ALS, AI, Early Detection and Clinical Trials - Indu Navar, Everything ALS

Amyotrophic lateral sclerosis, or ALS, is a devastating neurodegenerative disease that gradually strips away muscle control. The whole time leaving the mind intact. Beyond the staggering medical challenges, ALS shifts an immense financial and emotional weight onto the healthcare system and family and caregivers navigating a long, complex, and deeply emotional battle. In today's episode, we're looking at the current frontier of diagnostic tools and how AI meets digital health and neuroscience, and possibly what modern biotechnology offers to patients and the loved ones who are beside them. We're speaking with Indu Navar. She's a CEO and founder of Everything ALS. So welcome to the podcast, Indu.

Thank you very much for having me, Kevin.

Yeah, this is really a long time coming because I've spoken about ALS with some other scientists before and some of the frontier of the diagnostics. And really, the personal side of this is much more important, but also some of the new diagnostic stuff is fantastic. And I really am excited to talk to you about that. So it really maybe is rooted in your Silicon Valley career that really spans a bunch of different disciplines. So what brought you back to ALS?

Yeah, great question. You know, if you had asked me maybe 10 years ago that this is what I would be doing, I would say you're nuts. I mean, had no desire to be in, you know, I had no understanding. You know, short story is that I'm a Silicon Valley entrepreneur. I've built companies, software companies, and always, you know, we look at a problem that we know and we try to solve it because we want a better world and better, you know, way to learn from it and build a better tomorrow. That is kind of why you become an entrepreneur. And, of course, there's also financial incentives and building a capital market. And so, my husband was very early at Amazon, and I built software companies. And we were kind of semi-retired. We're still in our early 40s and retired. And he got His early symptoms, what turned out to be ALS. And the whole diagnosis process of us not going, oh, it might be just a muscle strain or a spinal pinch or something, to having a serious issue, which took us about almost 18 months to 2 years to get diagnosed, going to all the—

Mm-hmm.

Tier 1 centers. What I realized was there's really no diagnostics. There is no— it's kind of called the method of elimination. That is, you go through the process and you say, come back after 6 months, come back after 8 months. I'm not seeing— because we went very early to the neurologist. And when we got diagnosed, on the other hand, it was like too late to get into the treatments because there is also, you know, in clinical trials, there is all these artificial, you know, inclusion criteria. Criteria, as we'll call it, or exclusion. You have to be within 16 months of having had the, uh, um, you know, symptom. Nobody can still explain to me very well why we've come up with these, uh, things which kind of, you know, um, gets inherited without asking why. Because we don't have a way to diagnose people. We have— don't have a way to know how they're going to progress and how, you know, what is happening. So we have this artificial barriers, but Again, you know, Peter passed away in 2019, and the whole process for me was— felt injustice and also inhumane because there was nobody who really was— had like the holistic thinking of what happens in the patient journey. We were all trying to do better in our own silo, but then a lot of things are getting lost in the, you know, between the silos when you go from care to cure to, you know, clinical trials. Who are these people? Why? It's just like there's so much of navigation. When I asked some people, how do people do this, they said they don't. And that's why we don't have— we have a lot of failed trials, not because of not attempting to come up with better therapeutics. It's really for not having a way. So that's why as a Silicon Valley entrepreneur, what do we do? We put on our hat and try to solve it. That's how I got into this.

Well, let's start with more of a medical briefing on, you know, what exactly is ALS? This is Lou Gehrig's disease also, right? Same one?

Correct. So it's called Lou Gehrig disease because over 90 years ago Lou Gehrig had it. And so we, you know, it was named as Lou Gehrig because he did a famous speech that is still reiterated. But, you know, over 5,000 to 7,000 people die in the United States. And today, you know, we have about 40,000, 45,000 people living with the disease. But the prevalence is the same as Multiple sclerosis, so just that people with ALS don't live too long to actually make up for the numbers of people who are living with the disease. That's the only reason. But the prevalence is still very high. It is one in three hundred people. So, so it's it's just the fact that people don't live long. We can't say you know it's like MS. There is a lot of people living with the disease or Parkinson's. A lot of people living with the disease. That is actually kind of falls into ALS where you're not a really a rare disease, nor are you really a disease that has a lot of people who are living with the disease. So we call it an orphan disease. So we kind of get into this thing of— and what is the disease, to your question? It's really you lose all the involuntary and voluntary muscle movements. And so the muscle starts atrophying. So it's really, again, the disease from 1,000 cuts. It's like, you know, it'll take away ability to walk, Use your hands, move your body, breathe, speak. So it's really a horrendous way if you think about it, like, and we need to do something about it.

