ABSTRACT
Anesthesiology is not the first medical specialty that comes to mind when one thinks of machine learning applications in healthcare because the use of images to detect pathology plays a much smaller role in this field than in other healthcare fields. However, machine learning encompasses far more than just image analysis. The ability of machine learning to use/develop algorithms, statistical models, regression, and/or pattern recognition has great applicability in the field of anesthesiology. Research has been performed on the use of machine learning techniques of gradient boosting and neural networks in order to predict a hypotensive or hypoxemic event before it occurs and during testing, and these machine learning models have provided excellent area under the curve values. Artificial intelligence has also been used to estimate the depth of anesthesia and predict mortality, again with high accuracy. These machine learning applications offer great utility in the field of anesthesiology because even though many of the anesthesiologists working in the operating room require fast recognition and response, if the anesthesiologist can be provided with an advanced warning, then he or she will have enough time to prepare and even take preventive measures. Machine learning has the potential to provide anesthesiologists with another set of eyes both in the operating room and outside the operating room.
