Breast cancer affects 6,000 women a year in Czech Republic. It is the most common cancer in women in its incidence is constantly increasing. The only way to save their lives today is regular mammography screening. But most women wait a long time for it, the results are obtained under great pressure and need to be verified.
To make doctors' jobs easier and give women fast and accurate information about their condition, Trask, one of the leading IT providers in CEE region, decided to involve artificial intelligence in the process.
At Trask, we are sensitive to what's going on around us and try to react in a timely manner. Back in the first wave of the pandemic, we came up with the idea of using AI to diagnose coronavirus quickly and accurately. The solution was initially offered to doctors from the Covid Department of the Prague’s University Hospital Bulovka. However, they agreed that our years of experience with digitalization would be more useful in the field of mammography as around 2,000 women succumb to breast cancer every year. Early diagnosis saves up to 90% of patients. However, most women wait a very long time for a mammogram, sometimes up to six months. In addition, the results themselves are produced under considerable time pressure and must be checked repeatedly by two radiologists. The complexity of the whole process puts a strain on the work of doctors and the lives of patients.
A doctor's personality is irreplaceable in any treatment, but when combined with AI, it creates a compact and highly efficient team. Artificial intelligence speeds up the entire diagnostic process significantly, while at the same time it can identify findings that the human eye cannot see. For example, it can detect tiny calcium deposits tens of millimeters in size that form in the very early stages of a tumor.
The solution was developed by Trask's Data Science department and has been tested on millions of mammography images. As it turned out, the test was successful. Mammographic output can now be evaluated automatically, very accurately, and in a matter of seconds. The initial R&D stage resulted in launch of Pledio medical platform, that on top of the breast cancer diagnosis aggregates AI models for other diseases in form of open marketplace. Pledio thus offers accessible opportunity for AI scientists from the best research labs worldwide to roll-out their models directly to hospitals and make significant impact on the health. For hospitals on the other hand, thanks to Trask’s proven ability of large-scale integration projects, it offers quick and easy ability to extend the AI-supported diagnosis into new medical disciplines. Entire team of Pledio is working on making the impact significant – more accurate diagnosis available in shorter time to broader global audience of patients. Last but not least – for lower costs.
Daniela Kuklova, head of Pledio