Over in China, one algorithm is predicting which patients will emerge from a coma more accurately than their human contemporaries.
In China, people doctors diagnosed a number of patients in a vegetative state as unlikely to ever wake up—but a second opinion from an algorithm said they would recover in less than a year.
In seven cases, the algorithm was right.
The AI algorithm in question analyses scans of a patient’s brains to gauge how blood flows to different areas of the brain, as well as information given by doctors like the patient’s age, how long they’ve lost consciousness, and the cause of the coma, et cetera.
When the patients’ families were told the algorithm’s scoring, the patients’ doctors said not to base their entire decision to continue life support on the algorithm’s assessment. That’s because the algorithm isn’t right every time. (For example, a 36-year-old man who was scored to not recover by both doctor and algorithm ended up making a full recovery within a year.) Plus, the algorithm can only predict what’s happening inside the patient’s brain, meaning it couldn’t account outside factors like, say, a disease caught from another patient in the hospital.
The algorithm was developed over the course of eight years, and trained on scans of 160 patients with consciousness disorders, meaning they were either in a vegetative state or not very conscious. The data analysed by the algorithm came from two medical hubs, which proved to have different kinds of patients. For instance, in one medical centre, there were more stroke patients, while the other had more patients in a coma from lack of oxygen.
Despite this, the algorithm was able to achieve 88% accuracy in prediction when tested on both data sets.