Can the American College of Surgeons Risk Calculator Predict 30-Day Complications After Knee and Hip Arthroplasty?

Patients Who Have a Prior History of Pulmonary Embolism Require Increased Postoperative Care Following Total Joint Arthroplasty

BACKGROUND

This study examined the effect of prior pulmonary embolism (PE) on total joint arthroplasty (TJA) outcomes.

METHODS

We reviewed patients who had a prior PE undergoing TJA at a single tertiary medical center between January 1, 2012 and January 1, 2021. There were 177 TJA patients who had a prior PE who underwent 1:3 propensity-matching to patients without a history of prior PE. Bivariable and multivariable analyses were performed. Changes over time were evaluated.

RESULTS

Patients undergoing total knee arthroplasty who had a prior PE had more complications (25.3% versus 2.0%, P < .001), and postoperative PE (17.3% versus 0.0%, P < .001).and longer hospitalizations (3.15 versus 2.32 days, P = .006). Patients undergoing total hip arthroplasty who had a prior PE demonstrated more complications (14.7% versus 1.77%, P < .001) more postoperative PE (17.3% versus 0.0%, P < .001), and longer hospitalizations (3.30 versus 2.11 days, P < .001). Over the study, complication rates and hospitalizations lengths remained elevated in patients who had a prior PE. On multivariate analyses, prior PE was associated with longer hospitalizations (β: 0.67, P = .015) and increased complications (odds ratio [OR]: 9.44, P < .001) among total hip arthroplasty patients. Total knee arthroplasty patients had increased readmission (OR: 4.89, P = .003) and complication rates (OR: 21.4, P < .001).

CONCLUSIONS

Patients undergoing TJA who had a prior PE are at higher risk of requiring postoperative care. Therefore, thorough preoperative evaluation must be implemented, especially in clinical environments lacking resources for acute care escalation.

Accuracy of the ACS NSQIP Surgical Risk Calculator for Predicting Postoperative Complications in Gastric Cancer Following Open Gastrectomy

INTRODUCTION

The prediction of complications before gastric surgery is of utmost importance in shared decision making and proper counseling of the patient in order to minimize postoperative complications. Our aim was to evaluate the predictive validity of American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) risk calculator in gastric cancer patients who underwent gastrectomy.

METHODS

Preoperative assessment data of 432 patients were retrospectively reviewed and manually entered into the calculator. The accuracy of the calculator was evaluated using Pearson's chi-squared test, C-statistic, Brier score, and Hosmer-Lemeshow test.

RESULTS

The lowest Brier scores were observed in urinary tract infection, renal failure, venous thromboembolism, pneumonia, and cardiac complications. Best results were obtained for predicting sepsis, discharge to rehabilitation facility, and death (low Brier scores, C-statistic >.7, and Hosmer-Lemeshow P > .05).

CONCLUSION

The calculator had a strong performance in predicting sepsis, discharge to the rehabilitation facility, and death. However, it performed poor in predicting the most commonly observed events (any or serious complication and surgical site infection).

Assessment of Patient Satisfaction and Outcomes After Outpatient Joint Arthroplasty in Academic Medical Centers

Background

There is limited literature evaluating patient satisfaction and outcomes after outpatient joint arthroplasty procedures in academic medical centers (AMCs). The aims of this study are to determine: (1) patients' desires to repeat their procedures and be discharged on the same day, (2) patient-reported outcome measures (PROMs), (3) time to discharge, (4) readmission rates, and (5) factors that predict PROMs in patients undergoing outpatient joint arthroplasty in AMCs.

Methods

A prospective survey was completed by 66 total hip arthroplasty (THA), 35 total knee arthroplasty (TKA), and 180 unicondylar knee arthroplasty (UKA) outpatients who underwent surgery from May 2018 to December 2020 in 2 AMCs. The survey consisted of questions regarding hip or knee PROMs (Hip Disability and Osteoarthritis Outcome Score for Joint Replacement, and Knee Injury and Osteoarthritis Outcome Score for Joint Replacement), satisfaction with outpatient procedures and discharges, and reasons for readmissions. Linear regression analysis was conducted with statistical significance set at P < .05.

Results

100% of THA, 93.8% of TKA, and 93.0% of UKA outpatients stated that they would re-elect to undergo their respective procedure. Furthermore, 94% of THA, 81% of TKA, and 95% of UKA patients stated they would like same-day discharge again. THA, TKA, and UKA patients reported respective mean PROM scores of 94.7, 89.9, and 86.1. Readmission rates were 1.5%, 0.0%, and 0.5%, for THA, TKA, and UKA, respectively.

Conclusions

Patients who underwent outpatient joint arthroplasty procedures at 2 AMCs experienced minimal readmissions and reported a high desire to repeat their outpatient procedures.

Development and External Validation of the Spinal Tumor Surgery Risk Index

BACKGROUND

Patients undergoing surgical procedures for spinal tumors are vulnerable to major adverse events (AEs) and death in the postoperative period. Shared decision making and preoperative optimization of outcomes require accurate risk estimation.

OBJECTIVE

To develop and validate a risk index to predict short-term major AEs after spinal tumor surgery.

METHODS

Prospectively collected data from multiple medical centers affiliated with the American College of Surgeons National Surgical Quality Improvement Program from 2006 to 2020 were reviewed. Multiple logistic regression was used to assess sociodemographic, tumor-related, and surgery-related factors in the derivation cohort. The spinal tumor surgery risk index (STSRI) was built based on the resulting scores. The STSRI was internally validated using a subgroup of patients from the American College of Surgeons National Surgical Quality Improvement Program database and externally validated using a cohort from a single tertiary center.

RESULTS

In total, 14 982 operations were reviewed and 4556 (16.5%) major AEs occurred within 30 days after surgery, including 209 (4.5%) deaths. 22 factors were independently associated with major AEs or death and were included in the STSRI. Using the internal and external validation cohorts, the STSRI produced an area under the curve of 0.86 and 0.82, sensitivity of 80.1% and 79.7%, and specificity of 74.3% and 73.7%, respectively. The STSRI, which is freely available, outperformed the modified frailty indices, the American Society of Anesthesiologists classification, and the American College of Surgeons risk calculator.

CONCLUSION

In patients undergoing surgery for spinal tumors, the STSRI showed the highest predictive accuracy for major postoperative AEs and death compared with other current risk predictors.

External Validation of Prediction Models for Surgical Complications in People Considering Total Hip or Knee Arthroplasty Was Successful for Delirium but Not for Surgical Site Infection, Postoperative Bleeding, and Nerve Damage: A Retrospective Cohort Study

Although several models for the prediction of surgical complications after primary total hip or total knee replacement (THA and TKA, respectively) are available, only a few models have been externally validated. The aim of this study was to externally validate four previously developed models for the prediction of surgical complications in people considering primary THA or TKA. We included 2614 patients who underwent primary THA or TKA in secondary care between 2017 and 2020. Individual predicted probabilities of the risk for surgical complication per outcome (i.e., surgical site infection, postoperative bleeding, delirium, and nerve damage) were calculated for each model. The discriminative performance of patients with and without the outcome was assessed with the area under the receiver operating characteristic curve (AUC), and predictive performance was assessed with calibration plots. The predicted risk for all models varied between <0.01 and 33.5%. Good discriminative performance was found for the model for delirium with an AUC of 84% (95% CI of 0.82-0.87). For all other outcomes, poor discriminative performance was found; 55% (95% CI of 0.52-0.58) for the model for surgical site infection, 61% (95% CI of 0.59-0.64) for the model for postoperative bleeding, and 57% (95% CI of 0.53-0.61) for the model for nerve damage. Calibration of the model for delirium was moderate, resulting in an underestimation of the actual probability between 2 and 6%, and exceeding 8%. Calibration of all other models was poor. Our external validation of four internally validated prediction models for surgical complications after THA and TKA demonstrated a lack of predictive accuracy when applied in another Dutch hospital population, with the exception of the model for delirium. This model included age, the presence of a heart disease, and the presence of a disease of the central nervous system as predictor variables. We recommend that clinicians use this simple and straightforward delirium model during preoperative counselling, shared decision-making, and early delirium precautionary interventions.

