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

Machine learning model identifies patient gait speed throughout the episode of care, generating notifications for clinician evaluation

INTRODUCTION

The advent of digital and mobile health innovations, especially use of wearables for passive data collection, allows remote monitoring and creates an abundance of data. For this information to be interpretable, machine learning (ML) processes are necessary.

RESEARCH QUESTION

Can a machine learning model successfully identify patients expected to have low gait speed in the early recovery period following joint replacement surgery?

METHODS

A commercial database from a smartphone-based care management platform passively collecting mobility data pre- and post-lower limb arthroplasty was used. We sought to create a ML model to predict gait speed recovery curves and identify patients at risk of poor gait speed outcome, a measure associated with range of motion and patient-reported outcomes. Model performance including sensitivity, specificity, precision, and accuracy were determined. Receiver operator curve (ROC) analysis was used to compare true and false positive rates. To benchmark our model, we compared threshold-based notifications based on the patient's current gait speed.

RESULTS

The performance of the predictive model was significantly improved compared to baseline of threshold-based exceptions using current gait speed. The ML model currently provides 53 % precision, 88 % accuracy, 36 % sensitivity, and 95 % specificity on the held-out test set. The ROC analysis suggests good clinical performance (AUC=0.81).

SIGNIFICANCE

Utilization of ML to predict gait recovery following total joint replacement is feasible and provides results with excellent specificity. This model will allow inclusion of additional data for retraining as patient populations evolve. Clinician feedback regarding notifications, including resulting actions and outcomes, can be used to further inform the model and improve clinical utility.

Optimal inputs for machine learning models in predicting total joint arthroplasty outcomes: a systematic review

INTRODUCTION

Machine learning (ML) models may offer a novel solution to reducing postoperative complication rates and improving post-surgical outcomes after total joint arthroplasty (TJA). However, the variety of different ML models that exist paired with the increasing number of potential inputs can make the implementation of this tool challenging. Therefore, we conducted a systematic review to assess the most optimal inputs of different ML models in predicting postoperative (1) medical outcomes, (2) orthopedic outcomes, and (3) patient-reported outcome measures (PROMs) after total joint arthroplasty.

METHODS

The PubMed, MEDLINE, EBSCOhost, and Google Scholar databases were utilized to identify all studies evaluating ML models predicting outcomes following TJA between January 1, 2000, and June 23, 2023 (PROSPERO study protocol registration: CRD42023437586). The mean risk of bias in non-randomized studies-of interventions score, was 13.8 ± 0.5. Our initial query yielded 656 articles, of which 25 articles aligned with our aims, examining over 20 machine learning models and 1,555,300 surgeries. The area under the curve (AUC), accuracy, inputs, and the importance of each input were reported.

RESULTS

Twelve studies evaluating medical complications with 13 ML models reported AUCs ranging from 0.57 to 0.997 and accuracy between 88% and 99.98%. Key predictors included age, hyper-coagulopathy, total number of diagnoses, admission month, and malnutrition. Five studies evaluating orthopedic complications with 10 ML models reported AUCs from 0.49 to 0.93 and accuracy ranging from 92 to 97%, with age, BMI, CCI, AKSS scores, and height identified as key predictors. Ten studies evaluating PROMs comprising of 12 different ML models had an AUC ranging from 0.453 to 0.97 ranked preoperative PROMs as the post-predictive input. Overall, age was the most predictive risk factor for complications post-total joint arthroplasty (TJA).

CONCLUSION

These studies demonstrate the predictive capabilities of these models for anticipating complications and outcomes. Furthermore, these studies also highlight ML models' ability to identify non-classical variables not commonly considered in addition to confirming variables known to be crucial. To advance the field, forthcoming research should adhere to established guidelines for model development and training, employ industry-standard input parameters, and subject their models to external validity assessments.

Robotics in Arthroplasty: Historical Progression, Contemporary Applications, and Future Horizons With Artificial Intelligence (AI) Integration

Robotic technology is increasingly utilized in surgical procedures to enhance precision, particularly in tasks demanding delicate maneuvers beyond human capabilities. Robotic orthopedic surgery emerges as a dynamic and compelling technology reshaping the landscape of surgical practice. This aids surgeons in achieving enhanced accuracy and reproducibility, ultimately aiming for improved patient outcomes. As of now, the majority of these systems are in a developed stage and are gradually gaining broader adoption. These systems have to show that they are user-friendly, are successful in clinical settings, and have a good cost-effectiveness ratio before they can be widely adopted in the field of surgery. In this review, we examine the evolution of robotics in orthopedic surgery, assess its current applications, and provide insights into the future trajectory of this technology, particularly in light of advances in artificial intelligence (AI) and machine learning (ML).

Artificial intelligence in total and unicompartmental knee arthroplasty

The application of Artificial intelligence (AI) and machine learning (ML) tools in total (TKA) and unicompartmental knee arthroplasty (UKA) emerges with the potential to improve patient-centered decision-making and outcome prediction in orthopedics, as ML algorithms can generate patient-specific risk models. This review aims to evaluate the potential of the application of AI/ML models in the prediction of TKA outcomes and the identification of populations at risk.An extensive search in the following databases: MEDLINE, Scopus, Cinahl, Google Scholar, and EMBASE was conducted using the PIOS approach to formulate the research question. The PRISMA guideline was used for reporting the evidence of the data extracted. A modified eight-item MINORS checklist was employed for the quality assessment. The databases were screened from the inception to June 2022.Forty-four out of the 542 initially selected articles were eligible for the data analysis; 5 further articles were identified and added to the review from the PUBMED database, for a total of 49 articles included. A total of 2,595,780 patients were identified, with an overall average age of the patients of 70.2 years ± 7.9 years old. The five most common AI/ML models identified in the selected articles were: RF, in 38.77% of studies; GBM, in 36.73% of studies; ANN in 34.7% of articles; LR, in 32.65%; SVM in 26.53% of articles.This systematic review evaluated the possible uses of AI/ML models in TKA, highlighting their potential to lead to more accurate predictions, less time-consuming data processing, and improved decision-making, all while minimizing user input bias to provide risk-based patient-specific care.

Predicting 30-day unplanned hospital readmission after revision total knee arthroplasty: machine learning model analysis of a national patient cohort

Revision total knee arthroplasty (TKA) is associated with a higher risk of readmission than primary TKA. Identifying individual patients predisposed to readmission can facilitate proactive optimization and increase care efficiency. This study developed machine learning (ML) models to predict unplanned readmission following revision TKA using a national-scale patient dataset. A total of 17,443 revision TKA cases (2013-2020) were acquired from the ACS NSQIP database. Four ML models (artificial neural networks, random forest, histogram-based gradient boosting, and k-nearest neighbor) were developed on relevant patient variables to predict readmission following revision TKA. The length of stay, operation time, body mass index (BMI), and laboratory test results were the strongest predictors of readmission. Histogram-based gradient boosting was the best performer in distinguishing readmission (AUC: 0.95) and estimating the readmission probability for individual patients (calibration slope: 1.13; calibration intercept: -0.00; Brier score: 0.064). All models produced higher net benefit than the default strategies of treating all or no patients, supporting the clinical utility of the models. ML demonstrated excellent performance for the prediction of readmission following revision TKA. Optimization of important predictors highlighted by our model may decrease preventable hospital readmission following surgery, thereby leading to reduced financial burden and improved patient satisfaction.

Can generative artificial intelligence pass the orthopaedic board examination?

Background

Resident training programs in the US use the Orthopaedic In-Training Examination (OITE) developed by the American Academy of Orthopaedic Surgeons (AAOS) to assess the current knowledge of their residents and to identify the residents at risk of failing the Amerian Board of Orthopaedic Surgery (ABOS) examination. Optimal strategies for OITE preparation are constantly being explored. There may be a role for Large Language Models (LLMs) in orthopaedic resident education. ChatGPT, an LLM launched in late 2022 has demonstrated the ability to produce accurate, detailed answers, potentially enabling it to aid in medical education and clinical decision-making. The purpose of this study is to evaluate the performance of ChatGPT on Orthopaedic In-Training Examinations using Self-Assessment Exams from the AAOS database and approved literature as a proxy for the Orthopaedic Board Examination.

