Angel Alberich-Bayarri Presents Quibim at LSI Europe '23

Transcription

Angel Alberich-Bayarri  0:05  
Well, hello, everyone. Let's start with why Why does Quibim exist, actually. So we want to make precision medicine really successful. And what do we understand for success in personalized medicine? Well, first of all, many disease subtypes remain yet undiscovered. We don't know why some lung cancer patients have a really short survival, and others are long survivor, even with the same mutation, or why some colon cancer patients will relapse and not others. So we need to better stratify the patients we have today. Also, believe it or not, one of the tracks where we are putting more money in the biotech space, that's immunotherapy, we still have no specific biomarker to uniquely identify treatment response. And we see many companies developing, developing immunotherapies and even using PDL one, but it has been demonstrated not a final biomarker. So we're still in the search for a solution for a predictive biomarker for treatment response in some advanced complex treatments. And finally, it has also been proven that using real world data, and real world evidence that we can extract out of these data, we can reduce drug development times in around 30%, because we can build synthetic control arms. Well, it turns out that nowadays, around 10 million imaging exams are performed per day, and globally, as we speak, and imaging can analyze the deepest, deepest part of our neural inner body, we can use all that information to extract very relevant insights as real world imaging data, and can be helpful also to reduce these drug development programs. However, so far, imaging thus has not had a real impact in the development of companion diagnostics, we can see how the area of diagnostics has been mainly centered in developing molecular techniques, molecular biology techniques, like immunohistochemistry in situ hybridization, PCR or NGS, but imaging still remains to have a significant leader that can convert the data that we can obtain into actionable insights for oncologist to indicate a treatment. This is why we say that imaging has had a low impact in treatment indication. So far, no CVX yet dedicated, for example, in the area of oncology, and this is the category we are building at giving. But this is not an easy task. Today we have a gap between radiology and what the oncologist one, for example, in the area of Radiology, we are very much used to identify the findings or even to use AI to accelerate workflow. But what the oncologist one is to know what are the clinical endpoints of the disease, they want to know if the patient will metastasize. Or if the tumor has angiogenesis, or they want to know if this patient should go into surgery, or to go into radiotherapy, which is the arm that will benefit more this kind of patient. And this is exactly what we need to solve to cover this challenge that today we are facing in imaging. How we are going to do that? Well, we propose to couple imaging techniques with molecular biology with existing biomarkers. We have areas of imaging that remain uncovered by current molecular biology techniques. For example, the most relevant one is tumor churchianity. We can see how atherogenic it is one of the key hallmarks of cancer. And the only way we have to visualize the different cell habitats in a tumor and the different the only way we have to visualize also the heterogeneity at a human level. Our imaging techniques and imaging techniques mainly coming from MRI CT scans and PET scans non invasively. Also, by the use of imaging techniques, we have minimum turnaround time as compared to current molecular biology techniques that we need to wait around two to three weeks to get results. As we know also molecular biology depends on a sample, typically blood sample or tissue sample that's obtained from the biopsy. And we will need to perform these probably only once it's very unlikely that we will re biopsy the patient in the future. So imaging remains the only eyes that we have to visualize the disease through time. In patients, for example, from lung cancer or other oncology areas. Even more, we need a minimum sample size. It's not enough sometimes to perform an NGS test, depending on the sample we have obtained. There is an attrition rate of around 40% in some labs, whereas using imaging we can have already actionable insights that can be helpful to provide results. And finally, we always see that when we add imaging to molecular biology, when we combine them, we always increase the performance. So today, with liquid biopsy with NGS, we are obtaining areas under the curve of 0.7, 0.8 in some disease classifications. When we combine imaging, we grow in at least 10 points, these performance metrics that we are obtaining. But how we are going to do this? Well, the business model we are proposing is not really new. It's a business model that's already been proven successful in other spaces. Let's have a look at the area of genomics. We have had companies that master the creation of the NGS sequencing technology, but there had to be other companies that built a business model around information. We have companies like Foundation medicine, or exact that started to create an information business out of the DNA profiles, discovered new mutations created medical teams ended up setting new guidelines for disease management. Similar happened to the EHR or the areas of pathology. In the clinical record. We have companies like flatiron that could have stayed being a software company, but ended up creating an information business out of it extracting insights and having an impact for oncologist and biopharma companies. And what we see in the imaging space today is that the market is mainly controlled by machine manufacturers, either the ones acquiring the imaging data or AI companies that have developed algorithms to optimize the workflow of the Radiology Departments, but not to link the findings from the imaging with patient outcomes. And keeping him is basically creating an information business a new category, transforming all that imaging data into actionable insights that can help to improve patient outcomes. How we do that three pillars, huge data access, we have sourcing data from many different research projects and partnerships, our technology platform, we have our own IP in a unique technology to harmonize the image quality across many different hospitals and vendors, we are harmonizing all the image quality of the large biopharma companies and hospitals. Also, we have developed our own IP in lesions detection. But we don't stop there. Most of our competitors stop in just identifying the organs, the lesions, but we extract the insights from these tumors, the insights from these organs and link those insights to predictions to what is helping us to develop this new women's in biomarker panels for the oncologist. We have sold this data from many research collaborations, we can see the number of patients we have in any of these projects, and we are accumulating more than 100,000 patients in cancer. We also published our business model, as a reference of what we are building here we have collaboration in the life sciences space on the left, we learn from these research activities, which features and which algorithms are the best candidates to deploy to healthcare providers in clinical practice. And then this becomes a flywheel clinical practice in the end becomes also a way for us to learn what are the new biomarkers that we can develop in research and what are the main clinical needs. But otherwise, we have structured our offering in SAS model and a partnership model. In one side on the life sciences space, where we work mainly at population level. Through our QP discovery platform. We extract insights and algorithms that we can apply to the single patient through a pipeline of medical devices that are not only extracting organs and identifying lesions, but also linking those insights to actionable outcomes. And to finalize a little bit on the story of the company and the track record and current milestones. We kicked off the expansion plan around 2020 2021. We got FDA clearance for Quibim prostate, and also we onboard the Janssen and Merck for developing new algorithms on prediction 2022 Last year, we made 2.6 million ARR. We on boarded Novartis as well for an expanded relationship. It's a multi year relationship on diagnostic. And now this year we are targeting 6 million ARR we are about to announce a large partnership with our big OEM machine manufacturer. And also we are finalizing strategic agreement with a top real world evidence player. Everything to become category King in imaging based personalized medicine. But this is thanks to our great team. We are rooted locally. We are from Valencia here from Spain but our team our management team is global. We have People from Eli Lilly, Samsung, HP, companies as relevant as iqvia, and different places of the world. And to finalize some of the metrics, we are growing three times, revenue 60% of pharma working with us right now. We have four FDA, CE mark and UK ca clearances, 80 plus employees. And there is one important thing we keep very rooted in science. And for us publications. IP is very relevant in this challenge of transforming imaging data into actionable prediction. So this is what they find our company at the very beginning. And what keeps defining us right now. Thank you very much. We'll be around the conference and thanks for time