Artificial intelligence and machine learning as a viable solution for hip implant failure diagnosis-Review of literature and in vitro case study

The digital health industry is experiencing fast-paced research which can provide digital care programs and technologies to enhance the competence of healthcare delivery. Orthopedic literature also confirms the applicability of artificial intelligence (AI) and machine learning (ML) models to medical diagnosis and clinical decision-making. However, implant monitoring after primary surgery often happens with a wellness visit or when a patient complains about it. Neglecting implant design and other technical errors in this scenario, unmonitored circumstances, and lack of post-surgery monitoring may ultimately lead to the implant system's failure and leave us with the only option of high-risk revision surgery. Preventive maintenance seems to be a good choice to identify the onset of an irreversible prosthesis failure. Considering all these aspects for hip implant monitoring, this paper explores existing studies linking ML models and intelligent systems for hip implant diagnosis. This paper explores the feasibility of an alternative continuous monitoring technique for post-surgery implant monitoring backed by an in vitro ML case study. Tribocorrosion and acoustic emission (AE) data are considered based on their efficacy in determining irreversible alteration of implant material to prevent total failures. This study also facilitates the relevance of developing an artificially intelligent implant monitoring methodology that can function with daily patient activities and how it can influence the digital orthopedic diagnosis. AI-based non-invasive hip implant monitoring system enabling point-of-care testing.

Improved Preoperative Risk Assessment Tools Are Needed to Guide Informed Decision Making before Esophagectomy

OBJECTIVE

We sought to evaluate the performance of 2 commonly used prediction models for postoperative morbidity in patients undergoing open and minimally invasive esophagectomy.

SUMMARY BACKGROUND DATA

Patients undergoing esophagectomy have a high risk of postoperative complications. Accurate risk assessment in this cohort is important for informed decision-making.

METHODS

We identified patients who underwent esophagectomy between January 2016 and June 2018 from our prospectively maintained database. Predicted morbidity was calculated using the American College of Surgeons National Surgical Quality Improvement Program Surgical Risk Calculator (SRC) and a 5-factor National Surgical Quality Improvement Programderived frailty index. Performance was evaluated using concordance index (C-index) and calibration curves.

RESULTS

In total, 240 consecutive patients were included for analysis. Most patients (85%) underwent Ivor Lewis esophagectomy. The observed overall complication rate was 39%; the observed serious complication rate was 33%.The SRC did not identify risk of complications in the entire cohort (C-index, 0.553), patients undergoing open esophagectomy (C-index, 0.569), or patients undergoing minimally invasive esophagectomy (C-index, 0.542); calibration curves showed general underestimation. Discrimination of the SRC was lowest for reoperation (C-index, 0.533) and highest for discharge to a facility other than home (C-index, 0.728). Similarly, the frailty index had C-index of 0.513 for discriminating any complication, 0.523 for serious complication, and 0.559 for readmission.

CONCLUSIONS

SRC and frailty index did not adequately predict complications after esophagectomy. Procedure-specific risk-assessment tools are needed to guide shared patient-physician decision-making in this high-risk population.

Predicting Length of Stay using machine learning for total joint replacements performed at a rural community hospital

Background

Predicting patient’s Length of Stay (LOS) before total joint replacement (TJR) surgery is vital for hospitals to optimally manage costs and resources. Many hospitals including in rural areas use publicly available models such as National Surgical Quality Improvement Program (NSQIP) calculator which, unfortunately, performs suboptimally when predicting LOS for TJR procedures.

Objective

The objective of this research was to develop a Machine Learning (ML) model to predict LOS for TJR procedures performed at a Perioperative Surgical Home implemented rural community hospital for better accuracy and interpretation than the NSQIP calculator.

Methods

A total of 158 TJR patients were collected and analyzed from a rural community hospital located in Montana. A random forest (RF) model was used to predict patient’s LOS. For interpretation, permuted feature importance and partial dependence plot methods were used to identify the important variables and their relationship with the LOS.

Results

The root mean square error for the RF model (0.7) was lower than the NSQIP calculator (1.21). The five most important variables for predicting LOS were BMI, Duke Activity Status-Index, diabetes, patient’s household income, and patient’s age.

Conclusion

This pilot study is the first of its kind to develop an ML model to predict LOS for TJR procedures that were performed at a small-scale rural community hospital. This pilot study contributes an approach for rural hospitals, making them more independent by developing their own predictions instead of relying on public models.

Predicting Postoperative Troponin in Patients Undergoing Elective Hip or Knee Arthroplasty: A Comparison of Five Cardiac Risk Prediction Tools

Background

Elderly patients undergoing hip or knee arthroplasty are at a risk for myocardial injury after noncardiac surgery (MINS). We evaluated the ability of five common cardiac risk scores, alone or combined with baseline high-sensitivity cardiac troponin I (hs-cTnI), in predicting MINS and postoperative day 2 (POD2) hs-cTnI levels in patients undergoing elective total hip or knee arthroplasty.

Methods

This study is ancillary to the Genetics-InFormatics Trial (GIFT) of Warfarin Therapy to Prevent Deep Venous Thrombosis, which enrolled patients 65 years and older undergoing elective total hip or knee arthroplasty. The five cardiac risk scores evaluated were the atherosclerotic cardiovascular disease calculator (ASCVD), the Framingham risk score (FRS), the American College of Surgeon's National Surgical Quality Improvement Program (ACS-NSQIP) calculator, the revised cardiac risk index (RCRI), and the reconstructed RCRI (R-RCRI).

Results

None of the scores predicted MINS in women. Among men, the ASCVD (C-statistic of 0.66; p=0.04), ACS-NSQIP (C-statistic of 0.69; p=0.01), and RCRI (C-statistic of 0.64; p=0.04) predicted MINS. Among all patients, spearman correlations (r_s) of the risk scores with the POD2 hs-cTnI levels were 0.24, 0.20, 0.11, 0.11, and 0.08 for the ASCVD, Framingham, ACS-NSQIP, RCRI, and R-RCRI scores, respectively, with p values of <0.001, <0.001, <0.001, 0.006, and 0.025. Baseline hs-cTnI predicted MINS (C-statistics: 0.63 in women and 0.72 in men) and postoperative hs-cTnI (r_s = 0.51, p=0.001).

Conclusion

In elderly patients undergoing elective hip or knee arthroplasty, several of the scores modestly predicted MINS in men and correlated with POD2 hs-cTnI.

Opioid-Related Genetic Polymorphisms of Cytochrome P450 Enzymes after Total Joint Arthroplasty: A Focus on Drug-Drug-Gene Interaction with Commonly Coprescribed Medications

Pharmacogenomic testing, together with the early detection of drug-drug-gene interactions (DDGI) before initiating opioids, can improve the selection of dosage and reduce the risk of adverse drug interactions and therapeutic failures following Total Joint Arthroplasty. The variants of CYP genes can mediate DDGI. Orthopedic surgeons should become familiar with the genetic aspect of opioid use and abuse, as well as the influence of the patient genetic makeup in opioid selection and response, and polymorphic variants in pain modulation.