Yeah. And you've spoken about this before as death by a thousand cuts and that families are facing this long agonizing process during just even getting diagnostics, let alone therapy for it. And so what are the Biological and clinical reasons it takes so long to confirm ALS? Like, is it just that the symptoms are ambiguous between patients or that they just overlap with other things?

It's very ambiguous in the sense that ALS can occur in many different ways. It could say, you know, it can come in limb, like you can just say, oh, I've got like a little, you know, muscle fatigue. You know, I'm not able to use my ankle properly, what we call a drop foot, or, you know, people have like, looks like arthritis. They're not able to really do, use their golf swing, or use their gloves. I mean, it's kind of a very simple, we always, because also our medical system is set up in such a way, you go to primary care, then you'll go to orthopedic or you'll go to, because we're very set up in just looking at the problem. And sometimes it's like a nail looking, hammer looking for a nail, right? I mean, you go into, I think about 30 to 40% of ALS patients have some kind of surgery or some kind of intervention that's not related to ALS at all.

Wow.

you know, they go into steroid shots or they go into— so you're really looking at the wrong problem. And, what we are not looking at is as the changes are happening in fine motor, maybe there is something else is happening in speech or there is something else is happening in other organ that that physician does not take care of, right? So, that is one of the things that we have is that we're not looking at it holistically. That's one. Of course, this is a clinical diagnosis. We don't have a blood test, we don't have an image that says, that you have ALS. So it's really a clinical diagnosis. So as people are— I mean, I can tell you, like Google told us long time before we got diagnosed. And people say, yeah, you know, maybe they make mistakes as well, but that's okay. Even if I had 80% probability that he had ALS, I could do something about it and done within first 1 or 2 months. It's a lot better than for me to say, you know, hey, I'll just wait and be definite when he's in deathbed, right? I mean, like, you know, so the good times of what we could have done is taken away because we don't want to assume that it could get ALS. But if you don't make those assumptions and if you don't partner with the patients, we'll never come up with the more efficient way of doing it because we don't collect any data for people who are in that limbo state. We only have data from people who get diagnosed, right? And then that's, And then that is not useful. So this is where I'm talking about, like, you know, our system in the silo is broken. And if you say, why does it take too long? It's also some of the things structural.

Yeah, it mirrors with things we've heard about other neurodegenerative diseases too.

Yeah.

And from a molecular and genetic standpoint, when you talk about ALS, it's really complex and there's different types, I guess, those different subtypes. Some of it's familial. So there's actually mutations that they can detect that underlie this. Some of it's idiopathic. But how is Everything ALS working to take apart these different subtypes so that research can begin to see early onset symptoms or even define underlying causes?

Yeah, good question. We do have 10%, as we know right now, which we call familial. That is, they have the genetics that is inherited or they They some people don't even know that they you know inherited it, but they have a gene. So some people didn't have a gene; they have inherited the parents had it. They thought they did not have it, but they still got aella. So there is still a lot of mystery even in the family tree. But we do know that 10% is the known gene, and what we call 90% is sporadic. So that is we have no idea why somebody gets it. But there is also a very good you know. science or research or people looking at everything is genetic, just that because we don't know the 90% doesn't mean that, you know, it's not genetic. So, it's really what we don't know, right? So, yes. So, genetic is 10% where it carries within the family and 90% is sporadic.

And, one of the exciting parts about looking at what Everything ALS does is big strides with AI and machine learning in detecting or predicting disease progression. And can you talk about how this analysis of a simple 1-minute audio recording can really identify motor neuron decline with really strong accuracy?

