Thank you for your interest in our webinar

James Stoller answer: Currently, the available therapy is so-called augmentation therapy, which is the infusion of pooled human plasma-derived alpha-1 antitrypsin intravenously on a regular basis.

The FDA indicated frequency and dose is 60mg/kg of body weight once weekly with demonstrable pharmacokinetics that preserve the serum level of alpha-1 above the so-called protective threshold of 11 micromolar or 57 milligrams per decilitre. And so augmentation therapy – Dr. Tejwani and I have many patients receiving such therapy – is indicated for individuals, not based on symptoms, but based on demonstrable emphysema. Such therapy does nothing to address the liver disease. It addresses the toxic loss of function, which is part of the pathogenesis of the emphysema in alpha-1, the liver disease being related to a different problem: a toxic gain of function which is too much protein in the ZZ state, for example, in the liver. The accumulation of variant AAT protein in the liver prompts a whole fibrogenic cascade and can lead to cirrhosis and hepatocellular cancer. On the other hand, there is currently in the pipeline – still under investigation, all of them – a number of novel approaches that will address the underlying predisposition to alpha-1, namely approaches that include conformational molecules, chaperones, mRNA editing, gene therapy, and DNA editing. None of these treatments is available currently, but many, if demonstrated to be effective, may be.

And this is where, of course, detection becomes important, because registrational trials for such drugs will require a big patient cohort that's currently unavailable given the under-recognition of alpha-1. So, in a future state, one could well imagine indications to treat individuals who have yet to develop disease, as is currently not the case. Currently, the indications for augmentation therapy, quite concordant across multiple guidelines, are that this is indicated for individuals who have severe deficiency of alpha-1 and demonstrable emphysema. Most patients with AATD-related emphysema have the PI*ZZ genotype, although there are other genotypes that are rare – Mmalton, Siiyama, etc. – that predispose to emphysema. Many AATD deficient individuals with emphysema have fixed airflow obstruction on pulmonary function tests, but some have preserved airflow with emphysema on imaging.

Vickram Tejwani answer: Yes, I agree. As Dr. Stoller alluded to, there are a number of pipeline therapies. And then the other kind of pipeline component is predictive models, typically omics-based models, to understand who's going to do poorly and who's going to do well, because even among ZZs, there's a huge spectrum of heterogeneity in terms of outcomes, and MZs as well, which we're studying quite intensively, locally. I think it comes down to this jugular point, which is: if you don't know that they have this, they'll never be included in these things moving ahead. And then on a more practical, just immediately implementable component, we know actually from work Dr. Stoller and I did, that in a delayed diagnosis, these patients end up doing worse. Anecdotally, we've had patients where they get identified, they're perhaps asymptomatic at that time – and we're certainly not treating them, given normal lung function and no emphysema – but on subsequent surveillance, they do develop airflow obstruction. And now we're not dealing with this delay on the back-end of them getting tested. We're already aware of their ZZ status and able to imminently start guideline indicated therapy as opposed to an additional delay, later.

Marie Sanchirico answer: I'm not a clinician, but I would probably even step back and just simply say that being aware of their genetic risk factors, physicians can work with their patients and really minimise maybe behaviours that would lead to onset of pathogenic disease or pathologic disease – reducing smoking and taking care of your lungs and environmental exposures – that awareness can change whether or not the disease is going to onset, but definitely when it might onset.

Scott Bryant answer: I'll keep it simple, but it's a multifaceted approach. We use Datavant as our tokenisation engine such that we never touch or see any PHI. It comes to us de-identified and tokenised, which is one important measure. But on top of that, our healthcare map is under a master certification. I think, as I said at the top of the call, we source our data from a myriad of sources. And it's really important that the disparate data sources that exist together that create our healthcare map are also compliant: an additional layer of reducing the risk of re-identification. So that's the most simplistic answer. Datavant tokenisation and master certification to ensure that populations of interest aren't re-identified or individuals aren't re-identified.

Vahid Esmaeili answer: Often, we get this question when we suggest starting the foundational model from claims data. Given that claims data is large-scale, it gives us access to a more representative population. Some people are initially sceptical, and worry that we might be missing important clinical signals for disease learning. But what we consider as key is generalisability.

Even if you build a strong predictive model, using lab values or imaging results, it may not generalise well to other clinical settings because that data may not be available or might be recorded differently. So then you have a difficulty in moving that model from claims data to other clinical setting, which was key, I think, to this project and important in general.

We are also collaborating with Komodo Health on another project focused on real-world natural history of diseases using claims data. At first, it might sound surprising, but, as Scott mentioned, we have ways to link EMRs or other data sources to that. The challenge is, as soon as we start to do that, that overlap often becomes small and you end up with a smaller cohort it’s harder to track the patient journey.

So if your goal is representative data and meaningful conclusions, whether it is outcome prediction modelling, disease learning, finding undiagnosed patients, I think claims data could be fit for purpose. And we are now stretching that use case to going even beyond that and performing real-world evidence generation, health economics research, as well as natural history studies.

Marie Sanchirico answer: And I would say, Vahid, it comes back to – I think you mentioned it early on – asking the right questions. You do need to think deeply about whether or not the disease that you're exploring has the right data and you have to think about whether the right information is being entered in the data that would inform a model. I have worked in other therapeutic areas and with other models where it hasn't worked, and there are a myriad of reasons. Vahid, you mentioned you have to think about the biases, you have to think about what data is being entered, is the data actually being entered into structured data that you would need to diagnose the patient if you're going to try to accelerate diagnosis? Is it in the structured data or is it somewhere really hidden in messy notes? So really, you do have to do some deep thinking before you kick off a project and ask if your disease state is the right disease state to deploy an AI tool or to choose claims data or whatever approach that you might be thinking about taking.

