“Any sufficiently advanced technology is indistinguishable from magic.” - Arthur C. Clarke
The Healthcare industry, already the largest part of the U.S. economy, is expected to continue growing at a rate of approximately 5.8% per year (ref1). With this projected growth comes the need to balance the effectiveness of care with the corresponding healthcare costs. In the last couple of decades, the cost of healthcare in the United States has also continued to climb and today, access to healthcare in the U.S. is worse than in any other developed country in the world (ref2). Hospitals now face devastating financial challenges in light of the COVID-19 pandemic. The American Hospital Association (AHA) estimated a total economic impact of $202.6 billion in losses for America's hospitals and healthcare systems during the four months of March to June 2020, or an average of $50.7 billion per month. These issues, coupled with physician shortages and burnout, are forcing experts to find new solutions to provide accurate, accessible, and cost-effective healthcare options. For many, Artificial Intelligence provides the true answer to the problem.
The traditional approaches of Advanced Bronchoscopy were introduced with the first Electromagnetic Navigation System (ENB) over a decade ago. These are virtual-navigation solutions that are based on static preoperative CT images that neglect the true physiology of dynamic and flexible lungs. During a bronchoscopy, as has been shown in comprehensive clinical trials, patients’ lungs change shape and position from the shape and position that are captured by the preoperative CT. Moreover, atelectasis or partial lung collapse happens gradually during the procedure itself. These problems that are often referred to as “CT to Body divergence” can actually cause localization inaccuracy that is three times larger than the size of the lesion that has to be accessed for diagnosis. As a result, the diagnostic yield of these procedures remains relatively low and highly controversial according to different clinical studies (Ref5). “You’re essentially driving to where you think the small primary nodule is, but it’s not there anymore.” Dorian Averbuch, CEO of Body Vision Medical, explains.
At Body Vision Medical, we have pioneered the use of Artificial Intelligence in Navigation Bronchoscopy. Unlike traditional ENB approaches that bring more additional costly hardware and expensive disposables into the procedure room, the Body Vision technology limits the use of standard imaging equipment and disposable instruments and is heavily based on the power of data analysis. Through cutting-edge AI algorithms, we’ve enabled our system to understand data, learn from the data, and make decisions based on patterns hidden in the data that is otherwise impossible for humans to make themselves.
Body Vision technology integrates standard imaging modalities into fused interactive displays to create real-time guidance for existing tools towards suspicious lesions inside the lung. These tiny soft tissue lesions have historically been considered invisible during bronchoscopy, however, they are now revealed and reconstructed in 3D by Body Vision technology. Simply put, by means of Artificial Intelligence, the Body Vision Platform seamlessly integrates with existing equipment and tools in the procedure room to unlock underutilized imaging data and eliminates the need for electromagnetic sensors and expensive proprietary disposables.
Our approach allows physicians to navigate to complex areas of the bronchial tree and, for the first time ever, observe tool-in-lesion while performing a guided biopsy of the lesion in real-time. One of the additional “innovative features״ attributed to AI-powered technology is the ability to learn and improve over time while more data is collected. Because of this, Body Vision AI technology ensures robust and accurate guidance for the entire procedure with a 96.1% accuracy rate as confirmed by the CBCT (Ref3).
The Body Vision team is very aware of the economic constraints on the healthcare system so delivering superior clinical outcomes at a low operational cost has been a priority since the early days. Because we do not use ENB and our system is trained on where anatomical structures are without the need for sensors, we are able to reduce our overall costs. With an average operational savings of 50% per procedure compared to other navigation platforms on the market, we are able to meet the cost needs of patients and hospitals alike.
As a pioneer of Artificial Intelligence in the lung diagnostics space, we are committed to constantly improving the quality of our technology. Despite the uncertainties that the future holds—from physician shortages to decreased access to healthcare and rising costs—we believe that progress lies in our ability to provide more accurate, accessible, and cost-effective care, and, for us, that begins with Artificial Intelligence.
As Averbuch says, “Data-driven AI Navigation Bronchoscopy has the potential to transform lung cancer diagnostics and treatment and is the paradigm shift necessary to give patients hope and options.”