Yeah, that's, you know, the technology is there. The technology is here today. It's It's not rocket science, but we haven't really applied in a proper way to make that change, right? I mean, look at how we do today. Do you ever use maps? No, you use GPS. I mean, like, you know, do— I mean, like, you can't say, you know, how does it accurately tell me where to go, right? So this is not rocket science, people. We already are doing it in our everyday life. You use Venmo to pay people, and how does it happen? You're going to the bank, it actually took your money out, and it You can't say, oh my God, this is miracle. No, we're doing it. So why, when it comes to healthcare, we think that it is such a— because I really think that we need to change our attitude because we are doing it today in our daily life. What if we took away everybody's GPS, everybody's phones, everybody's way to actually do any banking and communicate? What will they do? That is the world we live in in healthcare. Really, seriously. We need to stop thinking that this is miracle. It's not miracle. Technology is already there. We need to apply the technology in a way that actually gives us the results. So to answer your question, yes, that's what we did. We created a methodology that we can all work on a fashion that's a fast-moving, agile methodology where we can see the result. So the old way was that, you know, you put— if you have a digital tool, you put through the validation process of what we call the high-risk, pathway, that is therapeutics. So if you have therapeutics, yes, you put through phase 1, phase 2, you know, pharma company, clinician, they give that. But we in digital tool, we do the same thing. We shouldn't be because it's a low-risk diagnostic. So what we have done is we've created a platform where patients are engaged all the time. And then we have clinicians who are engaged, many institutions, not just one institution. And many of the pharma are also involved from day one. So they know what's happening and they can put it into their trial as they see good evidence, right? So, so this creates a fast-moving agile methodology. Within 2 to 3 years, you can actually bring a product to market that you can submit to the FDA because there's also collaboration. So, you know, we did it. We actually came up with, yes, 90 seconds. We can actually have someone's speech in 90 seconds and we can actually predict not only where you are, where you're gonna be, because, you know, it again, you know, we collected a lot of speech from people instead of getting 25, 50 people over 2 years and doing a publication. We got about 1,000 people and we were able to look at the whole disease projection and get it distributed, you know, 50 states, remote people remotely were able to participate. So from that data, we put in AI and machine learning and also we used humans as well. We used speech-language pathologists, we used the clinicians to tell us if we are actually, you know, labeling correctly and we labeled the data correctly about who's progressing, how— there was a lot of grunt work that was done. Once we had the label on everybody, you know, 96% inter-rater reliability, that means 96% of the time when I talked to speech-language pathologist A versus B versus C, they saw the same progression. So that means we know inherently how people are progressing. It's just not automated. It's not put in technology, which is not a repeatable, scalable model, right? So what we are doing is taking something that's a tribal knowledge that's there, and engaging the patients so you can get the whole data. That's why we are like citizen-driven research. And then applying repeatability and scalability to it so we can productize it and use it over and over again with a reliable model, right? So it's really the methodology is how do we build this framework that we have seen in the tech world? You know, how do we come up with— in semiconductor manufacturing, we needed to have a fab first, your manufacturing. But today we don't. A company can come in and say, I have an idea in hardware, and they outsource their manufacturing, they outsource their thing, and they can come up with the same way that we do in software, right? Why haven't we done that in healthcare, right? That's a question to ask is that we don't think of new models. We think of the new innovation in the old model. We need to break open the model and say, if there's new innovation, then we need to come up with a new agile way of working. So it's really, you know, that's what our innovation is. platform to work in an agile, fast-moving, fail-fast way where we have— we take away the bottlenecks and frictions.

Yeah, I appreciate all of that very much. I mean, especially in the diagnostic end, it seems crazy that this would be so complex. And what's really interesting about this, this is the first time that I've really been acquainted with the idea of a speech-based digital biomarker. Okay, you're able to analyze speech and be— the neat part about that is that you're taking it out of the clinic and now you can remotely Diagnose. But can you give me some hints as to what exactly is it looking for in terms of signatures of one's speech? Is it picking up like delays or mispronunciations? Or what does it look for?

It's called speech clarity. So it's a dysarthria. It's really looking for how people are speaking, like, you know, how well do you understand them? So we call it listener effort. So that is, when I speak, how much of effort are you putting to understand me? So what you're looking at is a clarity of speech. If I I slur, if I have like, you know, certain thing, and how much attention do you have to pay for me? So that's kind of what we are measuring in ALS is the speech clarity, clarity of speech, because that is one of the things that get affected is not the pauses or the breath, it's really the clarity.

