Remote Summer Research Program to Improve Opportunity and Mentorship for Underrepresented Students With Interest in Orthopaedic Surgery: 3-Year Experiences.

INTRODUCTION: Medical students are challenged with a limited number of research opportunities to help prepare for an exceptionally competitive process for matching in an orthopaedic residency. The aim of this study was to assess the 3-year experience of our 8 to 10-week remote summer research program in support of underrepresented students with an interest in orthopaedic surgery. METHODS: We received over 500 applications, and a total of 37 students (7.4%) participated in the program over the past 3 years. A total of 14 faculty mentors were matched with 1 or 2 students each. The research program delivered a curriculum including (1) research-related topics led by a content expert; (2) weekly faculty lectures discussing topics including orthopaedic conditions, diversity in orthopaedics, leadership, and work-life balance; and (3) a minimum of 8 weeks of mentorship experience with an assigned faculty and a peer mentor. Students and faculty were surveyed to measure skill progression, research productivity, and program satisfaction. RESULTS: Program participants represented a range of race/ethnic backgrounds and research experience levels. The cohort included a high rate of female (51%) and Black (35%) participants relative to representation of these groups in orthopaedic surgery. Postprogram surveys indicated that all participants improved their research skills, orthopaedic interest, and mentorship/networking skills. Most students (89%) stated that they were adequately matched to their faculty mentor. Most students (79%) indicated that they contributed to either manuscript or conference abstract as coauthors. DISCUSSION: The study findings suggest improved research skills, interest, and confidence to pursue orthopaedic residency and mentorship/networks in the field. Our long-term vision is to improve the accessibility and quality of mentorship for underrepresented students to foster an equitable pathway into the field of orthopaedic surgery.

The Use of Artificial Intelligence for the Prediction of Periprosthetic Joint Infection Following Aseptic Revision Total Knee Arthroplasty.

Periprosthetic joint infection (PJI) following revision total knee arthroplasty (TKA) for aseptic failure is associated with poor outcomes, patient morbidity, and high health care expenditures. The aim of this study was to develop novel machine learning algorithms for the prediction of PJI following revision TKA for patients with aseptic indications for revision surgery. A single-institution database consisting of 1,432 consecutive revision TKA patients with aseptic etiologies was retrospectively identified. The patient cohort included 208 patients (14.5%) who underwent re-revision surgery for PJI. Three machine learning algorithms (artificial neural networks, support vector machines, k-nearest neighbors) were developed to predict this outcome and these models were assessed by discrimination, calibration, and decision curve analysis. This is a retrospective study. Among the three machine learning models, the neural network model achieved the best performance across discrimination (area under the receiver operating characteristic curve = 0.78), calibration, and decision curve analysis. The strongest predictors for PJI following revision TKA for aseptic reasons were prior open procedure prior to revision surgery, drug abuse, obesity, and diabetes. This study utilized machine learning as a tool for the prediction of PJI following revision TKA for aseptic failure with excellent performance. The validated machine learning models can aid surgeons in patient-specific risk stratifying to assist in preoperative counseling and clinical decision making for patients undergoing aseptic revision TKA.

Introduction of a Novel Sequential Approach to the Ponte Osteotomy to Minimize Spinal Canal Exposure.

Ponte osteotomy is an increasingly popular technique for multiplanar correction of adolescent idiopathic scoliosis. Prior cadaveric studies have suggested that sequential posterior spinal releases increase spinal flexibility. Here we introduce a novel technique involving a sequential approach to the Ponte osteotomy that minimizes spinal canal exposure. One fresh-frozen adult human cadaveric thoracic spine specimen with 4 cm of ribs was divided into three sections (T1-T5, T6-T9, T10-L1) and mounted for biomechanical testing. Each segment was loaded with five Newton meters under four conditions: baseline inferior facetectomy with supra/interspinous ligament release, superior articular process (SAP) osteotomy in situ, spinous process (SP) osteotomy in situ, and complete posterior column osteotomy with SP/SAP excision and ligamentum flavum release (PCO). Compared to baseline, in situ SAP osteotomy alone provided 3.5%, 7.6%, and 7.2% increase in flexion/extension, lateral bending, and axial rotation, respectively. In situ SP osteotomy increased flexion/extension, lateral bending, and axial rotation by 15%, 18%, and 10.3%, respectively. PCO increased flexion/extension, lateral bending, and axial rotation by 19.6%, 28.3%, and 12.2%, respectively. Our report introduces a novel approach where incremental increases in range of motion can be achieved with minimal spinal canal exposure and demonstrates feasibility in a cadaveric model.

