Algorithms improve hospitals' management of transfusions and help reduce blood waste. Not only is the algorithm informed by historical data, but by integrating the hospital's electronic health records, it is also able to adjust its predictions in real-time.


- Blood has a very limited time that it can be held. In Poland, it is 42 days. Until now, there have been no advanced statistical tools to predict how the blood will be distributed and how it should be ordered each day. This is provided by artificial intelligence, machine learning, i.e., statistical models that allow us to predict the future, find correlations in historical data on how blood was used in a given blood bank, and thus predict how best to approach today's stock,' explains to the Newseria Innowacje news agency Mateusz Pawełczuk, co-founder of AIDA Diagnostics.


The AIDA Blood system developed by the Poles, using artificial intelligence and machine learning mechanisms, allows for the management of blood resources and their processing. Although the transfusion of blood components - blood cells, platelets, and plasma - is itself a very common procedure, it is not always easy for doctors to decide whether a blood transfusion is really necessary. The system, thanks to artificial intelligence, supports the medics' decisions. What's more, the hybrid system uses neural networks to accurately determine how much blood to use for each patient and predict hospital demand.


An artificial intelligence-based module helps calculate how much blood to transfuse is needed for a given patient. By collecting all the necessary information, the system can optimize supply and at the same time minimize the number of transfusions, which is in the interest of patients.