Background: Artificial intelligence (AI) and machine learning (ML) modeling in hip and knee arthroplasty (total joint arthroplasty [TJA]) is becoming more commonplace. This systematic review aims to quantify the accuracy of current AI-and ML-based application for cognitive support and decision-making in TJA. Methods: A comprehensive search of publications was conducted through the EMBASE, Medline, and PubMed databases using relevant keywords to maximize the sensitivity of the search. No limits were placed on level of evidence or timing of the study. Findings were reported according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Analysis of variance testing with post-hoc Tukey test was applied to compare the area under the curve (AUC) of the models. Results: After application of inclusion and exclusion criteria, 49 studies were included in this review. The application of AI/ML-based models and average AUC is as follows: cost prediction-0.77, LOS and discharges-0.78, readmissions and reoperations-0.66, preoperative patient selection/planning-0.79, adverse events and other postoperative complications-0.84, postoperative pain-0.83, postoperative patient-reported outcomes measures and functional outcome-0.81. Significant variability in model AUC across the different decision support applications was found (P < .001) with the AUC for readmission and reoperation models being significantly lower than that of the other decision support categories. Conclusions: AI/ML-based applications in TJA continue to expand and have the potential to optimize patient selection and accurately predict postoperative outcomes, complications, and associated costs. On average, the AI/ML models performed best in predicting postoperative complications, pain, and patientreported outcomes and were less accurate in predicting hospital readmissions and reoperations.

Purpose Robotic-assisted total knee arthroplasty (RA-TKA) was introduced to improve limb alignment, component positioning, soft-tissue balance and to minimize surgical outliers. This study investigates perioperative outcomes, complications, and early patient-reported outcome measures (PROMs) of one imageless RA-TKA system compared to conventional method TKA (CM-TKA) at 24-month follow-up. Methods This multi-surgeon retrospective cohort analysis compared 111 imageless RA-TKA patients to 110 CM-TKA patients (n = 221). Basic demographic information, intraoperative and postoperative data, and PROMs, including the functional score of the Knee Society Score (KSS-FS), The Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC), and the Short Form 12 Mental and Physical scores (SF-12M and P), were collected and recorded preoperatively, at 3-, 12-and 24-months postoperatively. Range of motion (ROM), estimated blood loss (EBL), surgical duration, and complications were also collected. Results There were no baseline patient demographic diferences between groups. EBL (240 vs. 190 mL, p < 0.001) and surgical duration (123 vs. 107 min, p < 0.001) were signiicantly greater in RA-TKA. There were no signiicant diferences in postoperative complications, ROM, length of stay (LOS), and PROMs between cohorts at 3-, 12-, 24-months postoperatively. Conclusions Imageless RA-TKA is associated with greater EBL and surgical duration compared to CM-TKA. However, at 24-month follow-up, there were no signiicant diferences in ROM, LOS, complications and PROMs between cohorts. Imageless robotic surgery leads to similar 24-month clinical outcomes as compared to CM-TKA. Level of evidence IIIKeywords Total knee arthroplasty • Robotic-assisted total knee arthroplasty • Imageless robotic TKA • Patient-reported outcome measures • Complications

Background: The Fragility Index (FI) and Reverse Fragility Index are powerful tools to supplement the P value in evaluation of randomized clinical trial (RCT) outcomes. These metrics are defined as the number of patients needed to change the significance level of an outcome. The purpose of this study was to calculate these metrics for published RCTs in total joint arthroplasty (TJA). Methods: We performed a systematic review of RCTs in TJA over the last decade. For each study, we calculated the FI (for statistically significant outcomes) or Reverse Fragility Index (for nonstatistically significant outcomes) for all dichotomous, categorical outcomes. We also used the Pearson correlation coefficient to evaluate publication-level variables. Results: We included 104 studies with 473 outcomes; 92 were significant, and 381 were nonstatistically significant. The median FI was 6 overall and 4 and 7 for significant and nonsignificant outcomes, respectively. There was a positive correlation between FI and sample size (R ¼ 0.14, P ¼ .002) and between FI and P values (R ¼ 0.197, P ¼ .000012). Conclusions: This study is the largest evaluation of FI in orthopedics literature to date. We found a median FI that was comparable to or higher than FIs calculated in other orthopedic subspecialties. Although the mean and median FIs were greater than the 2 recommended by the American Academy of Orthopaedic Surgeons Clinical Practice Guidelines to demonstrate strong evidence, a large percentage of studies have an FI < 2. This suggests that the TJA literature is on par or slightly better than other subspecialties, but improvements must be made. Level of Evidence: Level I; Systematic Review.

Background: Robot-assisted surgery was developed to improve accuracy and outcomes in total knee arthroplasty (TKA). One important determinant of TKA success is a well-balanced knee throughout the range of motion. The purpose of this study is to determine if robot-assisted TKA (RA-TKA) results in improved intracompartmental ligament balance compared with conventional jig-based instrumentation (CM-TKA). Methods: This retrospective cohort study included 2 cohortsda CM-TKA (n ¼ 49) vs RA-TKA (n ¼ 37) cohort. Demographic and intraoperative data, including intraoperative compartment loads, were measured after final implant implantation in extension (10 ), mid-flexion (45 ), and full flexion (90 ), using an intraoperative compartment pressure sensor. An a priori power analysis revealed our study exhibited >80% power in detecting a 5-pound (lb) difference in compartment loads in the 2 cohorts. Results: There was no difference between medial and lateral compartment loads in extension, midflexion, and full flexion for the conventional (15.1 lbs, 15.9 lbs, and 13.4 lbs, respectively) vs RA-TKA (14.2 lbs, 15.1 lbs, and 10.3 lbs, respectively). The percentage of patients with high load compartment pressure in flexion (>40 lbs) by the conclusion of the surgery was significantly greater for the conventional (18%) vs the robotic TKA cohort (3%, P ¼ .025). The percentage of patients with unbalanced knees (>20 lbs differential between medial and lateral compartments) in flexion was significantly greater in the conventional (24%) vs robotic TKA cohort (5%, P ¼ .018). Conclusions: In this series, RA-TKA resulted in improved intraoperative compartment balancing in flexion with no observed difference in mid-flexion and extension compared with CM-TKA.