Methods

301 SAE questions from the AAOS database and associated AAOS literature were input into ChatGPT's interface in a question and multiple-choice format and the answers were then analyzed to determine which answer choice was selected. A new chat was used for every question. All answers were recorded, categorized, and compared to the answer given by the OITE and SAE exams, noting whether the answer was right or wrong.

Results

Of the 301 questions asked, ChatGPT was able to correctly answer 183 (60.8%) of them. The subjects with the highest percentage of correct questions were basic science (81%), oncology (72.7%, shoulder and elbow (71.9%), and sports (71.4%). The questions were further subdivided into 3 groups: those about management, diagnosis, or knowledge recall. There were 86 management questions and 47 were correct (54.7%), 45 diagnosis questions with 32 correct (71.7%), and 168 knowledge recall questions with 102 correct (60.7%).

Conclusions

ChatGPT has the potential to provide orthopedic educators and trainees with accurate clinical conclusions for the majority of board-style questions, although its reasoning should be carefully analyzed for accuracy and clinical validity. As such, its usefulness in a clinical educational context is currently limited but rapidly evolving.

Clinical relevance

ChatGPT can access a multitude of medical data and may help provide accurate answers to clinical questions.

Preoperative factors predict prolonged length of stay, serious adverse complications, and readmission following operative intervention of proximal humerus fractures: a machine learning analysis of a national database

Background

Proximal humerus fractures are a common injury, predominantly affecting older adults. This study aimed to develop risk-prediction models for prolonged length of hospital stay (LOS), serious adverse complications, and readmission within 30 days of surgically treated proximal humerus fractures using machine learning (ML) techniques.

Methods

Adult patients (age >18) who underwent open reduction internal fixation (ORIF), hemiarthroplasty, or total shoulder arthroplasty for proximal humerus fracture between 2016 and 2021 were included. Preoperative demographic and clinical variables were collected for all patients and used to establish ML-based algorithms. The model with optimal performance was selected according to area under the curve (AUC) on the receiver operating curve (ROC) curve and overall accuracy, and the specific predictive features most important to model derivation were identified.

Results

A total of 7473 patients were included (72.1% male, mean age 66.2 ± 13.7 years). Models produced via gradient boosting performed best for predicting prolonged LOS and complications. The model predicting prolonged LOS demonstrated good discrimination and performance, as indicated by (Mean: 0.700, SE: 0.017), recall (Mean: 0.551, SE: 0.017), accuracy (Mean: 0.717, SE: 0.010), F1-score (Mean: 0.616, SE: 0.014), AUC (Mean: 0.779, SE: 0.010), and Brier score (Mean: 0.283, SE: 0.010) Preoperative hematocrit, preoperative platelet count, and patient age were considered the strongest predictive features. The model predicting serious adverse complications exhibited comparable discrimination [precision (Mean: 0.226, SE: 0.024), recall (Mean: 0.697, SE: 0.048), accuracy (Mean: 0.811, SE: 0.010), F1-score (Mean: 0.341, SE: 0.031)] and superior performance relative to the LOS model [AUC (Mean: 0.806, SE: 0.024), Brier score (Mean: 0.189, SE: 0.010), noting preoperative hematocrit, operative time, and patient age to be most influential. However, the 30-day readmission model achieved the weakest relative performance, displaying low measures of precision (Mean: 0.070, SE: 0.012) and recall (Mean: 0.389, SE: 0.053), despite good accuracy (Mean: 0.791, SE: 0.009).

Conclusion

Predictive models constructed using ML techniques demonstrated favorable discrimination and satisfactory-to-excellent performance in forecasting prolonged LOS and serious adverse complications occurring within 30 days of surgical intervention for proximal humerus fracture. Modifiable preoperative factors such as hematocrit and platelet count were identified as significant predictive features, suggesting that clinicians could address these factors during preoperative patient optimization to enhance outcomes. Overall, these findings highlight the potential for ML techniques to enhance preoperative management, facilitate shared decision-making, and enable more effective and personalized orthopedic care by exploring alternative approaches to risk stratification.

Supervised machine learning for the prediction of post-operative clinical outcomes of hip and knee replacements: a review

Prediction models are being increasingly used in the medical field to identify risk factors and possible outcomes. Some of these are presently being used to develop guidelines for improving clinical practice. The application of machine learning (ML), comprising a powerful set of computational tools for analysing data, has been clearly expanding in the role of predictive modelling. This paper reviews the latest developments of supervised ML techniques that have been used to analyse data related to post-operative total hip and knee replacements. The aim was to review the most recent findings of relevant published studies by outlining the methodologies employed (most-widely used supervised ML techniques), data sources, domains, limitations of predictive analytics and the quality of predictions.

Evaluation of Preoperative Variables that Improve the Predictive Accuracy of the Risk Assessment and Prediction Tool in Primary Total Hip Arthroplasty

INTRODUCTION

Discharge disposition after total joint arthroplasty may be predictable. Previous literature has attempted to improve upon models such as the Risk Assessment and Prediction Tool (RAPT) in an effort to optimize postoperative planning. The purpose of this study was to determine whether preoperative laboratory values and other previously unstudied demographic factors could improve the predictive accuracy of the RAPT.

METHODS

All patients included had RAPT scores in addition to the following preoperative laboratory values: red blood cell count, albumin, and vitamin D. All values were recorded within 90 days of surgery. Demographic variables including marital status, American Society of Anesthesiologists (ASA) scores, body mass index, Charlson Comorbidity Index, and depression were also evaluated. Binary logistic regression was used to determine the significance of each factor in association with discharge disposition.

RESULTS

Univariate logistic regression found significant associations between discharge disposition and all original RAPT factors as well as nonmarried patients (P < 0.001), ASA class 3 to 4 (P < 0.001), body mass index >30 kg/m2 (P = 0.065), red blood cell count <4 million/mm3 (P < 0.001), albumin <3.5 g/dL (P < 0.001), Charlson Comorbidity Index (P < 0.001), and a history of depression (P < 0.001). All notable univariate models were used to create a multivariate model with an overall predictive accuracy of 90.1%.

CONCLUSIONS

The addition of preoperative laboratory values and additional demographic data to the RAPT may improve its PA. Orthopaedic surgeons could benefit from incorporating these values as part of their discharge planning in THA. Machine learning may be able to identify other factors to make the model even more predictive.

Machine Learning-Based Predictive Models for Patients with Venous Thromboembolism: A Systematic Review

BACKGROUND

 Venous thromboembolism (VTE) is a chronic disorder with a significant health and economic burden. Several VTE-specific clinical prediction models (CPMs) have been used to assist physicians in decision-making but have several limitations. This systematic review explores if machine learning (ML) can enhance CPMs by analyzing extensive patient data derived from electronic health records. We aimed to explore ML-CPMs' applications in VTE for risk stratification, outcome prediction, diagnosis, and treatment.

METHODS

 Three databases were searched: PubMed, Google Scholar, and IEEE electronic library. Inclusion criteria focused on studies using structured data, excluding non-English publications, studies on non-humans, and certain data types such as natural language processing and image processing. Studies involving pregnant women, cancer patients, and children were also excluded. After excluding irrelevant studies, a total of 77 studies were included.

RESULTS

 Most studies report that ML-CPMs outperformed traditional CPMs in terms of receiver operating area under the curve in the four clinical domains that were explored. However, the majority of the studies were retrospective, monocentric, and lacked detailed model architecture description and external validation, which are essential for quality audit. This review identified research gaps and highlighted challenges related to standardized reporting, reproducibility, and model comparison.

CONCLUSION

 ML-CPMs show promise in improving risk assessment and individualized treatment recommendations in VTE. Apparently, there is an urgent need for standardized reporting and methodology for ML models, external validation, prospective and real-world data studies, as well as interventional studies to evaluate the impact of artificial intelligence in VTE.