Okay. Now it's interesting. One of my favorite episodes of this podcast series came up a few years ago and I interviewed Dr. Avindra Nath at NIH and he's an ALS researcher and he's been looking the role of human endogenous retroviruses, so the HERVs, and their potential role in ALS. And are there any new breakthroughs or anything happening on that front in terms of the causal basis for some of the sporadic forms of ALS?

What we know is that ALS is not one disease. It does not happen by retrovirus, or it's not going to be Just you know some bacteria or you know genetic that we don't know. It's gonna be subtypes, just like how we have in breast cancer. Breast cancer is not one. There are many different types of breast cancer, and I think one of the injustice that we're doing is that or we're not cracked it. That's where we should focus on a lot on it. What are the subtypes? Because if you actually give the same one vanilla breast cancer therapy to all the different breast cancers, it's not gonna work. So we need to. Personalize it. So precision medicine is very, very important here. So we understand. So that's where the digital signature is very important for me to see that why somebody did not have any issue in speech, but they had something in just the upper motor, or they had it only in the, you know, in their limbs or in the breathing, in the abdominal, but everything else was fine. So we need to see why these digital signatures are different. And with a digital signature, I can actually say, There are also in speech, there are 4 or 5 different ways people belong, right? Fast progressing, medium progressing, you know, slow progressing. So you actually put them in different subtypes, and then we can go in and say biologically, how are they different? So that is kind of the work we are doing is really looking at digital phenotype and then say, how do we actually go back and understand their Have cuts at NIH or other agencies really affected ALS research? That is a very, you know, a question for a lot of people who depend on the NIH grant. We actually don't depend on NIH grant. We actually enable a lot of people to apply for NIH grant. So we do work with researchers. Who actually apply to NIH grant because they want to work with us. They say, you be the technology partner and you, you know, whatever you're doing. So, for example, in speech, we were able to say, you know, work with an entity called NSU. They collaborated with us to actually go into Spanish. So, we actually expanded from just English to now Spanish, and they got the NIH grant, and we are, you know, subawardee and we are working together. So we see, we just finished about 11 of them recently in the last 60 days with a lot of researchers coming in and saying, hey, can I do, you know, what you're doing? I'm in the same field. So can I expand into either different languages or different modalities, right? We do gait, walking, breathing. We do all of that, right? Like we look at all of the symptoms of ALS. So NIH grant, has it affected? Maybe. It's got its pros and cons. Like, you know, it's got everybody to think about trying to be a lot more useful in a way that, you know, we have to be thinking about where do we get— what is the impact that I'm going to do to get that money? And, you know, sometimes that's kind of what I've seen is that a lot more people want to make sure that we can work together to apply.

Very good. Well, we're speaking with Indu Navar. She's the CEO and founder of Everything ALS. And on the other side of the break, we'll talk about some of the AI applications and other ways that modern tools are working in the diagnostic end of ALS. This is the Talking Biotech Podcast, and we'll be back in just a moment. And now we're back on the Talking Biotech Podcast. We're speaking with Indu Navar. She's the CEO and founder of Everything ALS. And we're talking about amyotrophic sclerosis, lateral sclerosis, I always get that wrong, and Lou Gehrig's disease and some of its modern methods, some of the challenges in diagnostics, the modern ways in which those diagnostics are improving, and potentially some of the new therapies. So you've recently launched something called SAVA on the website, and this is an AI-powered clinical trial matching tool. Matching tool. I'm skipping over words today myself. So clinical trial enrollment is always difficult for orphan diseases or rare diseases. So how does Sava help bridge that? So getting people connected with experimental therapies?