The Use of Artificial Neural Networks for the Prediction of Surgical Site Infection Following TKA.

This is a retrospective study. Surgical site infection (SSI) is associated with adverse postoperative outcomes following total knee arthroplasty (TKA). However, accurately predicting SSI remains a clinical challenge due to the multitude of patient and surgical factors associated with SSI. This study aimed to develop and validate machine learning models for the prediction of SSI following primary TKA. This is a retrospective study for patients who underwent primary TKA. Chart review was performed to identify patients with superficial or deep SSIs, defined in concordance with the criteria of the Musculoskeletal Infection Society. All patients had a minimum follow-up of 2 years (range: 2.1-4.7 years). Five machine learning algorithms were developed to predict this outcome, and model assessment was performed by discrimination, calibration, and decision curve analysis. A total of 10,021 consecutive primary TKA patients was included in this study. At an average follow-up of 2.8 ± 1.1 years, SSIs were reported in 404 (4.0%) TKA patients, including 223 superficial SSIs and 181 deep SSIs. The neural network model achieved the best performance across discrimination (area under the receiver operating characteristic curve = 0.84), calibration, and decision curve analysis. The strongest predictors of the occurrence of SSI following primary TKA, in order, were Charlson comorbidity index, obesity (BMI >30 kg/m2), and smoking. The neural network model presented in this study represents an accurate method to predict patient-specific superficial and deep SSIs following primary TKA, which may be employed to assist in clinical decision-making to optimize outcomes in at-risk patients.

Impact of Preoperative Opioid Use on Patient-Reported Outcomes after Revision Total Knee Arthroplasty: A Propensity Matched Analysis.

This is a retrospective study. Prior studies have characterized the deleterious effects of narcotic use in patients undergoing primary total knee arthroplasty (TKA). While there is an increasing revision arthroplasty burden, data on the effect of narcotic use in the revision surgery setting remain limited. Our aim was to characterize the effect of active narcotic use at the time of revision TKA on patient-reported outcome measures (PROMs). A total of 330 consecutive patients who underwent revision TKA and completed both pre- and postoperative PROMs was identified. Due to differences in baseline characteristics, 99 opioid users were matched to 198 nonusers using the nearest-neighbor propensity score matching. Pre- and postoperative knee disability and osteoarthritis outcome score physical function (KOOS-PS), patient reported outcomes measurement information system short form (PROMIS SF) physical, PROMIS SF mental, and physical SF 10A scores were evaluated. Opioid use was identified by the medication reconciliation on the day of surgery. Propensity score-matched opioid users had significantly lower preoperative PROMs than the nonuser for KOOS-PS (45.2 vs. 53.8, p < 0.01), PROMIS SF physical (37.2 vs. 42.5, p < 0.01), PROMIS SF mental (44.2 vs. 51.3, p < 0.01), and physical SF 10A (34.1 vs. 36.8, p < 0.01). Postoperatively, opioid-users demonstrated significantly lower scores across all PROMs: KOOS-PS (59.2 vs. 67.2, p < 0.001), PROMIS SF physical (43.2 vs. 52.4, p < 0.001), PROMIS SF mental (47.5 vs. 58.9, p < 0.001), and physical SF 10A (40.5 vs. 49.4, p < 0.001). Propensity score-matched opioid-users demonstrated a significantly smaller absolute increase in scores for PROMIS SF Physical (p = 0.03) and Physical SF 10A (p < 0.01), as well as an increased hospital length of stay (p = 0.04). Patients who are actively taking opioids at the time of revision TKA report significantly lower preoperative and postoperative outcome scores. These patients are more likely to have longer hospital stays. The apparent negative effect on patient reported outcomes after revision TKA provides clinically useful data for surgeons in engaging patients in a preoperative counseling regarding narcotic use prior to revision TKA to optimize outcomes.

