Exposure to Extended Reality and Artificial Intelligence-Based Manifestations: A Primer on the Future of Hip and Knee Arthroplasty.

BACKGROUND: Software-infused services, from robot-assisted and wearable technologies to artificial intelligence (AI)-laden analytics, continue to augment clinical orthopaedics - namely hip and knee arthroplasty. Extended reality (XR) tools, which encompass augmented reality, virtual reality, and mixed reality technology, represent a new frontier for expanding surgical horizons to maximize technical education, expertise, and execution. The purpose of this review is to critically detail and evaluate the recent developments surrounding XR in the field of hip and knee arthroplasty and to address potential future applications as they relate to AI. METHODS: In this narrative review surrounding XR, we discuss (1) definitions, (2) techniques, (3) studies, (4) current applications, and (5) future directions. We highlight XR subsets (augmented reality, virtual reality, and mixed reality) as they relate to AI in the increasingly digitized ecosystem within hip and knee arthroplasty. RESULTS: A narrative review of the XR orthopaedic ecosystem with respect to XR developments is summarized with specific emphasis on hip and knee arthroplasty. The XR as a tool for education, preoperative planning, and surgical execution is discussed with future applications dependent upon AI to potentially obviate the need for robotic assistance and preoperative advanced imaging without sacrificing accuracy. CONCLUSION: In a field where exposure is critical to clinical success, XR represents a novel stand-alone software-infused service that optimizes technical education, execution, and expertise but necessitates integration with AI and previously validated software solutions to offer opportunities that improve surgical precision with or without the use of robotics and computed tomography-based imaging.

Artificial Intelligence for Automated Implant Identification in Knee Arthroplasty: A Multicenter External Validation Study Exceeding 3.5 Million Plain Radiographs.

BACKGROUND: Surgical management of complications following knee arthroplasty demands accurate and timely identification of implant manufacturer and model. Automated image processing using deep machine learning has been previously developed and internally validated; however, external validation is essential prior to scaling clinical implementation for generalizability. METHODS: We trained, validated, and externally tested a deep learning system to classify knee arthroplasty systems as one of the 9 models from 4 manufacturers derived from 4,724 original, retrospectively collected anteroposterior plain knee radiographs across 3 academic referral centers. From these radiographs, 3,568 were used for training, 412 for validation, and 744 for external testing. Augmentation was applied to the training set (n = 3,568,000) to increase model robustness. Performance was determined by the area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. The training and testing sets were drawn from statistically different populations of implants (P < .001). RESULTS: After 1,000 training epochs by the deep learning system, the system discriminated 9 implant models with a mean area under the receiver operating characteristic curve of 0.989, accuracy of 97.4%, sensitivity of 89.2%, and specificity of 99.0% in the external testing dataset of 744 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image. CONCLUSION: An artificial intelligence-based software for identifying knee arthroplasty implants demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents a responsible and meaningful clinical application of artificial intelligence with immediate potential to globally scale and assist in preoperative planning prior to revision knee arthroplasty.

Modern Hip Arthroscopy for FAIS May Delay the Natural History of Osteoarthritis in 25% of Patients: A 12-Year Follow-up Analysis.