Yeah, so very good question. So, you know, in the era of LLMs and AI, people want to just get the answer. We're not going to be Googling, we're not going to be calling. I mean, calling is gone. You know, those days are gone. And we were trying to find it online. And the old way was, you know, people will call, they do hours and hours of web search and look at it, look at whom to call, what to do, and then make their own list of, you know, clinical trials, personalize it. Instead, you know, we're in the world of AI where people can come in and talk to Sava, Sava AI. Again, it's named after a person with ALS who was actually doing that himself. Somehow the clinicians actually found out and said, hey, there is this beautiful, you know, Google Doc. Somebody puts it together and keeps it updated. He was doing it for himself, but everybody else started using it. And we found out that he's in Amsterdam and he was, you know, an engineer who got diagnosed with ALS. And we said— that's when we said, you know what, it's such a need that people have to do it themselves. That's why we are citizen-driven research. We automate it. We automate it in a way that we know it's a need and everybody else should have the same access, right? So we democratize this. So in Sava AI, it's a simple LLM, just like how you chat with ChatGPT or Claude or Grok or Gemini. You just come in and say, I am— and of course, it's, it's really, um, made for clinical trials. So it's going to guide you through the clinical trials. What are you looking for? Which, which state are you looking for? Are you looking for some particular, you know, method? You don't want to get poked and thing? Are you looking for only, you know, pills and placebo? You don't want to know that— you don't want to be in a place where you might not get the pill but you're in the trial, right? So it's called placebo. And so all that is really— you can ask the question and our goal is to create accurate answers. So we did a lot of backend work to make sure that data is synchronized, that data is, you know, validated. And also the way we do the backend retrieving it from our database and things like, you know, we need to get near 100% accuracy in terms of, you know, who is recruiting, why they're recruiting, where it's recruiting. And on top of it, it's a collaborative. That is, the pharma companies are updating their information and the clinics are updating when they're recruiting, when they're not recruiting. And sometimes if there's an error, they'll correct it. And the clinicians are also updating what are the trials that they see as a good one, that they know about it. So, for example, if you go to Columbia, you know, the physician there, what they'll tell to their community of their patients, they'll go in and put it into as a review almost like, you know, that will be something that patients can say, oh, this is what the physician in Columbia said. This is what the physician in Harvard said. Right. So now you have got a view of many different physicians. That's something that happened to me as I was going. I'm like, who else would recommend this? What would they think? Mayo told me this, but would Merit say this? Or I don't even know who these people are. You know, it gives me a better understanding of what I want when I know what the community of physicians and also, you know, help of the pharma thinks, right? Like, so, so the Sava AI is really a matching— beyond matching tool, it's a collaborative tool between bringing the patients, physicians, pharma, the sites where the trials are happening, And also, it's also the ALS nonprofits where they're actually putting this as a link on their website so everybody can have access to this. So SAVA is really increasing the— 2 things it's doing. One is it's increasing awareness for the patients easily what's available for them. And we also have a way for them to— we help them handhold and make sure they're in the trial. And also it helps for the pharma and the sites to get really patients who are eligible because we went through in the AI and we made sure that these people are eligible before we presented to them saying, you know, if they're not eligible, we'll say, hey, you know, these are the things you're eligible for and these are the reasons why you're not eligible in a way that's compassionate, talking the patient language. It's not like, you know, very crude technology where it's, you need to be compassionate, you need to be, emotionally engaged with people. So, that's where the AI is going to be very positive in terms of guiding people through what they can do and what they're eligible for and what they're not.

Okay. So, one side of this is really an important recruiting tool and that's really helpful. But on the same level, with more people come more data. And as you start to accumulate data, now we can recruit it or what we can identify it like never before and get things like proteomic data, transcriptomic data. Just tons of data regarding what's happening at the biological basis of the disorder. And how does Everything ALS really open this up and really just provide this open data platform that allows researchers to access global data regarding ALS?

So yeah, I want to separate out what SAVA and what it's used for is the recruiting. And we have another study which is called PathoTrials, that we just, you know, opened up. And we do a lot of research, as you know, like we had a speech study, we have Radcliffe study. Yes, we have, you know, this PATHO trial is where, you know, patients can actually engage, where we will keep track of their data and also match them to the trial as they become available. So this is like they don't have to go in and engage. This is going to be— it's like AI, you know, your personalized AI that's going to work for you, right? So, so that is one of the things where in that population we do actually work with a lot of the community and they say, hey, I need to get blood for NFL or I want to get, you know, these other things. So yes, we do collect the data, but we're— we also want to be very conscious of why we are collecting the data. So there is a lot of— because if you don't answer why from the beginning, you miss out on doing the right thing. Because it's one of the mistakes— many of the mistakes happens in research is you think, I collect all the data and somehow the data will give me the answer. If you don't know what the intention of what you're trying to find, you will never collect the right data in the right fashion, in the right way to actually answer your question. And then not only that, not only are you going to answer that question, you need to know So, if you're collecting inline, you should do data analysis to see, is that actually deviating from my why? And if I'm not getting my why, maybe I need to change the protocol, or I need to change the way I'm collecting the data, or, you know, your why has changed, right? So, it's a process where you do the engagement, data collection, and analysis together in an agile way. So those days of, I'm going to collect a lot of data and somehow somebody is going to find it, it's a myth. It has never happened, and it'll never happen.