Can machine learning models predict failure of revision total hip arthroplasty?

INTRODUCTION: Revision total hip arthroplasty (THA) represents a technically demanding surgical procedure which is associated with significant morbidity and mortality. Understanding risk factors for failure of revision THA is of clinical importance to identify at-risk patients. This study aimed to develop and validate novel machine learning algorithms for the prediction of re-revision surgery for patients following revision total hip arthroplasty. METHODS: A total of 2588 consecutive patients that underwent revision THA was evaluated, including 408 patients (15.7%) with confirmed re-revision THA. Electronic patient records were manually reviewed to identify patient demographics, implant characteristics and surgical variables that may be associated with re-revision THA. Machine learning algorithms were developed to predict re-revision THA and these models were assessed by discrimination, calibration and decision curve analysis. RESULTS: The strongest predictors for re-revision THA as predicted by the four validated machine learning models were the American Society of Anaesthesiology score, obesity (> 35 kg/m2) and indication for revision THA. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.80), calibration and decision curve analysis. Higher net benefits for all machine learning models were demonstrated, when compared to the default strategies of changing management for all patients or no patients. CONCLUSION: This study developed four machine learning models for the prediction of re-revision surgery for patients following revision total hip arthroplasty. The study findings show excellent model performance, highlighting the potential of these computational models to assist in preoperative patient optimization and counselling to improve revision THA patient outcomes. LEVEL OF EVIDENCE: Level III, case-control retrospective analysis.

Complete blood platelet and lymphocyte ratios increase diagnostic accuracy of periprosthetic joint infection following total hip arthroplasty.

INTRODUCTION: Systemically, changes in serum platelet to lymphocyte ratio (PLR), platelet count to mean platelet volume ratio (PVR), neutrophil to lymphocyte ratio (NLR) and monocyte to lymphocyte (MLR) represent primary responses to early inflammation and infection. This study aimed to determine whether PLR, PVR, NLR, and MLR can be useful in diagnosing periprosthetic joint infection (PJI) in total hip arthroplasty (THA) patients. METHODS: A total of 464 patients that underwent revision THA with calculable PLR, PVR, NLR, and MLR in 2 groups was evaluated: 1) 191 patients with a pre-operative diagnosis of PJI, and 2) 273 matched patients treated for revision THA for aseptic complications. RESULTS: The sensitivity and specificity of PLR combined with erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), synovial white blood cell count (WBC) and synovial polymorphonuclear leukocytes (PMN) (97.9%; 98.5%) is significantly higher than only ESR combined with CRP, synovial WBC and synovial PMN (94.2%; 94.5%; p < 0.01). The sensitivity and specificity of PVR combined with ESR, CRP and synovial WBC, and synovial PMN (98.4%; 98.2%) is higher than only ESR combined with CRP, synovial WBC and synovial PMN (94.2%; 94.5%; p < 0.01). CONCLUSION: The study results demonstrate that both PLR and PVR calculated from complete blood counts when combined with serum and synovial fluid markers have increased diagnostic sensitivity and specificity in diagnosing periprosthetic joint infection in THA patients. LEVEL OF EVIDENCE: III, case-control retrospective analysis.

The utility of machine learning algorithms for the prediction of patient-reported outcome measures following primary hip and knee total joint arthroplasty.