Bibliometric analysis of machine learning trends and hotspots in arthroplasty literature over 31 years

Background

Artificial intelligence has demonstrated utility in orthopedic research. Algorithmic models derived from machine learning have demonstrated adaptive learning with predictive application towards outcomes, leading to increased traction in the literature. This study aims to identify machine learning arthroplasty research trends and anticipate emerging key terms.

Methods

Published literature focused on machine learning in arthroplasty from 1992 to 2023 was selected through the Web of Science Core Collection of Clarivate Analytics. Following that, bibliometric indicators were attained and brought in to perform an additional examination using Bibliometrix and VOSviewer to identify historical and present patterns within the literature.

Results

A total of 235 documents were obtained through bibliometric sourcing based on machine learning applications within the arthroplasty literature. Thirty-four countries published articles on the topic, and the United States was demonstrated to be the largest global contributor. Four hundred-five institutions internationally contributed articles, with Harvard Medical School and the University of California system as the most relevant institutes, with 75 and 44 articles produced, respectively. Kwon YM was the most productive author, while Haeberle HS and Ramkumar PN were the most impactful based on h-index. The Thematic map and Co-occurrence visualization helped identify both major and niche themes present in the scientific databases.

Conclusions

Machine learning in arthroplasty research continues to gain traction with a growing annual production rate and contributions from international authors and institutions. Institutions and authors based in the United States are the leading contributors to machine learning applications within arthroplasty research. This research discerns trends that have occurred, are presently ongoing, and are emerging within this field, aiming to inform future hotspot development.

Enabling Personalized Medicine in Orthopaedic Surgery Through Artificial Intelligence: A Critical Analysis Review

» The application of artificial intelligence (AI) in the field of orthopaedic surgery holds potential for revolutionizing health care delivery across 3 crucial domains: (I) personalized prediction of clinical outcomes and adverse events, which may optimize patient selection, surgical planning, and enhance patient safety and outcomes; (II) diagnostic automated and semiautomated imaging analyses, which may reduce time burden and facilitate precise and timely diagnoses; and (III) forecasting of resource utilization, which may reduce health care costs and increase value for patients and institutions.» Computer vision is one of the most highly studied areas of AI within orthopaedics, with applications pertaining to fracture classification, identification of the manufacturer and model of prosthetic implants, and surveillance of prosthesis loosening and failure.» Prognostic applications of AI within orthopaedics include identifying patients who will likely benefit from a specified treatment, predicting prosthetic implant size, postoperative length of stay, discharge disposition, and surgical complications. Not only may these applications be beneficial to patients but also to institutions and payors because they may inform potential cost expenditure, improve overall hospital efficiency, and help anticipate resource utilization.» AI infrastructure development requires institutional financial commitment and a team of clinicians and data scientists with expertise in AI that can complement skill sets and knowledge. Once a team is established and a goal is determined, teams (1) obtain, curate, and label data; (2) establish a reference standard; (3) develop an AI model; (4) evaluate the performance of the AI model; (5) externally validate the model, and (6) reinforce, improve, and evaluate the model's performance until clinical implementation is possible.» Understanding the implications of AI in orthopaedics may eventually lead to wide-ranging improvements in patient care. However, AI, while holding tremendous promise, is not without methodological and ethical limitations that are essential to address. First, it is important to ensure external validity of programs before their use in a clinical setting. Investigators should maintain high quality data records and registry surveillance, exercise caution when evaluating others' reported AI applications, and increase transparency of the methodological conduct of current models to improve external validity and avoid propagating bias. By addressing these challenges and responsibly embracing the potential of AI, the medical field may eventually be able to harness its power to improve patient care and outcomes.

Personalized Prognosis with Machine Learning Models for Predicting In-Hospital Outcomes Following Intracranial Meningioma Resections

BACKGROUND

Meningiomas display diverse biological traits and clinical behaviors, complicating patient outcome prediction. This heterogeneity, along with varying prognoses, underscores the need for a precise, personalized evaluation of postoperative outcomes.

METHODS

Data from the American College of Surgeons National Surgical Quality Improvement Program database identified patients who underwent intracranial meningioma resections from 2014 to 2020. We focused on 5 outcomes: prolonged LOS, nonhome discharges, 30-day readmissions, unplanned reoperations, and major complications. Six machine learning algorithms, including TabPFN, TabNet, XGBoost, LightGBM, Random Forest, and Logistic Regression, coupled with the Optuna optimization library for hyperparameter tuning, were tested. Models with the highest area under the receiver operating characteristic (AUROC) values were included in the web application. SHapley Additive exPlanations were used to evaluate the importance of predictor variables.

RESULTS

Our analysis included 7000 patients. Of these patients, 1658 (23.7%) had prolonged LOS, 1266 (18.1%) had nonhome discharges, 573 (8.2%) had 30-day readmission, 253 (3.6%) had unplanned reoperation, and 888 (12.7%) had major complications. Performance evaluation indicated that the top-performing models for each outcome were the models built with LightGBM and Random Forest algorithms. The LightGBM models yielded AUROCs of 0.842 and 0.846 in predicting prolonged LOS and nonhome discharges, respectively. The Random Forest models yielded AUROCs of 0.717, 0.76, and 0.805 in predicting 30-day readmissions, unplanned reoperations, and major complications, respectively.

CONCLUSIONS

The study successfully demonstrated the potential of machine learning models in predicting short-term adverse postoperative outcomes after meningioma resections. This approach represents a significant step forward in personalizing the information provided to meningioma patients.

The Use of Artificial Intelligence for the Prediction of Periprosthetic Joint Infection Following Aseptic Revision Total Knee Arthroplasty

Periprosthetic joint infection (PJI) following revision total knee arthroplasty (TKA) for aseptic failure is associated with poor outcomes, patient morbidity, and high health care expenditures. The aim of this study was to develop novel machine learning algorithms for the prediction of PJI following revision TKA for patients with aseptic indications for revision surgery. A single-institution database consisting of 1,432 consecutive revision TKA patients with aseptic etiologies was retrospectively identified. The patient cohort included 208 patients (14.5%) who underwent re-revision surgery for PJI. Three machine learning algorithms (artificial neural networks, support vector machines, k-nearest neighbors) were developed to predict this outcome and these models were assessed by discrimination, calibration, and decision curve analysis. This is a retrospective study. Among the three machine learning models, the neural network model achieved the best performance across discrimination (area under the receiver operating characteristic curve = 0.78), calibration, and decision curve analysis. The strongest predictors for PJI following revision TKA for aseptic reasons were prior open procedure prior to revision surgery, drug abuse, obesity, and diabetes. This study utilized machine learning as a tool for the prediction of PJI following revision TKA for aseptic failure with excellent performance. The validated machine learning models can aid surgeons in patient-specific risk stratifying to assist in preoperative counseling and clinical decision making for patients undergoing aseptic revision TKA.

Predicting health insurance uptake in Kenya using Random Forest: An analysis of socio-economic and demographic factors

Universal Health Coverage (UHC) is a global objective aimed at providing equitable access to essential and cost-effective healthcare services, irrespective of individuals' financial circumstances. Despite efforts to promote UHC through health insurance programs, the uptake in Kenya remains low. This study aimed to explore the factors influencing health insurance uptake and offer insights for effective policy development and outreach programs. The study utilized machine learning techniques on data from the 2021 FinAccess Survey. Among the models examined, the Random Forest model demonstrated the highest performance with notable metrics, including a high Kappa score of 0.9273, Recall score of 0.9640, F1 score of 0.9636, and Accuracy of 0.9636. The study identified several crucial predictors of health insurance uptake, ranked in ascending order of importance by the optimal model, including poverty vulnerability, social security usage, income, education, and marital status. The results suggest that affordability is a significant barrier to health insurance uptake. The study highlights the need to address affordability challenges and implement targeted interventions to improve health insurance uptake in Kenya, thereby advancing progress towards achieving Universal Health Coverage (UHC) and ensuring universal access to quality healthcare services.

