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 Jaroslav Blaha, co-founder of CellmatiQ 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 CellmatiQ? Why and how did you begin?
JB: Several engineers in our team have been working on AI for many years (myself since 1996). Yet, only a few years ago did the hardware enable production-level applications. At the end of 2017, we decided to step out of our enterprise-level jobs as corporate innovators in a US enterprise and begin to build an AI startup. We were then approached by physicians with a difficult problem in dental x-ray diagnostics, and they wondered whether we could automate (the problem).
We did, and during this explorative task, we recognized that there is a vast opportunity for AI-assisted image analysis across the entire medical profession. In February 2018, we founded CellmatiQ and began to establish our image analysis/diagnostics platform on which we develop, validate and deploy our AI modules.
2. Please describe your use case and how CellmatiQ uses AI:
JB: The first implemented and medically certified use case is the “Cephalometric Analysis”, in which an orthodontist must identify up to 42 intricate landmarks in a skull x-ray. Those landmarks are used to calculate angles and relations of jaws and teeth, which eventually are a contribution to the diagnosis and treatment (e.g. dental braces or oral surgery). This is a tedious and repetitive task, which takes roughly 10-15 minutes while being globally performed roughly 45 million times per year. We automate this in one second with our service “DentaliQ ortho”.
Based on the underlying platform and our AI technology (patent applied), we are developing further AI modules, e.g. for caries detection and classification in dentistry or early-stage glaucoma detection in ophthalmology.
3. Could you share a specific customer/user that benefits from what you offer? What has CellmatiQ done for them?
JB: All of our use cases aim to assist medical practitioners by replacing very narrow, but tedious, repetitive, or error-prone manual tasks related to images. In the case of “Cephalometric Analysis”, every dentist, orthodontist, or maxillo-facial surgeon across the globe can call our service through his/her web browser, upload an x-ray, and receive the resulting analysis report in real-time.
As another example, the early-stage glaucoma detection will allow insurers to equip their customers at risk (basically everybody above 40 years old, of which 3 percent will become sick) with a means to self-diagnose early onset and to stop the disease with little effort (typically eye drops) instead of battling with the tragedy and cost of blindness, which affects approximately ten percent of the patients.
4. What other use cases for AI in healthcare are you excited about?
JB: With the number of medical images increasing annually by roughly 10 percent on a global level, human radiologists of all kinds are becoming increasingly overwhelmed. AI will be able to assist in practically every image-based diagnostic procedure by offloading repetitive tasks to allow the doctor to focus on the patient and their specific case. Besides work in dentistry and ophthalmology, we are commencing expansion into the analysis of ECG recordings and cardio MRTs for early disease prediction.
5. Where will CellmatiQ be in five years?
JB: We follow a platform strategy, for which the foundation has been laid with our core technology and a bespoke diagnostic campaign management tool, with which we create AI training data of highest verified quality. Our medical partners are providing us with a plethora of useful use cases and associated data. In five years, we aim to have at least ten medically certified AI modules on the global market. To this end, we are in talks with strategic partners in healthcare to allow for a fast and wide scaling — to the benefit of physicians and their patients.