BACKGROUND: Patient-reported outcome measures (PROMs) are increasingly used as quality benchmark in total hip and knee arthroplasty (THA; TKA) due to bundled payment systems that aim to provide a patient-centered, value-based treatment approach. However, there is a paucity of predictive tools for postoperative PROMs. Therefore, this study aimed to develop and validate machine learning models for the prediction of numerous patient-reported outcome measures following primary hip and knee total joint arthroplasty. METHODS: A total of 4526 consecutive patients (2137 THA; 2389 TKA) who underwent primary hip and knee total joint arthroplasty and completed both pre- and postoperative PROM scores was evaluated in this study. The following PROM scores were included for analysis: HOOS-PS, KOOS-PS, Physical Function SF10A, PROMIS SF Physical and PROMIS SF Mental. Patient charts were manually reviewed to identify patient demographics and surgical variables associated with postoperative PROM scores. Four machine learning algorithms were developed to predict postoperative PROMs following hip and knee total joint arthroplasty. Model assessment was performed through discrimination, calibration and decision curve analysis. RESULTS: The factors most significantly associated with the prediction of postoperative PROMs include preoperative PROM scores, Charlson Comorbidity Index, American Society of Anaesthesiology score, insurance status, age, length of hospital stay, body mass index and ethnicity. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.83), calibration and decision curve analysis. CONCLUSION: This study developed machine learning models for the prediction of patient-reported outcome measures at 1-year following primary hip and knee total joint arthroplasty. The study findings show excellent performance on discrimination, calibration and decision curve analysis for all four machine learning models, highlighting the potential of these models in clinical practice to inform patients prior to surgery regarding their expectations of postoperative functional outcomes following primary hip and knee total joint arthroplasty. LEVEL OF EVIDENCE: Level III, case control retrospective analysis.

Artificial neural networks for the prediction of transfusion rates in primary total hip arthroplasty.

BACKGROUND: Despite advancements in total hip arthroplasty (THA) and the increased utilization of tranexamic acid, acute blood loss anemia necessitating allogeneic blood transfusion persists as a post-operative complication. The prevalence of allogeneic blood transfusion in primary THA has been reported to be as high as 9%. Therefore, this study aimed to develop and validate novel machine learning models for the prediction of transfusion rates following primary total hip arthroplasty. METHODS: A total of 7265 consecutive patients who underwent primary total hip arthroplasty were evaluated using a single tertiary referral institution database. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with transfusion rates. Four state-of-the-art machine learning algorithms were developed to predict transfusion rates following primary THA, and these models were assessed by discrimination, calibration, and decision curve analysis. RESULTS: The factors most significantly associated with transfusion rates include tranexamic acid usage, bleeding disorders, and pre-operative hematocrit (< 33%). The four machine learning models all achieved excellent performance across discrimination (AUC > 0.78), calibration, and decision curve analysis. CONCLUSION: This study developed machine learning models for the prediction of patient-specific transfusion rates following primary total hip arthroplasty. The results represent a novel application of machine learning, and has the potential to improve outcomes and pre-operative planning. LEVEL OF EVIDENCE: III, case-control retrospective analysis.

Elevated ESR and CRP Prior to Second-Stage Reimplantation Knee Revision Surgery for Periprosthetic Joint Infection Are Associated with Increased Reinfection Rates.

Although two-stage revision surgery is considered as the most effective treatment for managing chronic periprosthetic joint infection (PJI), there is no current consensus on the predictors of optimal timing to second-stage reimplantation. This study aimed to compare clinical outcomes between patients with elevated erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP) prior to second-stage reimplantation and those with normalized ESR and CRP prior to second-stage reimplantation. We retrospectively reviewed 198 patients treated with two-stage revision total knee arthroplasty for chronic PJI. Cohorts included patients with: (1) normal level of serum ESR and CRP (n = 96) and (2) elevated level of serum ESR and CRP prior to second-stage reimplantation (n = 102). Outcomes including reinfection rates and readmission rates were compared between both cohorts. At a mean follow-up of 4.4 years (2.8-6.5 years), the elevated ESR and CRP cohort demonstrated significantly higher reinfection rates compared with patients with normalized ESR and CRP prior to second-stage reimplantation (33.3% vs. 14.5%, p < 0.01). Patients with both elevated ESR and CRP demonstrated significantly higher reinfection rates, when compared with patients with elevated ESR and normalized CRP (33.3% vs. 27.6%, p = 0.02) as well as normalized ESR and elevated CRP (33.3% vs. 26.3%, p < 0.01). This study demonstrates that elevated serum ESR and/or CRP levels prior to reimplantation in two-stage knee revision surgery for chronic PJI are associated with increased reinfection rate after surgery. Elevation of both ESR and CRP were associated with a higher risk of reinfection compared with elevation of either ESR or CRP, suggesting the potential benefits of normalizing ESR and CRP prior to reimplantation in treatment of chronic PJI.