Accounting for clustering in automated variable selection using hospital data: a comparison of different LASSO approaches

BACKGROUND

Automated feature selection methods such as the Least Absolute Shrinkage and Selection Operator (LASSO) have recently gained importance in the prediction of quality-related outcomes as well as the risk-adjustment of quality indicators in healthcare. The methods that have been used so far, however, do not account for the fact that patient data are typically nested within hospitals.

METHODS

Therefore, we aimed to demonstrate how to account for the multilevel structure of hospital data with LASSO and compare the results of this procedure with a LASSO variant that ignores the multilevel structure of the data. We used three different data sets (from acute myocardial infarcation, COPD, and stroke patients) with two dependent variables (one numeric and one binary), on which different LASSO variants with and without consideration of the nested data structure were applied. Using a 20-fold sub-sampling procedure, we tested the predictive performance of the different LASSO variants and examined differences in variable importance.

RESULTS

For the metric dependent variable Duration Stay, we found that inserting hospitals led to better predictions, whereas for the binary variable Mortality, all methods performed equally well. However, in some instances, the variable importances differed greatly between the methods.

CONCLUSION

We showed that it is possible to take the multilevel structure of data into account in automated predictor selection and that this leads, at least partly, to better predictive performance. From the perspective of variable importance, including the multilevel structure is crucial to select predictors in an unbiased way under consideration of the structural differences between hospitals.

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

BACKGROUND

The purpose of the study was to use Machine Learning (ML) to construct a risk calculator for patients who undergo Total Joint Arthroplasty (TJA) on the basis of New York State Statewide Planning and Research Cooperative System (SPARCS) data and externally validate the calculator on a single TJA center.

METHODS

Seven ML algorithms, i.e., logistic regression, adaptive boosting, gradient boosting (Xg Boost), random forest (RF) classifier, support vector machine, and single and a five-layered neural network were trained on the derivation cohort. Models were trained on 68% of data, validated on 15%, tested on 15%, and externally validated on 2% of the data from a single arthroplasty center.

RESULTS

Validation of the models showed that the RF classifier performed best in terms of 30-d mortality AUROC (Area Under the Receiver Operating Characteristic) 0.78, 30-d readmission (AUROC 0.61) and 90-d composite complications (AUROC 0.73) amongst the test set. Additionally, Xg Boost was found to be the best predicting model for 90-d readmission and 90-d composite complications (AUC 0.73). External validation demonstrated that models achieved similar AUROCs to the test set although variation occurred in top model performance for 90-d composite complications and readmissions between our test and external validation set.

CONCLUSION

This was the first study to investigate the use of ML to create a predictive risk calculator from state-wide data and then externally validate it with data from a single arthroplasty center. Discrimination between best performing ML models and between the test set and the external validation set are comparable.

LEVEL OF EVIDENCE

III.

The Impact of Machine Learning on Total Joint Arthroplasty Patient Outcomes: A Systemic Review

BACKGROUND

Supervised machine learning techniques have been increasingly applied to predict patient outcomes after hip and knee arthroplasty procedures. The purpose of this study was to systematically review the applications of supervised machine learning techniques to predict patient outcomes after primary total hip and knee arthroplasty.

METHODS

A comprehensive literature search using the electronic databases MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, and Cochrane Database of Systematic Reviews was conducted in July of 2021. The inclusion criteria were studies that utilized supervised machine learning techniques to predict patient outcomes after primary total hip or knee arthroplasty.

RESULTS

Search criteria yielded n = 30 relevant studies. Topics of study included patient complications (n = 6), readmissions (n = 1), revision (n = 2), patient-reported outcome measures (n = 4), patient satisfaction (n = 4), inpatient status and length of stay (LOS) (n = 9), opioid usage (n = 3), and patient function (n = 1). Studies involved TKA (n = 12), THA (n = 11), or a combination (n = 7). Less than 35% of predictive outcomes had an area under the receiver operating characteristic curve (AUC) in the excellent or outstanding range. Additionally, only 9 of the studies found improvement over logistic regression, and only 9 studies were externally validated.

CONCLUSION

Supervised machine learning algorithms are powerful tools that have been increasingly applied to predict patient outcomes after total hip and knee arthroplasty. However, these algorithms should be evaluated in the context of prognostic accuracy, comparison to traditional statistical techniques for outcome prediction, and application to populations outside the training set. While machine learning algorithms have been received with considerable interest, they should be critically assessed and validated prior to clinical adoption.

Using exogenous organizational and regional hospital attributes to explain differences in case-mix adjusted hospital costs

Diagnosis-related group (DRG) hospital reimbursement systems differentiate cases into cost-homogenous groups based on patient characteristics. However, exogenous organizational and regional factors can influence hospital costs beyond case-mix differences. Therefore, most countries using DRG systems incorporate adjustments for such factors into their reimbursement structure. This study investigates structural hospital attributes that explain differences in average case-mix adjusted hospital costs in Switzerland. Using rich patient and hospital-level data containing 4 million cases from 120 hospitals across 3 years, we show that a regression model using only five variables (number of discharges, ratio of emergency/ambulance admissions, rate of DRGs to patients, expected loss potential based on DRG mix, and location in large agglomeration) can explain more than half of the variance in average case-mix adjusted hospital costs, capture all cost variations across commonly differentiated hospital types (e.g., academic teaching hospitals, children's hospitals, birth centers, etc.), and is robust in cross-validations across several years (despite differing hospital samples). Based on our findings, we propose a simple practical approach to differentiate legitimate from inefficiency-related or unexplainable cost differences across hospitals and discuss the potential of such an approach as a transparent way to incorporate structural hospital differences into cost benchmarking and payment schemes.

Artificial intelligence in orthopaedic surgery

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as 'big data', AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI's limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction.

Improved performance of machine learning models in predicting length of stay, discharge disposition, and inpatient mortality after total knee arthroplasty using patient-specific variables

BACKGROUND

This study aimed to compare the performance of ten predictive models using different machine learning (ML) algorithms and compare the performance of models developed using patient-specific vs. situational variables in predicting select outcomes after primary TKA.

METHODS

Data from 2016 to 2017 from the National Inpatient Sample were used to identify 305,577 discharges undergoing primary TKA, which were included in the training, testing, and validation of 10 ML models. 15 predictive variables consisting of 8 patient-specific and 7 situational variables were utilized to predict length of stay (LOS), discharge disposition, and mortality. Using the best performing algorithms, models trained using either 8 patient-specific and 7 situational variables were then developed and compared.

RESULTS

For models developed using all 15 variables, Linear Support Vector Machine (LSVM) was the most responsive model for predicting LOS. LSVM and XGT Boost Tree were equivalently most responsive for predicting discharge disposition. LSVM and XGT Boost Linear were equivalently most responsive for predicting mortality. Decision List, CHAID, and LSVM were the most reliable models for predicting LOS and discharge disposition, while XGT Boost Tree, Decision List, LSVM, and CHAID were most reliable for mortality. Models developed using the 8 patient-specific variables outperformed those developed using the 7 situational variables, with few exceptions.

CONCLUSION

This study revealed that performance of different models varied, ranging from poor to excellent, and demonstrated that models developed using patient-specific variables were typically better predictive of quality metrics after TKA than those developed employing situational variables.

LEVEL OF EVIDENCE

III.

Assessing the predictive capacity of machine learning models using patient-specific variables in determining in-hospital outcomes after THA

Background

Machine learning is a subset of artificial intelligence using algorithmic modeling to progressively learn and create predictive models. Clinical application of machine learning can aid physicians through identification of risk factors and implications of predicted patient outcomes.

Aims

The aim of this study was to compare patient-specific and situation perioperative variables through optimized machine learning models to predict postoperative outcomes.

