In all branches of medicine, there is an inevitable element of patient exposure to problems arising from human error. In fact, a report published in BMJ puts medical errors as the third leading cause of death in the US. With an increasing and aging global population, the demand for medical imaging services has been steadily outpacing the supply of radiologists, unfortunately increasing conditions of pressure and uncertainty. Wrong assessment of medical images increase healthcare costs, lower efficiency, and developing solutions that reduce the risk of human errors could be the difference between life and death.
The Israel-based startup Zebra Medical Vision is determined to provide a solutions to this global problem, and use advanced machine learning to assist radiologists in detecting often overlooked indications. They have developed algorithms that provide automated analysis of millions of real-time and retrospective imaging studies, allowing early identification of disease and offer preventative treatment pathways to improve patient care. Currently, the startup has developed algorithms in the fields of bone health, cardiovascular analysis, liver and lung indications, as well as an algorithm to detect internal brain bleeds.
In November, 2016 Zebra also announced they had developed an algorithm to identify early signs of breast cancer in mammograms, adding to the startup’s growing list of clinical algorithms. Later that month, they launched Profound, their web-based medical imaging analysis service, allowing anyone to upload their medical imaging scans and get automated analysis results within an hour. Currently, the service is able to highlight the presence of osteoporosis, compression fractures, fatty liver, coronary calcium, emphysema, and aortic aneurysms, with additional algorithms being added continuously.
Radiologists currently do not have the capability to fully analyze every imaging study, or search for every possible pathology. Zebra Medical Vision has developed an innovative technology that introduce automation to the process of reading and interpreting medical imaging data, allowing the identification of clinically relevant information that the patient not necessarily came in for. In addition, the technology could help increase access to efficient diagnostics in rural areas with limited number of medical professionals in niche fields.
It is important to highlight that the technology is not intended to replace radiologists, but help healthcare providers close the diagnostic gap created by an increasing world population. It will help radiologists prioritize cases, increase their throughput, while allowing early detection and treatment of some of the most debilitating and costly diseases. This means reducing the risk of human errors, increasing efficiency, improving treatment outcomes, while reducing overall healthcare costs.
Zebra Medical Vision was founded in 2014 by co-founders Eyal Toledano, Eyal Gura and Elad Benjamin, and the startup raised $8 million in 2015 led by Khosla Ventures, with participation from Deep Fork Capital and Marc Benioff. In 2016, they raised an additional $12 million in a round led by Intermountain Healthcare together with existing investors, as well as Dolby Family Ventures and Israeli crowdfunding business OurCrowd. Zebra has multiple strategic partnerships, including NTT DATA Services, formerly Dell Services, and has run pilots at Henry Ford Health System, Atlantic Health, Clalit Health System in Israel, and Assistance Publique in France, among others.