Prosthetic Hip Dislocations in Direct Anterior Versus Posterior Approach in Patients With Instrumented Lumbar Fusion.

BACKGROUND: Instrumented posterior lumbar spinal fusion (IPLSF) has been demonstrated to contribute to instability following total hip arthroplasty (THA). It is unclear whether a supine direct anterior (DA) approach reduces the risk of instability. METHODS: A retrospective review of 1,773 patients who underwent THA through either a DA approach or a posterior approach at our institution over a 7-year period was performed. Radiographic and chart reviews were then used to identify our primary group of interest comprised of 111 patients with previous IPLSF. Radiographic review, chart review, and phone survey was performed. Dislocation rates in each approach group were then compared within this cohort of patients with IPLSF. RESULTS: Within the group of patients with IPLSF, 33.3% (n = 37) received a DA approach while 66.6% (n = 74) received a posterior approach. None of the 9 total dislocations in the DA group had IPLSF, whereas 4 of the 16 total dislocations in the posterior approach group had IPLSF (P = .78). When examining the larger group of patients, including those without IPLSF, patients undergoing a DA approach had a lower BMI and were likely have a smaller head size implanted (P < .001 for both). Using Fischer's exact test, fusion was associated with dislocation in the posterior approach group (P < .01), whereas fusion was not associated with dislocation in the anterior approach group (P = 1.0). CONCLUSIONS: While there was no significant difference in dislocation rates between posterior and anterior approach groups, in patients with IPLSF, the anterior approach had a lower percentage of dislocation events compared to the posterior approach.

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.

Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs.

BACKGROUND: The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies. METHODS: We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. RESULTS: The training and testing sets were drawn from statistically different populations of implants (P < .001). After 1,000 training epochs by the deep learning system, the system discriminated 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image. CONCLUSION: An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.

Robotic Arm-Assisted versus Manual Total Knee Arthroplasty: A Propensity Score-Matched Analysis.

The purpose of this study was to compare (1) operative time, (2) in-hospital pain scores, (3) opioid medication use, (4) length of stay (LOS), (5) discharge disposition at 90-day postoperative, (6) range of motion (ROM), (7) number of physical therapy (PT) visits, (8) emergency department (ED) visits, (9) readmissions, (10) reoperations, (11) complications, and (12) 1-year patient-reported outcome measures (PROMs) in propensity matched patient cohorts who underwent robotic arm-assisted (RA) versus manual total knee arthroplasty (TKA). Using a prospectively collected institutional database, patients who underwent RA- and manual TKA were the nearest neighbor propensity score matched 3:1 (255 manual TKA:85 RA-TKA), accounting for various preoperative characteristics. Data were compared using analysis of variance (ANOVA), Kruskal-Wallis, Pearson's Chi-squared, and Fisher's exact tests, when appropriate. Postoperative pain scores, opioid use, ED visits, readmissions, and 1-year PROMs were similar between the cohorts. Manual TKA patients achieved higher maximum flexion ROM (120.3 ± 9.9 versus 117.8 ± 10.2, p = 0.043) with no statistical differences in other ROM parameters. Manual TKA had shorter operative time (105 vs.113 minutes, p < 0.001), and fewer PT visits (median [interquartile range] = 10.0 [8.0-13.0] vs. 11.5 [9.5-15.5] visits, p = 0.014). RA-TKA had shorter LOS (0.48 ± 0.59 vs.1.2 ± 0.59 days, p < 0.001) and higher proportion of home discharges (p < 0.001). RA-TKA and manual TKA had similar postoperative complications and 1-year PROMs. Although RA-TKA patients had longer operative times, they had shorter LOS and higher propensity for home discharge. In an era of value-based care models and the steady shift to outpatient TKA, these trends need to be explored further. Long-term and randomized controlled studies may help determine potential added value of RA-TKA versus manual TKA. This study reflects level of evidence III.

Concerns surrounding application of artificial intelligence in hip and knee arthroplasty : a review of literature and recommendations for meaningful adoption.

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular ("AI/machine learning"), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.Cite this article: Bone Joint J 2022;104-B(12):1292-1303.

Meaningless Applications and Misguided Methodologies in Artificial Intelligence-Related Orthopaedic Research Propagates Hype Over Hope.

