Machine learning

A supercomputer at Beth Israel Deaconess Medical Center in Boston, Mass. can decipher when your days are numbered. Patients are hooked up to the machine which processes all their available data, such as doctors visits, lab results, medications and vital signs, then comes up with a rapid diagnostic assessment. With an expanding database of patient data, the supercomputer applies machine learning by comparing current scenarios with previous results from over 250,000 individuals in the last 30 years. The program can determine the likelihood of present and future medical problems such as heart attacks, infections, cancers and, even death. “We can predict with almost a 96 percent confidence that a patient will have this probability of dying, so if the computer says you are going to die, you probably will die within the next 30 days,” says Beth Israel Project Lead Dr. Steve Horng

Artificial intelligence

A "death predicting machine" again brings out concerns on the ethical and societal consequences of artificial intelligence, concerns raised in the past by personalities like Elon Musk and Stephen Hawking. Horng counters that the project's purpose is to leverage big data to augment doctors’ abilities. He said: “Our goal is not to replace the clinician; this artificial intelligence is really about the doctor’s ability to take care of patients.”


Share This Article