Nociception management is a fundamental part of general anesthesia. Despite noteworthy technological advancements, intraoperative analgesic delivery is still at the discretion of treating anesthesiologists. The dose of the analgesics is built on the judgment of the severity of nociception by the anesthesiologist, typically based on basic vital parameters. Here, the clinician must correlate the values of vital parameters to different physiological situations before making their logical connection to nociception which may result in apparent subjective variation with consequent over or under-antinociceptive treatment. Over the last decades, various objective nociception monitors have yet to be developed without appreciable global acceptance. Artificial intelligence, i.e., machine learning, has been increasingly integrated into medical equipment. These machine learning algorithms learn patients’ behavior and responses to the treatments and make suitable adjustments in the subsequent delivery of the therapy. The latest objective pain monitor incorporates supervised machine learning and deep learning (through the neural network) software, which identifies the severity of nociception based on pre-saved data and derives an Index. It further learns patients’ behavior in different situations, outlines a response profile specific to the patient, and then adjusts the index. With this monitor, intraoperative analgesic management has been optimized and offered to encourage intraoperative and postoperative conditions.
Bhavsar et al. (Mon,) studied this question.