This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA). Data for this study were collected from the National Surgery Quality Improvement Program (NSQIP) database from the year 2018. Patients who received a primary, elective, unilateral TKA with a diagnosis of primary osteoarthritis were included. Demographic, preoperative, and intraoperative variables were analyzed. The ANN model was compared to a logistic regression model, which is a conventional machine-learning algorithm. Variables collected from 28,742 patients were analyzed based on their contribution to hospital length of stay.Aims
Methods
A rotational limit for screw insertion may improve screw purchase and plate compression by reducing stripping, as compared to a torque based limit. Over-tightening screws results in inadvertent stripping of 20% of cortical bone screws. The current method of “two-fingers tight” to insert screws relies on the surgeon receiving torque feedback. Torque, however, can be affected by screw pitch, bone density and bone-thread friction. An alternative method of tightening screws is the “turn-of-the-nut” model, commonly used in engineering applications. In the “turn-of-the-nut” method, nuts used to fasten a joint are rotated a specific amount in order to achieve a pre-specified bolt tension. When applied to orthopaedics, bone assumes the role of the nut and the screw is the bolt. The screw is turned a set angular rotation that is independent of torque feedback. Potentially the “turn-of-the-nut” method provides an easier way of screw insertion that might lessen inadvertent screw stripping. The purpose of the current study was to use the “turn-of-the-nut” method to determine the angular rotation that results in peak plate compression and peak screw pullout force.Summary
Introduction