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

BACKGROUND

A reliable predictive tool to predict unplanned readmissions has the potential to lower readmission rates through targeted pre-operative counseling and intervention with respect to modifiable risk factors. This study aimed to develop and internally validate machine learning models for the prediction of 90-day unplanned readmissions following total knee arthroplasty.

METHODS

A total of 10,021 consecutive patients underwent total knee arthroplasty. Patient charts were manually reviewed to identify patient demographics and surgical variables that may be associated with 90-day unplanned hospital readmissions. Four machine learning algorithms (artificial neural networks, support vector machine, k-nearest neighbor, and elastic-net penalized logistic regression) were developed to predict 90-day unplanned readmissions following total knee arthroplasty and these models were evaluated using ROC AUC statistics as well as calibration and decision curve analysis.

RESULTS

Within the study cohort, 644 patients (6.4%) were readmitted within 90 days. The factors most significantly associated with 90-day unplanned hospital readmissions included drug abuse, surgical operative time, and American Society of Anaesthesiologist Physical Status (ASA) score. The machine learning models all achieved excellent performance across discrimination (AUC > 0.82), calibration, and decision curve analysis.

CONCLUSION

This study developed four machine learning models for the prediction of 90-day unplanned hospital readmissions in patients following total knee arthroplasty. The strongest predictors for unplanned hospital readmissions were drug abuse, surgical operative time, and ASA score. The study findings show excellent model performance across all four models, highlighting the potential of these models for the identification of high-risk patients prior to surgery for whom coordinated care efforts may decrease the risk of subsequent hospital readmission.

LEVEL OF EVIDENCE

Level III, case-control retrospective analysis.

Development of a Risk Stratification Scoring System to Predict General Surgical Complications for Patients Undergoing Foot and Ankle Surgery

Preventing postoperative complications is crucial for patients, surgeons, and health care facilities. We developed a risk stratification scoring system to optimize postoperative outcomes for patients undergoing foot and ankle surgery. A total of 35,580 patients who underwent foot and ankle procedures from 2005 to 2017 were identified as part of the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP). To assess the risk of a postoperative complication, we identified several independent risk factors associated with 30-day postoperative complications, then proceeded to develop a point-based risk scoring system. To validate our scoring system, we used it on a cohort of patients from the database who underwent foot and ankle surgery. Risk factors that correlated with postoperative complications included tobacco abuse, age (≥65 years), diabetes mellitus, hypertension, elevated creatinine level (≥1.3 mg/dL), hypoalbuminemia (<3.5 g/dL), chronic obstructive pulmonary disease (COPD), congestive heart failure (CHF), hyponatremia (<135 mEq/L), and anemia (hematocrit value, men <42%; women <38%). Point scores for each factor were: anemia, +10; hypoalbuminemia, +9; elevated creatinine level, +6; CHF, +4; diabetes mellitus, +3; hyponatremia, +3; COPD, +2; hypertension, +2; age, +1; and tobacco abuse, +1. For the validation cohort, we stratified patients according to risk as low (0-20 points), medium (21-30 points), and high (≥31 points) risk. In terms of having a postoperative complication, compared with low-risk patients, patients who were at medium risk had an odds ratio of 4.7 (95% CI, 2.8-7.9) and those at high risk had an odds ratio of 8.3 (95% CI, 4.8-14.5). [Orthopedics. 2022;45(3):139-144.].

An Ounce of Prediction is Worth a Pound of Cure: Risk Calculators in Breast Reconstruction

Preoperative risk calculators provide individualized risk assessment and stratification for surgical patients. Recently, several general surgery–derived models have been applied to the plastic surgery patient population, and several plastic surgery–specific calculators have been developed. In this scoping review, the authors aimed to identify and critically appraise risk calculators implemented in postmastectomy breast reconstruction.

Development of a Machine Learning Algorithm for Prediction of Complications and Unplanned Readmission Following Primary Anatomic Total Shoulder Replacements

Background

The demand and incidence of anatomic total shoulder arthroplasty (aTSA) procedures is projected to increase substantially over the next decade. There is a paucity of accurate risk prediction models which would be of great utility in minimizing morbidity and costs associated with major post-operative complications. Machine learning is a powerful predictive modeling tool and has become increasingly popular, especially in orthopedics. We aimed to build a ML model for prediction of major complications and readmission following primary aTSA.

Methods

A large California administrative database was retrospectively reviewed for all adults undergoing primary aTSA between 2015 to 2017. The primary outcome was any major complication or readmission following aTSA. A wide scope of standard ML benchmarks, including Logistic regression (LR), XGBoost, Gradient boosting, AdaBoost and Random Forest were employed to determine their power to predict outcomes. Additionally, important patient features to the prediction models were indentified.

Results

There were a total of 10,302 aTSAs with 598 (5.8%) having at least one major post-operative complication or readmission. XGBoost had the highest discriminative power (area under receiver operating curve AUROC of 0.689) of the 5 ML benchmarks with an area under precision recall curve AURPC of 0.207. History of implant complication, severe chronic kidney disease, teaching hospital status, coronary artery disease and male sex were the most important features for the performance of XGBoost. In addition, XGBoost identified teaching hospital status and male sex as markedly more important predictors of outcomes compared to LR models.

Conclusion

We report a well calibrated XGBoost ML algorithm for predicting major complications and 30-day readmission following aTSA. History of prior implant complication was the most important patient feature for XGBoost performance, a novel patient feature that surgeons should consider when counseling patients.

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.

Between 2000 and 2020, Reimbursement for Orthopaedic Foot and Ankle Surgery Decreased by 30%

Purpose

To examine and analyze Medicare reimbursement rates from 2000 to 2020 for orthopaedic foot and ankle procedures.

Methods

The 20 most used orthopaedic foot and ankle surgical procedures were gathered from the Centers for Medicare & Medicaid Services website using the Medicare Provider Utilization and Payment Data Public Use File 2017. The reimbursement data for each code were gathered from The Physician Fee Schedule Look-Up Tool from Centers for Medicare & Medicaid Services. The reimbursement values were adjusted for inflation to 2020 U.S. dollars using the consumer price index.

Results

The average inflation-adjusted reimbursement for included procedures decreased by 30% from 2000 to 2020. The greatest mean decreases were observed for “correction of hallux valgus” (–47%) and “partial excision of foot bone” (–41%). The procedures with the smallest mean decreases were observed in “treatment of “Amputation of toe” (–19%) and “closed treatment of metatarsal fracture” (–7%).

Conclusions

From 2000 to 2020, Inflation-adjusted Medicare reimbursement for foot and ankle surgery decreased by 30%.

Level of Evidence

IV; economic analysis.

Prediction of Early Periprosthetic Joint Infection After Total Hip Arthroplasty

Purpose

To develop a parsimonious risk prediction model for periprosthetic joint infection (PJI) within 90 days after total hip arthroplasty (THA).

Patients and Methods

We used logistic LASSO regression with bootstrap ranking to develop a risk prediction model for PJI within 90 days based on a Swedish cohort of 88,830 patients with elective THA 2008–2015. The model was externally validated on a Danish cohort with 18,854 patients.

Results

Incidence of PJI was 2.45% in Sweden and 2.17% in Denmark. A model with the underlying diagnosis for THA, body mass index (BMI), American Society for Anesthesiologists (ASA) class, sex, age, and the presence of five defined comorbidities had an area under the curve (AUC) of 0.68 (95% CI: 0.66 to 0.69) in Sweden and 0.66 (95% CI: 0.64 to 0.69) in Denmark. This was superior to traditional models based on ASA class, Charlson, Elixhauser, or the Rx Risk V comorbidity indices. Internal calibration was good for predicted probabilities up to 10%.

