Artificial intelligence has been applied to various aspects of medicine, ranging from largely diagnostic applications in radiology and pathology to more therapeutic and interventional applications in cardiology and surgery. 

As the development and application of artificial intelligence technologies in medicine continue to grow, it is important for clinicians in every field to understand what these technologies are and how they can be leveraged to deliver safer, more efficient, and more cost-effective care. 

Anesthesiology is well-positioned to benefit from advances in artificial intelligence as it touches on multiple elements of clinical care, including perioperative and intensive care, pain management, and drug delivery and discovery. Researchers Daniel A. Hashimoto, M.D., M.S.; Elan Witkowski, M.D., M.P.H.; Lei Gao, M.D.; Ozanan Meireles, M.D.; and Guy Rosman, Ph.D., analyzed the impact of AI in anesthesiology. 

Traditional computer programs are programmed with explicit instructions to elicit certain behaviors from a machine based on specific inputs. Machine learning, on the other hand, allows programs to learn from and react to data without explicit programming. Data that can be analyzed through machine learning are broad and include, but are not limited to, numerical data, images, text, and speech or sound. 

AI applications 

There are several areas in which AI plays a significant role in anesthesiology. Some of them are mentioned below: 

• Depth of anesthesia monitoring: Machine learning approaches are well-suited to analyze complex data streams such as electroencephalographies; thus, a range of electroencephalography-based signals was found to have been investigated to measure the depth of anesthesia.  
• Control of anesthesia delivery: As automated delivery of anesthesia also requires a machine's determination of the depth of anesthesia, approaches to control require the measurement of clinical signs or surrogate markers of anesthetic depth. Thus, the evolution of control system research in anesthesia is evident in the various targets used to approximate the depth of anesthesia. 
• Event prediction: For perioperative care risk prediction, various techniques in machine learning, neural networks, and fuzzy logic have all been applied.
• Ultrasound guidance: In addition to specific structure detection in ultrasound images, researchers have also used neural networks to assist in identifying vertebral levels and other anatomical landmarks for epidural placement. 
• Pain management: Machine Learning can analyze differences in functional magnetic resonance imaging data collected from human volunteers exposed to painful and nonpainful thermal stimuli, demonstrating that machine learning analysis of whole brain scans could more accurately identify pain than analysis of individual brain regions traditionally associated with nociception. 
• Operating room logistics: Fuzzy logic and neural networks were used to optimize bed use for patients undergoing ophthalmologic surgery by modeling the type of case, modeling surgeon experience, staff experience, type of anesthesia and the experience of the anesthesiologist, patient factors, and comorbidities with error rates ranging from 14% to 19% depending on the type of case. 

Like a chess game! 

Advances in technology and monitoring can change the impetus for machine learning. For example, a neural network developed to detect oesophagal intubation from flow-loop parameters is obviated by continuous capnography. In this instance, a reliable clinical test has made what was once an insidious and devastating complication readily apparent.

The most exciting recent advance in machine learning has been the development of AlphaGo Zero, a system capable of learning how to play board games without human guidance, solely through self-play alone. It performs at a level superior to all previous algorithms and human players in chess, Go, and shogi. 

This learning approach requires that the system be able to play several lifetimes' worth of simulated games against itself. Although anesthesia simulators exist, they do not currently simulate patient physiology with the fidelity that a simulated chess game matches a real game. 

Future directions 

Maintaining a stable anesthetic is an excellent first application because the algorithms do not necessarily have to be able to render diagnoses but rather to detect if the patient has begun to drift outside the control parameters set by the anesthesiologist. 

A closed-loop control system need not necessarily have any learning capability itself. Still, it provides the means to collect a large amount of physiologic data from many patients with high fidelity, and this is an essential precursor for machine learning.