Results of bibliometric analysis and a detailed review are reported on the use of supervised machine learning to study hazardous drilling events. The bibliometric analysis attempts to answer pertinent questions related to progress in the use of supervised machine learning for hazardous events due to drilling fluid density/mud weight. The analysis indicates artificial neural network as the most popular algorithm among researchers. Also, deep learning, random forest and support vector machine have gained momentum in recent use. A critical review of literature on hazardous events and supervised machine learning algorithms are reported. This review was done to observe how the algorithms were used, their relative successes, limitations, as well as input parameters which aided in detection or estimation by the machine learning algorithms. An introduction to deep learning and a review of literature on the use of deep learning with respect to operations involving drilling parameters is presented. The review on deep learning and drilling parameters covered the following operations: lithology identification, drilling rig state determination, generating logging/other drilling parameters and detecting abnormality in data. The study highlights need of publicly accessible large database with data from different oilfields for development of machine learning algorithms. These algorithms could be used globally for the enhancement of machine learning for new fields or fields with limited data. The availability of such large database would aid researchers in improving or customizing deep learning algorithms in line with the unique needs of drilling activities. (C) 2020 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.