Methods

Data from 2016 to 2017 from the National Inpatient Sample was used to identify 177,442 discharges undergoing primary total hip arthroplasty, which were included in the training, testing, and validation of 10 machine learning models. 15 predictive variables consisting of 8 patient-specific and 7 situational specific variables were utilized to predict 3 outcome variables: length of stay, discharge, and mortality. The machine learning models were assessed in responsiveness via area under the curve and reliability.

Results

For all outcomes, Linear Support Vector Machine had the highest responsiveness among all models when using all variables. When utilizing patient-specific variables only, responsiveness of the top 3 models ranged between 0.639 and 0.717 for length of stay, 0.703-0.786 for discharge disposition, and 0.887-0.952 for mortality. The top 3 models utilizing situational variables only produced responsiveness of 0.552-0.589 for length of stay, 0.543-0.574 for discharge disposition, and 0.469-0.536 for mortality.

Conclusions

Linear Support Vector Machine was the most responsive machine learning model of the 10 algorithms trained, while decision list was most reliable. Responsiveness was observed to be consistently higher with patient-specific variables than situational variables, emphasizing the predictive capacity and value of patient-specific variables. The current practice in machine learning literature generally deploys a single model, it is suboptimal to develop optimized models for application into clinical practice. The limitation of other algorithms may prohibit potential more reliable and responsive models.Level of Evidence III.

An Update on the Management and Optimization of the Patient with Morbid Obesity Undergoing Hip or Knee Arthroplasty

The prevalence of obesity in the United States is at a record high of 42%. In 1999, the Centers for Disease Control and Prevention recognized the obesity epidemic as a national problem, spurring the first generation of interventions for obesity prevention and control. Despite billions of dollars in funding, legislative changes, and public health initiatives, the trajectory of American obesity has not waivered. Obesity is also strongly associated with the development of osteoarthritis. The growing population of young, obese, and sick patients presents a unique dilemma for orthopedic surgeons performing joint replacement, as obesity levels and the demand for joint replacement are only expected to rise further.

How to Develop and Validate Prediction Models for Orthopedic Outcomes

Prediction models are common in medicine for predicting outcomes such as mortality, complications, or response to treatment. Despite the growing interest in these models in arthroplasty (and orthopaedics in general), few have been adopted in clinical practice. If robustly built and validated, prediction models can be excellent tools to support surgical decision making. In this paper, we provide an overview of the statistical concepts surrounding prediction models and outline practical steps for prediction model development and validation in arthroplasty research. Please visit the followinghttps://www.youtube.com/watch?v=9Yrit23Rkicfor a video that explains the highlights of the paper in practical terms.

Development and internal validation of machine learning algorithms for predicting complications after primary total hip arthroplasty

INTRODUCTION

Complications after total hip arthroplasty (THA) may result in readmission or reoperation and impose a significant cost on the healthcare system. Understanding which patients are at-risk for complications can potentially allow for targeted interventions to decrease complication rates through pursuing preoperative health optimization. The purpose of the current was to develop and internally validate machine learning (ML) algorithms capable of performing patient-specific predictions of all-cause complications within two years of primary THA.

METHODS

This was a retrospective case-control study of clinical registry data from 616 primary THA patients from one large academic and two community hospitals. The primary outcome was all-cause complications at a minimum of 2-years after primary THA. Recursive feature elimination was applied to identify preoperative variables with the greatest predictive value. Five ML algorithms were developed on the training set using tenfold cross-validation and internally validated on the independent testing set of patients. Algorithms were assessed by discrimination, calibration, Brier score, and decision curve analysis to quantify performance.

RESULTS

The observed complication rate was 16.6%. The stochastic gradient boosting model achieved the best performance with an AUC = 0.88, calibration intercept = 0.1, calibration slope = 1.22, and Brier score = 0.09. The most important factors for predicting complications were age, drug allergies, prior hip surgery, smoking, and opioid use. Individual patient-level explanations were provided for the algorithm predictions and incorporated into an open access digital application: https://sorg-apps.shinyapps.io/tha_complication/ CONCLUSIONS: The stochastic boosting gradient algorithm demonstrated good discriminatory capacity for identifying patients at high-risk of experiencing a postoperative complication and proof-of-concept for creating office-based applications from ML that can perform real-time prediction. However, this clinical utility of the current algorithm is unknown and definitions of complications broad. Further investigation on larger data sets and rigorous external validation is necessary prior to the assessment of clinical utility with respect to risk-stratification of patients undergoing primary THA.

LEVEL OF EVIDENCE

III, therapeutic study.

Development of machine-learning algorithms for 90-day and one-year mortality prediction in the elderly with femoral neck fractures based on the HEALTH and FAITH trials

To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials. This study included 2,388 patients from the HEALTH and FAITH trials, with 90-day and one-year mortality proportions of 3.0% (71/2,388) and 6.4% (153/2,388), respectively. The mean age was 75.9 years (SD 10.8) and 65.9% of patients (1,574/2,388) were female. The algorithms included patient and injury characteristics. Six algorithms were developed, internally validated and evaluated across discrimination (c-statistic; discriminative ability between those with risk of mortality and those without), calibration (observed outcome compared to the predicted probability), and the Brier score (composite of discrimination and calibration). The developed algorithms distinguished between patients at high and low risk for 90-day and one-year mortality. The penalized logistic regression algorithm had the best performance metrics for both 90-day (c-statistic 0.80, calibration slope 0.95, calibration intercept -0.06, and Brier score 0.039) and one-year (c-statistic 0.76, calibration slope 0.86, calibration intercept -0.20, and Brier score 0.074) mortality prediction in the hold-out set. Using high-quality data, the ML-based prediction models accurately predicted 90-day and one-year mortality in patients aged 50 years or older with a FNF. The final models must be externally validated to assess generalizability to other populations, and prospectively evaluated in the process of shared decision-making.

Machine Learning Can Accurately Predict Overnight Stay, Readmission, and 30-Day Complications Following Anterior Cruciate Ligament Reconstruction

PURPOSE

This study aimed to develop machine learning (ML) models to predict hospital admission (overnight stay) as well as short-term complications and readmission rates following anterior cruciate ligament reconstruction (ACLR). Furthermore, we sought to compare the ML models with logistic regression models in predicting ACLR outcomes.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients who underwent elective ACLR from 2012 to 2018. Artificial neural network ML and logistic regression models were developed to predict overnight stay, 30-day postoperative complications, and ACL-related readmission, and model performance was compared using the area under the receiver operating characteristic curve. Regression analyses were used to identify variables that were significantly associated with the predicted outcomes.

RESULTS

A total of 21,636 elective ACLR cases met inclusion criteria. Variables associated with hospital admission included White race, obesity, hypertension, and American Society of Anesthesiologists classification 3 and greater, anesthesia other than general, prolonged operative time, and inpatient setting. The incidence of hospital admission (overnight stay) was 10.2%, 30-day complications was 1.3%, and 30-day readmission for ACLR-related causes was 0.9%. Compared with logistic regression models, artificial neural network models reported superior area under the receiver operating characteristic curve values in predicting overnight stay (0.835 vs 0.589), 30-day complications (0.742 vs 0.590), reoperation (0.842 vs 0.601), ACLR-related readmission (0.872 vs 0.606), deep-vein thrombosis (0.804 vs 0.608), and surgical-site infection (0.818 vs 0.596).

CONCLUSIONS

The ML models developed in this study demonstrate an application of ML in which data from a national surgical patient registry was used to predict hospital admission and 30-day postoperative complications after elective ACLR. ML models developed performed well, outperforming regression models in predicting hospital admission and short-term complications following elective ACLR. ML models performed best when predicting ACLR-related readmissions and reoperations, followed by overnight stay.

LEVEL OF EVIDENCE

IV, retrospective comparative prognostic trial.

Advancements in Artificial Intelligence for Foot and Ankle Surgery: A Systematic Review

Background

There has been a rapid increase in research applying artificial intelligence (AI) to various subspecialties of orthopaedic surgery, including foot and ankle surgery. The purpose of this systematic review is to (1) characterize the topics and objectives of studies using AI in foot and ankle surgery, (2) evaluate the performance of their models, and (3) evaluate their validity (internal or external validation).

