Arvind V, London DA, Cirino C, et al. - This research was intended to evaluate which of 5 machine learning (ML) algorithms best predicts 30-day readmission, investigate select ML strategies to optimize the algorithms, and present on which patient variables contribute most to risk prediction in total shoulder arthroplasty (TSA) across algorithms. Between 2011 and 2015, researchers distinguished 9,043 individuals in the American College of Surgeons National Surgical Quality Improvement Database who had undergone primary TSA. For TSA, predictive analytics algorithms can achieve acceptable prognostication of unplanned readmission with the RF classifier outperforming other common algorithms.