Risk Prediction Tools for Hip and Knee Arthroplasty

A predictive algorithm for perioperative complications and readmission after ankle arthrodesis

PURPOSE

Ankle arthrodesis is a mainstay of surgical management for ankle arthritis. Accurately risk-stratifying patients who undergo ankle arthrodesis would be of great utility. There is a paucity of accurate prediction models that can be used to pre-operatively risk-stratify patients for ankle arthrodesis. We aim to develop a predictive model for major perioperative complication or readmission after ankle arthrodesis.

METHODS

This is a retrospective cohort study of adult patients who underwent ankle arthrodesis at any non-federal California hospital between 2015 and 2017. The primary outcome is readmission within 30 days or major perioperative complication. We build logistic regression and ML models spanning different classes of modeling approaches, assessing discrimination and calibration. We also rank the contribution of the included variables to model performance for prediction of adverse outcomes.

RESULTS

A total of 1084 patients met inclusion criteria for this study. There were 131 patients with major complication or readmission (12.1%). The XGBoost algorithm demonstrates the highest discrimination with an area under the receiver operating characteristic curve of 0.707 and is well-calibrated. The features most important for prediction of adverse outcomes for the XGBoost model include: diabetes, peripheral vascular disease, teaching hospital status, morbid obesity, history of musculoskeletal infection, history of hip fracture, renal failure, implant complication, history of major fracture.

CONCLUSION

We report a well-calibrated algorithm for prediction of major perioperative complications and 30-day readmission after ankle arthrodesis. This tool may help accurately risk-stratify patients and decrease likelihood of major complications.

Prognostic value of perioperative high sensitivity troponin in patients undergoing hip and knee arthroplasty

The authors conducted a prospective observational study to investigate the prognostic value of high-sensitivity Troponin I (hs-TnI) in the short- and long-term periods after orthopedic surgery, including Total Hip and Knee Arthroplasty (THA and TKA, respectively), in a tertiary orthopedic center in Brazil. Perioperative Myocardial Injury (PMI) was defined as an absolute increase in hs-TnI of ≥ 26 ng/L above preoperative values. The primary endpoint was all-cause mortality assessed at 30 days and 18 months after surgery. The secondary endpoint consisted of a composite outcome: cardiovascular death, acute myocardial infarction, angina requiring revascularization, and/or stroke. The authors compared Relative Risks (RR) of all-cause mortality and composite outcomes in patients with or without PMI at 30 days and 18 months. A Cox proportional hazards model for long-term outcomes was calculated and adjusted for age > 70 years, gender, and Revised Cardiac Risk Index (RCRI) class ≥ 2. PMI occurred in 3.4 % of all surgeries. At 30-days, 6.6 % of patients with PMI had died versus none without PMI. At 18 months, 20.0 % of PMI versus 4.7 % without PMI had died (RR = 5.0; 95 % Confidence Interval [95 % CI 1.3-19.3]). Based on composite outcomes in short and long-term periods, the RRs were 16.2 (95 % CI 2.7-96.5) and 7.7 (95 % CI 2.2-26.6), respectively. PMI was associated with all-cause mortality after 18 months and increased risk for a composite outcome (Hazard Ratio [HR = 3.97], 95 % CI 1.13-13.89 and HR = 5.80, 95 % CI 1.93-17.45, respectively). Patients with PMI who underwent THA or TKA presented worse short- and long-term prognoses compared to those without PMI.

Recommendations for the management of hip and knee osteoarthritis: A systematic review of clinical practice guidelines

OBJECTIVES

Guideline adherence for hip and knee osteoarthritis management is often poor, possibly related to the quality and/or inconsistent recommendations. This systematic review of hip and knee osteoarthritis guidelines aimed to appraise the quality and consistency in recommendations across higher-quality guidelines.

METHODS

Eight databases, guideline repositories, and professional associations websites were searched on 27/10/2022. Guideline quality was appraised using the Appraisal of Guidelines for Research and Evaluation II (AGREE II tool) (six domains). Higher quality was defined as scoring ≥60% for domains 3 (rigour of development), 6 (editorial independence), plus one other. Consistency in recommendations across higher-quality guidelines was reported descriptively. This review was registered prospectively (CRD42021216154).

RESULTS

Seven higher-quality and 18 lesser-quality guidelines were included. AGREE II domain scores for higher-quality guidelines were > 60% except for applicability (average 46%). Higher-quality guidelines consistently recommended in favour of education, exercise, and weight management and non-steroidal anti-inflammatory drugs (hip and knee), and intra-articular corticosteroid injections (knee). Higher quality guidelines consistently recommended against hyaluronic acid (hip) and stem cell (hip and knee) injections. Other pharmacological recommendations in higher-quality guidelines (e.g., paracetamol, intra-articular corticosteroid (hip), hyaluronic acid (knee)) and adjunctive treatments (e.g., acupuncture) were less consistent. Arthroscopy was consistently recommended against in higher-quality guidelines. No higher-quality guidelines considered arthroplasty.

CONCLUSION

Higher-quality guidelines for hip and knee osteoarthritis consistently recommend clinicians implement exercise, education, and weight management, alongside consideration of Non-Steroidal Anti-Inflammatory Drugs and intra-articular corticosteroid injections (knee). Lack of consensus on some pharmacological options and adjunctive treatments creates challenges for guideline adherence. Future guidelines must prioritise providing implementation guidance, considering consistently low applicability scores.

Predicting 30-day readmission following total knee arthroplasty using machine learning and clinical expertise applied to clinical administrative and research registry data in an Australian cohort

BACKGROUND

Thirty-day readmission is an increasingly important problem for total knee arthroplasty (TKA) patients. The aim of this study was to develop a risk prediction model using machine learning and clinical insight for 30-day readmission in primary TKA patients.

METHOD

Data used to train and internally validate a multivariable predictive model were obtained from a single tertiary referral centre for TKA located in Victoria, Australia. Hospital administrative data and clinical registry data were utilised, and predictors were selected through systematic review and subsequent consultation with clinicians caring for TKA patients. Logistic regression and random forest models were compared to one another. Calibration was evaluated by visual inspection of calibration curves and calculation of the integrated calibration index (ICI). Discriminative performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC).

RESULTS

The models developed in this study demonstrated adequate calibration for use in the clinical setting, despite having poor discriminative performance. The best-calibrated readmission prediction model was a logistic regression model trained on administrative data using risk factors identified from systematic review and meta-analysis, which are available at the initial consultation (ICI = 0.012, AUC-ROC = 0.589). Models developed to predict complications associated with readmission also had reasonable calibration (ICI = 0.012, AUC-ROC = 0.658).

CONCLUSION

Discriminative performance of the prediction models was poor, although machine learning provided a slight improvement. The models were reasonably well calibrated, meaning they provide accurate patient-specific probabilities of these outcomes. This information can be used in shared clinical decision-making for discharge planning and post-discharge follow up.

Development and External Validation of a Risk Calculator for Prediction of Major Complications and Readmission After Anterior Cervical Discectomy and Fusion

STUDY DESIGN

A retrospective, case-control study.

OBJECTIVE

We aim to build a risk calculator predicting major perioperative complications after anterior cervical fusion. In addition, we aim to externally validate this calculator with an institutional cohort of patients who underwent anterior cervical discectomy and fusion (ACDF).

SUMMARY OF BACKGROUND DATA

The average age and proportion of patients with at least one comorbidity undergoing ACDF have increased in recent years. Given the increased morbidity and cost associated with perioperative complications and unplanned readmission, accurate risk stratification of patients undergoing ACDF is of great clinical utility.

METHODS

This is a retrospective cohort study of adults who underwent anterior cervical fusion at any nonfederal California hospital between 2015 and 2017. The primary outcome was major perioperative complication or 30-day readmission. We built standard and ensemble machine learning models for risk prediction, assessing discrimination, and calibration. The best-performing model was validated on an external cohort comprised of consecutive adult patients who underwent ACDF at our institution between 2013 and 2020.

RESULTS

A total of 23,184 patients were included in this study; there were 1886 cases of major complication or readmissions. The ensemble model was well calibrated and demonstrated an area under the receiver operating characteristic curve of 0.728. The variables most important for the ensemble model include male sex, medical comorbidities, history of complications, and teaching hospital status. The ensemble model was evaluated on the validation cohort (n=260) with an area under the receiver operating characteristic curve of 0.802. The ensemble algorithm was used to build a web-based risk calculator.

CONCLUSION

We report derivation and external validation of an ensemble algorithm for prediction of major perioperative complications and 30-day readmission after anterior cervical fusion. This model has excellent discrimination and is well calibrated when tested on a contemporaneous external cohort of ACDF cases.

Positive Preoperative Colonization With Methicillin Resistant Staphylococcus Aureus Is Associated With Inferior Postoperative Outcomes in Patients Undergoing Total Joint Arthroplasty

BACKGROUND

The impact of preoperative nasal colonization with methicillin resistant staphylococcus aureus (MRSA) on total joint arthroplasty (TJA) outcomes is not well understood. This study aimed to evaluate complications following TJA based on patients' preoperative staphylococcal colonization status.

METHODS

We retrospectively analyzed all patients undergoing primary TJA between 2011 and 2022 who completed a preoperative nasal culture swab for staphylococcal colonization. Patients were 1:1:1 propensity matched using baseline characteristics, and stratified into 3 groups based on their colonization status: MRSA positive (MRSA+), methicillin sensitive staphylococcus aureus positive (MSSA+), and MSSA/MRSA negative (MSSA/MRSA-). All MRSA+ and MSSA + underwent decolonization with 5% povidone iodine, with the addition of intravenous vancomycin for MRSA + patients. Surgical outcomes were compared between groups. Of the 33,854 patients evaluated, 711 were included in final matched analysis (237 per group).

RESULTS

The MRSA + TJA patients had longer hospital lengths of stay (P = .008), were less likely to discharge home (P = .003), and had higher 30-day (P = .030) and 90-day (P = .033) readmission rates compared to MSSA+ and MSSA/MRSA-patients, though 90-day major and minor complications were comparable across groups. MRSA + patients had higher rates of all-cause (P = .020), aseptic (P = .025) and septic revisions (P = .049) compared to the other cohorts. These findings held true for both total knee and total hip arthroplasty patients when analyzed separately.

CONCLUSION

Despite targeted perioperative decolonization, MRSA + patients undergoing TJA have longer lengths of stay, higher readmission rates, and higher septic and aseptic revision rates. Surgeons should consider patients' preoperative MRSA colonization status when counseling on the risks of TJA.

An orthopaedic intelligence application successfully integrates data from a smartphone-based care management platform and a robotic knee system using a commercial database

PURPOSE

To evaluate the feasibility of using a smartphone-based care management platform (sbCMP) and robotic-assisted total knee arthroplasty (raTKA) to collect data throughout the episode-of-care and assess if intra-operative measures of soft tissue laxity in raTKA were associated with post-operative outcomes.

METHODS

A secondary data analysis of 131 patients in a commercial database who underwent raTKA was performed. Pre-operative through six week post-operative step counts and KOOS JR scores were collected and cross-referenced with intra-operative laxity measures. A Kruskal-Wallis test or a Wilcoxon sign-rank was used to assess outcomes.

