Clinical decision support tools are software that match the input characteristics of an individual patient to an established knowledge base to create patient-specific assessments that support and better inform individualized healthcare decisions. Clinical decision support tools can facilitate better evidence-based care and offer the potential for improved treatment quality and selection, shared decision making, while also standardizing patient expectations. Predict+ is a novel, clinical decision support tool that leverages clinical data from the Exactech Equinoxe shoulder clinical outcomes database, which is composed of >11,000 shoulder arthroplasty patients using one specific implant type from more than 30 different clinical sites using standardized forms. Predict+ utilizes multiple coordinated and locked supervised machine learning algorithms to make patient-specific predictions of 7 outcome measures at multiple postoperative timepoints (from 3 months to 7 years after surgery) using as few as 19 preoperative inputs. Predict+ algorithms predictive accuracy for the 7 clinical outcome measures for each of aTSA and rTSA were quantified using the mean absolute error and the area under the receiver operating curve (AUROC).Introduction
Methods
Determining proper joint tension in reverse total shoulder arthroplasty (rTSA) can be a challenging task for shoulder surgeons. Often, this is a subjective metric learned by feel during fellowship training with no real quantitative measures of what proper tension encompasses. Tension too high can potentially lead to scapular stress fractures and limitation of range of motion (ROM), whereas tension too low may lead to instability. New technologies that detect joint load intraoperatively create the opportunity to observe rTSA joint reaction forces in a clinical setting for the first time. The purpose of this study was to observe the differences in rTSA loads in cases that utilized two different humeral liner sizes. Ten different surgeons performed a total of 37 rTSA cases with the same implant system. During the procedure, each surgeon reconstructed the rTSA implants to his or her own preferred tension. A wireless load sensing humeral liner trial (VERASENSE for Equinoxe, OrthoSensor, Dania Beach, FL) was used in lieu of a traditional plastic humeral liner trial to provide real-time load data to the operating surgeon during the procedure. Two humeral liner trial sizes were offered in 38mm and 42mm curvatures and were selected each case based on surgeon preference. To ensure consistent measurements between surgeons, a standardized ROM assessment consisting of four dynamic maneuvers (maximum internal to external rotation at 0°, 45°, and 90° of abduction, and a maximum flexion/extension maneuver) and three static maneuvers (arm overhead, across the body, and behind the back) was completed in each case. Deidentified load data in lbf was collected and sorted based on which size liner was selected. Differences in means for minimum and maximum load values for the four dynamic maneuvers and differences in means for the three static maneuvers were calculated using 2-tailed unpaired t-tests.INTRODUCTION
METHODS