Methods

A systematic literature review was conducted using PubMed/MEDLINE and Embase databases in December 2022. All studies that used AI or its subsets machine learning (ML) and deep learning (DL) in the setting of foot and ankle surgery relevant to orthopaedic surgeons were included. Studies were evaluated for their demographics, subject area, outcomes of interest, model(s) tested, model(s)' performance, and validity (internal or external).

Results

A total of 31 studies met inclusion criteria: 14 studies investigated AI for image interpretation, 13 studies investigated AI for clinical predictions, and 4 studies were grouped as "other." Studies commonly explored AI for ankle fractures, calcaneus fractures, hallux valgus, Achilles tendon pathologies, plantar fasciitis, and sports injuries. For studies reporting the area under the receiver operating characteristic curve (AUC), AUCs ranged from 0.64 (poor) to 0.99 (excellent). Two studies (6.45%) reported external validation.

Conclusion

Applications of AI in the field of foot and ankle surgery are expanding, particularly for image interpretation and clinical predictions. Current model performances range from poor to excellent, and most studies lack external validation, demonstrating a need for further research prior to deploying AI-based clinical applications.

Level of Evidence

Level III, retrospective cohort study.

External validation of prediction models for patient-reported outcome measurements collected using the selfBACK mobile app

BACKGROUND

External validation is essential in examining the disparities in the training and validation cohorts during the development of prediction models, especially when the application domain is healthcare-oriented. Currently, the use of prediction models in healthcare research aimed at utilising the under-explored potential of patient-reported outcome measurements (PROMs) is limited, and few are validated using external datasets.

OBJECTIVE

To validate the machine learning prediction models developed in our previous work [29] for predicting four pain-related patient-reported outcomes from the selfBACK clinical trial datasets.

METHODS

We evaluate the validity of three pre-trained prediction models based on three methods- Case-Based Reasoning, Support Vector Regression, and XGBoost Regression-using an external dataset that contains PROMs collected from patients with non-specific neck and or low back pain using the selfBACK mobile application.

RESULTS

Overall, the predictive power was low, except for prediction of one of the outcomes. The results indicate that while the predictions are far from immaculate in either case, the models show ability to generalise and predict outcomes for a new dataset.

CONCLUSION

External validation of the prediction models presents modest results and highlights the individual differences and need for external validation of prediction models in clinical settings. There is need for further development in this area of machine learning application and patient-centred care.

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

PURPOSE

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

METHODS

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

RESULTS

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

CONCLUSION

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

External Validation of 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.

Epidemiology of total hip arthroplasty: demographics, comorbidities and outcomes

BACKGROUND

Primary THA (THA) is a successful procedure for end-stage hip osteoarthritis. In the setting of a failed THA, revision total hip arthroplasty (rTHA) acts as a salvage procedure. This procedure has increased risks, including sepsis, infection, prolonged surgery time, blood loss, and increased length of stay. Increasing focus on understanding of demographics, comorbidities, and inpatient outcomes can lead to better perioperative optimization and post-operative outcomes. This epidemiological registry study aimed to compare the demographics, comorbidity profiles, and outcomes of patients undergoing THA and rTHA.

METHODS

A retrospective review of discharge data reported from 2006 to the third quarter of 2015 using the National Inpatient Sample registry was performed. The study included adult patients aged 40 and older who underwent either THA or rTHA. A total of 2,838,742 THA patients and 400,974 rTHA patients were identified.

RESULTS

The primary reimbursement for both THA and rTHA was dispensed by Medicare at 53.51% and 65.36% of cases respectively. Complications arose in 27.32% of THA and 39.46% of rTHA cases. Postoperative anemia was the most common complication in groups (25.20% and 35.69%). Common comorbidities in both groups were hypertension and chronic pulmonary disease. rTHA indications included dislocation/instability (21.85%) followed by mechanical loosening (19.74%), other mechanical complications (17.38%), and infection (15.10%).

CONCLUSION

Our data demonstrated a 69.50% increase in patients receiving THA and a 28.50% increase in rTHA from the years 2006 to 2014. The data demonstrated 27.32% and 39.46% complication rate with THA and rTHA, with postoperative anemia as the most common cause. Common comorbidities were hypertension and chronic pulmonary disease. Future analyses into preoperative optimizations, such as prior consultation with medical specialists or improved primary hip protocol, should be considered to prevent/reduce postoperative complications amongst a progressive expansion in patients receiving both THA and rTHA.

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.

Applying machine learning methods to predict the hospital re-admission within 30 days of total hip arthroplasty and hemiarthroplasty

BACKGROUND

Total hip arthroplasty (THA) and hemiarthroplasty are common treatments for severe hip joint disease. To predict the probability of re-admission after discharge when patients are hospitalized will support providing appropriate health education and guidance.

METHODS

The research aims to use logistic regression (LR), decision trees (DT), random forests (RF), and artificial neural networks (ANN) to establish predictive models and compare their performances on re-admissions within 30 days after THA or hemiarthroplasty. The data of this study includes patient demographics, physiological measurements, disease history, and clinical laboratory test results.

RESULTS

There were 508 and 309 patients in the THA and hemiarthroplasty studies respectively from September 2016 to December 2018. The accuracies of the four models LR, DT, RF, and ANN in the THA experiment are 94.3%, 93.2%, 97.3%, and 93.9%, respectively. In the hemiarthroplasty experiment, the accuracies of the four models are 92.4%, 86.1%, 94.2%, and 94.8%, respectively. Among these, we found that the RF model has the best sensitivity and ANN model has the best area under the receiver operating characteristic (AUROC) score in both experiments.

CONCLUSIONS

The THA experiment confirmed that the performance of the RF model is better than the other models. The key factors affecting the prognosis after THA surgery are creatinine, sodium, anesthesia duration, and dialysis. In the hemiarthroplasty experiment, the ANN model showed more accurate results. Poor kidney function increases the risk of hospital re-admission. This research highlights that RF and ANN model perform well on the hip replacement surgery outcome prediction.

Applications of artificial intelligence in orthopaedic surgery

The practice of medicine is rapidly transforming as a result of technological breakthroughs. Artificial intelligence (AI) systems are becoming more and more relevant in medicine and orthopaedic surgery as a result of the nearly exponential growth in computer processing power, cloud based computing, and development, and refining of medical-task specific software algorithms. Because of the extensive role of technologies such as medical imaging that bring high sensitivity, specificity, and positive/negative prognostic value to management of orthopaedic disorders, the field is particularly ripe for the application of machine-based integration of imaging studies, among other applications. Through this review, we seek to promote awareness in the orthopaedics community of the current accomplishments and projected uses of AI and ML as described in the literature. We summarize the current state of the art in the use of ML and AI in five key orthopaedic disciplines: joint reconstruction, spine, orthopaedic oncology, trauma, and sports medicine.

Concerns surrounding application of artificial intelligence in hip and knee arthroplasty

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

Cite this article: Bone Joint J 2022;104-B(12):1292–1303.

Machine-learning Models Predict 30-Day Mortality, Cardiovascular Complications, and Respiratory Complications After Aseptic Revision Total Joint Arthroplasty

BACKGROUND

Aseptic revision THA and TKA are associated with an increased risk of adverse outcomes compared with primary THA and TKA. Understanding the risk profiles for patients undergoing aseptic revision THA or TKA may provide an opportunity to decrease the risk of postsurgical complications. There are risk stratification tools for postoperative complications after aseptic revision TKA or THA; however, current tools only include nonmodifiable risk factors, such as medical comorbidities, and do not include modifiable risk factors.

QUESTIONS/PURPOSES

(1) Can machine learning predict 30-day mortality and complications for patients undergoing aseptic revision THA or TKA using a cohort from the American College of Surgeons National Surgical Quality Improvement Program database? (2) Which patient variables are the most relevant in predicting complications?