Conclusion

A new PJI prediction model based on easily accessible data available before THA was developed and externally validated. The model had superior discriminatory ability compared to ASA class alone or more complex comorbidity indices and had good calibration. We provide a web-based calculator (https://erikbulow.shinyapps.io/thamortpred/) to facilitate shared decision making by patients and surgeons.

Point your SmartPhone at the code above. If you have a QR code reader the video abstract will appear. Or use:

https://youtu.be/T0qfHTvBEs4

Applications of artificial intelligence and machine learning for the hip and knee surgeon: current state and implications for the future

BACKGROUND

Artificial Intelligence (AI)/Machine Learning (ML) applications have been proven efficient to improve diagnosis, to stratify risk, and to predict outcomes in many respective medical specialties, including in orthopaedics.

CHALLENGES AND DISCUSSION

Regarding hip and knee reconstruction surgery, AI/ML have not made it yet to clinical practice. In this review, we present sound AI/ML applications in the field of hip and knee degenerative disease and reconstruction. From osteoarthritis (OA) diagnosis and prediction of its advancement, clinical decision-making, identification of hip and knee implants to prediction of clinical outcome and complications following a reconstruction procedure of these joints, we report how AI/ML systems could facilitate data-driven personalized care for our patients.

The American College of Surgeons National Surgical Quality Improvement Program surgical risk calculator is not reliable in predicting complications and length of stay after primary total hip arthroplasty at an institution implementing clinical pathways

INTRODUCTION

The authors aimed to: (1) determine how length of stay (LOS) and complication rates changed over the past 10 years, in comparison to values estimated by the ACS-NSQIP surgical risk calculator, at a single private institution open to external surgeons; and (2) determine preoperative patient factors associated with complications.

METHODS

We retrospectively assessed 1018 consecutive patients who underwent primary elective THA over 10 years. We excluded 87 with tumours and 52 with incomplete records. Clinical data of the remaining 879 were used to determine real LOS and rate of 9 adverse events over time, as well as to estimate these values using the risk calculator. Its predictive reliability was represented on receiver operating characteristic curves. Multivariable analyses were performed to determine associations of complications with age, sex, ASA score, diabetes, hypertension, heart disease, smoking and BMI.

RESULTS

Over the 10-year period, real LOS and real complication rates decreased considerably, while LOS and complication rates estimated by the surgical risk calculator had little or no change. The difference between real and estimated LOS decreased over time. The overall estimated and real rates of any complication were respectively 3.3% and 2.8%. The risk calculator had fair reliability for predicting any complications (AUC 0.72). Overall estimated LOS was shorter than the real LOS in 764 (86.9%) patients. Multivariable analysis revealed risks of any complication to be greater in patients aged ⩾75 (OR = 4.36, p = 0.002), and with hypertension (OR = 3.13, p = 0.016).

CONCLUSIONS

Since the implementation of clinical pathways at our institution, real LOS and complication rates decreased considerably, while LOS and complication rates estimated by the surgical risk calculator had little or no change. The difference between real and estimated LOS decreased over time, which could lead some clinicians to reconsider their discharge criteria, knowing that advanced age and hypertension increased risks of encountering complications.

From Winners to Losers: The Methodology of Bundled Payments for Care Improvement Advanced Disincentivizes Participation in Bundled Payment Programs

BACKGROUND

The Bundled Payments for Care Improvement (BPCI) initiative improved quality and reduced costs following total hip (THA) and knee arthroplasty (TKA). In October 2018, the BPCI-Advanced program was implemented. The purpose of this study is to compare the quality metrics and performance between our institution's participation in the BPCI program with the BPCI-Advanced initiative.

METHODS

We reviewed a consecutive series of Medicare primary THA and TKA patients. Demographics, medical comorbidities, discharge disposition, readmission, and complication rates were compared between BPCI and BPCI-Advanced groups. Medicare claims data were used to compare episode-of-care costs, target price, and margin per patient between the cohorts.

RESULTS

Compared to BPCI patients (n = 9222), BPCI-Advanced patients (n = 2430) had lower rates of readmission (5.8% vs 3.8%, P = .001) and higher rate of discharge to home (72% vs 78%, P < .001) with similar rates of complications (4% vs 4%, P = .216). Medical comorbidities were similar between groups. BPCI-Advanced patients had higher episode-of-care costs ($22,044 vs $18,440, P < .001) and a higher mean target price ($21,154 vs $20,277, P < .001). BPCI-Advanced patients had a reduced per-patient margin compared to BPCI ($890 loss vs $1459 gain, P < .001), resulting in a $2,138,670 loss in the first three-quarters of program participation.

CONCLUSION

Despite marked improvements in quality metrics, our institution suffered a substantial loss through BPCI-Advanced secondary to methodological changes within the program, such as the exclusion of outpatient TKAs, facility-specific target pricing, and the elimination of different risk tracks for institutions. Medicare should consider adjustments to this program to keep surgeons participating in alternative payment models.

The ACS-NSQIP surgical risk calculator is a poor predictor of postoperative complications in patients undergoing oncologic distal femoral replacement

BACKGROUND

Distal femur replacement (DFR) has become a preferred reconstruction for tumors involving the femur but is associated with known complications. The ACS-NSQIP surgical risk calculator is an online tool developed to estimate postoperative complications in the first 30-days, however, has not been used in patients undergoing DFR. The purpose of this study was determining the utility of the ACS-NSQIP calculator to predict postoperative complications.

METHODS

56 (30 male, 26 female) patients who underwent DFR were analyzed using the CPT codes: 27,365 (Under Excision Procedures on the Femur and Knee Joint), 27,447 (Arthroplasty, knee, condyle and plateau), 27,486 (Revision of total knee arthroplasty, with or without allograft), 27,487 (Revision of total knee arthroplasty, with or without allograft) and 27,488 (Repair, Revision, and/or Reconstruction Procedures on the Femur [Thigh Region] and Knee Joint). The predicted rates of complications were compared to the observed rates.

RESULTS

Complications were noted in 30 (54%) of patients. The predicted risk of complications based off the CPT codes were: 27,356 (14%); 27,447 (5%); 27,486 (7%); 27,487 (8%) and 27,488 (12%). Based on ROC curves, the use of the ACS-NSQIP score were poor predictors of complications (27356, AUC 0.54); (27447, AUC 0.45); (27486, AUC 0.45); (27487, AUC 0.46); (27488, AUC 0.46).

CONCLUSIONS

Distal femur arthroplasty performed in the setting of oncologic orthopedics is a complex procedure in a "high risk" surgical group. The ACS-NSQIP does not adequately predict the incidence of complications in these patients and cannot be reliably used in the shared decision-making process.

Association of Social Behaviors With Community Discharge in Patients with Total Hip and Knee Replacement

OBJECTIVES

Understand the association between social determinants of health and community discharge after elective total joint arthroplasty.

DESIGN

Retrospective cohort design using Optum de-identified electronic health record dataset.

SETTING AND PARTICIPANTS

A total of 38 hospital networks and 18 non-network hospitals in the United States; 79,725 patients with total hip arthroplasty and 136,070 patients with total knee arthroplasty between 2011 and 2018.

METHODS

Logistic regression models were used to examine the association among pain, weight status, smoking status, alcohol use, substance disorder, and postsurgical community discharge, adjusted for patient demographics.