RESULTS

There were higher step counts at six weeks post-operatively in knees with increased laxity in both the lateral compartment in extension and medial compartment in flexion (p < 0.05). Knees balanced in flexion within < 0.5 mm had higher KOOS JR scores at six weeks post-operative (p = 0.034) compared to knees balanced within 0.5-1.5 mm.

CONCLUSION

A smartphone-based care management platform can be integrated with raTKA to passively collect data throughout the episode-of-care. Associations between intra-operative decisions regarding laxity and post-operative outcomes were identified. However, more robust analysis is needed to evaluate these associations and ensure clinical relevance to guide machine learning algorithms.

External validation of a predictive algorithm for in-hospital and ninety-day mortality after spinal epidural abscess

BACKGROUND CONTEXT

Mortality in patients with spinal epidural abscess (SEA) remains high. Accurate prediction of patient-specific prognosis in SEA can improve patient counseling as well as guide management decisions. There are no externally validated studies predicting short-term mortality in patients with SEA.

PURPOSE

The purpose of this study was to externally validate the Skeletal Oncology Research Group (SORG) stochastic gradient boosting algorithm for prediction of in-hospital and 90-day postdischarge mortality in SEA.

STUDY DESIGN/SETTING

Retrospective, case-control study at a tertiary care academic medical center from 2003 to 2021.

PATIENT SAMPLE

Adult patients admitted for radiologically confirmed diagnosis of SEA who did not initiate treatment at an outside institution.

OUTCOME MEASURES

In-hospital and 90-day postdischarge mortality.

METHODS

We tested the SORG stochastic gradient boosting algorithm on an independent validation cohort. We assessed its performance with discrimination, calibration, decision curve analysis, and overall performance.

RESULTS

A total of 212 patients met inclusion criteria, with a short-term mortality rate of 10.4%. The area under the receiver operating characteristic curve (AUROC) of the SORG algorithm when tested on the full validation cohort was 0.82, the calibration intercept was -0.08, the calibration slope was 0.96, and the Brier score was 0.09.

CONCLUSIONS

With a contemporaneous and geographically distinct independent cohort, we report successful external validation of a machine learning algorithm for prediction of in-hospital and 90-day postdischarge mortality in SEA.

Comparative Analysis of the Ability of Machine Learning Models in Predicting In-hospital Postoperative Outcomes After Total Hip Arthroplasty

BACKGROUND

Machine learning (ML) methods have shown promise in a wide range of applications including the development of patient-specific predictive models before surgical interventions. The purpose of this study was to develop, test, and compare four distinct ML models to predict postoperative parameters after primary total hip arthroplasty.

METHODS

Data from the Nationwide Inpatient Sample were used to identify patients undergoing total hip arthroplasty from 2016 to 2017. Linear support vector machine (LSVM), random forest (RF), neural network (NN), and extreme gradient boost trees (XGBoost) predictive of mortality, length of stay, and discharge disposition were developed and validated using 15 predictive patient-specific and hospital-specific factors. Area under the curve of the receiver operating characteristic (AUCROC) curve and accuracy were used as validity metrics, and the strongest predictive variables under each model were assessed.

RESULTS

A total of 177,442 patients were included in this analysis. For mortality, the XGBoost, NN, and LSVM models all had excellent responsiveness during validation while RF had fair responsiveness. LSVM had the highest responsiveness with an AUCROC of 0.973 during validation. For the length of stay, the LSVM and NN models had fair responsiveness while the XGBoost and random forest models had poor responsiveness. LSVM had the highest responsiveness with an AUCROC of 0.744 during validation. For the discharge disposition outcome, LSVM had good responsiveness while the XGBoost, NN, and RF models all had fair responsiveness. LSVM had the highest responsiveness with an AUCROC of 0.801.

DISCUSSION

The ML methods tested demonstrated a range of poor-to-excellent responsiveness and accuracy in the prediction of the assessed metrics, with LSVM being the best performer. Such models should be further developed, with eventual integration into clinical practice to inform patient discussions and management decision making, with the potential for integration into tiered bundled payment models.

A Risk Calculator for the Prediction of C5 Nerve Root Palsy After Instrumented Cervical Fusion

BACKGROUND

C5 palsy is a common postoperative complication after cervical fusion and is associated with increased health care costs and diminished quality of life. Accurate prediction of C5 palsy may allow for appropriate preoperative counseling and risk stratification. We primarily aim to develop an algorithm for the prediction of C5 palsy after instrumented cervical fusion and identify novel features for risk prediction. Additionally, we aim to build a risk calculator to provide the risk of C5 palsy.

METHODS

We identified adult patients who underwent instrumented cervical fusion at a tertiary care medical center between 2013 and 2020. The primary outcome was postoperative C5 palsy. We developed ensemble machine learning, standard machine learning, and logistic regression models predicting the risk of C5 palsy-assessing discrimination and calibration. Additionally, a web-based risk calculator was built with the best-performing model.

RESULTS

A total of 1024 patients were included, with 52 cases of C5 palsy. The ensemble model was well-calibrated and demonstrated excellent discrimination with an area under the receiver-operating characteristic curve of 0.773. The following features were the most important for ensemble model performance: diabetes mellitus, bipolar disorder, C5 or C4 level, surgical approach, preoperative non-motor neurologic symptoms, degenerative disease, number of fused levels, and age.

CONCLUSIONS

We report a risk calculator that generates patient-specific C5 palsy risk after instrumented cervical fusion. Individualized risk prediction for patients may facilitate improved preoperative patient counseling and risk stratification as well as potential intraoperative mitigating measures. This tool may also aid in addressing potentially modifiable risk factors such as diabetes and obesity.

Evaluating methodological quality of prognostic prediction models on patient reported outcome measurements after total hip replacement and total knee replacement surgery: a systematic review protocol

BACKGROUND

Prediction models for poor patient-reported surgical outcomes after total hip replacement (THR) and total knee replacement (TKR) may provide a method for improving appropriate surgical care for hip and knee osteoarthritis. There are concerns about methodological issues and the risk of bias of studies producing prediction models. A critical evaluation of the methodological quality of prediction modelling studies in THR and TKR is needed to ensure their clinical usefulness. This systematic review aims to (1) evaluate and report the quality of risk stratification and prediction modelling studies that predict patient-reported outcomes after THR and TKR; (2) identify areas of methodological deficit and provide recommendations for future research; and (3) synthesise the evidence on prediction models associated with post-operative patient-reported outcomes after THR and TKR surgeries.

METHODS

MEDLINE, EMBASE, and CINAHL electronic databases will be searched to identify relevant studies. Title and abstract and full-text screening will be performed by two independent reviewers. We will include (1) prediction model development studies without external validation; (2) prediction model development studies with external validation of independent data; (3) external model validation studies; and (4) studies updating a previously developed prediction model. Data extraction spreadsheets will be developed based on the CHARMS checklist and TRIPOD statement and piloted on two relevant studies. Study quality and risk of bias will be assessed using the PROBAST tool. Prediction models will be summarised qualitatively. Meta-analyses on the predictive performance of included models will be conducted if appropriate. A narrative review will be used to synthesis the evidence if there are insufficient data to perform meta-analyses.

DISCUSSION

This systematic review will evaluate the methodological quality and usefulness of prediction models for poor outcomes after THR or TKR. This information is essential to provide evidence-based healthcare for end-stage hip and knee osteoarthritis. Findings of this review will contribute to the identification of key areas for improvement in conducting prognostic research in this field and facilitate the progress in evidence-based tailored treatments for hip and knee osteoarthritis.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO registration number CRD42021271828.

Cardiac Comorbidity Risk Score: Zero-Burden Machine Learning to Improve Prediction of Postoperative Major Adverse Cardiac Events in Hip and Knee Arthroplasty

Background In this retrospective, observational study we introduce the Cardiac Comorbidity Risk Score, predicting perioperative major adverse cardiac events (MACE) after elective hip and knee arthroplasty. MACE is a rare but important driver of mortality, and existing tools, eg, the Revised Cardiac Risk Index demonstrate only modest accuracy. We demonstrate an artificial intelligence-based approach to identify patients at high risk of MACE within 4 weeks (primary outcome) of arthroplasty, that imposes zero additional burden of cost/resources. Methods and Results Cardiac Comorbidity Risk Score calculation uses novel machine learning to estimate MACE risk from patient electronic health records, without requiring blood work or access to any demographic data beyond that of sex and age, and accounts for variable/missing/incomplete information across patient records. Validated on a deidentified cohort (age >45 years, n=445 391), performance was evaluated using the area under the receiver operator characteristics curve (AUROC), sensitivity/specificity, positive predictive value, and positive/negative likelihood ratios. In our cohort (age 63.5±10.5 years, 58.2% women, 34.2%/65.8% hip/knee procedures), 0.19% (882) experienced the primary outcome. Cardiac Comorbidity Risk Score achieved area under the receiver operator characteristics curve=80.0±0.4% (95% CI) for women and 80.1±0.5% (95% CI) for males, with 36.4% and 35.1% sensitivities, respectively, at 95% specificity, significantly outperforming Revised Cardiac Risk Index across all studied age-, sex-, risk-, and comorbidity-based subgroups. Conclusions Cardiac Comorbidity Risk Score, a novel artificial intelligence-based screening tool using known and unknown comorbidity patterns, outperforms state-of-the-art in predicting MACE within 4 weeks postarthroplasty, and can identify patients at high risk that do not demonstrate traditional risk factors.

Machine learning-driven identification of novel patient factors for prediction of major complications after posterior cervical spinal fusion

PURPOSE

Posterior cervical fusion is associated with increased rates of complications and readmission when compared to anterior fusion. Machine learning (ML) models for risk stratification of patients undergoing posterior cervical fusion remain limited. We aim to develop a novel ensemble ML algorithm for prediction of major perioperative complications and readmission after posterior cervical fusion and identify factors important to model performance.

METHODS

This is a retrospective cohort study of adults who underwent posterior cervical fusion at non-federal California hospitals between 2015 and 2017. The primary outcome was readmission or major complication. We developed an ensemble model predicting complication risk using an automated ML framework. We compared performance with standard ML models and logistic regression (LR), ranking contribution of included variables to model performance.

RESULTS

Of the included 6822 patients, 18.8% suffered a major complication or readmission. The ensemble model demonstrated slightly superior predictive performance compared to LR and standard ML models. The most important features to performance include sex, malignancy, pneumonia, stroke, and teaching hospital status. Seven of the ten most important features for the ensemble model were markedly less important for LR.

CONCLUSION

We report an ensemble ML model for prediction of major complications and readmission after posterior cervical fusion with a modest risk prediction advantage compared to LR and benchmark ML models. Notably, the features most important to the ensemble are markedly different from those for LR, suggesting that advanced ML methods may identify novel prognostic factors for adverse outcomes after posterior cervical fusion.

