Table 2.

Overview of papers about intraoperative phase included in our analysis

Author, years	Study design	Objective	Final cohort	Outcomes	Type of ML	Prediction performance
Ingrande J 2020	Prospective, single center	Modeling inductionphase kinetics using a high-resolution pharmacokinetic dataset	30	Drug concentrations	4-compartment model, recirculatory model, gated recurrent unit neural network	Direct comparison of observed versus predicted concentrations
Twinanda AP 2019	Retrospective, single center	Intraoperative accurate surgery duration estimation by using only visual information from laparoscopic videos	290	Remaining surgery duration estimation	Deep Learning- a convolutional neural network and a long-short term memory network	The proposed network significantly outperforms a traditional method of estimating surgery duration without utilizing manual annotation
Hashimoto DA 2019	Retrospective, single center	To identify operative steps in laparoscopic sleeve gastrectomy	88	Automatic extraction of quantitative surgical data from operative video of laparoscopic sleeve gastrectomy	Deep Learning	SleeveNet demonstrated a mean classification accuracy of 82% ± 4% with a minimum classification accuracy of 73% and a maximum classification accuracy of 85.6%