There exists great hope and hype in the literature surrounding applications of artificial intelligence (AI) to orthopaedic surgery. Between 2018 and 2021, a total of 178 AI-related articles were published in orthopaedics. However, for every 2 original research papers that apply AI to orthopaedics, a commentary or review is published (30.3%). AI-related research in orthopaedics frequently fails to provide use cases that offer the uninitiated an opportunity to appraise the importance of AI by studying meaningful questions, evaluating unknown hypotheses, or analyzing quality data. The hype perpetuates a feed-forward cycle that relegates AI to a meaningless buzzword by rewarding those with nascent understanding and rudimentary technical knowhow into committing several basic errors: (1) inappropriately conflating vernacular ("AI/machine learning"), (2) repackaging registry data, (3) prematurely releasing internally validated algorithms, (4) overstating the "black box phenomenon" by failing to provide weighted analysis, (5) claiming to evaluate AI rather than the data itself, and (6) withholding full model architecture code. Relevant AI-specific guidelines are forthcoming, but forced application of the original Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis guidelines designed for regression analyses is irrelevant and misleading. To safeguard meaningful use, AI-related research efforts in orthopaedics should be (1) directed toward administrative support over clinical evaluation and management, (2) require the use of the advanced model, and (3) answer a question that was previously unknown, unanswered, or unquantifiable.

Operative times in primary total hip arthroplasty will remain stable up to the year 2027: prediction models based on 85,808 cases.

PURPOSE: Recently, the Centers for Medicare and Medicaid have announced the decision to review "potentially misvalued" Current Procedural Terminology codes, including those for primary total hip arthroplasty (THA). While recent studies have suggested that THA operative times have remained stable in recent years, there is an absence of information regarding how operative times are expected to change in the future. Therefore, the purpose of our analysis was to produce 2- and 10-year prediction models developed from contemporary operative time data. METHODS: Utilizing the American College of Surgeons National Surgical Quality Improvement patient database, all primary THA procedures performed between January 1st, 2008 and December 31st, 2017 were identified (n = 85,808 THA patients). Autocorrelation fit significance was determined through Box-Ljung lack of fit tests. Time series stationarity was evaluated using augmented Dickey-Fuller tests. After adjusting non-stationary time series for seasonality-dependent changes, 2-year and 10-year operative times were predicted using Autoregressive integrated moving average forecasting models. RESULTS: Our models indicate that operative time will continue to remain stable. Specifically, operative time for ASA Class 2 is projected to fall within 1 min of the previously calculated weighted mean. Additionally, ASA Class 3 projections fall within 3 min of this value. CONCLUSION: Operative time will remain within 3 min of the most recently reported mean up to the year 2027. Therefore, our findings do not support lowering physician compensation based on this metric. Future analyses should evaluate if operative times adjust over in light of changing patient demographics and alternative reimbursement models.

Sports Medicine and Artificial Intelligence: A Primer.

Artificial intelligence (AI) represents the fourth industrial revolution and the next frontier in medicine poised to transform the field of orthopaedics and sports medicine, though widespread understanding of the fundamental principles and adoption of applications remain nascent. Recent research efforts into implementation of AI in the field of orthopaedic surgery and sports medicine have demonstrated great promise in predicting athlete injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting the patient experience. Not unlike the recent emphasis thrust upon physicians to understand the business of medicine, the future practice of sports medicine specialists will require a fundamental working knowledge of the strengths, limitations, and applications of AI-based tools. With appreciation, caution, and experience applying AI to sports medicine, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. In this Current Concepts review, we discuss the definitions, strengths, limitations, and applications of AI from the current literature as it relates to orthopaedic sports medicine.

The international normalised ratio predicts perioperative complications in revision total hip arthroplasty.