Predictive capacity of four machine learning models for in-hospital postoperative outcomes following total knee arthroplasty

Background

Machine learning (ML) methods have shown promise in the development of patient-specific predictive models prior to surgical interventions. The purpose of this study was to develop, test, and compare four distinct ML models to predict postoperative parameters following primary total knee arthroplasty (TKA).

Methods

Data from the Nationwide Inpatient Sample was used to identify patients undergoing TKA during 2016-2017. Four distinct ML models predictive of mortality, length of stay (LOS), and discharge disposition were developed and validated using 15 predictive patient and hospital-specific factors. Area under the curve of the receiver operating characteristic curve (AUCROC) and accuracy were used as validity metrics, and the strongest predictive variables under each model were assessed.

Results

A total of 305,577 patients were included. For mortality, the XGBoost, neural network (NN), and LSVM models all had excellent responsiveness during validation, while random forest (RF) had fair responsiveness. For predicting LOS, all four models had poor responsiveness. For the discharge disposition outcome, the LSVM, NN, and XGBoost models had good responsiveness, while the RF model had poor responsiveness. LSVM and XGBoost had the highest responsiveness for predicting discharge disposition with an AUCROC of 0.747.

Discussion

The ML models tested demonstrated a range of poor to excellent responsiveness and accuracy in the prediction of the assessed metrics, with considerable variability noted in the predictive precision between the models. The continued development of ML models should be encouraged, with eventual integration into clinical practice in order to inform patient discussions, management decision making, and health policy.

Prediction of Complications and Surgery Duration in Primary Total Hip Arthroplasty Using Machine Learning: The Necessity of Modified Algorithms and Specific Data

Background: Machine Learning (ML) in arthroplasty is becoming more popular, as it is perfectly suited for prediction models. However, results have been heterogeneous so far. We hypothesize that an accurate ML model for outcome prediction in THA must be able to compute arthroplasty-specific data. In this study, we evaluate a ML approach applying data from two German arthroplasty-specific registries to predict adverse outcomes after THA, after careful evaluations of ML algorithms, outcome and input variables by an interdisciplinary team of data scientists and surgeons. Methods: Data of 1217 cases of primary THA from a single center were derived from two German arthroplasty-specific registries between 2016 to 2019. The XGBoost algorithm was adjusted and applied. Accuracy, sensitivity, specificity and AUC were calculated. Results: For the prediction of complications, the ML algorithm achieved an accuracy of 80.3%, a sensitivity of 31.0%, a specificity of 89.4% and an AUC of 64.1%. For the prediction of surgery duration, the ML algorithm yielded an accuracy of 81.7%, a sensitivity of 58.2%, a specificity of 91.6% and an AUC of 89.1%. The feature importance indicated non-linear outcomes for age, height, weight and surgeon. No relevant linear correlations were found. Conclusion: The attunement of input and output data as well as the modifications of the ML algorithm permitted the development of a feasible ML model for the prediction of complications and surgery duration.

Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data

PURPOSE

The number of primary total knee arthroplasties (TKA) is expected to rise constantly. For patients and healthcare providers, the early identification of risk factors therefore becomes increasingly fundamental in the context of precision medicine. Others have already investigated the detection of risk factors by conducting literature reviews and applying conventional statistical methods. Since the prediction of events has been moderately accurate, a more comprehensive approach is needed. Machine learning (ML) algorithms have had ample success in many disciplines. However, these methods have not yet had a significant impact in orthopaedic research. The selection of a data source as well as the inclusion of relevant parameters is of utmost importance in this context. In this study, a standardized approach for ML in TKA to predict complications during surgery and an irregular surgery duration using data from two German arthroplasty-specific registries was evaluated.

METHODS

The dataset is based on two initiatives of the German Society for Orthopaedics and Orthopaedic Surgery. A problem statement and initial parameters were defined. After screening, cleaning and preparation of these datasets, 864 cases of primary TKA (2016-2019) were gathered. The XGBoost algorithm was chosen and applied with a hyperparameter search, a cross validation and a loss weighting to cope with class imbalance. For final evaluation, several metrics (accuracy, sensitivity, specificity, AUC) were calculated.

RESULTS

An accuracy of 92.0%, sensitivity of 34.8%, specificity of 95.8%, and AUC of 78.0% were achieved for predicting complications in primary TKA and 93.4%, 74.0%, 96.3%, and 91.6% for predicting irregular surgery duration, respectively. While traditional statistics (correlation coefficient) could not find any relevant correlation between any two parameters, the feature importance revealed several non-linear outcomes.

CONCLUSION

In this study, a feasible ML model to predict outcomes of primary TKA with very promising results was built. Complex correlations between parameters were detected, which could not be recognized by conventional statistical analysis. Arthroplasty-specific data were identified as relevant by the ML model and should be included in future clinical applications. Furthermore, an interdisciplinary interpretation as well as evaluation of the results by a data scientist and an orthopaedic surgeon are of paramount importance.

LEVEL OF EVIDENCE

Level IV.

Do In-Hospital Rothman Index Scores Predict Postdischarge Adverse Events and Discharge Location After Total Knee Arthroplasty?

BACKGROUND

There have been efforts to reduce adverse events and unplanned readmissions after total joint arthroplasty. The Rothman Index (RI) is a real-time, composite measure of medical acuity for hospitalized patients. We aimed to examine the association among in-hospital RI scores and complications, readmissions, and discharge location after total knee arthroplasty (TKA). We hypothesized that RI scores could be used to predict the outcomes of interest.

METHODS

This is a retrospective study of an institutional database of elective, primary TKA from July 2018 until December 2019. Complications and readmissions were defined per Centers for Medicare and Medicaid Services. Analysis included multivariate regression, computation of the area under the curve (AUC), and the Youden Index to set RI thresholds.

RESULTS

The study cohort's (n = 957) complications (2.4%), readmissions (3.6%), and nonhome discharge (13.7%) were reported. All RI metrics (minimum, maximum, last, mean, range, 25th%, and 75th%) were significantly associated with increased odds of readmission and home discharge (all P < .05). RI scores were not significantly associated with complications. The optimal RI thresholds for increased risk of readmission were last ≤ 71 (AUC = 0.65), mean ≤ 67 (AUC = 0.66), or maximum ≤ 80 (AUC = 0.63). The optimal RI thresholds for increased risk of home discharge were minimum ≥ 53 (AUC = 0.65), mean ≥ 69 (AUC = 0.65), or maximum ≥ 81 (AUC = 0.60).

CONCLUSION

RI values may be used to predict readmission or home discharge after TKA.

A Nomogram for Predicting Non-Response to Surgery One Year after Elective Total Hip Replacement

Background: Total hip replacement (THR) is a common and cost-effective procedure for end-stage osteoarthritis, but inappropriate utilization may be devaluing its true impact. The purpose of this study was to develop and test the internal validity of a prognostic algorithm for predicting the probability of non-response to THR surgery at 1 year. Methods: Analysis of outcome data extracted from an institutional registry of individuals (N = 2177) following elective THR performed between January 2012 and December 2019. OMERACT-OARSI responder criteria were applied to Western Ontario and McMaster Universities Arthritis Index (WOMAC) pain and function scores at pre- and 1 year post-THR, to determine non-response to surgery. Independent prognostic correlates of post-operative non-response observed in adjusted modelling were then used to develop a nomogram. Results: A total of 194 (8.9%) cases were deemed non-responders to THR. The degree of contribution (OR, 95% CI) of each explanatory factor to non-response on the nomogram was, morbid obesity (1.88, 1.16, 3.05), Kellgren−Lawrence grade <4 (1.89, 1.39, 2.56), WOMAC Global rating per 10 units (0.86, 0.79, 0.94) and the following co-morbidities: cerebrovascular disease (2.39, 1.33, 4.30), chronic pulmonary disease (1.64; 1.00, 2.71), connective tissue disease (1.99, 1.17, 3.39), diabetes (1.86, 1.26, 2.75) and liver disease (2.28, 0.99, 5.27). The concordance index for the nomogram was 0.70. Conclusion: We have developed a prognostic nomogram to calculate the probability of non-response to THR surgery. In doing so, we determined that both the probability of and predictive prognostic factors for non-response to THR differed from a previously developed nomogram for total knee replacement (TKR), confirming the benefit of designing decision support tools that are both condition and surgery site specific. Future external validation of the nomogram is required to confirm its generalisability.

Artificial intelligence in diagnosis of knee osteoarthritis and prediction of arthroplasty outcomes: a review

Background

Artificial intelligence is an emerging technology with rapid growth and increasing applications in orthopaedics. This study aimed to summarize the existing evidence and recent developments of artificial intelligence in diagnosing knee osteoarthritis and predicting outcomes of total knee arthroplasty.

Methods

PubMed and EMBASE databases were searched for articles published in peer-reviewed journals between January 1, 2010 and May 31, 2021. The terms included: ‘artificial intelligence’, ‘machine learning’, ‘knee’, ‘osteoarthritis’, and ‘arthroplasty’. We selected studies focusing on the use of AI in diagnosis of knee osteoarthritis, prediction of the need for total knee arthroplasty, and prediction of outcomes of total knee arthroplasty. Non-English language articles and articles with no English translation were excluded. A reviewer screened the articles for the relevance to the research questions and strength of evidence.

Results

Machine learning models demonstrated promising results for automatic grading of knee radiographs and predicting the need for total knee arthroplasty. The artificial intelligence algorithms could predict postoperative outcomes regarding patient-reported outcome measures, patient satisfaction and short-term complications. Important weaknesses of current artificial intelligence algorithms included the lack of external validation, the limitations of inherent biases in clinical data, the requirement of large datasets in training, and significant research gaps in the literature.

Conclusions

Artificial intelligence offers a promising solution to improve detection and management of knee osteoarthritis. Further research to overcome the weaknesses of machine learning models may enhance reliability and allow for future use in routine healthcare settings.

The Impact of Pre-Operative Healthcare Utilization on Complications, Readmissions, and Post-Operative Healthcare Utilization Following Total Joint Arthroplasty

BACKGROUND

Identifying risk factors for adverse outcomes and increased costs following total joint arthroplasty (TJA) is needed to ensure quality. The interaction between pre-operative healthcare utilization (pre-HU) and outcomes following TJA has not been fully characterized.

METHODS

This is a retrospective cohort study of patients undergoing elective, primary total hip arthroplasty (THA, N = 1785) or total knee arthroplasty (TKA, N = 2159) between 2015 and 2019 at a single institution. Pre-HU and post-operative healthcare utilization (post-HU) included non-elective healthcare utilization in the 90 days prior to and following TJA, respectively (emergency department, urgent care, observation admission, inpatient admission). Multivariate regression models including age, gender, American Society of Anesthesiologists, Medicaid status, and body mass index were fit for 30-day readmission, Centers for Medicare and Medicaid services (CMS)-defined complications, length of stay, and post-HU.

