Background: The utilization of total ankle arthroplasty (TAA) for managing severe ankle osteoarthritis has become increasingly common, leading to a higher occurrence of revision TAA procedures because of failure of primary TAA. This study aims to examine the clinical results associated with revision TAA using the INBONE II system. Given the growing number of TAA revision procedures and a focus on motion-preserving salvage options, we evaluated our early experience with revision TAA. Methods: A retrospective analysis was conducted on a group of 60 presumed noninfected patients who underwent revision TAA with the INBONE II system. Detailed information was collected on patient demographics, implant characteristics, concurrent procedures, and complications. The implant survival was estimated using Kaplan-Meier analysis. Results: The study revealed high complication rates but generally fair clinical outcomes for revision TAA using the INBONE II system. Complications were observed in 22 patients (36.7%), including persistent pain (n = 6), nerve injury/impingement (n = 5), infection (n = 3), fracture (n = 3), implant failure (n = 3), impaired wound healing (n = 2), and osteolysis (n = 3). The 3-year survivorship rate from reoperation was 92.0% (82.7%-100.0%) whereas the 3-year survivorship rate from major complications was 90.4% (80.8%-100.0%). Conclusion: We report high complication rates but generally fair clinical results for revision TAA utilizing the INBONE II system.

Introduction: Launched in 2018 for revision total ankle arthroplasty (rTAA), the INVISION talar component addresses subsidence when poor talar bone stock is present. Due to the recency of the market-availability of the INVISION, studies evaluating its efficacy are lacking. This study presents the first analysis of early-term outcomes of patients undergoing rTAA with the INVISION talar component. Methods: This was a single-center, retrospective review of 28 patients undergoing rTAA with the INVISION talar component and INBONE II tibial component performed between 2018 and 2022. Data on preoperative characteristics, postoperative complications, secondary procedures, and survivorship were collected. The primary outcome measures were rates of major complications, re-operation, and implant failure. Secondary outcomes included post-operative changes in varus and valgus alignment of the tibia and talus. Results: The most common secondary procedures performed with rTAA were medial malleolus fixation (n = 22, 78.6%) and gastrocnemius recession (n = 14, 50%). Overall, 10.7% (n = 3) of patients underwent reoperation and 14.3% (n = 4) suffered major complications. Incidence of implant failure was 10.7% (n = 3). All reoperations were caused by infection. Mean varus alignment of the tibia and talus improved from 4.07 degrees and 4.83 degrees to 1.67 degrees and 1.23 degrees, respectively. Mean valgus alignment of the tibia and talus improved from 3.67 degrees and 4.22 degrees to 2.00 degrees and 2.32 degrees, respectively. Conclusions: In a series of 28 patients undergoing rTAA with the INVISION talar component, we discovered comparatively low rates of reoperation, major complication, and implant failure (10.7%, 14.3%, and 10.7%). The INVISION system appears to have a reasonable safety profile, but further studies evaluating long-term outcomes are required to assess the efficacy of the INVISION system.

Bundled payment models gained traction in recent years in total joint arthroplasty (TJA) as an alternative to fee-for-service models, aiming to reduce health-care spending by holding providers accountable for quality and costs. While they can enhance care, they may inadvertently exacerbate racial health-care disparities. This study assessed racial disparities in high-cost outlier patients enrolled in the TJA bundled payment model. A retrospective review included patients enrolled in a Medicare bundled payment plan for TJA from January 1, 2022, to June 30, 2023. High-cost outliers had total adjusted costs 5% or higher than the practice mean. Statistical analysis included Wilcoxon rank sum and Chi-square tests. One hundred seventy patients met the inclusion criteria: 74 underwent total hip arthroplasty and 96 underwent total knee arthroplasty. Of these, 34 identified as Black or African American, 133 as White, 2 as Other, and 1 as American Indian. The median adjusted cost for TJA for Black patients was $16,680 vs $15,720 for White non-Hispanic patients (P = .4). Black race was significantly associated with an increased emergency department return or hospital readmission (P = .013). Race was not associated with high-cost outliers but was linked to higher emergency department return and readmission rates. No significant difference in total adjusted cost was found between Black and White patients, though costs trended higher in the Black patients. Highlighting racial disparities in bundled payment models can help health-care stakeholders strive toward equity. Further research with larger populations is necessary to examine whether these models widen racial disparities in TJA.