BACKGROUND: Little is known about the effect of modern hip arthroscopy on the natural history of femoroacetabular impingement syndrome (FAIS) with respect to joint preservation. PURPOSE: To (1) characterize the natural history of FAIS and (2) understand the effect of modern hip arthroscopy by radiographically comparing the hips of patients who underwent only unilateral primary hip arthroscopy with a minimum follow-up of 10 years. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: Between 2010 and 2012, 619 consecutive patients were reviewed from the practice of a single fellowship-trained hip arthroscopic surgeon. Inclusion criteria were FAIS, bilateral radiographic findings of femoroacetabular impingement, primary unilateral hip arthroscopy (labral repair, femoroplasty, or capsular closure), and minimum 10-year follow-up. The preoperative and minimum 10-year postoperative radiographs of patients were evaluated at each time point. Both operative and nonoperative hips were graded using the Tönnis classification or the presence of hip arthroplasty by 2 independent reviewers. Subgroup analyses were performed. RESULTS: A total of 200 hips from 100 patients were evaluated at a mean follow-up of 12.0 years. Preoperatively, 98% and 99% of operative and nonoperative hips were evaluated as Tönnis grades 0 and 1, respectively; 5% of nonoperative hips had worse Tönnis grades than operative hips. The nonoperative hip advanced to a worse Tönnis grade in 48% (48/100) of cases compared with 28% (28/100) among operative hips. At follow-up, Tönnis grades between hips were equal in 70% (70/100) of the cases, the operative hip had a better grade 25% (25/100) of the time, and the nonoperative hip had a better grade 5% (5/100) of the time. Modern hip arthroscopy was associated with a relative risk reduction of 42% in osteoarthritis progression. Impingement with borderline dysplasia, age, preoperative Tönnis grade, and alpha angle >65° were key risk factors in the radiographic progression of osteoarthritis. CONCLUSION: Although the majority of patients (70%) undergoing hip arthroscopy for FAIS did not experience differences between operative and nonoperative hips in terms of the radiographic progression of osteoarthritis, the natural history may be favorably altered for 25% of patients whose Tönnis grade was better after undergoing arthroscopic correction. Modern hip arthroscopy indications and techniques represent a valid joint-preservation procedure conferring a relative risk reduction of 42% in the progression of osteoarthritis. Arthroscopy for mixed patterns of impingement and instability were the fastest to degenerate.

Socioeconomic disadvantage is correlated with worse PROMIS outcomes following lumbar fusion.

BACKGROUND CONTEXT: Socioeconomic status (SES) has been associated with differential healthcare outcomes and may be proxied using the area-deprivation index (ADI). Few studies to date have investigated the role of ADI on patient-reported outcomes and clinically meaningful improvement following lumbar spine fusion surgery. PURPOSE: The purpose of this study is to investigate the role of SES on lumbar fusion outcomes using Patient-Reported Outcomes Measurement Information System (PROMIS) surveys. STUDY DESIGN/SETTING: Retrospective review of a single institution cohort. PATIENT SAMPLE: About 205 patients who underwent elective one-to-three level posterior lumbar spine fusion. OUTCOME MEASURES: Change in PROMIS scores and achievement of minimum clinically important difference (MCID). METHODS: Patients 18 years or older undergoing elective one-to-three level lumbar spine fusion secondary to spinal degeneration from January 2015 to September 2021 with minimum one year follow-up were reviewed. ADI was calculated using patient-supplied addresses and patients were grouped into quartiles. Higher ADI values represent worse deprivation. Minimum clinically important difference (MCID) thresholds were calculated using distribution-based methods. Analysis of variance testing was used to assess differences within and between the quartile cohorts. Multivariable regression was used to identify features associated with the achievement of MCID. RESULTS: About 205 patients met inclusion and exclusion criteria. The average age of our cohort was 66±12 years. The average time to final follow-up was 23±8 months (range 12-36 months). No differences were observed between preoperative baseline scores amongst the four quartiles. All ADI cohorts showed significant improvement for pain interference (PI) at final follow-up (p<.05), with patients who had the lowest socioeconomic status having the lowest absolute improvement from preoperative baseline physical function (PF) and PI (p=.01). Only those patients who were in the lowest socioeconomic quartile failed to significantly improve for PF at final follow-up (p=.19). There was a significant negative correlation between socioeconomic level and the absolute proportion of patients reaching MCID for PI (p=.04) and PF (p=.03). However, while ADI was a significant predictor of achieving MCID for PI (p=.02), it was nonsignificant for achieving MCID for PF. CONCLUSIONS: Our study investigated the influence of ADI on postoperative PROMIS scores and identified a negative correlation between ADI quartile and the proportion of patients reaching MCID. Patients in the worse ADI quartile had lower chances of reaching clinically meaningful improvement in PI. Policies focused on alleviating geographical deprivation may augment clinical outcomes following lumbar surgery.

Clinical Improvement After Lumbar Fusion: Using PROMIS to Assess Recovery Kinetics.