METHODS

This was a temporally validated, retrospective study analyzing the 2014 to 2019 National Surgical Quality Improvement Program database, as this database captures a large cohort of aseptic revision THA and TKA patients across a broad range of clinical settings and includes preoperative laboratory values. The training data set was 2014 to 2018, and 2019 was the validation data set. Given that predictive models learn expected prevalence of outcomes, this split allows assessment of model performance in contemporary patients. Between 2014 and 2019, a total of 24,682 patients underwent aseptic revision TKA and 17,871 patients underwent aseptic revision THA. Of those, patients with CPT codes corresponding to aseptic revision TKA or THA were considered as potentially eligible. Based on excluding procedures involving unclean wounds, 78% (19,345 of 24,682) of aseptic revision TKA procedures and 82% (14,711 of 17,871) of aseptic revision THA procedures were eligible. Ten percent of patients in each of the training and validation cohorts had missing predictor variables. Most of these missing data were preoperative sodium or hematocrit (8% in both the training and validation cohorts). No patients had missing outcome data. No patients were excluded due to missing data. The mean patient was age 66 ± 12 years, the mean BMI was 32 ± 7 kg/m 2 , and the mean American Society of Anesthesiologists (ASA) Physical Score was 3 (56%). XGBoost was then used to create a scoring tool for 30-day adverse outcomes. XGBoost was chosen because it can handle missing data, it is nonlinear, it can assess nuanced relationships between variables, it incorporates techniques to reduce model complexity, and it has a demonstrated record of producing highly accurate machine-learning models. Performance metrics included discrimination and calibration. Discrimination was assessed by c-statistics, which describe the area under the receiver operating characteristic curve. This quantifies how well a predictive model discriminates between patients who have the outcome of interest versus those who do not. Relevant ranges for c-statistics include good (0.70 to 0.79), excellent (0.80 to 0.89), and outstanding (> 0.90). We estimated 95% confidence intervals (CIs) for c-statistics by 500-sample bootstrapping. Calibration curves quantify reliability of model predictions. Reliable models produce prediction probabilities for outcomes that are similar to observed probabilities of those outcomes, so a well-calibrated model should demonstrate a calibration curve that does not deviate substantially from a line of slope 1 and intercept 0. Calibration curves were generated on the 2019 validation data. Shapley Additive Explanations (SHAP) visualizations were used to investigate feature importance to gain insight into how models made predictions. The models were built into an online calculator for ongoing testing and validation. The risk calculator, which is freely available ( http://nb-group.org/rev2/ ), allows a user to input patient data to calculate postoperative risk of 30-day mortality, cardiac, and respiratory complications after aseptic revision TKA or THA. A post hoc analysis was performed to assess whether using data from 2020 would improve calibration on 2019 data.

RESULTS

The model accurately predicted mortality, cardiac complications, and respiratory complications after aseptic revision THA or TKA, with c-statistics of 0.88 (95% CI 0.83 to 0.93), 0.80 (95% CI 0.75 to 0.84), and 0.78 (95% CI 0.74 to 0.82), respectively, on internal validation and 0.87 (95% CI 0.77 to 0.96), 0.70 (95% CI 0.61 to 0.78), and 0.82 (95% CI 0.75 to 0.88), respectively, on temporal validation. Calibration curves demonstrated slight over-confidence in predictions (most predicted probabilities were higher than observed probabilities). Post hoc analysis of 2020 data did not yield improved calibration on the 2019 validation set. Important risk factors for all models included increased age and higher ASA, BMI, hematocrit level, and sodium level. Hematocrit and ASA were in the top three most important features for all models. The factor with the strongest association for mortality and cardiac complication models was age, and for the respiratory model, chronic obstructive pulmonary disease. Risk related to sodium followed a U-shaped curve. Preoperative hyponatremia and hypernatremia predicted an increased risk of mortality and respiratory complications, with a nadir of 138 mmol/L; hyponatremia was more strongly associated with mortality than hypernatremia. A hematocrit level less than 36% predicted an increased risk of all three adverse outcomes. A BMI less than 24 kg/m 2 -and especially less than 20 kg/m 2 -predicted an increased risk of all three adverse outcomes, with little to no effect for higher BMI.

CONCLUSION

This temporally validated model predicted 30-day mortality, cardiac complications, and respiratory complications after aseptic revision THA or TKA with c-statistics ranging from 0.78 to 0.88. This freely available risk calculator can be used preoperatively by surgeons to educate patients on their individual postoperative risk of these specific adverse outcomes. Unanswered questions that remain include whether altering the studied preoperative patient variables, such as sodium or hematocrit, would affect postoperative risk of adverse outcomes; however, a prospective cohort study is needed to answer this question.

LEVEL OF EVIDENCE

Level III, therapeutic study.

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

BACKGROUND

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

METHODS

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

RESULTS

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

DISCUSSION

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

Predicting Prolonged Hospital Stays in Elderly Patients With Hip Fractures Managed During the COVID-19 Pandemic in Chile: An Artificial Neural Networks Study

Background: Prolonged length of stay (LOS) after a hip fracture is associated with increased mortality. Purpose: We sought to create a model to predict prolonged LOS in elderly Chilean patients with hip fractures managed during the COVID-19 pandemic. Methods: Employing an official database, we created an artificial neural network (ANN), a computational model corresponding to a subset of machine learning, to predict prolonged LOS (≥14 days) among 2686 hip fracture patients managed in 43 Chilean public hospitals during 2020. We identified 18 clinically relevant variables as potential predictors; 80% of the sample was used to train the ANN and 20% was used to test it. The performance of the ANN was evaluated via measuring its discrimination power through the area under the curve of the receiver operating characteristic curve (AUC-ROC). Results: Of the 2686 patients, 820 (30.2%) had prolonged LOS. In the training sample (2,125 cases), the ANN correctly classified 1,532 cases (72.09%; AUC-ROC: 0.745). In the test sample (561 cases), the ANN correctly classified 401 cases (71.48%; AUC-ROC: 0.742). The most relevant variables to predict prolonged LOS were the patient’s admitting hospital (relative importance [RI]: 0.11), the patient’s geographical health service providing health care (RI: 0.11), and the patient’s surgery being conducted within 2 days of admission (RI: 0.10). Conclusions: Using national-level big data, we developed an ANN that predicted with fair accuracy prolonged LOS in elderly Chilean patients with hip fractures during the COVID-19 pandemic. The main predictors of a prolonged LOS were unrelated to the patient’s individual health and concerned administrative and organizational factors.

Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes

BACKGROUND

Patient-reported outcome measurements (PROMs) are commonly used in clinical practice to support clinical decision making. However, few studies have investigated machine learning methods for predicting PROMs outcomes and thereby support clinical decision making.

OBJECTIVE

This study investigates to what extent different machine learning methods, applied to two different PROMs datasets, can predict outcomes among patients with non-specific neck and/or low back pain.

METHODS

Using two datasets consisting of PROMs from (1) care-seeking low back pain patients in primary care who participated in a randomized controlled trial, and (2) patients with neck and/or low back pain referred to multidisciplinary biopsychosocial rehabilitation, we present data science methods for data prepossessing and evaluate selected regression and classification methods for predicting patient outcomes.

RESULTS

The results show that there is a potential for machine learning to predict and classify PROMs. The prediction models based on baseline measurements perform well, and the number of predictors can be reduced, which is an advantage for implementation in decision support scenarios. The classification task shows that the dataset does not contain all necessary predictors for the care type classification. Overall, the work presents generalizable machine learning pipelines that can be adapted to other PROMs datasets.

CONCLUSION

This study demonstrates the potential of PROMs in predicting short-term patient outcomes. Our results indicate that machine learning methods can be used to exploit the predictive value of PROMs and thereby support clinical decision making, given that the PROMs hold enough predictive power.

Development of prediction models for complications after primary total hip and knee arthroplasty: a single-centre retrospective cohort study in the Netherlands

OBJECTIVE

The aim of this study was to develop prediction models for patients with total hip arthroplasty (THA) and total knee arthroplasty (TKA) to predict the risk for surgical complications based on personal factors, comorbidities and medication use.