RESULTS

Mean ages for patients with hip and knee arthroplasty were 64.5 (SD 11.3) and 65.9 (SD 9.6) years; most patients were women (53.6%, 60.2%), respectively. The unadjusted community discharge rate was 82.8% after hip and 81.1% after knee arthroplasty. After adjusting for demographics, clinical factors, and behavioral factors, we found obesity [hip: odds ratio (OR) 0.81, 95% confidence interval (CI) 0.76-0.85; knee: OR 0.73, 95% CI 0.69-0.77], current smoking (hip: OR 0.82, 95% CI 0.77-0.88; knee: OR 0.90, 95% CI 0.85-0.95), and history of substance use disorder (hip: OR 0.55, 95% CI 0.50-0.60; knee: OR 0.57, 95% CI 0.53-0.62) were associated with lower odds of community discharge after hip and knee arthroplasty, respectively.

CONCLUSIONS AND IMPLICATIONS

Social determinants of health are associated with odds of community discharge after total hip and knee joint arthroplasty. Our findings demonstrate the value of using electronic health record data to analyze more granular patient factors associated with patient discharge location after total joint arthroplasty. Although bundled payment is increasing community discharge rates, post-acute care facilities must be prepared to manage more complex patients because odds of community discharge are diminished in those who are obese, smoking, or have a history of substance use disorder.

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.

Utility of the ACS-NSQIP surgical risk calculator in predicting postoperative complications in patients undergoing oncologic proximal femoral replacement

INTRODUCTION

Proximal femur replacement (PFR) in the setting of tumor resection is associated with a high rate of postoperative complication. The online American College of Surgeons-National Surgical Quality Improvement Program (ACS-NSQIP) surgical risk calculator is approved by the Center of Medicare and Medicaid services to estimate 30-day postoperative complications. This study was to determine if the ACS-NSQIP can predict postoperative complications following PFR.

METHODS

We reviewed 103 (61 male and 42 female) patients undergoing PFR using the Current Procedural Terminology (CPT) codes available in the calculator: 27125 (hemiarthroplasty), 27130 (total hip), 27132 (conversion to total hip), 27134 (revision total hip), 27137 (revision acetabulum), 27138 (revision femur), and 27365 (excision tumor hip). The predicted rates of complications were compared with the observed rates.

RESULTS

Complications occurred in 54 (52%) of patients, with the predicted risk based on CPT codes: 27125 (21.5%); 27130 (7.8%); 27132 (16.6%), 27134 (17.8%), 27137 (14.4%), 274138 (22.7%), and 27365 (16.2%). The calculator was a poor predictor of complications (27125, area under the curve [AUC] 0.576); (27130, AUC 0.489); (27132, AUC 0.490); (27134, AUC 00.489); (27137, AUC 0.489); (27138, AUC 0.471); and (27365, AUC 0.538).

CONCLUSION

Oncologic PFR is known for complications. The ACS-NSQIP does not adequately predict the incidence of complications, and therefore cannot reliably be used in their shared decision-making process preoperative.

Does the ACS NSQIP Surgical Risk Calculator Accurately Predict Complications Rates After Anterior Lumbar Interbody Fusion Procedures?

STUDY DESIGN

Clinical case series.

OBJECTIVE

The aim of this study was to determine the effectiveness of the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) surgical risk calculator in the prediction of complications after anterior lumbar interbody fusion (ALIF).

SUMMARY OF BACKGROUND DATA

Identifying at-risk patients may aid in the prevention of complications after spine procedures. The ACS NSQIP surgical risk calculator was developed to predict 30-day postoperative complications for a variety of operative procedures.

METHODS

Medical records of patients undergoing ALIF at our institution from 2009 to 2019 were retrospectively reviewed. Demographic and comorbidity variables were entered into the ACS NSQIP surgical risk calculator to generate percentage predictions for complication incidence within 30 days postoperatively. The observed incidences of these complications were also abstracted from the medical record. The predictive ability of the ACS NSQIP surgical risk calculator was assessed in comparison to the observed incidence of complications using area under the curve (AUC) analyses.

RESULTS

Two hundred fifty-three (253) patients were analyzed. The ACS NSQIP surgical risk calculator was a fair predictor of discharge to non-home facility (AUC 0.71) and surgical site infection (AUC 0.70). The ACS NSQIP surgical risk calculator was a good predictor of acute kidney injury/progressive renal insufficiency (AUC 0.81). The ACS NSQIP surgical risk calculator was not an adequate predictive tool for any other category, including: pneumonia, urinary tract infections, venous thromboembolism, readmission, reoperations, and aggregate complications (AUC < 0.70).

CONCLUSION

The ACS NSQIP surgical risk calculator is an adequate predictive tool for a subset of complications after ALIF including acute kidney injury/progressive renal insufficiency, surgical site infections, and discharge to non-home facilities. However, it is a poor predictor for all other complication groups. The reliability of the ACS NSQIP surgical risk calculator is limited, and further identification of models for risk stratification is necessary for patients undergoing ALIF.Level of Evidence: 3.

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.

Predicting 30-Day and 180-Day Mortality in Elderly Proximal Hip Fracture Patients: Evaluation of 4 Risk Prediction Scores at a Level I Trauma Center

This study evaluated the use of risk prediction models in estimating short- and mid-term mortality following proximal hip fracture in an elderly Austrian population. Data from 1101 patients who sustained a proximal hip fracture were retrospectively analyzed and applied to four models of interest: Physiological and Operative Severity Score for the enUmeration of Mortality and Morbidity (POSSUM), Charlson Comorbidity Index, Portsmouth-POSSUM and the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP^®) Risk Score. The performance of these models according to the risk prediction of short- and mid-term mortality was assessed with a receiver operating characteristic curve (ROC). The median age of participants was 83 years, and 69% were women. Six point one percent of patients were deceased by 30 days and 15.2% by 180 days postoperatively. There was no significant difference between the models; the ACS-NSQIP had the largest area under the receiver operating characteristic curve for within 30-day and 180-day mortality. Age, male gender, and hemoglobin (Hb) levels at admission <12.0 g/dL were identified as significant risk factors associated with a shorter time to death at 30 and 180 days postoperative (p < 0.001). Among the four scores, the ACS-NSQIP score could be best-suited clinically and showed the highest discriminative performance, although it was not specifically designed for the hip fracture population.

Development of a Preoperative Risk Calculator for Reinfection Following Revision Surgery for Periprosthetic Joint Infection

BACKGROUND

A recent systematic review demonstrated that reinfection rates following eradication of hip and knee periprosthetic joint infection (PJI) may be as high as 29%. This study aimed to develop a preoperative risk calculator for assessing patient's individual risk associated with reinfection following treatment of PJI in total joint arthroplasty (TJA).

METHODS

A total of 1081 consecutive patients who underwent revision TJA for PJI were evaluated. In total, 293 patients were diagnosed with TJA reinfection. A total of 56 risk factors, including patient characteristics and surgical variables, were evaluated with multivariate regression analysis. Analysis of the area under the receiver operating characteristics curve was performed to evaluate the strength of the predictive model.

RESULTS

Of the 56 risk factors studied, 19 were found to have a significant effect as risk factor for TJA reinfection. The strongest predictors for TJA reinfection included previous PJI treatment techniques such as irrigation and debridement, the number of previous surgical interventions, medical comorbidities such as obesity, drug abuse, depression and smoking, as well as microbiology including the presence of Enterococcus species. The combined area under the receiver operating characteristics curve of the risk calculator for periprosthetic hip and knee joint reinfection was 0.75.