STUDY DESIGN: Retrospective review of a single institution cohort. OBJECTIVE: The goal of this study is to identify features that predict delayed achievement of minimum clinically important difference (MCID) following elective lumbar spine fusion using Patient-Reported Outcomes Measurement Information System (PROMIS) surveys. SUMMARY OF BACKGROUND DATA: Preoperative prediction of delayed recovery following lumbar spine fusion surgery is challenging. While many studies have examined factors impacting the achievement of MCID for patient-reported outcomes in similar cohorts, few studies have assessed predictors of early functional improvement. METHODS: We retrospectively reviewed patients undergoing elective one-level posterior lumbar fusion for degenerative pathology. Patients were subdivided into two groups based on achievement of MCID for each respective PROMIS domain either before six months ("early responders") or after six months ("late responders") following surgical intervention. Multivariable logistic regression analysis was used to determine features associated with odds of achieving distribution-based MCID before or after six months follow up. RESULTS: 147 patients were included. The average age was 64.3±13.0 years. At final follow-up, 57.1% of patients attained MCID for PI and 72.8% for PF. However, 42 patients (49.4%) reached MCID for PI by six months, compared to 44 patients (41.1%) for PF. Patients with severe symptoms had the highest probability of attaining MCID for PI (OR 10.3; P =0.001) and PF (OR 10.4; P =0.001) Preoperative PROMIS symptomology did not predict early achievement of MCID for PI or PF. Patients who received concomitant iliac crest autograft during their lumbar fusion had increased odds of achieving MCID for PI (OR 8.56; P =0.001) before six months. CONCLUSION: Our study demonstrated that the majority of patients achieved MCID following elective one-level lumbar spine fusion at long-term follow-up, although less than half achieved this clinical benchmark for each PROMIS metric by six months. We also found that preoperative impairment was not associated with when patients would achieve MCID. Further prospective investigations are warranted to characterize the trajectory of clinical improvement and identify the risk factors associated with poor outcomes more accurately.

Depression State Correlates with Functional Recovery Following Elective Lumbar Spine Fusion.

OBJECTIVE: To determine how depression state impacts postoperative Patient-Reported Outcomes Measurement Information System (PROMIS) scores and achievement of minimum clinically important difference (MCID) following lumbar fusion. Depression has been shown to negatively impact outcomes following numerous orthopedic surgeries. Situational and major clinical depression can differentially affect postoperative outcomes. METHODS: Adult patients undergoing elective 1-3 level lumbar fusion were reviewed. Patients with a formal diagnosis of major depression were classified as "clinically depressed" whereas patients with at least "mild" PROMIS Depression scores in the absence of formal depression diagnosis were deemed "situationally depressed." analysis of variance testing was used to assess differences within and between groups. Multivariate regression was used to identify features associated with the achievement of MCID. RESULTS: Two hundred patients were included. The average age was 65.9 ± 12.2 years. 75 patients (37.5%) were nondepressed, 66 patients (33.0%) were clinically depressed, and 59 patients (29.5%) were situationally depressed. Situationally depressed patients had worse preoperative physical function (PF) and pain interference (PI) scores and were more likely to have severe symptoms (P = 0.001, P = 0.001). All groups improved significantly from preoperative baseline scores. All groups met MCID PF at different rates, with highest proportion of situationally depressed reaching this metric (P = 0.03). Rates of achieving MCID PI were not significantly different between groups (P = 0.47). Situational depression was predictive of achieving MCID PF (P = 0.002) but not MCID PI. CONCLUSIONS: Our study investigated the relationship between depression and postoperative PROMIS scores and identified situationally depressed patients as having the worst preoperative impairment. Despite this, the situationally depressed cohort had the highest likelihood of achieving MCID PF, suggestive of a bidirectional relationship between lumbar degenerative disease and subclinical, situational depression. These findings may help guide preoperative counseling on expectations, and patient selection.

Arthroscopic subacromial decompression improved outcomes in situationally depressed patients compared to clinically depressed or nondepressed patients.