The Same Day Discharges following Primary Total Knee Arthroplasty: A Single Surgeon, Propensity Score-Matched Cohort Analysis.

This is a retrospective study. As new surgical techniques and improved perioperative care approaches have become available, the same-day discharge in selected total knee arthroplasty (TKA) patients was introduced to decrease health care costs without compromising outcomes. This study aimed to compare clinical and functional outcomes between same-day discharge TKA patients and inpatient-discharge TKA patients. A retrospective review of 100 consecutive patients with same-day discharge matched to a cohort of 300 patients with inpatient discharge that underwent TKA by a single surgeon at a tertiary referral center was conducted. Propensity-score matching was performed to adjust for baseline differences in preoperative patient demographics, medical comorbidities, and patient-reported outcome measures (PROMs) between both cohorts. All patients had a minimum of 1-year follow-up (range: 1.2-2.8 years). In terms of clinical outcomes for the propensity score-matched cohorts, there was no significant difference in terms of revision rates (1.0 vs. 1.3%, p = 0.76), 90-day emergency department visits (3.0 vs. 3.3%, p = 0.35), 30-day readmission rates (1.0 vs. 1.3%, p = 0.45), and 90-day readmission rates (3.0 vs. 3.6%, p = 0.69). Patients with same-day discharge demonstrated significantly higher postoperative PROM scores, at both 3-month and 1-year follow-up, for PROMIS-10 Physical Score (50 vs. 46, p = 0.028), PROMIS-10 Mental Score (56 vs. 53, p = 0.039), and Physical SF10A (57 vs. 52, p = 0.013). This study showed that patients with same-day discharge had similar clinical outcomes and superior functional outcomes, when compared with patients that had a standard inpatient protocol. This suggests that same-day discharge following TKA may be a safe, viable option in selected total knee joint arthroplasty patients.

The utilization of artificial neural networks for the prediction of 90-day unplanned readmissions following total knee arthroplasty.

BACKGROUND: A reliable predictive tool to predict unplanned readmissions has the potential to lower readmission rates through targeted pre-operative counseling and intervention with respect to modifiable risk factors. This study aimed to develop and internally validate machine learning models for the prediction of 90-day unplanned readmissions following total knee arthroplasty. METHODS: A total of 10,021 consecutive patients underwent total knee arthroplasty. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with 90-day unplanned hospital readmissions. Four machine learning algorithms (artificial neural networks, support vector machine, k-nearest neighbor, and elastic-net penalized logistic regression) were developed to predict 90-day unplanned readmissions following total knee arthroplasty and these models were evaluated using ROC AUC statistics as well as calibration and decision curve analysis. RESULTS: Within the study cohort, 644 patients (6.4%) were readmitted within 90 days. The factors most significantly associated with 90-day unplanned hospital readmissions included drug abuse, surgical operative time, and American Society of Anaesthesiologist Physical Status (ASA) score. The machine learning models all achieved excellent performance across discrimination (AUC > 0.82), calibration, and decision curve analysis. CONCLUSION: This study developed four machine learning models for the prediction of 90-day unplanned hospital readmissions in patients following total knee arthroplasty. The strongest predictors for unplanned hospital readmissions were drug abuse, surgical operative time, and ASA score. The study findings show excellent model performance across all four models, highlighting the potential of these models for the identification of high-risk patients prior to surgery for whom coordinated care efforts may decrease the risk of subsequent hospital readmission. LEVEL OF EVIDENCE: Level III, case-control retrospective analysis.

Predicting surgical operative time in primary total knee arthroplasty utilizing machine learning models.

