In a new study, a team of researchers from MIT and Massachusetts General Hospital shows that artificial intelligence can assess patient unconsciousness based on brain activity with high accuracy and reliability. That could help anesthesiologists optimize drug doses in the future.

"One of the things anesthesiologists are most concerned about is 'Is there someone in front of me who may be conscious and I don't realize it?' Being able to reliably maintain a patient's unconsciousness during surgery is fundamental to our work," the study authors write. The new algorithms not only provide a good indication of unconsciousness, they say, but also have the potential to allow anesthesiologists to maintain it at the desired level while using less medication. This can improve the patient's postoperative state, such as delirium.

In addition, the algorithms can be trained to be specifically suitable for use with children and seniors. Different types of drugs with different mechanisms of action can also be considered.