Machine Learning in the ICU

Blood testing
You might say that a serious illness, as those that go to an ICU, is a kind of math problem. At least that’s how researchers at Princeton University approached diagnosing kidney failure and sepsis. With a data training set from 6,060 ICU patients, 2001-2012, the group studied lactate, creatinine, blood urea nitrogen and white blood cell levels. Then, “[the] team’s algorithm uses a “reward function” that encourages a test order based on how informative the test is at a given time. In other words, there is greater reward in giving a patient a test if there is a higher probability that the patient’s state is significantly different from the previous measurement.” This reduced the number of tests that needed to be done, but more importantly, it cut four hours off the time from admission to actual treatment. MORE
Image Credit: Pixabay