BACKGROUND: Standard preoperative protocols in total joint arthroplasty utilise the international normalised ratio (INR) to determine patient coagulation profiles. However, the relevance of preoperative INR values in joint arthroplasty remains controversial. Therefore, we examined (1) the relationship between preoperative INR values and various outcome measures, including, but not limited to: surgical site complications, medical complications, bleeding, number of readmissions, and mortality. Additionally, we sought to determine (2) specific INR values associated with these complications and (3) cutoff INR levels which correlated with specific outcomes. We additionally applied these analyses to (4) examine the relationship between INR and length-of-stay (LOS). METHODS: The American College of Surgeons National Surgical Quality Improvement Program database (ACS-NSQIP) was queried for rTHA procedures performed between 2006 and 2017. INR ranges were used to stratify cohorts: ⩽1.0, 1.0-⩽1.25, 1.25-⩽1.5, >1.5. INR values were determined using receiver operating characteristics (ROC) curves for each outcome of interest. Optimal cutoff INR values for each outcome were then obtained using univariate/multivariate models. 2012 patients who underwent rTHA met inclusion criteria. RESULTS: Patients with progressively higher INR values had a significantly different risk of mortality within 30 days (p = 0.005), bleeding requiring transfusion (p < 0.001), sepsis (p = 0.002), stroke (p < 0.001), failure to wean from ventilator within 48 hours (p = 0.001), readmission (p = 0.01), and hospital length of stay (p < 0.001). Similar results were obtained when utilising optimal INR cutoff values. When correcting for other factors, the following poor outcomes were significantly associated with the respective INR cutoff values (Estimate, 95% CI, p-value): LOS >4 days (1.67, 1.34-2.08, p < 0.001), bleeding requiring transfusion (1.65, 1.30-2.09, p < 0.001), sepsis (2.15, 1.11-4.17, p = 0.022), and any infection (1.82, 1.01-3.29, p = 0.044). CONCLUSIONS: Our analysis illustrates a direct relationship between specific preoperative INR levels and poor outcomes following rTHA, including increased LOS, transfusion requirements and infection. Therefore, current INR guideline targets may need to be re-examined when optimising patients for revision arthroplasty.

Immune Checkpoint Inhibitors Mediated Lymphocytic and Giant Cell Myocarditis: Uncovering Etiological Mechanisms.

The advent of immune checkpoint inhibitors (ICIs) has revolutionized the field of oncology, but these are associated with immune related adverse events. One such adverse event, is myocarditis, which has limited the continued immunosuppressive treatment options in patients afflicted by the disease. Pre-clinical and clinical data have found that specific ICI targets and precipitate distinct myocardial infiltrates, consistent with lymphocytic or giant cell myocarditis. Specifically, it has been reported that CTLA-4 inhibition preferentially results in giant cell myocarditis with a predominately CD4+ T cell infiltrate and PD-1 inhibition leads to lymphocytic myocarditis, with a predominately CD8+ T cell infiltrate. Our manuscript discusses the latest literature surrounding ICI pathways and targets, while detailing proposed mechanisms behind ICI mediated myocarditis.

Predicting the Risk of Subsequent Hip Surgery Before Primary Hip Arthroscopy for Femoroacetabular Impingement Syndrome: A Machine Learning Analysis of Preoperative Risk Factors in Hip Preservation.

BACKGROUND: The number of patients requiring reoperation has increased as the volume of hip arthroscopy for femoroacetabular impingement syndrome (FAIS) has increased. The factors most important in determining patients who are likely to require reoperation remain elusive. PURPOSE: To leverage machine learning to better characterize the complex relationship across various preoperative factors (patient characteristics, radiographic parameters, patient-reported outcome measures [PROMs]) for patients undergoing primary hip arthroscopy for FAIS to determine which features predict the need for future ipsilateral hip reoperation, namely, revision hip arthroscopy, total hip arthroplasty (THA), hip resurfacing arthroplasty (HRA), or periacetabular osteotomy (PAO). STUDY DESIGN: Cohort study; Level of evidence, 3. METHODS: A cohort of 3147 patients undergoing 3748 primary hip arthroscopy procedures were included from an institutional hip preservation registry. Preoperative computed tomography of the hip was obtained for each patient, from which the following parameters were calculated: the alpha angle; the coronal center-edge angle; the neck-shaft angle; the acetabular version angle at 1, 2, and 3 o'clock; and the femoral version angle. Preoperative PROMs included the modified Harris Hip Score (mHHS), the Hip Outcome Score (HOS)-Activities of Daily Living subscale (HOS-ADL) and the Sport Specific subscale, and the international Hip Outcome Tool (iHOT-33). Random forest models were created for revision hip arthroscopy, the THA, the HRA, and the PAO. Area under the curve (AUC) for the receiver operating characteristic curve and accuracy were calculated to evaluate each model. RESULTS: A total of 171 patients (4.6%) underwent subsequent hip surgery after primary hip arthroscopy for FAIS. The AUC and accuracy, respectively, were 0.77 (fair) and 76% for revision hip arthroscopy (mean, 26.4-month follow-up); 0.80 (good) and 81% for THA (mean, 32.5-month follow-up); 0.62 (poor) and 69% for HRA (mean, 45.4-month follow-up); and 0.76 (fair) and 74% for PAO (mean, 30.4-month follow-up). The most important factors in predicting reoperation after primary hip arthroscopy were higher body mass index (BMI) and lower preoperative HOS-ADL for revision hip arthroscopy, greater age and lower preoperative iHOT-33 for THA, increased BMI for HRA, and larger neck-shaft angle and lower preoperative mHHS for PAO. CONCLUSION: Despite the low failure rate of hip arthroscopy for FAIS, our study demonstrated that machine learning has the capability to identify key preoperative risk factors that may predict subsequent ipsilateral hip surgery before the index hip arthroscopy. Knowledge of these demographic, radiographic, and patient-reported outcome data may aid in preoperative counseling and expectation management to better optimize hip preservation.

