Anaesthesia Monitoring using Artificial Intelligence Techniques

Abstract

Artificial Intelligence (AI) will change our lives beyond recognition, it will have a far bigger impact than the internet or mobile technology. We are now at the threshold where machine intelligence is comparable with human intelligence, in certain limited aspects, for the first time in history. Enhancements in technology, both software and hardware, have resulted in some human decision-making being inferior to, and more erratic than, AI in many fields, including medicine. However, it is widely accepted that rather than compete with machines, using AI to support and help make better informed decisions is the key to future medicine. In areas like anaesthesia, AI can be used to develop useful advanced clinical decision support tools based on machine learning.

Artificial intelligence in anesthesiology

“…Bickford introduced the first automated anesthesia system using EEG signals in 1950 5 . It automatically delivered barbiturate and ether anesthesia in a rabbit, cat, monkey and man 6 . Over half a century later, McSleepy, an invention of the McGill University in Montréal, Quebec, Canada, was introduced with a similar feedback control system 6 .…”

“…It automatically delivered barbiturate and ether anesthesia in a rabbit, cat, monkey and man 6 . Over half a century later, McSleepy, an invention of the McGill University in Montréal, Quebec, Canada, was introduced with a similar feedback control system 6 . AI, however, is much more than solely a closed-loop feedback mechanism 6 , which we will explain further on.…”

“…This technique allows results obtained with neural networks in various fields. Artificial neural network architectures rely on neural layers, imitating the human brain 6 . In contrast to shallow neural networks, deep neural networks consist of more than two layers and are further divided by their architecture into recurrent neural networks (RNN) 7 , convolutional neural networks (CNN), and many more.…”

“…are built. Data protection issues play a major role in this context 6 . Better, more comprehensive and easily accessible datasets are prerequisites for AI applications to become clinically meaningful 9 .…”