CONCLUSIONS

The study findings demonstrate that surgical factors, including previous PJI surgical treatment techniques as well as the number of previous surgeries, alongside microbiology including the presence of Enterococcus species have the strongest effect on the risk for periprosthetic THA and TKA joint reinfection, suggesting the limited applicability of the existing risk calculators for the development of PJI following primary TJA in predicting the risk of periprosthetic joint reinfection.

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.

Predicting Unplanned Readmissions Following a Hip or Knee Arthroplasty: Retrospective Observational Study

BACKGROUND

Total joint replacements are high-volume and high-cost procedures that should be monitored for cost and quality control. Models that can identify patients at high risk of readmission might help reduce costs by suggesting who should be enrolled in preventive care programs. Previous models for risk prediction have relied on structured data of patients rather than clinical notes in electronic health records (EHRs). The former approach requires manual feature extraction by domain experts, which may limit the applicability of these models.

OBJECTIVE

This study aims to develop and evaluate a machine learning model for predicting the risk of 30-day readmission following knee and hip arthroplasty procedures. The input data for these models come from raw EHRs. We empirically demonstrate that unstructured free-text notes contain a reasonably predictive signal for this task.

METHODS

We performed a retrospective analysis of data from 7174 patients at Partners Healthcare collected between 2006 and 2016. These data were split into train, validation, and test sets. These data sets were used to build, validate, and test models to predict unplanned readmission within 30 days of hospital discharge. The proposed models made predictions on the basis of clinical notes, obviating the need for performing manual feature extraction by domain and machine learning experts. The notes that served as model inputs were written by physicians, nurses, pathologists, and others who diagnose and treat patients and may have their own predictions, even if these are not recorded.

RESULTS

The proposed models output readmission risk scores (propensities) for each patient. The best models (as selected on a development set) yielded an area under the receiver operating characteristic curve of 0.846 (95% CI 82.75-87.11) for hip and 0.822 (95% CI 80.94-86.22) for knee surgery, indicating reasonable discriminative ability.

CONCLUSIONS

Machine learning models can predict which patients are at a high risk of readmission within 30 days following hip and knee arthroplasty procedures on the basis of notes in EHRs with reasonable discriminative power. Following further validation and empirical demonstration that the models realize predictive performance above that which clinical judgment may provide, such models may be used to build an automated decision support tool to help caretakers identify at-risk patients.

Compilation and Analysis of Web-Based Orthopedic Personalized Predictive Tools: A Scoping Review

Web-based personalized predictive tools in orthopedic surgery are becoming more widely available. Despite rising numbers of these tools, many orthopedic surgeons may not know what tools are available, how these tools were developed, and how they can be utilized. The aim of this scoping review is to compile and synthesize the profile of existing web-based orthopedic tools. We conducted two separate PubMed searches-one a broad search and the second a more targeted one involving high impact journals-with the aim of comprehensively identifying all existing tools. These articles were then screened for functional tool URLs, methods regarding the tool's creation, and general inputs and outputs required for the tool to function. We identified 57 articles, which yielded 31 unique web-based tools. These tools involved various orthopedic conditions (e.g., fractures, osteoarthritis, musculoskeletal neoplasias); interventions (e.g., fracture fixation, total joint arthroplasty); outcomes (e.g., mortality, clinical outcomes). This scoping review highlights the availability and utility of a vast array of web-based personalized predictive tools for orthopedic surgeons. Increased awareness and access to these tools may allow for better decision support, surgical planning, post-operative expectation management, and improved shared decision-making.

Performance of the American College of Surgeons NSQIP Surgical Risk Calculator for Total Gastrectomy

BACKGROUND

To encourage implementation of the American College of Surgeons (ACS) NSQIP Risk Calculator for total gastrectomy for gastric cancer, its predictive performance for this specific procedure should be validated. We assessed its discriminatory accuracy and goodness of fit for predicting 12 adverse outcomes.

STUDY DESIGN

Data were collected on all patients with gastric cancer who underwent total gastrectomy with curative intent at Memorial Sloan Kettering Cancer Center between 2002 and 2017. Preoperative risk factors from the electronic medical record were manually inserted into the ACS-NSQIP Risk Calculator. Predictions for adverse outcomes were compared with observed outcomes by Brier scores, c-statistics, and Hosmer-Lemeshow p value.

RESULTS

In a total of 452 patients, the predicted rate of all complications (29%) was lower than the observed rate (45%). Brier scores varied between 0.017 for death and 0.272 for any complication. C-statistics were moderate (0.7-0.8) for death and renal failure, good (0.8-0.9) for cardiac complication, and excellent (≥0.9) for discharge to nursing or rehabilitation facility. Hosmer-Lemeshow p value found poor goodness of fit for pneumonia only.

CONCLUSIONS

For adverse outcomes after total gastrectomy with curative intent in gastric cancer patients, performance of the ACS-NSQIP Risk Calculator is variable. Its predictive performance is best for cardiac complications, renal failure, death, and discharge to nursing or rehabilitation facility.

The Removal of Total Hip and Total Knee Arthroplasty From the Inpatient-Only List Increases the Administrative Burden of Surgeons and Continues to Cause Confusion

BACKGROUND

Several studies have shown that the removal of total knee arthroplasty (TKA) from the Centers for Medicare and Medicaid Services (CMS) inpatient-only (IPO) list has caused confusion among surgeons, hospitals, and patients. The purpose of this study is to determine whether similar confusion was present after CMS recently removed total hip arthroplasty (THA) from the IPO list.

METHODS

We surveyed the American Association of Hip and Knee Surgeons membership via an online web-based questionnaire in February 2020. The 12-question form asked about practice type and the impact that having both THA and TKA removed from the IPO list has had on each surgeon's practice. Responses were tabulated and descriptive statistics of each question reported.

RESULTS

Of the 2847 American Association of Hip and Knee Surgeons members surveyed, 419 responded (14.7% response rate). Three hundred forty-one surgeons (81%) stated that changes to IPO status have increased their practice's administrative burden. Fifty-four percent of surgeons reported that they have needed to obtain preauthorization or appeal a denial of preauthorization for an inpatient total joint arthroplasty at least monthly, while 257 surgeons (61%) have had patients contact their office regarding an unexpected copayment. Despite the commitment of CMS to waiving certain audits for 2 years, 43 respondents (10%) stated they had undergone an audit regarding a patient's inpatient status.

CONCLUSION

The removal of THA and TKA from the IPO list continues to be an administrative burden for arthroplasty surgeons and a source of confusion among patients. CMS should provide additional guidance to address surgeons' concerns about preauthorization for inpatient stays, unexpected patient copayments, and CMS audits.

Disparities in Hip Arthroplasty Outcomes: Results of a Statewide Hospital Registry From 2016 to 2018

BACKGROUND

In November 2019, Centers for Medicare and Medicaid Services announced total hip arthroplasty (THA) will be removed from the inpatient-only list. This may lead to avoidance of patients who have prolonged hospitalizations and discharge to skilled nursing facilities or push providers to unsafely push patients to outpatient surgery centers. Disparities in hip arthroplasty may worsen as patients are "risk stratified" preoperatively to minimize cost outliers. We aimed to evaluate which patient characteristics are associated with extended length of stay (eLOS)-greater than 2 days-and nonhome discharge in patients undergoing hip arthroplasty.

METHODS

The Illinois COMPdata administrative database was queried for THA admissions from January 2016 to June 2018. Variables included age, sex, race and ethnicity, median household income, Illinois region, insurance status, principal diagnosis, Charlson comorbidity index, obesity, discharge disposition, and LOS. Hospital characteristics included bundled payment participation and arthroplasty volume. Using multiple Poisson regression, we examined the association between these factors and the likelihood of nonhome discharge and eLOS.