Do Narcotic Use, Physical Therapy Location, or Payer Type Predict Patient-Reported Outcomes After Anterior Cruciate Ligament Reconstruction?

BACKGROUND: Opioid use and public insurance have been correlated with worse outcomes in a number of orthopaedic surgeries. These factors have not been investigated with anterior cruciate ligament reconstruction (ACLR). PURPOSE/HYPOTHESIS: To evaluate if narcotic use, physical therapy location, and insurance type are predictors of patient-reported outcomes after ACLR. It was hypothesized that at 1 year postsurgically, increased postoperative narcotic use would be associated with worse outcomes, physical therapy obtained within the authors' integrated health care system would lead to better outcomes, and public insurance would lead to worse outcomes and athletic activity. STUDY DESIGN: Cohort study; Level of evidence, 2. METHODS: All patients undergoing unilateral, primary ACLR between January 2015 and February 2016 at a large health system were enrolled in a standard-of-care prospective cohort. Knee injury and Osteoarthritis Score (KOOS) and the Hospital for Special Surgery Pediatric-Functional Activity Brief Scale (HSS Pedi-FABS) were collected before surgery and at 1 year postoperatively. Concomitant knee pathology was assessed arthroscopically and electronically captured. Patient records were analyzed to determine physical therapy location, insurance status, and narcotic use. Multivariable regression analyses were used to identify significant predictors of the KOOS and HSS Pedi-FABS score. RESULTS: A total of 258 patients were included in the analysis (mean age, 25.8; 51.2% women). In multivariable regression analysis, narcotic use, physical therapy location, and insurance type were not independent predictors of any KOOS subscales. Public insurance was associated with a lower HSS Pedi-FABS score (-4.551, P = .047) in multivariable analysis. Narcotic use or physical therapy location was not associated with the HSS Pedi-FABS score. CONCLUSION: Increased narcotic use surrounding surgery, physical therapy location within the authors' health care system, and public versus private insurance were not associated with disease-specific KOOS subscale scores. Patients with public insurance had worse HSS Pedi-FABS activity scores compared with patients with private insurance, but neither narcotic use nor physical therapy location was associated with activity scores. Physical therapy location did not influence outcomes, suggesting that patients be given a choice in the location they received physical therapy (as long as a standardized protocol is followed) to maximize compliance.

Effect of Preoperative Imaging and Patient Factors on Clinically Meaningful Outcomes and Quality of Life After Osteochondral Allograft Transplantation: A Machine Learning Analysis of Cartilage Defects of the Knee.

