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

Disparities in Demographics in Hip Arthroplasty Between U.S. Active Duty Military and the ACS-NSQIP Clinical Registry

INTRODUCTION

Patient demographics, such as sex and age, are known risk factors for undergoing revision following primary total hip arthroplasty (THA). The military population is unique because of the increased rates of primary and secondary osteoarthritis of the hip. Treatment options are limited for returning patients to their line of duty; however, THA has been shown to be an effective option. The primary purpose of this study was to evaluate and contrast the demographic differences of patients undergoing primary THA between the U.S. active duty military population and the general population. The secondary goal was to identify the proportion of primary THA performed at the MTF within the military health system (MHS).

METHODS

This was an exempt study determined by the local institutional review board. A retrospective analysis of the MHS Data Repository (MDR) and the National Surgical Quality Improvement Program (NSQIP) was performed. The databases were used to identify the patients who underwent THA from January 1, 2015 to December 31, 2020. The MDR was used to identify demographics such as sex, age, setting of surgery, geographic location, previous military deployments, history of deployment-related injuries, branch of service, and rank. The NSQIP database was queried for sex and age. The median age of the population was compared using the Mann-Whitney U test and gender was compared using the Chi-square test.

RESULTS

The MDR was used to evaluate 2,734 patients, whereas the NSQIP database was used to evaluate 223,832 patients. In the military population, patients who underwent THA were 87.7% male with an average age of 45 years, whereas in the general population as measured via the NSQIP database, 45.2% patients were male with an average age of 66.0 years. Comparing the two groups, we demonstrated that the military patients were significantly more likely to be younger (P < .001) and males (P < .001). Only 29.6% of primary THAs were performed within the MTF.

CONCLUSIONS

Patients in the MHS are undergoing THA at a younger age and are more likely to be male compared to the general population. A significant portion of primary THAs in the MHS are also being performed at civilian institutions. These demographics may result in increased risk of revision; however, long-term studies are warranted to evaluate survivorship in this unique population.

A Lack of Generalizability-Total Knee Demographics in the Active Duty Population

INTRODUCTION

Age and sex are known demographic risk factors for requiring revision surgery following primary total knee arthroplasty (TKA). Military service members are a unique population with barriers to long-term follow up after surgery. This study aims to compare demographic data between active duty military personnel and a nationwide sample to identify differences that may impact clinical and economic outcomes.

METHODS

A retrospective observational analysis was performed using the Military Health System Data Repository (MDR) and the National Surgical Quality Improvement Program (NSQIP). Databases were queried for patients undergoing primary TKA between January 1, 2015 and December 31, 2020. The MDR was queried for demographic data including age, sex, duty status, facility type, geographic region, history of prior military deployment, history of deployment-related health condition, branch of military service, and military rank. National Surgical Quality Improvement Program was queried for age and sex. Median age between populations was compared with the Mann-Whitney U test, and gender was compared with a chi-squared test.

RESULTS

During the study period, 2,094 primary TKA patients were identified from the MDR, and 357,865 TKA patients were identified from the NSQIP database. Military TKA patients were 79.4% male with a median age of 49.0, and NSQIP TKA patients were 38.9% were male, with a median age of 67. Military TKA patients were significantly more likely to be male (P < .001) and younger (P < .001).

CONCLUSION

Patients undergoing TKA in the military are younger and more likely to be male compared to national trends. Current evidence suggests these factors may place them at a significant revision risk in the future. The application of quality metrics based on nationwide demographics may not be applicable to military members within the Military Health System.

Incorporating Expected Outcomes Into Clinical Decision-Making for Total Knee Arthroplasty

OBJECTIVE

Expected outcomes (e.g., expected survivorship after a cancer treatment) have improved decision-making around treatment options in many clinical fields. Our objective was to evaluate the effect of expected values of 3 widely available total knee arthroplasty (TKA) outcomes (risk of serious complications, time to revision, and improvement in pain and function at 2 years after surgery) on clinical recommendation of TKA.