BACKGROUND: Prolonged surgical operative time is associated with postoperative adverse outcomes following total knee arthroplasty (TKA). Increasing operating room efficiency necessitates the accurate prediction of surgical operative time for each patient. One potential way to increase the accuracy of predictions is to use advanced predictive analytics, such as machine learning. The aim of this study is to use machine learning to develop an accurate predictive model for surgical operative time for patients undergoing primary total knee arthroplasty. METHODS: A retrospective chart review of electronic medical records was conducted to identify patients who underwent primary total knee arthroplasty at a tertiary referral center. Three machine learning algorithms were developed to predict surgical operative time and were assessed by discrimination, calibration and decision curve analysis. Specifically, we used: (1) Artificial Neural Networks (ANNs), (2) Random Forest (RF), and (3) K-Nearest Neighbor (KNN). RESULTS: We analyzed the surgical operative time for 10,021 consecutive patients who underwent primary total knee arthroplasty. The neural network model achieved the best performance across discrimination (AUC = 0.82), calibration and decision curve analysis for predicting surgical operative time. Based on this algorithm, younger age (< 45 years), tranexamic acid non-usage, and a high BMI (> 40 kg/m2) were the strongest predictors associated with surgical operative time. CONCLUSIONS: This study shows excellent performance of machine learning models for predicting surgical operative time in primary total knee arthroplasty. The accurate estimation of surgical duration is important in enhancing OR efficiency and identifying patients at risk for prolonged surgical operative time. LEVEL OF EVIDENCE: Level III, case control retrospective analysis.

Biceps Tenodesis cannot be used as primary treatment option in baseball pitchers with intact rotator cuff muscles.

Background Surgeons remain hesitant to perform biceps tenodesis in athletes with type II superior labrum anterior-to-posterior tears due to the lack of reported clinical outcomes for individual overhead throwing sports and associated concerns that this may predispose the joint to instability. This study aimed to assess the effect of biceps tenodesis on shoulder stability for major overhead throwing sports to aid sport-specific surgical decision-making for athletes with type II superior labrum anterior-to-posterior tears. METHODS: This is a combined modelling and experimental study. Motion data and external forces were measured from 13 participants performing five overhead throwing motions. These data served as input into a musculoskeletal shoulder model that quantifies shoulder stability and muscle loading. FINDINGS: The loading of the long head of the biceps brachii decreases significantly following biceps tenodesis in three overhead throwing motions (p = 0.02). The loss in joint stability following biceps tenodesis is compensated by a non-significant increase in rotator cuff muscle force which maintains shoulder stability across all overhead throwing motions, except baseball pitching (p = 0.01). The presence of a full-thickness supraspinatus tear post biceps tenodesis further decreases shoulder stability in four of the five overhead throwing motions (p = 0.01). INTERPRETATION: The study findings demonstrate that an increase in rotator cuff muscle force maintains joint stability for all overhead throwing motions post biceps tenodesis, except baseball pitching. As the presence of a full-thickness tear of the supraspinatus significantly reduces joint stability, biceps tenodesis may be used as a primary treatment in overhead throwing athletes with intact rotator cuff muscles, except baseball pitchers. LEVEL OF EVIDENCE: Controlled Laboratory Study; Level of Evidence 3.

Outcome of Two-Stage Revision Total Hip and Knee Arthroplasty as a Salvage Procedure for Deep Infection of Peri-Articular Fracture Fixation: Propensity Score-Matched Study.

Background: Failed open reduction internal fixation (ORIF) of peri-articular fractures due to deep infection is associated with decreased functional outcomes and increased mortality rates. Two-stage revision total joint arthroplasty (TJA) is often needed as a salvage procedure. The aim of this study was to evaluate the outcome of two-stage revision total hip and knee arthroplasty as a salvage procedure for the treatment of deep infection of peri-articular fracture fixation. Methods: Using propensity score-matching, a total of 120 patients was evaluated: 1) 40 consecutive patients were treated with planned salvage two-stage revision for the treatment of deep peri-articular infection, and 2) a control group of 80 patients who underwent two-stage revision for periprosthetic joint infection (PJI) after non-IF TJA. An infection occurred after a fracture of the acetabulum (27.5%), femoral neck (22.5%), intertrochanteric femur (15.0%), subtrochanteric femur (5.0%), femoral shaft (7.5%), distal femur (5.0%), and tibia (15.0%). Results: At an average follow up of 4.5 years (range, 1.0-25.8), the overall failure rate was 42.5% for the IF group compared to 21.3% for the non-ORIF group (P=0.03). There was a significantly higher reinfection rate for the IF group compared to the non-IF group (35.0% vs. 11.3%, p=0.005). Tissue cultures for the IF patients demonstrated significantly higher polymicrobial growth (30.0% vs. 11.3%, P=0.01) and methicillin-resistant Staphylococcus aureus (20.0% vs. 7.5%, P=0.04). Conclusion: Salvage two-stage revision arthroplasty for infected IF of peri-articular fractures was associated with poor outcome. The overall post-operative complications after salvage two-stage revision for infected IF of peri-articular fractures was high with 35% reinfection rates associated with the presence of mixed and resistant pathogens.