Introduction Return-to-acute-care metrics, such as early emergency department (ED) visits, are key indicators of healthcare quality, with ED returns following surgery often considered avoidable and costly events. Proactively identifying patients at high risk of ED return can support quality improvement efforts, allowing interventions to target vulnerable patients. With its predictive capabilities, machine learning (ML) has shown potential in forecasting various clinical outcomes but remains underutilised in orthopaedic trauma. This study uses a random forest model to predict 90-day ED return in orthopaedic trauma patients, aiming to identify high-risk individuals and elucidate risk factors associated with returns. This study hypothesised that a highly accurate model could be developed to predict patients at high risk of ED return within 90 days of surgery. Purpose To develop and validate an ML model that predicts 90-day ED returns after orthopaedic trauma surgery using input data readily available in the electronic health record. Methods This is a retrospective model development and validation study. The study used data from a registry that includes information on all orthopaedic surgeries conducted at a level 1 academic medical centre. Patients who underwent orthopaedic trauma between 1 January 2017 and 1 March 2023 were identified using common procedural terminology code. The model used demographic, comorbid and perioperative variables. Return to the ED was captured as a binary outcome. Model performance was evaluated using the area under the receiver operator curve (AUROC). Results A total of 12 069 patients met the inclusion criteria. Patients were predominantly female (53%) and white (70%), with a median age of 55. The 90-day ED return rate was 14% (table 1). The random forest model identified body mass index, distance from the patient’s residence to the hospital, age, length of hospital stay and complexity of procedure (work relative value unit) as significant predictors of ED return, each accounting for greater than 10% of the total importance across all features in the model (table 2). Further, the model displayed strong discrimination of patients returning to the ED (AUROC=0.74) (figure 1). Conclusions The random forest model demonstrated predictive discrimination of 90-day ED returns. Critical predictors such as patient distance from the hospital suggest considering geographical and socioeconomic factors in postdischarge care planning. Operational factors such as length of stay or complexity of the procedure also predicted return to the ED. The study lays the groundwork for future predictive models in clinical decision-making and healthcare resource utilisation. Level of evidence Level III, retrospective model development and validation study.

Importance Sepsis accounts for a substantial portion of global deaths and healthcare costs. Early detection using machine learning (ML) models offers a critical opportunity to improve care and reduce the burden of sepsis. Objective To externally validate the SepsisWatch ML model, initially developed at Duke University, in a community healthcare and assess its performance and clinical utility in early sepsis detection. Design This retrospective external validation study evaluated the performance of the SepsisWatch model in a new environment. Data from patient encounters at Summa Health’s emergency departments between 2020 and 2021 were used. The study analyzed the model’s ability to predict sepsis using a combination of static and dynamic patient data. Setting The study was conducted at Summa Health, a nonprofit healthcare system in Northeast Ohio, covering two emergency departments (EDs) associated with acute care hospitals, and two standalone EDs. Participants Encounters associated with adult patients in any of Summa Health’s four EDs were included. Encounters lasting <1 hour were excluded. Only the first 36 hours of each encounter were used in model evaluation. Intervention(s)/Exposure(s) The SepsisWatch model was used to predict sepsis based on patient data. Main Outcome(s) and Measure(s) The primary outcomes measured were the model’s area under the precision-recall curve (AUPRC), and area under the receiver operator curve (AUROC). Results The study included 205,005 encounters from 101,584 unique patients. 54.7% (n = 112,223) patients were female and the mean age was 50 (IQR, [38,71]). The model demonstrated strong performance across the Summa Health system, with little variation across different sites. The AUROC ranged from 0.906 to 0.960, and the AUPRC ranged from 0.177 to 0.252 across the four sites. Conclusions and Relevance The external validation of the SepsisWatch model in a community health system setting confirmed its robust performance and portability across different geographical and demographic contexts. The study underscores the potential of advanced ML models in improving sepsis detection in both academic and community hospital settings, paving the way for prospective studies to measure the clinical and operational impact of such models in healthcare.