Well, in the lines of therapeutics, and so Vision 2030 AI Hub, this is a partnership with MIT and Massachusetts General. It's really focused on cellular repair and regeneration rather than just managing symptoms. And so what specific regenerative therapeutic avenues are currently being explored, things like stem cells or gene therapy? Is any of that showing Is there really good promise to this kind of collaboration?

So yes, we just expanded our Vision 2030 advisory to 15 other institutions. We also started working with Allen Brain Institute in Seattle, where they actually have been doing a lot of deep work in, you know, cellular, molecular level. So yes, we are making progress there, but again, there is so many missing hoops We want to make sure that digital and molecular meet. And that's one of the things that we are now harped on is really to bring in that kind of end-to-end thinking. It's not just figuring out what might work. It's also what is possible to bring into the clinical trials and what is also FDA approvable. So you kind of have to think about all of those elements, not get excited about, you know, oh, it showed in the molecule, it showed in the thing. You have to think about the holistic view from day one. You need to walk backwards about is this approvable? Is this clinical trial? Can I actually run a clinical trial? If you have a method of delivery that's going to take 5 years of monitoring a patient, people are not going to do it. Too expensive to, you know, like, so there is so many of the the monetization element that's there as well. So not only have to come up with a target that works, it's also what's doable to bring it to market. So both of them have to coexist, and reprioritization is happening all the time. So yes, do we understand more about TDP-43? Do we understand more about the genetics? Do we need to get more deeper into understanding? Yes, we can do— we Absolutely. But again, the goal is in how do we build this agile infrastructure where we are learning quickly and creating a momentum of learning. Otherwise, if it takes too long, we lose not only the momentum, we also lose what we are learning, because by then the technology has changed. So we kind of are constantly, you know, not in the same zone. So it's very, very important to compress the time and building the momentum and creating this agile methodology of collecting something, analyzing at the same time, and making that quick iterations.

Well, one of the other big successes has been that Everything ALS has managed to unite a number of big pharma companies and biotech partners all together in one shared space. And this is always interesting to me that how do you convince traditionally competitive companies with all their independent financial interests and pipelines to collaborate and share data under a common operating framework?

So again, you know, healthcare is just so behind. And I think that's because we think in an old paradigm. The old paradigm has left us a long time ago. This is not how we're going to win. For example, I'll tell you an example in semiconductor companies. You know, when I started building my software in semiconductor, that was my previous company where we had NVIDIA, AMD, Cisco, Juniper. All those people competed with each other, but they all use the same manufacturing facilities to make their products. And my software was actually working with all of those manufacturers to say, oh, this is what Cisco can do. You know, we would like deliver there. They would have views of their own data and they can make quick decisions. So the competitive differentiation comes from how you make the decision and what your therapeutics are and what you're bringing to market. It's not about building the infrastructure. That is where we actually deviate in healthcare. I think as a community, we need to start thinking about people have to work together. We need to start thinking about encouraging people to say, this is— there is no competitive here when you're building an infrastructure. If I'm building an infrastructure on how to diagnose patients, how to actually come up with a better measurement for foundation, or doing foundational work of trying to bring, you know, postmortem tissue in a way that is going to tell me what's happening in the spinal cord and what's going to happen in the brain, these are not differentiation. These are infrastructure. These are companies. This is like Like everybody's saying, I'm going to build an outsourced manufacturer who's going to build my products, who's going to build everybody else's product. And it's fine, right? Because I'm going to take my product and I'm going to focus on my product and make sure that I beat the other product. But you can't hold on to saying, I'm going to build my own manufacturing. And those people who did it, they're not alive anymore, right? The agility wins, speed wins. So you just need to, you know, so these are the companies who started working with me, are forward thinkers. who understand that agility wins. And, you know, it's when we collectively work together, we're actually building an infrastructure that will benefit all of them.

