This interview is part of our new AI in Healthcare series, where we interview the world's top thought leaders on the front lines of the intersections between AI and healthcare.
In this interview, we speak with Dekel Gelbman, CEO of FDNA, to understand how his company is using AI to transform healthcare, and what the future of the industry holds.
1. What’s the story behind FDNA? Why and how did you begin?
DG: Our story actually starts with Facebook almost 10 years ago. A different company founded by FDNA’s founders (face.com) had developed the best facial recognition technology in the world at that time and was sold to Facebook. After that success, we were looking for the next challenge, utilizing our expertise. We recognized that artificial intelligence can make a huge impact in healthcare. After a diligent exploration, we learned that there is an unmet need in the rare disease space, where almost 10% of the pediatric population is impacted. Specifically, that rare disease patients wait for 7.5 years on average to get diagnosed and that in most cases they bear very distinct facial appearances that can help diagnose them earlier. This “diagnostic odyssey” was impacting patients’ outcome severely. If patients were diagnosed earlier, they can benefit from better disease management and treatments.
We started in 2011 and quickly realized that the main challenges were around obtaining data, integrating into doctors’ workflow and protecting patients’ privacy. Since our beginning, FDNA has established itself as a global digital health leader in the space of clinical genomics. Our next-generation phenotyping (NGP) technologies are used by more than 70% of clinical geneticists across 2,000 clinical sites from 130 countries, to produce actionable genomic insights, creating a new standard of care.
2. Please describe your use case and how FDNA uses artificial intelligence:
DG: DeepGestalt, recently published in Nature Medicine, is the first next-generation phenotyping (NGP) technology we have developed. It analyzes facial photos of patients to produce a list of syndromes that are found to have similar facial characteristics with accuracies of above 90%. DeepGestalt currently supports more than 300 specific genetic syndromes and syndrome groups, representing 45% of cases solved by whole exome sequencing. Also, recently published in the Nature journal – Genetics in Medicine, the Prioritization of Exome Data by Image Analysis (PEDIA) study found that for these diseases, the causative variant is ranked as the top results in more than 90% of cases when NGP and genomic scores are combined. This is a unique example of how integrating NGP technologies like DeepGestalt in the variant analysis workflow dramatically increases diagnostic accuracy and efficiency.
FDNA's flagship product, Face2Gene, uses our NGP technologies to help clinicians, researchers and laboratories make better diagnoses of patients with rare diseases.
3. Could you share a specific customer/user that benefits from what you offer? What has FDNA done for them?
DG: A clinician uploads clinical data about their patients (such as facial photos, symptoms, clinical notes, etc.) into our cloud platform. Our system then uses AI to analyze these data in real time and return a list of the most relevant known genetic syndromes for review, together with complete medical resources to support the evaluation process.
A researcher could upload groups of patients into our system to learn what characterizes different diseases and sometimes to discover and describe a new disease and potentially recruit patients to clinical trials for a new drug.
A laboratory uses the data generated through our system to interpret the genetic results obtained from a genome sequence.
4. What other AI use cases in healthcare are you excited about?
DG: We believe that AI will be increasingly impactful for all practices that heavily rely on human interpretation of unstructured data, such as medical imaging. We are already seeing how AI is integrated and used by medical professionals to augment their analysis. With this trend continuing, we are excited about how Telemedicine and consumer applications can benefit from more efficient streamline of data that can impact better diagnoses.
In addition, we see a growing use of AI in research and in drug discovery. Analyzing large cohorts of data and identifying unique patterns that could lead to important scientific breakthroughs is one of the most exciting use cases of AI in healthcare and we believe that this will support the advancement of precision medicine in the next few years.
5. Where will FDNA be in 5 years?
DG: We strive to be in the forefront of science and technology. FDNA will continue to use AI to develop new NGP technologies that support clinicians, labs, and researchers. We've already seen the significant impact that results from incorporating phenotypic information in the variant analysis workflow, and we're working on developing solutions that go beyond the face to look at other biomarkers such as video, voice, and other medical images.
A lot will depend on the pace and direction the industry goes. We anticipate shifts in ownership of medical data, such that patients will be more in control of their data and will have more flexibility in driving their own health outcome. We think that technology companies will play a larger role in providing health-related services and collaborate closely with medical and life-science companies. And above all, we anticipate that genomics will be a standardized integral data in all health-related decisions. In that future, we believe our technology will impact a majority of people and contribute to better outcomes.