Background: The purpose of this study is to evaluate patient reported outcomes after arthroscopic extensive débridement of the shoulder with subacromial decompression (SAD) for subacromial impingement using the Patient-Reported Outcomes Measurement Information System (PROMIS) system and evaluate if depression (Dep) (clinical or situational) impacts patients achieving a Minimal Clinically Important Difference (MCID). Methods: Preoperative PROMIS Physical function (PF), Mood, and Dep scores were obtained at the closest date prior to arthroscopic rotator cuff repair and postoperative scores were collected at every clinical visit thereafter. Final PROMIS score used for data analysis was determined by the patients final PROMIS value between 90 to 180 days. Clinical Dep was determined by patients having a formal diagnosis of "Depression or Major Depressive Disorder" at the time of their surgery. Situationally depressed patients, those without a formal diagnosis yet exhibited symptomatic depressive symptoms, were classified by having a PROMIS-Dep cutoff scores larger than 52.5. Results: A total of 136 patients were included for final statistical analysis. 13 patients had a clinical but not situational diagnosis of Dep, 86 patients were identified who had no instance of clinical or situational Dep (nondepressed). 35 patients were situationally depressed. All three cohorts demonstrated a significant improvement in postoperative PROMIS Dep, PI, and PF score relative to their preoperative value (P = .001). Situationally depressed patients achieved greater delta PROMIS-Dep compared to patients with major depressive disorder. Depressed patients had a higher chance of achieving MCID for PROMIS-Dep compared to nondepressed patients (P = .01). Logistic regression analysis demonstrated that underlying Dep did not alter the odds of obtaining MCID compared to nondepressed patients. Nonsmoking patients had significantly greater odds of achieving MCID for PF (P = .02). Discussion: Patients improved after undergoing SAD regardless of underlying Dep or depressive symptoms. Depressed patients exhibited greater change in PROMIS scores compared to nondepressed patients. Smoking remains a risk factor for postoperative outcomes in patients undergoing SAD for subacromial impingement. Identifying and counseling patients with underlying depressive symptoms without a formal major depressive disorder diagnosis may lead to improved outcomes. These findings may help guide clinicians in deciding who would benefit the most from this procedure.

Comparable performance of machine learning algorithms in predicting readmission and complications following total joint arthroplasty with external validation.

BACKGROUND: The purpose of the study was to use Machine Learning (ML) to construct a risk calculator for patients who undergo Total Joint Arthroplasty (TJA) on the basis of New York State Statewide Planning and Research Cooperative System (SPARCS) data and externally validate the calculator on a single TJA center. METHODS: Seven ML algorithms, i.e., logistic regression, adaptive boosting, gradient boosting (Xg Boost), random forest (RF) classifier, support vector machine, and single and a five-layered neural network were trained on the derivation cohort. Models were trained on 68% of data, validated on 15%, tested on 15%, and externally validated on 2% of the data from a single arthroplasty center. RESULTS: Validation of the models showed that the RF classifier performed best in terms of 30-d mortality AUROC (Area Under the Receiver Operating Characteristic) 0.78, 30-d readmission (AUROC 0.61) and 90-d composite complications (AUROC 0.73) amongst the test set. Additionally, Xg Boost was found to be the best predicting model for 90-d readmission and 90-d composite complications (AUC 0.73). External validation demonstrated that models achieved similar AUROCs to the test set although variation occurred in top model performance for 90-d composite complications and readmissions between our test and external validation set. CONCLUSION: This was the first study to investigate the use of ML to create a predictive risk calculator from state-wide data and then externally validate it with data from a single arthroplasty center. Discrimination between best performing ML models and between the test set and the external validation set are comparable. LEVEL OF EVIDENCE: III.

Increased Neighborhood Deprivation Is Associated with Prolonged Hospital Stays After Surgical Fixation of Traumatic Pelvic Ring Injuries.