METHODS

The RAND/University of California Los Angeles appropriateness criteria method was used to evaluate the role of the 3 expected outcomes in clinical recommendation of TKA. The expected outcomes were added to 5 established preoperative factors from the modified Escobar appropriateness criteria. The 8 indication factors were used to develop 279 clinical scenarios, and a panel of 9 clinicians rated the appropriateness of TKA for each scenario as inappropriate, inconclusive, and appropriate. Classification tree analysis was applied to these ratings to identify the most influential of the 8 factors in discriminating TKA appropriateness classifications.

RESULTS

Ratings for the 279 appropriateness scenarios deemed 34.4% of the scenarios as appropriate, 40.1% as inconclusive, and 25.5% as inappropriate. Classification tree analyses showed that expected improvement in pain and function and expected time to revision were the most influential factors that discriminated among the TKA appropriateness classification categories.

CONCLUSION

Our results showed that clinicians would use expected postoperative outcome factors in determining appropriateness for TKA. These results call for further work in this area to incorporate estimates of expected pain/function and revision outcomes into clinical practice to improve decision-making for TKA.

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.

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.

Global research landscape on artificial intelligence in arthroplasty: A bibliometric analysis

Background

Artificial intelligence (AI) has promising applications in arthroplasty. In response to the knowledge explosion resulting from the rapid growth of publications, we applied bibliometric analysis to explore the research profile and topical trends in this field.

Methods

The articles and reviews related to AI in arthroplasty were retrieved from 2000 to 2021. The Java-based Citespace, VOSviewer, R software-based Bibiometrix, and an online platform systematically evaluated publications by countries, institutions, authors, journals, references, and keywords.

Results

A total of 867 publications were included. Over the past 22 years, the number of AI-related publications in the field of arthroplasty has grown exponentially. The United States was the most productive and academically influential country. The Cleveland Clinic was the most prolific institution. Most publications were published in high academic impact journals. However, collaborative networks revealed a lack and imbalance of inter-regional, inter-institutional, and inter-author cooperation. Two emerging research areas represented the development trends: major AI subfields such as machine learning and deep learning, and the other is research related to clinical outcomes.

Conclusion

AI in arthroplasty is evolving rapidly. Collaboration between different regions and institutions should be strengthened to deepen our understanding further and exert critical implications for decision-making. Predicting clinical outcomes of arthroplasty using novel AI strategies may be a promising application in this field.

Large Surgical Databases with Direct Data Abstraction: VASQIP and ACS-NSQIP

Direct data abstraction from a patient's chart by experienced medical professional data abstractors has been the historical gold standard for quality and accuracy in clinical medical research. The limiting challenge to population-wide studies for quality and public health purposes is the high personnel costs associated with very large-scale efforts of this type. Two historically related programs that are at least partially able to successfully circumvent this problem and provide high-quality data relating to surgical procedures and the early postoperative period are reviewed in this article. Both utilize similar data abstraction efforts by specially trained and qualified medical abstractors of a sample subset of the total procedures performed at participating hospitals.The Veterans Affairs Surgical Quality Improvement Program (VASQIP), detailed by Nicholas J. Giori, MD, PhD, in the first section of this article, makes use of trained abstractors and has undergone recent additions and updates, including the development of an associated total hip registry for the VA system. The data elements and data integrity provided by both of these programs establish important benchmarks for other "big data" efforts, which often attempt to use alternative less-expensive methods of data collection in order to achieve more widespread or even nationwide data collection.In the second section, Elizabeth B. Habermann, PhD, MPH, provides a detailed review of the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP), the data elements collected, and examples of the range of quality improvement and outcomes studies in orthopaedic surgery that it has made possible, along with information on data that have not been collected and the resulting limitations. The ACS NSQIP was actually modeled after the very similar earlier effort started by the United States Department of Veterans Affairs (VA).

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.

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.

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.

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.

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.

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.

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.

Health Policy in Hand Surgery: Evaluating What Works

Health policy is a complex and fluid topic that addresses care delivery with the goal of improving patient care. Understanding health policy initiatives, their motivation, and their effects, can help ensure hand surgeons are prepared for the changing health care landscape.

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.