RESULTS

The 30-day readmission rate was 3.2% and 3.4% and the CMS-defined complication rate was 3.8% and 2.9% for THA and TKA, respectively. Multivariate regression showed that for THA, presence of any pre-HU was associated with increased risk of 30-day readmission (odds ratio [OR] 2.85, 95% confidence interval [CI] 1.48-5.50, P = .002), CMS complications (OR 2.42, 95% CI 1.27-4.59, P = .007), and post-HU (OR 3.65, 95% CI 2.54-5.26, P < .001). For TKA, ≥2 pre-HU events were associated with increased risk of 30-day readmission (OR 3.52, 95% CI 1.17-10.61, P = .026) and post-HU (OR 2.64, 95% CI 1.29-5.40, P = .008). There were positive correlations for THA (any pre-HU) and TKA (≥2 pre-HU) with length of stay and number of post-HU events.

CONCLUSION

Patients who utilize non-elective healthcare in the 90 days prior to TJA are at increased risk of readmission, complications, and unplanned post-HU.

LEVEL OF EVIDENCE

Level III.

The Predictive Accuracy of the CareMOSAIC Risk Assessment for Discharge Disposition in Medicare Bundle Patients After Total Joint Arthroplasty

Background

This article evaluates the predictive accuracy of the CareMOSAIC Risk Assessment for discharge disposition in Medicare patients undergoing total joint arthroplasty.

Methods

Retrospectively collected data from a single institution on 499 consecutive Medicare patients who underwent primary total hip arthroplasty or total knee arthroplasty were reviewed. The CareMOSAIC Risk Assessment was completed by each patient during the preoperative period. The CareMOSAIC Risk Assessment scores were calculated via the CareMOSAIC software, and the scores indicate a risk category for each patient as it relates to post–acute care discharge needs.

Results

The CareMOSAIC Risk Assessment with a binary logistic regression area under the receiver operating characteristic curve of 0.798 appears to be a reliable tool for predicting discharge disposition. The assessment had a positive predictive value of 90.0% and negative predictive value of 76.3% for discharge disposition.

Conclusions

The CareMOSAIC Risk Assessment effectively predicts the discharge disposition for Medicare patients undergoing total hip or total knee arthroplasty.

Red Cell Distribution Width: Commonly Performed Test Predicts Mortality in Primary Total Joint Arthroplasty

INTRODUCTION

Mortality after total joint arthroplasty (TJA) has been thoroughly explored. Short and long-term mortality appear to be correlated with patient comorbidities. Red Cell Distribution Width (RDW) is a commonly performed test that reflects the variation in red blood cell size. This study investigated the utility of RDW, when combined with comorbidity indices, in predicting mortality after TJA.

METHODS

Using a single institutional database, 30,437 primary TJA were identified. Patient demographics (age, gender, body mass index (BMI), pre-operative hemoglobin, RDW, and Charlson Comorbidity Index(CCI)) were queried. The primary outcome was 1-year mortality after TJA. Anemia was defined as hemoglobin <12g/dL for women and <13 g/dL for men. The normal range for RDW is 11.5-14.5%. A preliminary analysis assessed the bivariate association between demographics, preoperative anemia, RDW, CCI, and all-cause mortality within 1-year after TJA. A multivariate regression model was conducted to determine independent predictors of 1-year mortality. Finally, ROC curves were used to compare AUC of RDW, CCI and the combination of both in predicting 1-year mortality.

RESULTS

The mean RDW was 13.6% ± 1.2. Eighteen percent of patients had pre-operative anemia. The mean CCI was 0.4 ± 0.9. RDW, anemia, CCI, and age were significantly associated with a higher incidence of 1-year mortality. RDW, CCI, age, and male sex were found to be independent risk factors for 1-year mortality. RDW (AUC = 0.68) was a better predictor of mortality compared to CCI (AUC = 0.66). The combination of RDW and CCI (AUC = 0.76) predicted 1-year mortality more accurately than CCI or RDW alone.

CONCLUSION

RDW appears to be a useful parameter that, when combined with CCI, can predict the risk for 1-year mortality after TJA.

Reporting of Comorbidities in Total Hip and Knee Arthroplasty Clinical Literature: A Systematic Review

BACKGROUND

The effects of comorbid disease remain an area of interest. Concurrent diagnoses not only affect clinical outcomes but also affect health-care reimbursement. As the rate of arthroplasty increases, consistent risk stratification is imperative. Therefore, our aim was to ascertain how comorbidities have been reported in the recent total hip arthroplasty (THA) and total knee arthroplasty (TKA)-related literature; we also wanted to quantify the use of comorbidity scores for the assessment of comorbid disease in arthroplasty research.

METHODS

A systematic review of the recent THA and TKA literature that was published between January 1, 2019, and September 21, 2020, was performed using the PubMed and MEDLINE databases. Clinical studies that provided data on comorbidities were evaluated for method of comorbidity reporting. The prevalence of comorbidity reporting was assessed, and the manner of reporting was analyzed.

RESULTS

Among 659 articles, a total of 207 studies (31.4%) reported comorbidities and met our inclusion criteria. Of the 207 studies that reported comorbidities, only 57% used a comorbidity index to report comorbid disease. Of all of the indices, the American Society of Anesthesiologists (ASA) Physical Status Classification System was the score that was most commonly used (TKA, 86.2%; THA, 83.3%). Additional scores were used at varying frequencies. For TKA, the scores included the Charlson Comorbidity Index (CCI) (15.5%); the New York Heart Association (NYHA) Functional Classification (3.4%); and the CCI-Deyo (adapted by Deyo et al.), the age-adjusted CCI, the Cumulative Illness Rating Scale (CIRS), and the Readmission Risk Assessment Tool (RRAT) (1.7% each). For THA, the scores included the CCI (16.7%), the Elixhauser Comorbidity Measure (ECM) (6.7%), and the CCI-Deyo (1.7%).

CONCLUSIONS

Considering the impact of comorbid disease on outcomes, complications, and, ultimately, reimbursement, standardized risk stratification in arthroplasty is necessary. Current studies demonstrate inconsistent comorbidity reporting, making it challenging to further characterize the impact of comorbidities on outcomes. Future research should target the development of a standardized data-driven model for comorbidity assessment in the orthopaedic patient population.

Prediction of Major Complications and Readmission After Lumbar Spinal Fusion: A Machine Learning-Driven Approach

BACKGROUND

Given the significant cost and morbidity of patients undergoing lumbar fusion, accurate preoperative risk-stratification would be of great utility. We aim to develop a machine learning model for prediction of major complications and readmission after lumbar fusion. We also aim to identify the factors most important to performance of each tested model.

METHODS

We identified 38,788 adult patients who underwent lumbar fusion at any California hospital between 2015 and 2017. The primary outcome was major perioperative complication or readmission within 30 days. We build logistic regression and advanced machine learning models: XGBoost, AdaBoost, Gradient Boosting, and Random Forest. Discrimination and calibration were assessed using area under the receiver operating characteristic curve and Brier score, respectively.

RESULTS

There were 4470 major complications (11.5%). The XGBoost algorithm demonstrates the highest discrimination of the machine learning models, outperforming regression. The variables most important to XGBoost performance include angina pectoris, metastatic cancer, teaching hospital status, history of concussion, comorbidity burden, and workers' compensation insurance. Teaching hospital status and concussion history were not found to be important for regression.

CONCLUSIONS

We report a machine learning algorithm for prediction of major complications and readmission after lumbar fusion that outperforms logistic regression. Notably, the predictors most important for XGBoost differed from those for regression. The superior performance of XGBoost may be due to the ability of advanced machine learning methods to capture relationships between variables that regression is unable to detect. This tool may identify and address potentially modifiable risk factors, helping risk-stratify patients and decrease complication rates.

A Novel, Potentially Universal Machine Learning Algorithm to Predict Complications in Total Knee Arthroplasty

BACKGROUND

There remains a lack of accurate and validated outcome-prediction models in total knee arthroplasty (TKA). While machine learning (ML) is a powerful predictive tool, determining the proper algorithm to apply across diverse data sets is challenging. AutoPrognosis (AP) is a novel method that uses automated ML framework to incorporate the best performing stages of prognostic modeling into a single well-calibrated algorithm. We aimed to compare various ML methods to AP in predictive performance of complications after TKA.

METHODS

Thirty-eight preoperative patient demographics and clinical features from all primary TKAs performed at California-licensed hospitals between 2015 and 2017 were evaluated as predictors of major complications after TKA. Traditional logistic regression (LR), various other ML methods (XGBoost, Gradient Boosting, AdaBoost, and Random Forest), and AP were used for model building to determine discriminative power (area under receiver operating curve), calibration (Brier score), and feature importance.

RESULTS

Between 2015 and 2017, there were a total of 156,750 TKAs with 1109 (0.7%) total major complications. AP had the highest discriminative performance with area under receiver operating curve 0.679 compared with LR, XGBoost, Gradient Boosting, AdaBoost, and Random Forest (0.617, 0.601, 0.662, 0.657, and 0.545, respectively). AP (Brier score 0.007) had similar calibration as the other ML methods (0.006, 0.006, 0.022, 0.007, and 0.008, respectively). The variables that are most important for AP differ from those that are most important for LR.

CONCLUSION

Compared to conventional ML algorithms, AP has superior discriminative ability with similar calibration and suggests nonlinear relationships between variables in outcomes of TKA.

Development of a Novel, Potentially Universal Machine Learning Algorithm for Prediction of Complications After Total Hip Arthroplasty

BACKGROUND

As the prevalence of hip osteoarthritis increases, the number of total hip arthroplasty (THA) procedures performed is also projected to increase. Accurately risk-stratifying patients who undergo THA would be of great utility, given the significant cost and morbidity associated with developing perioperative complications. We aim to develop a novel machine learning (ML)-based ensemble algorithm for the prediction of major complications after THA, as well as compare its performance against standard benchmark ML methods.

METHODS

This is a retrospective cohort study of 89,986 adults who underwent primary THA at any California-licensed hospital between 2015 and 2017. The primary outcome was major complications (eg infection, venous thromboembolism, cardiac complication, pulmonary complication). We developed a model predicting complication risk using AutoPrognosis, an automated ML framework that configures the optimally performing ensemble of ML-based prognostic models. We compared our model with logistic regression and standard benchmark ML models, assessing discrimination and calibration.

RESULTS

There were 545 patients who had major complications (0.61%). Our novel algorithm was well-calibrated and improved risk prediction compared to logistic regression, as well as outperformed the other four standard benchmark ML algorithms. The variables most important for AutoPrognosis (eg malnutrition, dementia, cancer) differ from those that are most important for logistic regression (eg chronic atherosclerosis, renal failure, chronic obstructive pulmonary disease).

CONCLUSION

We report a novel ensemble ML algorithm for the prediction of major complications after THA. It demonstrates superior risk prediction compared to logistic regression and other standard ML benchmark algorithms. By providing accurate prognostic information, this algorithm may facilitate more informed preoperative shared decision-making.

Readmission, Complication, and Disposition Calculators in Total Joint Arthroplasty: A Systemic Review

BACKGROUND

Predictive tools are useful adjuncts in surgical planning. They help guide patient selection, candidacy for inpatient vs outpatient surgery, and discharge disposition as well as predict the probability of readmissions and complications after total joint arthroplasty (TJA). Surgeons may find it difficult due to significant variation among risk calculators to decide which tool is best suited for a specific patient for optimal decision-based care. Our aim is to perform a systematic review of the literature to determine the existing post-TJA readmission calculators and compare the specific elements that comprise their formula. Second, we intend to evaluate the pros and cons of each calculator.

