Bartek MA, Saxena RC, Solomon S, et al. - Statistical models were developed in a large retrospective data set so that estimation of case-time duration could be enhanced relative to current standards. Using linear regression and supervised machine learning, models to predict case-time duration were generated. For each of these models, an all-inclusive model, service-specific models, and surgeon-specific models were developed. Researchers developed individual models for each surgical service and surgeon, respectively, in the latter 2 approaches. Data from 46,986 scheduled operations performed at a large academic medical center from January 2014 to December 2017 were used; they used 80% for training and 20% for model testing/validation. The highest predictive capability was achieved with the machine learning algorithm. The surgeon-specific model vs the service-specific model had higher accuracy, a lower percentage of overage and underage, and a higher percentage of cases within the 10% threshold indicating the superiority of the former over the latter. Prediction of cases within 10% raised from 32% using the institutional standard to 39% with the machine learning surgeon-specific model.