BACKGROUND: The purpose of this study was to understand the role of social determinants of health assessed by the Area Deprivation Index (ADI) on hospital length of stay and discharge destination following surgical fixation of pelvic ring fractures. METHODS: A retrospective chart analysis was performed for all patients who presented to our level-I trauma center with pelvic ring injuries that were treated with surgical fixation. Social determinants of health were determined via use of the ADI, a comprehensive metric of socioeconomic status, education, income, employment, and housing quality. ADI values range from 0 to 100 and are normalized to a U.S. mean of 50, with higher scores representing greater social deprivation. We stratified our cohort into 4 ADI quartiles. Statistical analysis was performed on the bottom (25th percentile and below, least deprived) and top (75th percentile and above, most deprived) ADI quartiles. Significance was set at p < 0.05. RESULTS: There were 134 patients who met the inclusion criteria. Patients in the most deprived group were significantly more likely to have a history of smoking, to self-identify as Black, and to have a lower mean household income (p = 0.001). The most deprived ADI quartile had a significantly longer mean length of stay (and standard deviation) (19.2 ± 19 days) compared with the least deprived ADI quartile (14.7 ± 11 days) (p = 0.04). The least deprived quartile had a significantly higher percentage of patients who were discharged to a resource-intensive skilled nursing facility or inpatient rehabilitation facility compared with those in the most deprived quartile (p = 0.04). Race, insurance, and income were not significant predictors of discharge destination or hospital length of stay. CONCLUSIONS: Patients facing greater social determinants of health had longer hospital stays and were less likely to be discharged to resource-intensive facilities when compared with patients of lesser social deprivation. This may be due to socioeconomic barriers that limit access to such facilities. LEVEL OF EVIDENCE: Prognostic Level III . See Instructions for Authors for a complete description of levels of evidence.

Hip resurfacing arthroplasty as an alternative to total hip arthroplasty in patients aged under 40 years.

Aims: The aims of the study were to report for a cohort aged younger than 40 years: 1) indications for HRA; 2) patient-reported outcomes in terms of the modified Harris Hip Score (HHS); 3) dislocation rate; and 4) revision rate. Methods: This retrospective analysis identified 267 hips from 224 patients who underwent an hip resurfacing arthroplasty (HRA) from a single fellowship-trained surgeon using the direct lateral approach between 2007 and 2019. Inclusion criteria was minimum two-year follow-up, and age younger than 40 years. Patients were followed using a prospectively maintained institutional database. Results: A total of 217 hips (81%) were included for follow-up analysis at a mean of 3.8 years. Of the 23 females who underwent HRA, none were revised, and the median head size was 46 mm (compared to 50 mm for males). The most common indication for HRA was femoroacetabular impingement syndrome (n = 133), and avascular necrosis ( (n = 53). Mean postoperative HHS was 100 at two and five years. No dislocations occurred. A total of four hips (1.8%) required reoperation for resection of heterotopic ossification, removal of components for infection, and subsidence with loosening. The overall revision rate was 0.9%. Conclusion: For younger patients with higher functional expectations and increased lifetime risk for revision, HRA is an excellent bone preserving intervention carrying low complication rates, revision rates, and excellent patient outcomes without lifetime restrictions allowing these patients to return to activity and sport. Thus, in younger male patients with end-stage hip disease and higher demands, referral to a high-volume HRA surgeon should be considered.

Effect of Insurance Reimbursement Status on Pre- and Postoperative Patient-Reported Outcomes Measurement Information System (PROMIS) Scores After Arthroscopic Rotator Cuff Repair.