METHODS

Using a Preferred Reporting Items for Systematic Reviews and Meta-Analysis Protocols protocol, we conducted a systematic search through 3 major databases for publications addressing TJA risk stratification tools for readmission, discharge disposition, and early complications. We excluded those manuscripts that were not comprehensive for hips and knees, did not list discharge, readmission or complication as the primary outcome, or were published outside the North America.

RESULTS

Ten publications met our criteria and were compared on their sourced data, variable types, and overall algorithm quality. Seven of these were generated with single institution data and 3 from large administrative datasets. Three tools determined readmission risk, 5 calculated discharge disposition, and 2 predicted early complications. Only 4 prediction tools were validated by external studies. Seven studies utilized preoperative data points in their risk equations while 3 utilized intraoperative or postsurgical data to delineate risk.

CONCLUSION

The extensive variation among TJA risk calculators underscores the need for tools with more individualized stratification capabilities and verification. The transition to outpatient and same-day discharge TJA may preclude or change the need for many of these calculators. Further studies are needed to develop more streamlined risk calculator tools that predict readmission and surgical complications.

Increasing severity of anemia is associated with poorer 30-day outcomes for total shoulder arthroplasty

Background

Total shoulder arthroplasty (TSA) has increased in utilization over the past several decades. Anemia is a common preoperative condition among patients undergoing TSA and has been associated with poorer outcomes in other surgical procedures. To the best of our knowledge, no study has analyzed the association between anemia severity and TSA outcomes. Therefore, the purpose of this study is to determine the effects that increasing severity of anemia may have on the postoperative outcomes in patients receiving primary TSA.

Methods

A retrospective analysis was performed using the American College of Surgeons National Surgery Quality Improvement Project database from the years 2015 to 2018. Current Procedure Terminology code 23472 was used to identify all primary TSA procedures recorded during this time frame. Patients with greater than 38% preoperative hematocrit (HCT) were classified as having normal HCT levels. Patients with HCT values between 33% and 38% were classified as having mild anemia. All patients with less than 33% HCT were classified as having moderate/severe anemia. Patient demographic information, preoperative risk factors, and postoperative outcomes were compared among the 3 cohorts. A multivariate logistic regression including demographic factors and comorbidities was performed to determine whether increasing severity of anemia is independently associated with poorer postoperative outcomes.

Results

Of the 15,185 patients included in this study, 11,404 had normal HCT levels, 2962 patients were mildly anemic, and 819 patients had moderate to severe anemia. With increasing severity of anemia, there was an increased average hospital length of stay (1.6 vs. 2.1 vs. 3.0 days, P < .001), rate of readmissions (2.3% vs. 4.8% vs. 7.0%, P < .001), and rate of all reoperations (1.1% vs. 1.8% vs. 3.1%, P < .001). There was a statistically significant increase in both minor (1.9% vs. 2.7% vs. 4.4%, P < .001) and major (1.2% vs. 2.4% vs. 4.3%, P < .001) postoperative complication rates as well. Multivariate analysis identified anemia as an independent predictor of readmissions, reoperations, minor complications, and major complications.

Conclusion

We found increasing severity of anemia to be associated with progressively worse 30-day postoperative outcomes. This is consistent with the outcomes found for increasing severity of anemia in patients receiving other total joint procedures. Using preoperative HCT levels may be a useful tool for predicting the risk of postoperative complications in patients undergoing TSA. This information could be used to further optimize patient selection for primary TSA.

Artificial Intelligence for the Orthopaedic Surgeon: An Overview of Potential Benefits, Limitations, and Clinical Applications

Artificial intelligence (AI), along with its subset technology machine learning, has transformed numerous industries through newfound efficiencies and supportive decision-making. These technologies have similarly begun to find application within United States healthcare, particularly orthopaedics. Although these modalities have the potential to similarly transform health care, there exist limitations that must also be recognized and understood. Unfortunately, most clinicians do not have an understanding of the fundamentals of AI and therefore may have challenges in contextualizing its impact in modern healthcare. The purpose of this review was to provide an overview of the key concepts of AI and machine learning with the orthopaedic surgeon in mind. The review further highlights the potential benefits and limitations of AI, along with an overview of its applications, in orthopaedics.

Prediction of 90-day mortality after total hip arthroplasty

AIMS

To develop and externally validate a parsimonious statistical prediction model of 90-day mortality after elective total hip arthroplasty (THA), and to provide a web calculator for clinical usage.

METHODS

We included 53,099 patients with cemented THA due to osteoarthritis from the Swedish Hip Arthroplasty Registry for model derivation and internal validation, as well as 125,428 patients from England and Wales recorded in the National Joint Register for England, Wales, Northern Ireland, the Isle of Man, and the States of Guernsey (NJR) for external model validation. A model was developed using a bootstrap ranking procedure with a least absolute shrinkage and selection operator (LASSO) logistic regression model combined with piecewise linear regression. Discriminative ability was evaluated by the area under the receiver operating characteristic curve (AUC). Calibration belt plots were used to assess model calibration.

RESULTS

A main effects model combining age, sex, American Society for Anesthesiologists (ASA) class, the presence of cancer, diseases of the central nervous system, kidney disease, and diagnosed obesity had good discrimination, both internally (AUC = 0.78, 95% confidence interval (CI) 0.75 to 0.81) and externally (AUC = 0.75, 95% CI 0.73 to 0.76). This model was superior to traditional models based on the Charlson (AUC = 0.66, 95% CI 0.62 to 0.70) and Elixhauser (AUC = 0.64, 95% CI 0.59 to 0.68) comorbidity indices. The model was well calibrated for predicted probabilities up to 5%.

CONCLUSION

We developed a parsimonious model that may facilitate individualized risk assessment prior to one of the most common surgical interventions. We have published a web calculator to aid clinical decision-making. Cite this article: Bone Joint J 2021;103-B(3):469-478.

What Is the Effect of Using a Competing-risks Estimator when Predicting Survivorship After Joint Arthroplasty: A Comparison of Approaches to Survivorship Estimation in a Large Registry

BACKGROUND

There is increasing interest in the development of statistical models that can be used to estimate risk of adverse patient outcomes after joint arthroplasty. Competing risk approaches have been recommended to estimate risk of longer-term revision, which is often likely to be precluded by the competing risk of death. However, a common approach is to ignore the competing risk by treating death as a censoring event and using standard survival models such as Cox regression. It is well-known that this approach can overestimate the event risk for population-level estimates, but the impact on the estimation of a patient's individualized risk after joint arthroplasty has not been explored.

QUESTIONS/PURPOSES

We performed this study to (1) determine whether using a competing risk or noncompeting risk method affects the accuracy of predictive models for joint arthroplasty revision and (2) determine the magnitude of difference that using a competing risks versus noncompeting risks approach will make to predicted risks for individual patients.

METHODS

The predictive performance of a standard Cox model, with competing risks treated as censoring events, was compared with the performance of two competing risks approaches, the cause-specific Cox model and Fine-Gray model. Models were trained and tested using data pertaining to 531,304 TKAs and 274,618 THAs recorded in the Australian Orthopaedic Association National Joint Replacement Registry between January 1, 2003 and December 31, 2017. The registry is a large database with near-complete capture and follow-up of all hip and knee joint arthroplasty in Australia from 2003 onwards, making it an ideal setting for this study. The performance of the three modeling approaches was compared in two different prediction settings: prediction of the 10-year risk of all-cause revision after TKA and prediction of revision for periprosthetic fracture after THA. The calibration and discrimination of each approach were compared using the concordance index, integrated Brier scores, and calibration plots. Calibration of 10-year risk estimates was further assessed within subgroups of age by comparing the observed and predicted proportion of events. Estimated 10-year risks from each model were also compared in three hypothetical patients with different risk profiles to determine whether differences in population-level performance metrics would translate into a meaningful difference for individual patient predictions.

RESULTS

The standard Cox and two competing risks models showed near-identical ability to distinguish between high-risk and low-risk patients (c-index 0.64 [95% CI, 0.64 to 0.64] for all three modeling approaches for TKAs and 0.66 [95% CI 0.66 to 0.66] for THA). All models performed similarly in patients younger than 75 years, but for patients aged 75 years and older, the standard Cox model overestimated the risk of revision more than the cause-specific Cox and Fine-Gray model did. These results were echoed when predictions were made for hypothetical individual patients. For patients with a low competing risk of mortality, the 10-year predicted risks from the standard Cox, cause-specific Cox, and Fine-Gray models were similar for TKAs and THAs. However, a larger difference was observed for hypothetical 89-year-old patients with increased mortality risk. In TKAs, the revision risk for an 89-year-old patient was so low that this difference was negligible (0.83% from the cause-specific Cox model versus 1.1% from the standard Cox model). However, for THAs, where older age is a risk factor for both death and revision for periprosthetic fracture, a larger difference was observed in the 10-year predicted risks for a hypothetical 89-year-old patient (3.4% from the cause-specific Cox model versus 5.2% from the standard Cox model).

CONCLUSION

When developing models to predict longer-term revision of joint arthroplasty, failing to use a competing risks modeling approach will result in overestimating the revision risk for patients with a high risk of mortality during the surveillance period. However, even in an extreme instance, where both the frequency of the event of interest and the competing risk of death are high, the largest absolute difference in predicted 10-year risk for an individual patient was just 1.8%, which may not be of consequence to an individual. Despite these findings, when developing or using risk prediction models, researchers and clinicians should be aware of how competing risks were handled in the modeling process, particularly if the model is intended for use populations where the mortality risk is high.

LEVEL OF EVIDENCE

Level III, therapeutic study.

Comparison of machine learning techniques to predict unplanned readmission following total shoulder arthroplasty

BACKGROUND

Machine learning (ML) techniques have been shown to successfully predict postoperative complications for high-volume orthopedic procedures such as hip and knee arthroplasty and to stratify patients for risk-adjusted bundled payments. The latter has not been done for more heterogeneous, lower-volume procedures such as total shoulder arthroplasty (TSA) with equally limited discussion around strategies to optimize the predictive ability of ML algorithms. The purpose of this study was to (1) assess which of 5 ML algorithms best predicts 30-day readmission, (2) test select ML strategies to optimize the algorithms, and (3) report on which patient variables contribute most to risk prediction in TSA across algorithms.

METHODS

We identified 9043 patients in the American College of Surgeons National Surgical Quality Improvement Database who underwent primary TSA between 2011 and 2015. Predictors included demographics, comorbidities, laboratory data, and intraoperative variables. The outcome of interest was 30-day unplanned readmission. Five ML algorithms-support-vector machine (SVM), logistic regression, random forest (RF), an adaptive boosting algorithm, and neural network-were trained on the derivation cohort (2011-2014 TSA patients) to predict 30-day unplanned readmission rates. After training, weights for each respective model were fixed and the classifiers were evaluated on the 2015 TSA cohort to simulate a prospective evaluation. C-statistic and f1 scores were used to assess the performance of each classifier. After evaluation, features were removed independently to assess which features most affected classifier performance.