Insurance Payer Type Affects Outcomes after Revision Total Joint Arthroplasty: A Matched Cohort Analysis.

Background: The aim of this study is to evaluate the potential effects of insurance payer type on the postoperative outcomes following revision TJA. Methods: A single-institution database was utilized to identify 4,302 consecutive revision THA and TKA. Patient demographics and indications for revision were collected and compared based on patient insurance payer type: (1) Medicaid, (2) Medicare, and (3) private. Propensity score matching and, subsequent, multivariate regression analyses were applied to control for baseline differences between payer groups. Outcomes of interest were rates of complications occurring perioperatively and 90 days post-discharge. Results: After propensity-score-based matching, a total of 2,328 patients remained for further multivariate regression analyses (300 [12.9%] Medicaid, 1022 [43.9%] Medicare, 1006 [43.2%] private). Compared to privately insured patients, Medicaid and Medicare patients had 71% (P<0.01) and 53% (P=0.03) increased odds, respectively, for developing an in-hospital complication. At 90 days post-discharge, compared to privately insured patients, Medicaid and Medicare patients had 88% and 43% odds, respectively, for developing overall major complications. Conclusion: Our propensity-score-matched cohort study found that, compared to privately insured patients, patients with government-sponsored insurance were at an increased risk for developing both major or minor complications perioperatively and at 90-days post-discharge for revision TJA. This suggests that insurance payer type is an independent risk factor for poor outcomes following revision TJA.

Artificial Neural Networks Can Predict Early Failure of Cementless Total Hip Arthroplasty in Patients With Osteoporosis.

BACKGROUND: Total hip arthroplasty (THA) done in the aging population is associated with osteoporosis-related complications. The altered bone density in osteoporotic patients is a risk factor for revision surgery. This study aimed to develop and validate machine learning (ML) models to predict revision surgery in patients with osteoporosis after primary noncemented THA. METHODS: We retrospectively reviewed a consecutive series of 350 patients with osteoporosis (T-score less than or equal to -2.5) who underwent primary noncemented THA at a tertiary referral center. All patients had a minimum 2-year follow-up (range: 2.1 to 5.6). Four ML algorithms were developed to predict the probability of revision surgery, and these were assessed by discrimination, calibration, and decision curve analysis. RESULTS: The overall incidence of revision surgery was 5.2% at a mean follow-up of 3.7 years after primary noncemented THA in osteoporotic patients. Revision THA was done because of periprosthetic fracture in nine patients (50%), aseptic loosening/subsidence in five patients (28%), periprosthetic joint infection in two patients (11%) and dislocation in two patients (11%). The strongest predictors for revision surgery in patients after primary noncemented THA were female sex, BMI (>35 kg/m2), age (>70 years), American Society of Anesthesiology score (≥3), and T-score. All four ML models demonstrated good model performance across discrimination (AUC range: 0.78 to 0.81), calibration, and decision curve analysis. CONCLUSION: The ML models presented in this study demonstrated high accuracy for the prediction of revision surgery in osteoporotic patients after primary noncemented THA. The presented ML models have the potential to be used by orthopaedic surgeons for preoperative patient counseling and optimization to improve the outcomes of primary noncemented THA in osteoporotic patients.

The Ability of Deep Learning Models to Identify Total Hip and Knee Arthroplasty Implant Design From Plain Radiographs.