BACKGROUND: Fresh osteochondral allograft transplantation (OCA) is an effective method of treating symptomatic cartilage defects of the knee. This restoration technique involves the single-stage implantation of viable, mature hyaline cartilage into a chondral or osteochondral lesion. The extent to which preoperative imaging and patient factors predict achieving clinically meaningful outcomes among patients undergoing OCA for cartilage lesions of the knee remains unknown. PURPOSE: To determine the predictive relationship of preoperative imaging, preoperative patient-reported outcome measures (PROMs), and patient demographics with achievement of the minimal clinically important difference (MCID) and substantial clinical benefit (SCB) for functional and quality-of-life PROMs at 2 years after OCA for symptomatic cartilage defects of the knee. STUDY DESIGN: Case-control study; Level of evidence, 3. METHODS: Data were analyzed for patients who underwent OCA before May 1, 2018, by 2 high-volume fellowship-trained cartilage surgeons. The International Knee Documentation Committee (IKDC) subjective form, Knee Outcome Survey-Activities of Daily Living (KOS-ADL), and mental and physical component summaries of the SF-36 were administered preoperatively and at 2 years postoperatively. A total of 42 predictive models were created using 7 unique architectures to detect achievement of the MCID for each of the 4 outcome measures and the SCB for the IKDC and KOS-ADL. Data inputted into the models included sex, age, body mass index, baseline PROMs, lesion size, concomitant ligamentous or meniscal tear, and presence of "bone bruise" or osseous edema. Shapley additive explanations plot analysis identified predictors of reaching the MCID and SCB. RESULTS: Of the 185 patients who underwent OCA for the knee and met eligibility criteria from an institutional cartilage registry, 153 (83%) had 2-year follow-up. Preoperative magnetic resonance imaging (MRI), baseline PROMs, and patient demographics best predicted reaching the 2-year MCID and SCB of the IKDC and KOS-ADL PROMs, with areas under the receiver operating characteristic curve of the top-performing models ranging from good (0.88) to excellent (0.91). MRI faired poorly (areas under the curve, 0.60-0.68) in predicting the MCID for the mental and physical component summaries. Higher body mass index, knee malalignment, absence of preoperative osseous edema, concomitant anterior cruciate ligament or meniscal injury, larger defect size, and the implantation of >1 OCA graft were consistent findings contributing to failure to achieve the MCID or SCB at 2 years postoperatively. CONCLUSION: Our machine learning models demonstrated that preoperative MRI, baseline PROMs, and patient demographics reliably predict the ability to reach clinically meaningful thresholds for functional knee outcomes 2 years after OCA for cartilage defects. Although clinical improvement in knee function can be reliably predicted, improvements in quality of life after OCA depend on a comprehensive preoperative assessment of the patient's perception of his or her mental and physical health. Absence of osseous edema, concomitant anterior cruciate ligament or meniscal injury, larger lesion size on MRI, knee malalignment, and elevated body mass index are predictive of failure to achieve 2-year functional benefits after OCA of the knee.

Association Between Preoperative Mental Health and Clinically Meaningful Outcomes After Osteochondral Allograft for Cartilage Defects of the Knee: A Machine Learning Analysis.

BACKGROUND: Fresh osteochondral allograft transplantation (OCA) is an effective method of treating symptomatic cartilage defects of the knee. This cartilage restoration technique involves the single-stage implantation of viable, mature hyaline cartilage into the chondral or osteochondral lesion. Predictive models for reaching the clinically meaningful outcome among patients undergoing OCA for cartilage lesions of the knee remain under investigation. PURPOSE: To apply machine learning to determine which preoperative variables are predictive for achieving the minimal clinically important difference (MCID) and substantial clinical benefit (SCB) at 1 and 2 years after OCA for cartilage lesions of the knee. STUDY DESIGN: Case-control study; Level of evidence, 3. METHODS: Data were analyzed for patients who underwent OCA of the knee by 2 high-volume fellowship-trained cartilage surgeons before May 1, 2018. The International Knee Documentation Committee questionnaire (IKDC), Knee Outcome Survey-Activities of Daily Living (KOS-ADL), and Mental Component (MCS) and Physical Component (PCS) Summaries of the 36-Item Short Form Health Survey (SF-36) were administered preoperatively and at 1 and 2 years postoperatively. A total of 84 predictive models were created using 7 unique architectures to detect achievement of the MCID for each of the 4 outcome measures and the SCB for the IKDC and KOS-ADL at both time points. Data inputted into the models included previous and concomitant surgical history, laterality, sex, age, body mass index (BMI), intraoperative findings, and patient-reported outcome measures (PROMs). Shapley Additive Explanations (SHAP) analysis identified predictors of reaching the MCID and SCB. RESULTS: Of the 185 patients who underwent OCA for the knee and met eligibility criteria from an institutional cartilage registry, 135 (73%) patients were available for the 1-year follow-up and 153 (83%) patients for the 2-year follow-up. In predicting outcomes after OCA in terms of the IKDC, KOS-ADL, MCS, and PCS at 1 and 2 years, areas under the receiver operating characteristic curve (AUCs) of the top-performing models ranged from fair (0.72) to excellent (0.94). Lower baseline mental health (MCS), higher baseline physical health (PCS) and knee function scores (KOS-ADL, IKDC Subjective), lower baseline activity demand (Marx, Cincinnati sports), worse pain symptoms (Cincinnati pain, SF-36 pain), and higher BMI were thematic predictors contributing to failure to achieve the MCID or SCB at 1 and 2 years postoperatively. CONCLUSION: Our machine learning models were effective in predicting outcomes and elucidating the relationships between baseline factors contributing to achieving the MCID for OCA of the knee. Patients who preoperatively report poor mental health, catastrophize pain symptoms, compensate with higher physical health and knee function, and exhibit lower activity demands are at risk for failing to reach clinically meaningful outcomes after OCA of the knee.