RESULTS

There were 41,832 THA admissions from January 2016 to June 2018. A total of 36% had LOS greater than 2 midnights and 25.3% of patients had nonhome discharges. Female patients, non-Hispanic black patients, patients older than 75, obese patients, Medicaid or uninsured status, Charlson comorbidity index > 3, and hip arthroplasty for fracture were associated with increased risk of eLOS and/or nonhome discharge (P < .05).

CONCLUSION

With the Centers for Medicare and Medicaid Services emphasis on cost containment, patients at risk of extended stay or nonhome discharge may be deemed "high risk" and have difficulty accessing arthroplasty care. These are potentially vulnerable groups during the transition to the bundled payment model.

Data for registry and quality review can be retrospectively collected using natural language processing from unstructured charts of arthroplasty patients

Aims

Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction.

Methods

A group of 1,000 randomly selected clinical and hospital notes from eight different surgeons were collected for patients undergoing primary arthroplasty between 2012 and 2018. In all, 19 preoperative, 17 operative, and two postoperative variables of interest were manually extracted from these notes. A NLP algorithm was created to automatically extract these variables from a training sample of these notes, and the algorithm was tested on a random test sample of notes. Performance of the NLP algorithm was measured in Statistical Analysis System (SAS) by calculating the accuracy of the variables collected, the ability of the algorithm to collect the correct information when it was indeed in the note (sensitivity), and the ability of the algorithm to not collect a certain data element when it was not in the note (specificity).

Results

The NLP algorithm performed well at extracting variables from unstructured data in our random test dataset (accuracy = 96.3%, sensitivity = 95.2%, and specificity = 97.4%). It performed better at extracting data that were in a structured, templated format such as range of movement (ROM) (accuracy = 98%) and implant brand (accuracy = 98%) than data that were entered with variation depending on the author of the note such as the presence of deep-vein thrombosis (DVT) (accuracy = 90%).

Conclusion

The NLP algorithm used in this study was able to identify a subset of variables from randomly selected unstructured notes in arthroplasty with an accuracy above 90%. For some variables, such as objective exam data, the accuracy was very high. Our findings suggest that automated algorithms using NLP can help orthopaedic practices retrospectively collect information for registries and quality improvement (QI) efforts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):99–104.

Analysis and Review of Automated Risk Calculators Used to Predict Postoperative Complications After Orthopedic Surgery

PURPOSE OF REVIEW

To discuss the automated risk calculators that have been developed and evaluated in orthopedic surgery.

RECENT FINDINGS

Identifying predictors of adverse outcomes following orthopedic surgery is vital in the decision-making process for surgeons and patients. Recently, automated risk calculators have been developed to quantify patient-specific preoperative risk associated with certain orthopedic procedures. Automated risk calculators may provide the orthopedic surgeon with a valuable tool for clinical decision-making, informed consent, and the shared decision-making process with the patient. Understanding how an automated risk calculator was developed is arguably as important as the performance of the calculator. Additionally, conveying and interpreting the results of these risk calculators with the patient and its influence on surgical decision-making are paramount. The most abundant research on automated risk calculators has been conducted in the spine, total hip and knee arthroplasty, and trauma literature. Currently, many risk calculators show promise, but much research is still needed to improve them. We recommend they be used only as adjuncts to clinical decision-making. Understanding how a calculator was developed, and accurate communication of results to the patient, is paramount.

Patient Electronic Health Records Score for Preoperative Risk Assessment Before Total Knee Arthroplasty

Background:

Current preoperative risk assessment tools are often cumbersome, have limited accuracy, and are poorly adopted. The Care Assessment Need (CAN) score, an existing tool developed for primary care providers in the U.S. Veterans Administration health-care system (VA), is automatically calculated for individual patients using electronic health record data. Therefore, it could present an efficient preoperative risk assessment tool. The aim of this project was to determine if the CAN score can be repurposed as a preoperative risk assessment tool for patients undergoing total knee arthroplasty (TKA).

Methods:

A multicenter retrospective observational study was conducted using national VA data from 2013 to 2016. The cohort included veterans who underwent TKA identified through ICD-9 (International Classification of Diseases, Ninth Revision), ICD-10, and CPT (Current Procedural Terminology) codes. The focus of the study was the preoperative patient CAN score, a single numerical value ranging from 0 to 99 (with a higher score representing greater risk) that is automatically calculated each week using multiple data points in the VA electronic health record. Study outcomes of interest were 90-day readmission, prolonged hospital stay (>5 days), 1-year mortality, and non-routine patient discharge.

Results:

The study included 17,210 veterans. Their median preoperative CAN score was 75, although there was substantial variability in patient CAN scores among different facilities. A preoperative CAN score of >75 was significantly associated with mortality (odds ratio [OR] = 3.54), prolonged length of stay (OR = 1.97), 90-day readmission (OR = 1.65), and non-routine discharge (OR = 1.57). The CAN score had good accuracy with a receiver operating characteristic (ROC) curve value of >0.7 for all outcomes except 90-day readmission.

Conclusions:

The CAN score can be leveraged as an extremely efficient way to risk-stratify patients before TKA, with results that surpass other commonly available and labor-intensive alternatives. As a result, this simple and efficient solution is well positioned for broad adoption as a standardized decision support tool.

Level of Evidence:

Prognostic Level IV. See Instructions for Authors for a complete description of levels of evidence.

Can the American College of Surgeons Risk Calculator Predict 30-day Complications After Spine Surgery?

MINI: It is unclear whether the ACS NSQIP Surgical Risk Calculator can predict 30-day complications after lumbar and cervical spinal fusions. This study shows that the Risk Calculator is only of marginal benefit in predicting outcomes in cervical fusion and unlikely to be of benefit in lumbar fusions.

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

The aim of this study was to assess the American College of Surgeons National Surgery Quality Improvement Program (ACS NSQIP) Risk Calculator's ability to predict 30-day complications after spine surgery.

SUMMARY OF BACKGROUND DATA

Surgical risk calculators may identify patients at increased risk for complications, improve outcomes, enhance the informed consent process, and help modify risk factors. The ACS NSQIP Risk Calculator was developed from a cohort of >1.4 million patients, using 2805 unique CPT codes. It uses 21 patient predictors and the planned procedure to predict the risk of 12 different outcomes within 30 days following surgery.

METHODS

A retrospective chart review was performed on patients who underwent primary lumbar and cervical fusions with at least 30-day postoperative follow-up between 2009 and 2015 at a single-institution. Descriptive statistics were calculated for the overall sample, anterior versus posterior fusion (cervical only), and single versus multilevel fusion. Logistic regression models were fit with actual complication occurrence as the dependent variable in each model and ACS estimated risk as the independent variable. The c-statistic was used as the measure of concordance for each model. Receiver-operating charateristic curves depicted the predictive ability of the estimated risks. Acceptable concordance was set at c >0.80.

RESULTS

A total of 237 lumbar and 404 cervical patients were included in the study. The Risk Calculator risk estimates significantly predicted (P < 0.001) "any complication" and "discharge to skilled nursing facility" among the cervical cohort and demonstrated no significant outcome prediction the lumbar cohort.

CONCLUSION

The ACS Risk-Calculator accurately predicted complications in the categories of "any complication" and "discharge to skilled nursing facility" for our cervical cohort and failed to demonstrate benefit for our lumbar cohort. Although the ACS Risk-Calculator may be useful in general surgery, our findings demonstrate that it does not necessarily provide accurate information for patients undergoing spinal surgery.

