Modern medicine is aimed at preventing and foreseeing the development of serious life-threatening diseases. However, the strength and knowledge of a person is often not enough to predict certain complications. To help doctors in the future may come AI DeepMind from Google, which is currently learning to predict the death of people.
As often happens in such a situation, already known clinical cases were used for AI training. Developers from Google "fed" DeepMind data of almost 220 thousand adult patients treated in the period from 2009 to 2016. Information about the patients was provided by the medical center of the University of California at San Francisco and the Medical University of Chicago. In addition, the scientists used information obtained from the US Veterans Affairs Department, which gave access to data on 700,000 under the supervision of former military personnel. In total, more than 46 billion items on the most varied health indicators were added to the base. At the moment, the algorithm is aimed at finding such conditions as acute renal failure and pneumonia. These conditions were chosen not by chance, after all, according to the authors of the work,
"Acute renal failure or pneumonia can affect people of any age, and often they begin after routine procedures and operations. 11% of all deaths in the hospital are due to the deterioration of the patient's well-being, and changes in the patient's condition may not always be noticed at an early stage. "
Now the system is able to predict the probability of patient death within 24-48 hours, but the main goal of the project is to learn to predict death in the next 12 months. In addition, it is planned to expand data on deadly pathological conditions. Such use of artificial intelligence for medical purposes can be used not only to be ready for resuscitation, but also to prevent the development of severe conditions in patients.