BACKGROUND: Previous studies reported inferior patient-reported outcomes (PROs) after arthroscopic rotator cuff repair for patients receiving workers' compensation (WC) relative to patients with commercial insurance. The extent to which alternative insurance reimbursement, including Medicaid and Medicare, influences outcomes after arthroscopic rotator cuff repair remains understudied. HYPOTHESIS: Compared with patients with commercial insurance reimbursement, patients with WC or government-issued reimbursement would report lower pre- and postoperative Patient-Reported Outcomes Measurement Information System (PROMIS) Physical Function (PF) scores, report higher pre- and postoperative PROMIS Depression (D) and Pain Interference (PI) scores, and experience smaller levels of improvement in all PROMIS domains with surgical intervention. STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: Demographic and surgical data were extracted from the medical record, and PROMIS domains were prospectively collected. Patients were divided into cohorts based on insurance reimbursement status. Differences between insurance-based cohorts for baseline variables, pre- and postoperative PROMIS scores, and change from baseline to final follow-up (delta) for PROMIS scores were evaluated using Kruskal-Wallis or chi-square tests. Mixed-effects linear regression models were performed to assess the influence of insurance while controlling for other variables. Survival analysis was performed to determine time to achieve minimal clinically important difference (MCID) for each PROMIS domain per cohort. RESULTS: 1252 patients underwent arthroscopic rotator cuff repair, met inclusion criteria, and completed PROMIS questionnaires. Statistically significant differences were noted in demographic variables including age (P < .001), sex (P < .001), ethnicity (P < .001), and body mass index (P < .001) between insurance-based cohorts. Unadjusted analysis revealed significantly higher PF scores and lower PI and D scores for the group with commercial insurance relative to those with Medicare, Medicaid, and WC at 6- and 12-month follow-up (P < .01 all comparisons), except for the Medicare versus commercial subcohort analysis for PI at 6 months (P = .28). These differences persisted for the Medicare, Medicaid, and WC groups (P < .03 all comparisons) after adjustment for confounding variables in linear regression. CONCLUSIONS: The baseline characteristics of patients undergoing arthroscopic rotator cuff repair differed based on insurance reimbursement. Patients with commercial insurance reported improved physical function, decreased pain interference, and improved mood (less depression) relative to patients with government-issued and WC insurance, with maximum improvement 6 to 12 months postoperatively. There were few significant differences between insurance groups in change of PROMIS scores from preoperative to postoperative intervals, indicating that differences in the baseline demographic and surgical characteristics of these groups accounted for differences in response to surgery.

Use of Area Deprivation Index to Predict Minimal Clinically Important Difference for Patient Reported Outcomes Measurement Information System After Arthroscopic Rotator Cuff Repair.

BACKGROUND: Socioeconomic disparities correlate with worse outcomes after arthroscopic rotator cuff repair. However, use of a surrogate to describe socioeconomic disadvantage has been a challenge. The Area Deprivation Index (ADI) is a tool that encompasses 17 socioeconomic variables into a single metric based on census location. HYPOTHESIS: Higher ADI would result in a worse minimal clinically important difference (MCID) for the Patient Reported Outcomes Measurement Information System (PROMIS) and have less improvement in range of motion (ROM) following arthroscopic rotator cuff repair (ARCR). STUDY DESIGN: Cohort study; Level of evidence, 3. METHOD: A retrospective review was performed for patients who underwent arthroscopic rotator cuff repair. Patients in the most socioeconomically disadvantaged quartile (ADIHigh) were compared with the least disadvantaged quartile (ADILow) in the ability to reach MCID. Demographic and surgical features were assessed for attainment of MCID. RESULTS: In total 1382 patients were identified who underwent ARCR, of which a total of 306 patients met final inclusion criteria. A higher percentage of patients within the ADIHigh cohort identified as "Black" or "other" race and had government-issued insurance compared with the ADILow cohort (P < .05). The ADIHigh cohort had significantly worse postoperative forward flexion compared with the ADILow cohort (145.0°± 32.5° vs 156.3°± 23.4°; P = .001) despite starting with comparable preoperative ROM (P = .17). Logistic regression showed that ADI was the only variable significant for predicting achievement of MCID for all 3 PROMIS domains, with the ADIHigh cohort having significantly worse odds of achieving MCID Physical Function (odds ratio [OR], 0.31; P = .001), Pain Interference (OR, 0.21; P = .001), and Depression (OR, 0.28; P = .001). Meanwhile, age, sex, body mass index, and smoking history were nonsignificant. Moreover, "other" for race and Medicare insurance were significant for achievement of MCID Depression but not Physical Function or Pain Interference. Finally, ADI was the main feature for predictive logistic regression modeling. CONCLUSION: ADI served as the only significant predictor for achieving MCID for all 3 PROMIS domains after arthroscopic rotator cuff repair. Patients who face high levels of socioeconomic disadvantage have lower rates of achieving MCID. In addition, patients with greater neighborhood disadvantage demonstrated significantly worse improvement in active forward flexion. Further investigation is required to understand the role of ADI on physical therapy compliance and to identify the barriers that prevent equitable postoperative care.