately create sustainable work models so we're not seeing rates of burnout and ultimately therapists leaving the profession, which is top of mind for many organizations today. We get, you know, I have the privilege of spending an inordinate amount of time with clinical leaders across hundreds and hundreds of different organizations. And what we hear loud and clear is that there's a competition for clinical talent, that once you get a quote, unquote good therapist or good provider in the organization, keeping them engaged, keeping them happy, and providing the right support so that they can deliver on the great care that they provide every day. This is increasingly becoming more and more difficult. And so we see AI scribing as one part of a broader solution. So at Blueprint, we exist to help clinicians do their life's best work. We build tools for mental health providers. And while yes, there's benefits to the bottom line, such as with AI scribing, we see an increase in clean claim rates, a decrease in audit rates, a decrease in clawback percentage and amounts on average. And so there is a business case to be made in terms of the clear ROI at the workforce sustainability level, creating an experience of work that doesn't feel as demanding. The administrative burdens of documentation in particular, especially when working in partnership with payers, this is really key. But beyond that, not every clinician can ultimately soak up the depth of research in terms of randomized control, controlled trials, peer reviewed journal articles, and so the other Thing that we ultimately do is using patient reported outcome data on our system. Again, transcription data through the AI kind of process, we now can surface just in time, insights before a session. So providing a very clear recap, here's what you addressed last time. Here are some of the suggestions you may consider in terms of how you prepare to go into this next session. In session guidance, let's say that your patient or your client endorses thoughts of suicide. While we'd like to think that every clinicians going to, you know, ask all of the right questions in the right order to assess for and ultimately manage risk of suicide, we know that's not necessarily true. And so to be able to have the resources right there at your fingertips to ultimately help the clinicians follow a gold star evidence based process, let's say in this, this example of a suicide risk assessment, that's key. And then post visit we have suggestions that ultimately support recommendation of different patient reported outcome measures. Let's say that your client endorses distractibility, difficulty completing tasks, impact at work. They're naive for having, let's say an ADHD or some sort of executive functioning measure. We may suggest, hey therapist, you may want to assign 1, 2 or 3, one of these patient reported outcome assessments to have a more clear view of, let's say an ADHD presentation. Second, we also offer up content such as homework assignments, worksheets. These are the things that clients can work on between each visit. And this extends that limited resource of the psychotherapeutic hour, the 50 minutes or so, as well as the resource of the therapist and can kind of extend the value of therapy as the modality and then last, interventional information. So suggestions for a therapist given, let's say their therapeutic modality, cbt, dbt, act, internal family systems, whatever, it might be a robust clinical library to help, you know, have these types of nudges at one's fingertips. So at the end of the day, we are a tool that helps support the practice of high quality behavioral healthcare for clinicians and the organizations they work in.

Yeah, and one of the things I loved about your article is there's no doubt that the convenience piece is there with AI, but we have that concern of what is stored, of privacy, of protecting confidentiality. Right. Of psychophantic bias or hallucination. Hallucination. Hallucinations from AI. So we don't have a whole lot of time to dive into that. I just wanted to highlight that piece and I know in your article you bring some of that up, but in closing, I would like to ask you if there is one thing that you could say to the whole spectrum of this industry, patients, clinicians as well as businesses, what would that be? What's the most important thing to know about what is going on in our industry right now?

That's a huge question. I know, and I've got competing answers in my head.

Sorry.

Yeah. Ultimately we have a crisis that is of population level, size and impact in our nation today when it comes to to mental and behavioral health. We have a workforce that is ultimately less prepared than they should be to rise to meet that need. And we have a system. And I'll put some air quotes around that because at times the fragmentation challenges that what a true system should look and function like. But one of the quotes that has always stood with me from Deming is, you know, every system is perfectly designed to get the results that it does. And we've built a system here in our nation to deliver health and behavioral health care that is not delivering on what is sorely needed. And at each level of the system there are key actions that can be taken from the patient level, provider level, organization, payer policy, public health and beyond. And this is going to require our best and brightest minds, but also putting aligned incentives and putting the financial investment to change the system that we've ultimately built such that we can yield the outcomes that are deserved by so many. So we have a long way to go. There's no silver bullet and we need to do lots of things in concert. But at the end of the day, we have an opportunity and the call to action, both here and frankly, globally, to address the unmet behavioral health needs that impact family, society and individuals so deeply.

I love it. Well, Dylan, thank you so much for your time here. I encourage everybody to check out the show notes, get a little more educated on these topics if you're interested. And we will be back next week with more on the Mental Health Evolution Podcast. Can't wait to see you then.