Operative Times in Primary Total Knee Arthroplasty: Can We Predict the Future Based on Contemporary Nationwide Data.

Recently, the Centers for Medicare & Medicaid Services announced its decision to review "potentially misvalued" Current Procedural Terminology (CPT) codes, including those for primary total knee arthroplasty (TKA). CPT 27447 is being reevaluated to determine contemporary relative value units for work value, with operative time considered a primary factor in this revaluation. Despite broader indications for TKA, including extension of the procedure to more complex patient populations, it is unknown whether operative times may remain stable in the future. Therefore, the purpose of this study was to specifically evaluate future trends in TKA operative times across a large sample from a national database. The American College of Surgeons National Surgical Quality Improvement Project database was queried from January 1, 2008 to December 31, 2017 to identify 286,816 TKAs using the CPT code 27447. Our final analysis included 140,890 TKAs. Autoregressive integrated moving average forecasting models were built to predict 2- and 10-year operative times. While operative times were significantly different between American Society of Anesthesiologists (ASA) classes 1 and 2 (p = 0.035), there were not enough patients in ASA class 1 to perform rigorous inference. Additionally, operative times were not significantly different between ASA classes 3 and the combined ASA classes 4 and 5 cohort (p = 0.95). Therefore, we were only able to perform forecasts for ASA classes 2 and 3. Operative time was found to be nonstationary for both ASA class 2 (p = 0.08269) and class 3 (p = 0.2385). As a whole, the projection models indicated that operative time will remain within 2 minutes of the present operative time, up to the year 2027. Our projections indicate that operative times will remain stable over the next decade. This suggests that there is a lack of evidence for reducing the valuation of CPT code 27477 based on intraservice time for TKA. Further study should examine operative time trends in the setting of evolving alternative payment models, increasing patient complexity, and governmental restrictions.

Clinical and Research Medical Applications of Artificial Intelligence.

Artificial intelligence (AI), including machine learning (ML), has transformed numerous industries through newfound efficiencies and supportive decision-making. With the exponential growth of computing power and large datasets, AI has transitioned from theory to reality in teaching machines to automate tasks without human supervision. AI-based computational algorithms analyze "training sets" using pattern recognition and learning from inputted data to classify and predict outputs that otherwise could not be effectively analyzed with human processing or standard statistical methods. Though widespread understanding of the fundamental principles and adoption of applications have yet to be achieved, recent applications and research efforts implementing AI have demonstrated great promise in predicting future injury risk, interpreting advanced imaging, evaluating patient-reported outcomes, reporting value-based metrics, and augmenting telehealth. With appreciation, caution, and experience applying AI, the potential to automate tasks and improve data-driven insights may be realized to fundamentally improve patient care. The purpose of this review is to discuss the pearls, pitfalls, and applications associated with AI.

Artificial Intelligence to Identify Arthroplasty Implants From Radiographs of the Knee.

BACKGROUND: Revisions and reoperations for patients who have undergone total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA), and distal femoral replacement (DFR) necessitates accurate identification of implant manufacturer and model. Failure risks delays in care, increased morbidity, and further financial burden. Deep learning permits automated image processing to mitigate the challenges behind expeditious, cost-effective preoperative planning. Our aim was to investigate whether a deep-learning algorithm could accurately identify the manufacturer and model of arthroplasty implants about the knee from plain radiographs. METHODS: We trained, validated, and externally tested a deep-learning algorithm to classify knee arthroplasty implants from one of 9 different implant models from retrospectively collected anterior-posterior (AP) plain radiographs from four sites in one quaternary referral health system. The performance was evaluated by calculating the area under the receiver-operating characteristic curve (AUC), sensitivity, specificity, and accuracy when compared with a reference standard of implant model from operative reports. RESULTS: The training and validation data sets were comprised of 682 radiographs across 424 patients and included a wide range of TKAs from the four leading implant manufacturers. After 1000 training epochs by the deep-learning algorithm, the model discriminated nine implant models with an AUC of 0.99, accuracy 99%, sensitivity of 95%, and specificity of 99% in the external-testing data set of 74 radiographs. CONCLUSIONS: A deep learning algorithm using plain radiographs differentiated between 9 unique knee arthroplasty implants from four manufacturers with near-perfect accuracy. The iterative capability of the algorithm allows for scalable expansion of implant discriminations and represents an opportunity in delivering cost-effective care for revision arthroplasty.