RESULTS

The derivation and validation cohorts comprised 5857 and 3186 primary TSA patients, respectively, with similar demographics, comorbidities, and 30-day unplanned readmission rates (2.9% vs. 2.7%). Of the ML algorithms, SVM performed the worst with a c-statistic of 0.54 and an f1-score of 0.07, whereas the random-forest classifier performed the best with the highest c-statistic of 0.74 and an f1-score of 0.18. In addition, SVM was most sensitive to loss of single features, whereas the performance of RF did not dramatically decrease after loss of single features. Within the trained RF classifier, 5 variables achieved weights >0.5 in descending order: high bilirubin (>1.9 mg/dL), age >65, race, chronic obstructive pulmonary disease, and American Society of Anesthesiologists' scores ≥3. In our validation cohort, we observed a 2.7% readmission rate. From this cohort, using the RF classifier we were then able to identify 436 high-risk patients with a predicted risk score >0.6, of whom 36 were readmitted (readmission rate of 8.2%).

CONCLUSION

Predictive analytics algorithms can achieve acceptable prediction of unplanned readmission for TSA with the RF classifier outperforming other common algorithms.

Risk of Postoperative Complications and Revision Surgery Following Robot-assisted Posterior Lumbar Spinal Fusion

STUDY DESIGN

Retrospective Study.

OBJECTIVE

This investigation examined matched cohorts of lumbar spinal fusion (LSF) patients undergoing robot-assisted and conventional LSF to compare risk of revision, 30-day readmission, 30-day complications, and postoperative opioid utilization.

SUMMARY OF BACKGROUND DATA

Patient outcomes and complication rates associated with robot-assisted LSF compared to conventional fusion techniques are incompletely understood.

METHODS

The PearlDiver Research Program (www.pearldiverinc.com) was used to identify patients undergoing primary LSF between 2011 and 2017. Patients receiving robot-assisted or conventional LSF were matched using key demographic and comorbidity variables. Indication for revision was also studied. Risk of revision, 30-day readmission, 30-day complications, and postoperative opioid utilization at 1 and 6 months was compared between the cohorts using multivariable logistic regression additionally controlling for age, sex, and Charlson Comorbidity Index.

RESULTS

The percent of LSFs that were robot-assisted rose by 169% from 2011 to 2017, increasing linearly each year (p = 0.0007). Matching resulted in 2528 patients in each cohort for analysis. Robot-assisted LSF patients experienced higher risk of revision (adjusted odds ratio [aOR] = 2.35, P ≤ 0.0001), 30-day readmission (aOR = 1.39, P = 0.0002), and total 30-day complications (aOR = 1.50, P < 0.0001), specifically respiratory (aOR = 1.56, P = 0.0006), surgical site infection (aOR = 1.56, P = 0.0061), and implant-related complications (aOR = 1.74, P = 0.0038). The risk of revision due to infection after robot-assisted LSF was an estimated 4.5-fold higher (aOR = 4.46, 95% confidence interval [CI] 1.95-12.04, P = 0.0011). Furthermore, robot-assisted LSF had increased risk of revision due to instrument failure (aOR = 1.64, 95% CI 1.05-2.58, P = 0.0300), and pseudarthrosis (aOR = 2.24, 95%CI = 1.32-3.95, P = 0.0037). A higher percentage of revisions were due to infection in robot-assisted LSF (19.0%) than in conventional LSF (9.2%) (P = 0.0408).

CONCLUSION

Robotic-assisted posterior LSF is independently associated with increased risk of revision surgery, infection, instrumentation complications, and postoperative opioid utilization compared to conventional fusion techniques. Further research is needed to investigate long-term postoperative outcomes following robot-assisted LSF. Spine surgeons should be cautious when considering immediate adoption of this emerging surgical technology.

LEVEL OF EVIDENCE

3.

Stratifying Venous Thromboembolism Risk in Arthroplasty: Do High-Risk Patients Exist?

BACKGROUND

While there are many possible complications associated with total joint arthroplasty (TJA), venous thromboembolism (VTE) is both frequent and potentially severe. Despite this importance, there are inconsistent recommendations for prophylaxis based on patient risk factors.

METHODS

A predictive model was constructed to compare low-molecular-weight heparin(LMWH) and aspirin (ASA) for prevention of VTE-associated complications following TJA.The model used risks from prior prophylaxis studies to estimate the risk of developing a symptomatic deep vein thrombosis, pulmonary embolism, thrombocytopenia, and operative or nonoperative site bleeding. We also evaluated the progression to 4 possible final health states: postphlebitis syndrome, intracranial hemorrhage, death, or baseline health. Within published ranges, we selected assumptions that were favorable to LMWH such that these analyses represent a best case scenario for LMWH or an alternative more aggressive low-molecular-weight heparin alternative (LMWHA). Events and outcomes were assigned quality-adjusted life-year (QALY) losses according to prior studies to determine the effect on patients' outcomes for ASA and LMWHA prophylaxis.

RESULTS

Assessing VTE risk populations from 0.2% to 2% with life expectancies ranging from 5 to 40 years postoperatively, patients with a risk ratio less than 3.7 showed increased expected QALY with ASA compared to LMWHA. For patients with a baseline VTE risk of 1% and a 15 year life expectancy, a risk ratio of 13.4 was needed to identify patients that would benefit from LMWHA. With life expectancy increased to 30 years, the risk ratio needed to idetify these patients was 7.4.

CONCLUSION

Patients undergoing TJA should receive ASA chemoprophylaxis in nearly all situations, unless the patient has a significantly increased VTE risk compared to the baseline population and a long life expectancy.

The Effects of Bundled Payment Programs for Hip and Knee Arthroplasty on Patient-Reported Outcomes

BACKGROUND

Patient-reported outcomes are essential to demonstrate the value of hip and knee arthroplasty, a common target for payment reforms. We compare patient-reported global and condition-specific outcomes after hip and knee arthroplasty based on hospital participation in Medicare's bundled payment programs.

METHODS

We performed a prospective observational study using the Comparative Effectiveness of Pulmonary Embolism Prevention after Hip and Knee Replacement trial. Differences in patient-reported outcomes through 6 months were compared between bundle and nonbundle hospitals using mixed-effects regression, controlling for baseline patient characteristics. Outcomes were the brief Knee Injury and Osteoarthritis Outcomes Score or the brief Hip Disability and Osteoarthritis Outcomes Score, the Patient-Reported Outcomes Measurement Information System Physical Health Score, and the Numeric Pain Rating Scale, measures of joint function, overall health, and pain, respectively.

RESULTS

Relative to nonbundled hospitals, arthroplasty patients at bundled hospitals had slightly lower improvement in Knee Injury and Osteoarthritis Outcomes Score (-1.8 point relative difference at 6 months; 95% confidence interval -3.2 to -0.4; P = .011) and Hip Disability and Osteoarthritis Outcomes Score (-2.3 point relative difference at 6 months; 95% confidence interval -4.0 to -0.5; P = .010). However, these effects were small, and the proportions of patients who achieved a minimum clinically important difference were similar. Preoperative to postoperative change in the Patient-Reported Outcomes Measurement Information System Physical Health Score and Numeric Pain Rating Scale demonstrated a similar pattern of slightly worse outcomes at bundled hospitals with similar rates of achieving a minimum clinically important difference.

CONCLUSIONS

Patients receiving care at hospitals participating in Medicare's bundled payment programs do not have meaningfully worse improvements in patient-reported measures of function, health, or pain after hip or knee arthroplasty.

Patient-Reported Outcomes Following Total Hip Arthroplasty: A Multicenter Comparison Based on Surgical Approaches

BACKGROUND

Comparisons of patient-reported outcomes (PROs) based on surgical approach for total hip arthroplasty (THA) in the United States are limited to series from single surgeons or institutions. Using prospective data from a large, multicenter study, we compare preoperative to postoperative changes in PROs between posterior, transgluteal, and anterior surgical approaches to THA.

METHODS

Patient-reported function, global health, and pain were systematically collected preoperatively and at 1, 3, and 6 months postoperatively from patients undergoing primary THA at 26 sites participating in the Comparative Effectiveness of Pulmonary Embolism Prevention After Hip and Knee Replacement (ClinicalTrials.gov: NCT02810704). Outcomes consisted of the brief Hip disability and Osteoarthritis Outcome Score, the Patient-Reported Outcomes Measurement Information System Physical Health score, and the Numeric Pain Rating Scale. Operative approaches were grouped by surgical plane relative to the abductor musculature as being either anterior, transgluteal, or posterior.

RESULTS

Between 12/12/2016 and 08/31/2019, outcomes from 3018 eligible participants were examined. At 1 month, the transgluteal cohort had a 2.2-point lower improvement in Hip disability and Osteoarthritis Outcomes Score (95% confidence interval, 0.40-4.06; P = .017) and a 1.3-point lower improvement in Patient-Reported Outcomes Measurement Information System Physical Health score (95% confidence interval, 0.48-2.04; P = .002) compared to posterior approaches. There was no significant difference in improvement between anterior and posterior approaches. At 3 and 6 months, no clinically significant differences in PRO improvement were observed between groups.

CONCLUSION

PROs 6 months following THA dramatically improved regardless of the plane of surgical approach, suggesting that choice of surgical approach can be left to the discretion of surgeons and patients without fear of differential early outcomes.

Surgical selection criteria compliance is associated with a lower risk of periprosthetic joint infection in total hip arthroplasty

Background

Periprosthetic joint infection (PJI) is a devastating complication of total hip arthroplasty (THA). Patient optimization represents an important target for PJI prevention. Unfortunately, best practice screening guidelines are not consistently followed by all surgeons. Our study aimed to determine both the degree and the effect that compliance with our institutional preoperative surgical selection criteria had on PJI rates for patients undergoing elective primary THA.

Methods

A retrospective review was conducted on 455 elective primary THA procedures performed at an academic tertiary care center over a 2-year period. Institutional preoperative surgical selection criteria included the following: body mass index ≤40 kg/m², hemoglobin A1c ≤7.5%, hemoglobin ≥12 g/dL, albumin ≥3.5 g/dL, no smoking within 30 days prior to surgery, and completion of a decolonization protocol if a nasal polymerase chain reaction was positive for Staphylococcus aureus. PJI was assessed for a minimum 1-year follow-up using Musculoskeletal Infection Society criteria from 2011. Rates of compliance and PJI were compared using a chi-squared test.

Results

Surgeon compliance with institutional preoperative selection criteria was 62.4% and ranged from 0.0% to 83.9%. Five of 455 patients developed a PJI. The total PJI rate was 1.1%. The compliant patient cohort had a PJI rate of 0.0%, while the noncompliant cohort had a PJI rate of 2.9% (P = .0038).

Conclusions

This study identified a statistically significant decrease in PJI rates among patients who met all preoperative screening criteria.