LEVEL OF EVIDENCE

3.

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.

Evaluation of the ACS NSQIP Surgical Risk Calculator in Elderly Patients Undergoing Hepatectomy for Hepatocellular Carcinoma

BACKGROUND

The American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP) surgical risk calculator (SRC) aims to help predict patient-specific risk for morbidity and mortality. The performance of the SRC among an elderly population undergoing curative-intent hepatectomy for hepatocellular carcinoma (HCC) remains unknown.

METHODS

Patients > 70 years of age who underwent hepatectomy for HCC between 1998 and 2017 were identified using a multi-institutional international database. To estimate the performance of SRC, 12 observed postoperative outcomes were compared with median SRC-predicted risk, and C-statistics and Brier scores were calculated.

RESULTS

Among 500 patients, median age was 75 years (IQR 72-78). Most patients (n = 324, 64.8%) underwent a minor hepatectomy, while 35.2% underwent a major hepatectomy. The observed incidence of venous thromboembolism (VTE) (3.2%) and renal failure (RF) (4.4%) exceeded the median predicted risk (VTE, 1.8%; IQR 1.5-3.1 and RF, 1.0%; IQR 0.5-2.0). In contrast, the observed incidence of 30-day readmission (7.0%) and non-home discharge (2.5%) was lower than median-predicted risk (30-day readmission, 9.4%; IQR 7.4-12.8 and non-home discharge, 5.7%; IQR 3.3-11.7). Only 57.8% and 71.2% of patients who experienced readmission (C-statistic, 0.578; 95%CI 0.468-0.688) or mortality (C-statistic, 0.712; 95%CI 0.508-0.917) were correctly identified by the model.

CONCLUSION

Among elderly patients undergoing hepatectomy for HCC, the SRC underestimated the risk of complications such as VTE and RF, while being no better than chance in estimating the risk of readmission. The ACS SRC has limited clinical applicability in estimating perioperative risk among elderly patients being considered for hepatic resection of HCC.

Spinal Anesthesia Is Associated With Decreased Complications After Total Knee and Hip Arthroplasty

BACKGROUND

We compared the following 30-day outcomes for total knee arthroplasty (TKA) and total hip arthroplasty in spinal anesthesia (SA) versus general anesthesia (GA) (1) mortality, (2) major and minor complication rates, and (3) discharge disposition.

METHODS

From 2011 to 2016, the American College of Surgeons National Surgical Quality Improvement Program database contained 45,871 SA total hip arthroplasties and 65,092 receiving GA. There were 80,077 SA TKAs and 103,003 GA TKAs. Adjusted multivariate logistic regression evaluated associations between anesthesia type and 30-day outcomes.

RESULTS

Anesthesia modality was not associated with 30-day mortality (P > 0.05). The GA cohorts were at a greater risk for any complication, major complications, and minor complications (P < 0.05). Patients who received GA were at an increased risk for nonhome discharge.

CONCLUSION

Patients who undergo total joint arthroplasty with SA experience fewer 30-day complications and are less likely to have a nonhome discharge than those with GA.

Predicting Post-operative Complications in Crohn's Disease: an Appraisal of Clinical Scoring Systems and the NSQIP Surgical Risk Calculator

BACKGROUND

Surgery is common in patients with Crohn's disease and can contribute significantly to patient morbidity. The National Surgical Quality Improvement Program surgical risk calculator (NSQIP-SRC) that is currently utilized to predict surgical risk does not take Crohn's disease into account and, as a result, seems to underestimate risk in this patient population. This study aimed to evaluate the accuracy of the NSQIP-SRC in Crohn's disease patients and to evaluate the utility of disease severity scores in predicting surgical risk.

METHODS

Between 2011 and 2017, there were 176 surgical cases involving Crohn's disease patients. Demographic data and 30-day surgical outcomes were collected. Disease severity scores including Harvey Bradshaw Index (HBI), Crohn's Disease Activity Index (CDAI), Simple Endoscopic Score for Crohn's Disease (SES-CD), and NSQIP-SRC risk percentages were calculated.

RESULTS

Patients in remission based on HBI had a complication rate of 8.57% (n = 3), while those with mild or moderate-severe disease had rates of 33.33% (n = 11) and 38.46% (n = 20) respectively (p = 0.0045). In multivariable analysis, those with mild (OR; 8.37, 95% CI; 1.64, 42.78; p = 0.011) or moderate-severe (OR; 11.69, 95% CI; 2.42, 56.46; p = 0.002) disease had increased odds of complication compared to remission. Complication rate was not associated with NSQIP-SRC percent risk of any complication.

CONCLUSION

NSQIP-SRC does not accurately predict risk in patients with CD undergoing surgery. Higher disease activity based on HBI is associated with increased odds of complication and may prove to be more predictive of surgical complication in the Crohn's patient population.

Can the American College of Surgeons Risk Calculator Predict 30-Day Complications After Cervical Spine Surgery?

STUDY DESIGN

This was a retrospective cohort study.

OBJECTIVE

The objective of this study was to assess the American College of Surgeons (ACS) Risk Calculator's ability to accurately predict complications after cervical spine surgery.

SUMMARY OF BACKGROUND DATA

Surgical risk calculators exist in many fields and may assist in the identification of patients at increased risk for complications and readmissions. Risk calculators may allow for improved outcomes, an enhanced informed consent process, and management of modifiable risk factors. The American College of Surgeons National Surgery Quality Improvement Program (ACS NSQIP) Risk Calculator was developed from a cohort of over 1.4 million patients, using 2805 unique Current Procedural Terminology (CPT) codes. The risk calculator uses 21 patient predictors (eg, age, American Society of Anesthesiologists class, body mass index, hypertension) and the planned procedure (CPT code) to predict the chance that patients will have any of 12 different outcomes (eg, death, any complication, serious complication, reoperation) within 30 days following surgery. The purpose of this study is to determine if the ACS NISQIP risk calculator can predict 30-day complications after cervical fusion.

METHODS

A retrospective chart review was performed on patients that underwent primary cervical fusions between January 2009 and 2015 at a single institution, utilizing cervical fusion CPT codes. Patients without 30 days of postoperative follow-up were excluded. Descriptive statistics were calculated for the overall sample, anterior versus posterior fusion, and single versus multilevel fusion. Logistic regression models were fit with actual complication occurrence as the dependent variable in each model and ACS estimated risk as the independent variable. The c-statistic was used as the measure of concordance for each model. Receiver operating characteristic curves were plotted to visually depict the predictive ability of the estimated risks. Acceptable concordance was set at c>0.80. All analyses were conducted using SAS, v9.4.

RESULTS

A total of 404 patients met the inclusion criteria for this study. Age, body mass index, sex, and a number of levels of fusion were gathered as input data the ACS NSQIP Risk Calculator. Results of Risk Calculator were compared with observed complication rates. Descriptive statistics of the Risk Calculator risk estimates showed a significant prediction of "any complication" and "discharge to skilled nursing facility" among the cohort. Because there were no deaths or urinary tract infections, no models were fit for these outcomes.

CONCLUSIONS

The ACS Risk Calculator accurately predicted complications in the categories of "any complication" (P<0.0001) and "discharge to the skilled nursing facility" (P<0.001) for our cohort. We conclude that the ACS Risk Calculator was unable to accurately predict specific complications on a more granular basis for the patients of this study. Although the ACS risk calculator may be useful in the field of general surgery and in the development of new institutional strategies for risk mitigation, our findings demonstrate that it does not necessarily provide accurate information for patients undergoing cervical spinal surgery.