INTRODUCTION: The surgical management of patients with failed total hip or knee arthroplasty (THA and TKA) necessitates the identification of the implant manufacturer and model. Failure to accurately identify implant design leads to delays in care, increased morbidity, and healthcare costs. The automated identification of implant designs has the potential to assist in the surgical management of patients with failed arthroplasty. This study aimed to develop and validate a convolutional neural network deep learning model for the identification of primary and revision hip and knee total joint arthroplasty designs from plain radiographs. METHODS: This study trained a convolutional neural network deep learning model to automatically identify 24 THA designs and 14 TKA designs from 11,204 anterior-posterior radiographs obtained from 8,763 patients. From these radiographs, 8,963 radiographs (80%) were used for model training and 2,241 radiographs (20%) were used for model validation. Model performance was assessed through receiver operating curve characteristics. RESULTS: After 1,000 training epochs by the convolutional neural network deep learning model, the computational model discriminated 17 primary THA designs with an area under the receiver operating curve (AUC) of 0.98, sensitivity of 95.8%, and specificity of 98.6%. The deep learning model discriminated eight primary TKA designs with an AUC of 0.97, sensitivity of 94.9%, and specificity of 97.8%. The deep learning model demonstrated an AUC of 0.98 and 0.96 for the identification of seven revision THA and six revision TKA designs, respectively. DISCUSSION: This study developed and validated a convolutional neural network deep learning model for the identification of hip and knee total joint arthroplasty designs from plain radiographs. The study findings demonstrate excellent accuracy of the deep learning model for the identification of 24 THA and 14 TKA designs, illustrating the great potential of the deep learning model to assist in preoperative surgical planning of failed arthroplasty patients.

Metal Articulations as a Source of Total Hip Arthroplasty Pain.

The consensus systematic risk stratification algorithm from the American Association of Hip and Knee Surgeons, the American Academy of Orthopaedic Surgeons, and The Hip Society summarizes clinical challenges in evaluation and treatment of metal-on-polyethylene total hip arthroplasty (THA) patients with adverse local tissue reaction (ALTR) due to mechanically assisted crevice corrosion (MACC), reviews up-to-date evidence, and identifies the areas for future research in order to provide a useful resource for orthopedic surgeons providing care to these patients. A painful THA has various intrinsic and extrinsic causes. ALTR is one of the intrinsic causes in patients with painful THA. The occurrence of ALTR due to MACC at modular junctions is likely to be multifactorial, including implant, surgical, and patient factors. Therefore, a systematic evaluation needs to involve a focused clinical history, detailed physical examination, laboratory tests, and imaging in order to identify potential differential diagnoses. There should be a low threshold to perform a systematic evaluation of patients with painful non-metal-on-metal THA, including patients with metal-on-polyethylene THA, and modular dual-mobility THA with the CoCr metal acetabular insert, as early recognition and diagnosis of ALTR due to MACC will facilitate initiation of appropriate treatment prior to significant adverse biological reactions. Specialized tests such as blood metal analysis and metal artifact reduction sequence magnetic resonance imaging are important modalities in evaluation and management of ALTR in patients with painful THA.

The Utility of Machine Learning Algorithms for the Prediction of Early Revision Surgery After Primary Total Hip Arthroplasty.

BACKGROUND: Revision total hip arthroplasty (THA) is associated with increased morbidity, mortality, and healthcare costs due to a technically more demanding surgical procedure when compared with primary THA. Therefore, a better understanding of risk factors for early revision THA is essential to develop strategies for mitigating the risk of patients undergoing early revision. This study aimed to develop and validate novel machine learning (ML) models for the prediction of early revision after primary THA. METHODS: A total of 7,397 consecutive patients who underwent primary THA were evaluated, including 566 patients (6.6%) with confirmed early revision THA (<2 years from index THA). Electronic patient records were manually reviewed to identify patient demographics, implant characteristics, and surgical variables that may be associated with early revision THA. Six ML algorithms were developed to predict early revision THA, and these models were assessed by discrimination, calibration, and decision curve analysis. RESULTS: The strongest predictors for early revision after primary THA were Charlson Comorbidity Index, body mass index >35 kg/m2, and depression. The six ML models all achieved excellent performance across discrimination (area under the curve >0.80), calibration, and decision curve analysis. CONCLUSION: This study developed ML models for the prediction of early revision surgery for patients after primary THA. The study findings show excellent performance on discrimination, calibration, and decision curve analysis for all six candidate models, highlighting the potential of these models to assist in clinical practice patient-specific preoperative quantification of increased risk of early revision THA.