Preoperative Patient-Reported Outcomes and Clinical Characteristics as Predictors of 90-Day Cost/Utilization and Complications

BACKGROUND

With the advent of mandatory bundle payments for total joint arthroplasty (TJA), assessing patients' risk for increased 90-day complications and resource utilization is crucial. This study assesses the degree to which preoperative patient-reported outcomes predict 90-day complications, episode costs, and utilization in TJA patients.

METHODS

All TJA cases in 2017 at 2 high-volume hospitals were queried. Preoperative HOOS/KOOS JR (Hip Injury and Osteoarthritis Outcome Score/Knee Injury and Osteoarthritis Outcome Score) and Veterans RAND 12-item health survey (VR-12) were administered to patients preoperatively via e-collection platform. For patients enrolled in the Medicare bundle, cost data were extracted from claims. Bivariate and multivariate regression analyses were performed.

RESULTS

In total, 2108 patients underwent TJA in 2017; 1182 (56%) were missing patient-reported outcome data and were excluded. The final study population included 926 patients, 199 (21%) of which had available cost data. Patients with high bundle costs tended to be older, suffer from vascular disease and anemia, and have higher Charlson scores (P < .05 for all). These patients also had lower baseline VR-12 Physical Component Summary Score (PCS; 24 vs 30, P ≤ .001) and higher rates of extended length of stay, skilled nursing facility discharge, 90-day complications, and 90-day readmission (P ≤ .04 for all). In multivariate analysis, higher baseline VR-12 PCS was protective against extended length of stay, skilled nursing facility discharge, >75th percentile bundle cost, and 90-day bundle cost exceeding target bundle price (P < .01 for all). Baseline VR-12 Mental Component Summary Score and HOOS/KOOS JR were not predictive of complications or bundle cost.

CONCLUSION

Low baseline VR-12 PCS is predictive of high 90-day bundle costs. Baseline HOOS/KOOS JR scores were not predictive of utilization or cost. Neither VR-12 nor HOOS/KOOS JR was predictive of 90-day readmission or complications.

Can Machine Learning Methods Produce Accurate and Easy-to-use Prediction Models of 30-day Complications and Mortality After Knee or Hip Arthroplasty?

BACKGROUND

Existing universal and procedure-specific surgical risk prediction models of death and major complications after elective total joint arthroplasty (TJA) have limitations including poor transparency, poor to modest accuracy, and insufficient validation to establish performance across diverse settings. Thus, the need remains for accurate and validated prediction models for use in preoperative management, informed consent, shared decision-making, and risk adjustment for reimbursement.

QUESTIONS/PURPOSES

The purpose of this study was to use machine learning methods and large national databases to develop and validate (both internally and externally) parsimonious risk-prediction models for mortality and complications after TJA.

METHODS

Preoperative demographic and clinical variables from all 107,792 nonemergent primary THAs and TKAs in the 2013 to 2014 American College of Surgeons-National Surgical Quality Improvement Program (ACS-NSQIP) were evaluated as predictors of 30-day death and major complications. The NSQIP database was chosen for its high-quality data on important outcomes and rich characterization of preoperative demographic and clinical predictors for demographically and geographically diverse patients. Least absolute shrinkage and selection operator (LASSO) regression, a type of machine learning that optimizes accuracy and parsimony, was used for model development. Tenfold validation was used to produce C-statistics, a measure of how well models discriminate patients who experience an outcome from those who do not. External validation, which evaluates the generalizability of the models to new data sources and patient groups, was accomplished using data from the Veterans Affairs Surgical Quality Improvement Program (VASQIP). Models previously developed from VASQIP data were also externally validated using NSQIP data to examine the generalizability of their performance with a different group of patients outside the VASQIP context.

RESULTS

The models, developed using LASSO regression with diverse clinical (for example, American Society of Anesthesiologists classification, comorbidities) and demographic (for example, age, gender) inputs, had good accuracy in terms of discriminating the likelihood a patient would experience, within 30 days of arthroplasty, a renal complication (C-statistic, 0.78; 95% confidence interval [CI], 0.76-0.80), death (0.73; 95% CI, 0.70-0.76), or a cardiac complication (0.73; 95% CI, 0.71-0.75) from one who would not. By contrast, the models demonstrated poor accuracy for venous thromboembolism (C-statistic, 0.61; 95% CI, 0.60-0.62) and any complication (C-statistic, 0.64; 95% CI, 0.63-0.65). External validation of the NSQIP- derived models using VASQIP data found them to be robust in terms of predictions about mortality and cardiac complications, but not for predicting renal complications. Models previously developed with VASQIP data had poor accuracy when externally validated with NSQIP data, suggesting they should not be used outside the context of the Veterans Health Administration.

CONCLUSIONS

Moderately accurate predictive models of 30-day mortality and cardiac complications after elective primary TJA were developed as well as internally and externally validated. To our knowledge, these are the most accurate and rigorously validated TJA-specific prediction models currently available (http://med.stanford.edu/s-spire/Resources/clinical-tools-.html). Methods to improve these models, including the addition of nonstandard inputs such as natural language processing of preoperative clinical progress notes or radiographs, should be pursued as should the development and validation of models to predict longer term improvements in pain and function.

LEVEL OF EVIDENCE

Level III, diagnostic study.

Statistical Methods Dictate the Estimated Impact of Body Mass Index on Major and Minor Complications After Total Joint Arthroplasty

BACKGROUND

Elevated body mass index (BMI) is considered a risk factor for complications after THA and TKA. Stakeholders have proposed BMI cutoffs for those seeking arthroplasty. The research that might substantiate BMI cutoffs is sensitive to the statistical methods used, but the impact of the statistical methods used to model BMI has not been defined.

QUESTIONS/PURPOSES

(1) How does the estimated postarthroplasty risk of minor and major complications vary as a function of the statistical method used to model BMI? (2) What is the prognostic value of BMI for predicting complications with each statistical method?

METHODS

Using the American College of Surgeons National Surgical Quality Improvement Program from 2005 to 2012, we investigated the impact of BMI on major and minor complication risk for THA and TKA. Analyses were weighted with covariate-balancing propensity scores to account for the differential rate of comorbidities across the range of BMI. We specified BMI in two ways: (1) categorically by World Health Organization (WHO) BMI classes; and (2) as a smooth, continuous variable using splines. Models of risk for major complications (deep surgical site infection [SSI], pulmonary embolism, stroke, cardiac arrest, myocardial infarction, wound disruption, implant failure, unplanned intubation, > 48 hours on a ventilator, acute renal insufficiency, coma, sepsis, reoperation, or mortality) and minor complications (superficial SSI, pneumonia, urinary tract infection, deep vein thrombosis, or peripheral nerve injury) were constructed and were adjusted for confounding variables known to correlate with complications (eg, American Society of Anesthesiologists classification). Results were compared for different specifications of BMI. Receiver operating characteristic (ROC) curves were compared to determine the additive prognostic value of BMI.

RESULTS

The type of BMI parameterization leads to different assessments of risk of postarthroplasty complications for BMIs > 30 kg/m and < 20 kg/m with the spline specification showing better fit in all adjusted models (Akaike Information Criteria favors spline). Modeling BMI categorically using WHO classes indicates that BMI cut points of 40 kg/m for TKA or 35 kg/m for THA are associated with higher risks of major complications. Modeling BMI continuously as a spline suggests that risk of major complications is elevated at a cut point of 44 kg/m for TKA and 35 kg/m for THA. Additionally, in these models, risk does not uniformly increase with increasing BMI. Regardless of the method of modeling, BMI is a poor prognosticator for complications with area under the ROC curves between 0.51 and 0.56, false-positive rates of 96% to 97%, and false-negative rates of 2% to 3%.

CONCLUSIONS

The statistical assumptions made when modeling the effect of BMI on postarthroplasty complications dictate the results. Simple categorical handling of BMI creates arbitrary cutoff points that should not be used to inform larger policy decisions. Spline modeling of BMI avoids arbitrary cut points and provides a better model fit at extremes of BMI. Regardless of statistical management, BMI is an inadequate independent prognosticator of risk for individual patients considering total joint arthroplasty. Stakeholders should instead perform comprehensive risk assessment and avoid use of BMI as an isolated indicator of risk.

LEVEL OF EVIDENCE

Level III, diagnostic study.

American Joint Replacement Registry Risk Calculator Does Not Predict 90-day Mortality in Veterans Undergoing Total Joint Replacement

BACKGROUND

The American Joint Replacement Registry (AJRR) Total Joint Risk Calculator uses demographic and clinical parameters to provide risk estimates for 90-day mortality and 2-year periprosthetic joint infection (PJI). The tool is intended to help surgeons counsel their Medicare-eligible patients about their risk of death and PJI after total joint arthroplasty (TJA). However, for a predictive risk model to be useful, it must be accurate when applied to new patients; this has yet to be established for this calculator.

QUESTIONS/PURPOSES

To produce accuracy metrics (ie, discrimination, calibration) for the AJRR mortality calculator using data from Medicare-eligible patients undergoing TJA in the Veterans Health Administration (VHA), the largest integrated healthcare system in the United States, where more than 10,000 TJAs are performed annually.

METHODS

We used the AJRR calculator to predict risk of death within 90 days of surgery among 31,214 VHA patients older than 64 years of age who underwent primary TJA; data was drawn from the Veterans Affairs Surgical Quality Improvement Project (VASQIP) and VA Corporate Data Warehouse (CDW). We then used VHA mortality data to evaluate the extent to which the AJRR calculator estimates distinguished individuals who died compared with those who did not (C-statistic), and graphically depicted the relationship between estimated risk and observed mortality (calibration). As a secondary evaluation of the calculator, a sample of 39,300 patients younger than 65 years old was assigned to the youngest age group available to the user (65-69 years) as might be done in real-world practice.

RESULTS

C-statistics for 90-day mortality for the older samples were 0.62 (95% CI, 0.60-0.64) and for the younger samples they were 0.46 (95% CI, 0.43-0.49), suggesting poor discrimination. Calibration analysis revealed poor correspondence between deciles of predicted risk and observed mortality rates. Poor discrimination and calibration mean that patients who died will frequently have a lower estimated risk of death than surviving patients.

CONCLUSIONS

For Medicare-eligible patients receiving TJA in the VA, the AJRR risk calculator had a poor performance in the prediction of 90-day mortality. There are several possible reasons for the model's poor performance. Veterans Health Administration patients, 97% of whom were men, represent only a subset of the broader Medicare population. However, applying the calculator to a subset of the target population should not affect its accuracy. Other reasons for poor performance include a lack of an underlying statistical model in the calculator's implementation and simply the challenge of predicting rare events. External validation in a more representative sample of Medicare patients should be conducted to before assuming this tool is accurate for its intended use.

LEVEL OF EVIDENCE

Level I, diagnostic study.

Prediction Models for 30-Day Mortality and Complications After Total Knee and Hip Arthroplasties for Veteran Health Administration Patients With Osteoarthritis

BACKGROUND

Statistical models to preoperatively predict patients' risk of death and major complications after total joint arthroplasty (TJA) could improve the quality of preoperative management and informed consent. Although risk models for TJA exist, they have limitations including poor transparency and/or unknown or poor performance. Thus, it is currently impossible to know how well currently available models predict short-term complications after TJA, or if newly developed models are more accurate. We sought to develop and conduct cross-validation of predictive risk models, and report details and performance metrics as benchmarks.