Jamie Stoller answer: Indeed, this is a critical consideration. I appreciate the question. Patient confidentiality, of course, underpins everything that we do. And personal health information is sacrosanct, as everyone understands. So this is why, in Phase 1 of the study, these were all de-identified patients. And this was reviewed carefully by the IRB and approved. There were no specific patient identifiers that could be ascertained with the algorithm in Phase 1. In Phase 2, of course, as Dr. Tejwani pointed out, the AI prompt is to the physician who's caring for the patient with whom the patient has a relationship, so that there is no testing outside of the clinician-patient relationship in Phase 2. That is to say, the doctor seeing the patient, who has a relationship with the patient will get a prompt suggesting that AI has identified features in that patient that would prompt and recommend testing for alpha-1.

And then, the question is: will the physician – as Vick mentioned – will the physician behave compliantly on that basis? And if he or she does, does the test demonstrate the presence or absence of alpha-1 – the 6% prevalence that Dr. Tejwani mentioned before. So in that context, because the algorithm is prompting the caring / treating physician, it

is not independently generating a test without the physician-patient relationship. This approach is, in our IRB's view , perfectly acceptable.

I'll say one other thing, because I'm aware that one of the other questions regarded newborn screening. And, of course, there is no intent for this AI algorithm to engage with newborn screening. As the questioner is aware, if we, in fact, had a population-based approach to newborn screening, which is a very complicated issue, that would pre-empt the need for testing patients with an AI algorithm, because in that regard, much like cystic fibrosis or phenylketonuria or congenital hypothyroidism, which are routinely tested in the United States at birth, newborn screening would likely obviate the need for an AI algorithm. But again, newborn screening is a very complicated issue with important guardrails on psychological well-being for the patient and for the parents.

Vahid Esmaeili answer: Yes, at least in our initial, in silico analysis, we saw evidence that the model can identify patients earlier in their journey. In the initial model developed on Komodo data, we applied the model to a large population of at-risk patients. We then compared the distribution of age among those currently diagnosed in the data set to those predicted by the model as being likely AATD patients, but yet undiagnosed. What we observed was that in the diagnosed population, about 47% were under 60 years old. While, in the predicted undiagnosed population by the model, 67%, were under 60. That shift suggests the model is identifying people earlier than the typical observed age at diagnosis in the data, which is consistent with earlier detection.

That said, this was in silico comparison. In Phase 2, as we scale up into Cleveland Clinic, we plan to track confirmed diagnoses and directly compare age at diagnosis by the model versus the current baseline. So we can make a more confirmatory real-world assessment of how much earlier diagnosis occurs.

Vahid Esmaeili answer: One of the main challenges in this project is that claims and EMR data are inherently different. When you move into a specific clinical setting, coding practices can differ, what’s captured can differ, and the EMR is often richer in certain aspects than claims data. The key question for us was: how do we leverage what we already learned on Komodo, without losing it, and then recalibrate it so it’s properly adjusted and fine-tuned to the EMR environment?

We did not start from scratch. We reused the core features and signals learned from claims and then recalibrated the model in the EMR setting. As part of that recalibration, the relative importance of features shifted; which was the purpose of recalibrating on more “gold-standard” labelled patients and cohorts, as Dr. Stoller mentioned.

So the core signals were robust and we were able to migrate them, but we still needed fine-tuning and recalibration to reflect the new environment. This is critical, because one common pitfall is that models developed solely on claims can fail when moved into a clinical setting if that end-to-end adaptation isn’t planned from the start. That’s why we considered the final deployment setting from the beginning..

Is the MZ population also included or only ZZ

Jamie Stoller answer: The algorithm is designed to identify individuals with any deficiency of AAT, including PI*MZ individuals.

Vickram Tejwani answer: This process is underway, but both education on the algorithm and impetus around diagnostic delay, as well as disease specific resources are being provided. The latter is to allow for seamless care of an abnormal test and to minimize additional burden to clinicians.

When I worked in newborn screening, there was a phenomenon where parents of babies with a false positive screen still believed that their baby was not healthy. Do you have any concerns that the algorithm would lead to people thinking they are at increased risk even if they test negative.

Jamie Stoller answer: This is a good question. I will remind that the AI algorithm does not regard neonatal screening, so the issue that you raise falls outside the study issues. I would regard the test results as being definitive and am hopeful that clinicians discussing the results with patients or their parents could allay concerns is the AAT test shows no deficiency.

At this stage, we can’t provide test positivity rate yet, because that metric requires a prospective, real-world rollout where testing happen in routine care.

Measuring test positivity rate is a core endpoint for the next phase: in Phase 2 we will run a prospective study and track AATD test orders and results among model-flagged patients versus baseline practice, with testing performed at the clinician’s discretion. That will allow us to report the test positivity rate before and after deployment in a clinically meaningful way.

Jamie Stoller / Vickram Tejwani answer: This is a good question. Bronchiectasis does occur in association with AATD and we anticipate, based on Phase 1 data, will be a feature that factors in to increasing the probability of any single individual’s likelihood of AATD. Imaging studies suggest that radiographic evidence of bronchiectasis is very common and that clinical bronchiectasis – with copious purulent phlegm, etc. – occurs less commonly, i.e., in approximately one quarter of individuals with severe deficiency of AATD. Bronchiectasis is usually associated with some evidence of emphysema, in which case augmentation therapy might be indicated. I am unaware if data supporting augmentation therapy in the presence of “pure” bronchiectasis.