Well, that's really spot on. Everything ALS was born out of really your personal journey. We talked about that at the beginning of the podcast as a caregiver for your late husband. And looking down the road, just the next few years, What does a realistic win look like for an ALS patient who's really just entering the healthcare system, maybe because of a suspicion or a symptom, that things would be different because of the infrastructure that you are building today?

What I would like to, you know, the difference is gonna be that when anybody suspects you might have, even if it's a small chance, give them sensors. There'll be a box that comes in. And we say, Kevin, take this box and just use it. You know, there's an app. Do record your speech once a week. And here are some sensors. You you want socks. You want you know sole in your shoes, insoles. You want to have you know how do you walk? So let me look at your balance, your walking, and your breathing, right? I mean, like so. And, I just measure it. And, when I see the deviations, even small deviations, we've already done a lot of research already that you could have diagnosed 5, 6 years before. So, we know that, hey, you're heading towards having multiple systems which is kind of degrading. And, that was the time when the body is trying to repair itself too. That's why it's slow in the beginning and then it goes off, right? So right now we're diagnosing at the point of no return, like, you know, when it just breaks. And if we actually do it at the time when it's early, when it's still breaking, and then actually match them to clinical trials, because clinical trials want people in the early as well, and have these digital measures in the clinical trials, where I can say, okay, this person, Mr. Smith, who took this, actually can actually see the difference, which we're doing it right now. I can actually— I have a company right now. We've monitored patients remotely. I can actually show the data that this person on this treatment did not degrade as they should have, right, with the respiratory. So, so then we do the precision medicine. So it's going to be precision for each one because each one is different. We know exactly what their metrics are. And then we'll be able to subtype too. Why did this person actually respond and not this person? Now I've got enough data. So that's where I see early diagnosis and the therapies meeting each other.

Yeah, that's really pretty amazing 'cause it seems so much is missed because of that later diagnostic. And so if people wanted to learn more about Everything ALS, where could they follow online, either website or social media?

Yes. So go to everythingals.org and please subscribe to our YouTube video, YouTube channel, that is Everything ALS, and also our Instagram, Facebook, and we're on all the social media channels.

And are there opportunities to donate or what ways can they help in ways like that?

Yes, absolutely. We always love for people to join us in any way possible. If you go to everythingals.org and, you know, how you can get involved and donate, there is a page that you can actually donate online or just contact us to send us a check.

Oh, very good. Well, thank you very much, Indu. I really appreciate you spending the time with us today. And it's really inspiring to see how you've turned a personal tragedy into a way that's really changing the game that will help other families. So some of the things you've discussed here today were the fact that you're only looking at late-stage disease to try to unravel how to treat a patient. And it's already, you know, the horse has already left the barn, right, to say it that way. And this is the same complaint we've seen about other neurodegenerative diseases like Alzheimer's. So are there facets of what you're doing with Everything ALS that may relate to other neurodegenerative disease populations?

Absolutely. We just launched everythingalz.org. So that is Alzheimer's, for focusing on Alzheimer's patients. So we are looking for early Alzheimer's patients, whether they're diagnosed or they're in the process of getting diagnosed or even worried. Well, you know, that some people are like worried about what is going to happen. They're figuring out that something is off, like, What we do is we monitor them. We monitor them digitally. Everything is free. We say, come in and work with us. And then we also have blood tests. So we look at P-tau 217. That is a test that's now breakthrough for Alzheimer's. So we look at the cognition changes and also the P-tau test. And we see that if they are eligible, we also connect them to the clinical trials using our AI. And also what we have is concierge service. So we will personally actually help patients actually get into the trials.

Excellent. That's very good. And to the listeners, this is just another example of how personalized medicine is changing the way that we're going to be discovering new diagnostics as well as new therapeutics that can treat some of our most challenging diseases. And problem is things like ALS are still pretty rare, and that makes this even harder. to collect those data that ultimately can inform the guidance that we would provide in personalized therapeutics. But this is getting faster because of efforts like Everything ALS. So learn more about this organization and how you can help. This is the Talking Biotech Podcast, and we'll talk to you again next week.