METHODS

Over 90 preoperative variables were used as candidate predictors of death and major complications within 30 days for Veterans Health Administration patients with osteoarthritis who underwent TJA. Data were split into 3 samples-for selection of model tuning parameters, model development, and cross-validation. C-indexes (discrimination) and calibration plots were produced.

RESULTS

A total of 70,569 patients diagnosed with osteoarthritis who received primary TJA were included. C-statistics and bootstrapped confidence intervals for the cross-validation of the boosted regression models were highest for cardiac complications (0.75; 0.71-0.79) and 30-day mortality (0.73; 0.66-0.79) and lowest for deep vein thrombosis (0.59; 0.55-0.64) and return to the operating room (0.60; 0.57-0.63).

CONCLUSIONS

Moderately accurate predictive models of 30-day mortality and cardiac complications after TJA in Veterans Health Administration patients were developed and internally cross-validated. By reporting model coefficients and performance metrics, other model developers can test these models on new samples and have a procedure and indication-specific benchmark to surpass.

Risk Reduction Compared with Access to Care: Quantifying the Trade-Off of Enforcing a Body Mass Index Eligibility Criterion for Joint Replacement

BACKGROUND

Morbidly obese patients with severe osteoarthritis benefit from successful total joint arthroplasty. However, morbid obesity increases the risk of complications. Because of this, some surgeons enforce a body mass index (BMI) eligibility criterion above which total joint arthroplasty is denied. In this study, we investigate the trade-off between avoiding complications and restricting access to care when enforcing BMI-based eligibility criteria for total joint arthroplasty.

METHODS

In this retrospective cohort study, the Veterans Health Administration (VHA) Corporate Data Warehouse (CDW) and Veterans Affairs Surgical Quality Improvement Program (VASQIP) databases were reviewed for patients undergoing total joint arthroplasty from October 2011 through September 2014. We determined, if various BMI eligibility criteria had been enforced over that period of time, how many short-term complications would have been avoided, how many complication-free surgical procedures would have been denied, and the positive predictive value of BMI eligibility criteria as tests for major complications. To provide a frame of reference, we also determined what would have happened if eligibility for total joint arthroplasty were arbitrarily determined by flipping a coin.

RESULTS

In this study, 27,671 total joint arthroplasties were reviewed. With a BMI criterion of ≥40 kg/m, 1,148 patients would have been denied a surgical procedure free of major complications, and 83 patients would have avoided a major complication. The positive predictive value of a complication using a BMI of ≥40 kg/m as a test for major complications was 6.74% (95% confidence interval [CI], 5.44% to 8.33%). The positive predictive value of a complication using a BMI criterion of 30 kg/m was 5.33% (95% CI, 4.99% to 5.71%). Flipping a coin had a positive predictive value of 5.05%.

CONCLUSIONS

A 30 kg/m criterion for total joint arthroplasty eligibility is marginally better than flipping a coin and should not determine surgical eligibility. With a BMI criterion of ≥40 kg/m, the number of patients denied a complication-free surgical procedure is about 14 times larger than those spared a complication. Although the acceptable balance between avoiding complications and providing access to care can be debated, such a quantitative assessment helps to inform decisions regarding the advisability of enforcing a BMI criterion for total joint arthroplasty.

LEVEL OF EVIDENCE

Therapeutic Level III. See Instructions for Authors for a complete description of levels of evidence.

Appropriateness Criteria for Total Knee Arthroplasty: Additional Comments and Considerations

Appropriateness classification for total knee arthroplasty (TKA) has received substantial attention recently, and Katz and colleagues published an Orthopaedic Forum on the topic in The Journal of Bone & Joint Surgery in February 2017. Classifications of appropriateness are particularly important given the rapid rise in use of TKA and a variety of third-party payer approaches designed to control health-care costs. We respond to some of the concerns addressed by Katz and colleagues, and elaborate on what we believe are some important issues related to both older and newer appropriateness criteria for TKA.

The Effect of Smoking on Thirty-Day Postoperative Complications After Total Joint Arthroplasty: A Propensity Score-Matched Analysis

BACKGROUND

Total joint arthroplasty (TJA) is a highly successful treatment, but is burdensome to the national healthcare budget. National quality initiatives seek to reduce costly complications. Smoking's role in perioperative complication after TJA is less well known. This study aims to identify smoking's independent contribution to the risk of short-term complication after TJA.

METHODS

All patients undergoing primary TJA between 2011 and 2012 were selected from the American College of Surgeon's National Surgical Quality Improvement Program's database. Outcomes of interest included rates of readmission, reoperation, mortality, surgical complications, and medical complications. To eliminate confounders between smokers and nonsmokers, a propensity score was used to generate a 1:1 match between groups.

RESULTS

A total of 1251 smokers undergoing TJA met inclusion criteria. Smokers in the combined total hip and knee arthroplasty cohort had higher 30-day readmission (4.8% vs 3.2%, P = .041), were more likely to have a surgical complication (odds ratio 1.84, 95% confidence interval 1.21-2.80), and had a higher rate of deep surgical site infection (SSI) (1.1% vs 0.2%, P = .007). Analysis of total hip arthroplasty only revealed that smokers had higher rates of deep SSI (1.3% vs 0.2%, P = .038) and higher readmission rate (4.3% vs 2.2%, P = .034). Analysis of total knee arthroplasty only revealed greater surgical complications (2.8% vs 1.2%, P = .048) and superficial SSI (1.8% vs 0.2%, P = .002) in smokers.

CONCLUSION

Smoking in TJA is associated with higher rates of SSI, surgical complications, and readmission.

Correlation of the Caprini Score and Venous Thromboembolism Incidence Following Primary Total Joint Arthroplasty-Results of a Single-Institution Protocol

BACKGROUND

Venous thromboembolism (VTE), including pulmonary embolism (PE) and deep vein thrombosis, is a serious complication after total joint arthroplasty (TJA). Risk assessment models are increasingly used to provide patient-specific risk stratification. A recently implemented protocol mandates calculation of a Caprini Score for all surgical patients at our institution. We investigated the accuracy of the Caprini Score in predicting VTE events following TJA.

METHODS

A retrospective review of patients undergoing primary total hip (THA) and total knee arthroplasty (TKA) over a 1-year time period was performed. The 90-day postoperative incidence of emergency department evaluations, hospital readmissions, medical complications, need for revision surgery, and symptomatic VTE was recorded. "Preoperative" Caprini Scores routinely recorded per protocol and calculated during review ("Calculated") were compared and assessed for relationship with VTE events. A "VTEstimator" Score was calculated for each patient.

RESULTS

Three hundred seventy-six arthroplasties (151 TKA and 225 THA) meeting inclusion criteria were identified. Ten patients (2.5%) had symptomatic VTE postoperatively, with 3 pulmonary embolism (0.8%) and 7 deep vein thrombosis (1.8%). Eight VTE (5.3%) occurred following TKA and 2 (0.9%) occurred following THA. For each surgical characteristic evaluated, no significant difference was observed between mean Preoperative or Calculated Caprini Scores for patients with and without VTE (P > .05). Additionally, the distribution of VTEstimator Scores for patients with and without VTE was not significantly different (P = .93).

CONCLUSION

The Caprini risk assessment model does not appear to provide clinically useful risk stratification for TJA patients. Alternative risk stratification protocols may provide assistance in balancing safety and efficacy of thromboprophylaxis.

Day of Surgery and Surgical Start Time Affect Hospital Length of Stay After Total Hip Arthroplasty

BACKGROUND

The United States spends $12 billion each year on ∼332,000 total hip arthroplasty (THA) procedures with the postoperative period accounting for ∼40% of costs. The purpose of this study was to evaluate the effect of surgical scheduling (day of week and start time) on clinical outcomes, hospital length of stay (LOS), and rate of nonhome discharge in THA patients.

METHODS

Analysis of perioperative variables was performed for patients who underwent THA at an urban tertiary care teaching hospital from 2009 to 2014.

RESULTS

A total of 580 THA patients were included for analysis. LOS was higher for the Thursday/Friday cohort compared to Monday/Tuesday (3.7 vs 3.4 days; P = .03). Patients who had a surgical start time after 2 PM had longer LOS compared to patients operated on before 2 PM (3.9 vs 3.5 days; P = .03). After controlling for patient comorbidities and THA surgical approach (direct anterior vs posterior), Thursday/Friday THAs were associated with a 3.27 times risk of extended LOS (>75th percentile LOS) compared to Monday/Tuesday THAs (P < .001). Additionally, case start before 2 PM was protective and associated with a 0.46 times odds of extended LOS (P = .01). LOS reduction opportunity for changing surgical start time to before 2 PM was 0.9 days for high-risk patients (American Society of Anesthesiology class 3/4 and/or liver disease) and 0.2 days for low-risk patients (American Society of Anesthesiology class 1/2).

CONCLUSION

Patients who underwent THA Thursday/Friday or had start times after 2 PM had significantly extended hospital LOS. Preoperative risk modification along with adjustments to surgical scheduling and/or perioperative staffing may reduce LOS and thus hospital expenditures for THA procedures.

Incidence and Risk Factors for Health-Care Associated Infections after Hip Operation

BACKGROUND

Hip operation reduces pain and improves mobility and quality of life for more than 300,000 people annually, most of whom are more than 65 years old. Substantial increases in surgical volume are projected between 2005 and 2030 in primary total (174%) and revision (137%) procedures. This projection demands that the impact of increasing age on the relative risk of health-care associated infections (HAI) after hip surgical procedures be assessed. Our aim was to examine the incidence and risk factors of HAI among patients who underwent hip operations between 2006 and 2012.

PATIENTS AND METHODS

This secondary analysis included data from patients 18 years old or older and having a hip prosthesis procedure in three New York City hospitals between 2006 and 2012. Procedures were categorized as total or partial hip replacements or revision and re-surfacing procedures. Outcomes of interest were blood stream infections (BSI), urinary tract infections (UTI), or surgical site infections (SSI). Patients in whom an infection developed during the hospital visit in which the hip procedure occurred were counted as cases.

RESULT

Of 2021 patients, approximately 11% (n = 218) had an HAI. There was no difference in infection rates by admission year despite an increase in surgical volume. SSI was associated with younger age, previous hospitalization, and hip revision surgical procedure whereas UTI and BSI were associated with older age, greater co-morbidity, longer pre-operative length of stay and intensive care unit stay, (p < 0.05).

CONCLUSION

HAI after hip operation affected approximately one in 10 patients over a 7-year period in three high-volume hospitals. SSI occurred least frequently, predominantly among patients who underwent revision surgery (without previous SSI), were younger, and had a history of previous hospitalization. Infections such as BSI and UTI, although rare, occurred more frequently and in patients with more co-morbidities, longer pre-operative length of stay, and who required higher level care. Further research to understand these unexpected findings and target interventions is warranted.