DESIGN

Retrospective cohort study.

SETTING

Tertiary care in outpatient clinic of university medical centre.

PARTICIPANTS

3776 patients with a primary THA or TKA between 2004 and 2018.

PRIMARY AND SECONDARY OUTCOME MEASURES

Multivariable logistic regression models were developed for primary outcome surgical site infection (SSI), and secondary outcomes venous thromboembolism (VTE), postoperative bleeding (POB), luxation, delirium and nerve damage (NER).

RESULTS

For SSI, age, smoking status, body mass index, presence of immunological disorder, diabetes mellitus, liver disease and use of non-steroidal anti-inflammatory drugs were included. An area under the receiver operating characteristic curve (AUC) of 71.9% (95% CI=69.4% to 74.4%) was found. For this model, liver disease showed to be the strongest predictor with an OR of 10.7 (95% CI=2.4 to 46.6). The models for POB and NER showed AUCs of 73.0% (95% CI=70.7% to 75.4%) and 76.6% (95% CI=73.2% to 80.0%), respectively. For delirium an AUC of 85.9% (95% CI=83.8% to 87.9%) was found, and for the predictive algorithms for luxation and VTE we found least favourable results (AUC=58.4% (95% CI=55.0% to 61.8%) and AUC=66.3% (95% CI=62.7% to 69.9%)).

CONCLUSIONS

Discriminative ability was reasonable for SSI and predicted probabilities ranged from 0.01% to 51.0%. We expect this to enhance shared decision-making in considering THA or TKA since current counselling is predicated on population-based probability of risk, rather than using personalised prediction. We consider our models for SSI, delirium and NER appropriate for clinical use when taking underestimation and overestimation of predicted risk into account. For VTE and POB, caution concerning overestimation exceeding a predicted probability of 0.08 for VTE and 0.05 for POB should be taken into account. Furthermore, future studies should evaluate clinical impact and whether the models are feasible in an external population.

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

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

Machine learning models accurately predict recurrent infection following revision total knee arthroplasty for periprosthetic joint infection

PURPOSE

This study aimed to develop and validate machine-learning models for the prediction of recurrent infection in patients following revision total knee arthroplasty for periprosthetic joint infection.

METHODS

A total of 618 consecutive patients underwent revision total knee arthroplasty for periprosthetic joint infection. The patient cohort included 165 patients with confirmed recurrent periprosthetic joint infection (PJI). Potential risk factors including patient demographics and surgical characteristics served as input to three machine-learning models which were developed to predict recurrent periprosthetic joint. The machine-learning models were assessed by discrimination, calibration and decision curve analysis.

RESULTS

The factors most significantly associated with recurrent PJI in patients following revision total knee arthroplasty for PJI included irrigation and debridement with/without modular component exchange (p < 0.001), > 4 prior open surgeries (p < 0.001), metastatic disease (p < 0.001), drug abuse (p < 0.001), HIV/AIDS (p < 0.01), presence of Enterococcus species (p < 0.01) and obesity (p < 0.01). The machine-learning models all achieved excellent performance across discrimination (AUC range 0.81-0.84).

CONCLUSION

This study developed three machine-learning models for the prediction of recurrent infections in patients following revision total knee arthroplasty for periprosthetic joint infection. The strongest predictors were previous irrigation and debridement with or without modular component exchange and prior open surgeries. The study findings show excellent model performance, highlighting the potential of these computational tools in quantifying increased risks of recurrent PJI to optimize patient outcomes.

LEVEL OF EVIDENCE

IV.

Enhancing Orthopedic Surgery and Treatment Using Artificial Intelligence and Its Application in Health and Dietary Welfare

The current decade has seen an increased usage of high-end digital technologies like machine learning in the field of health care services which enable in supporting and performing different functions with less or no human interventions. The application of machine learning tools in the orthopedic area is gaining more popularity as it can support in analyzing the issues in a more comprehensive manner, provide accurate data, support in forecasting the pattern. It enables offering critical information for taking quick decisions by the medical practitioners in order to enhance the health and dietary care service delivery. The ML tools can support in collecting patient centric data related to orthopedic surgery and also estimate the postoperative complications, level of treatment modalities to be provided, and guide the medical practitioners in taking effective clinical device decisions. The ML approach also supports in providing prediction methods of implementing the ortho surgical outcomes. Furthermore, it can also guide in making better treatment procedures, forecast the patterns, and stream the health care management services for better patient recovery. This study implements a quantitative research approach which will support in sourcing the data from the respondents who are currently working as medical practitioners, orthopedic experts, and radiologists who use ML-based models in making critical decisions related to orthopedic surgery. The researchers chose nearly 149 respondents, and the information was analysed using the IBM SPSS package for gaining critical interpretation. The major analyses cover descriptive analysis, regression analysis, and analysis of variances.

Efficacy and Applications of Artificial Intelligence and Machine Learning Analyses in Total Joint Arthroplasty: A Call for Improved Reporting

BACKGROUND

There has been a considerable increase in total joint arthroplasty (TJA) research using machine learning (ML). Therefore, the purposes of this study were to synthesize the applications and efficacies of ML reported in the TJA literature, and to assess the methodological quality of these studies.

METHODS

PubMed, OVID/MEDLINE, and Cochrane libraries were queried in January 2021 for articles regarding the use of ML in TJA. Study demographics, topic, primary and secondary outcomes, ML model development and testing, and model presentation and validation were recorded. The TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis) guidelines were used to assess the methodological quality.

RESULTS

Fifty-five studies were identified: 31 investigated clinical outcomes and resource utilization; 11, activity and motion surveillance; 10, imaging detection; and 3, natural language processing. For studies reporting the area under the receiver operating characteristic curve (AUC), the median AUC (and range) was 0.80 (0.60 to 0.97) among 26 clinical outcome studies, 0.99 (0.83 to 1.00) among 6 imaging-based studies, and 0.88 (0.76 to 0.98) among 3 activity and motion surveillance studies. Twelve studies compared ML to logistic regression, with 9 (75%) reporting that ML was superior. The average number of TRIPOD guidelines met was 11.5 (range: 5 to 18), with 38 (69%) meeting greater than half of the criteria. Presentation and explanation of the full model for individual predictions and assessments of model calibration were poorly reported (<30%).

CONCLUSIONS

The performance of ML models was good to excellent when applied to a wide variety of clinically relevant outcomes in TJA. However, reporting of certain key methodological and model presentation criteria was inadequate. Despite the recent surge in TJA literature utilizing ML, the lack of consistent adherence to reporting guidelines needs to be addressed to bridge the gap between model development and clinical implementation.

Can machine learning models predict failure of revision total hip arthroplasty?

INTRODUCTION

Revision total hip arthroplasty (THA) represents a technically demanding surgical procedure which is associated with significant morbidity and mortality. Understanding risk factors for failure of revision THA is of clinical importance to identify at-risk patients. This study aimed to develop and validate novel machine learning algorithms for the prediction of re-revision surgery for patients following revision total hip arthroplasty.

METHODS

A total of 2588 consecutive patients that underwent revision THA was evaluated, including 408 patients (15.7%) with confirmed re-revision THA. Electronic patient records were manually reviewed to identify patient demographics, implant characteristics and surgical variables that may be associated with re-revision THA. Machine learning algorithms were developed to predict re-revision THA and these models were assessed by discrimination, calibration and decision curve analysis.

RESULTS

The strongest predictors for re-revision THA as predicted by the four validated machine learning models were the American Society of Anaesthesiology score, obesity (> 35 kg/m²) and indication for revision THA. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.80), calibration and decision curve analysis. Higher net benefits for all machine learning models were demonstrated, when compared to the default strategies of changing management for all patients or no patients.

CONCLUSION

This study developed four machine learning models for the prediction of re-revision surgery for patients following revision total hip arthroplasty. The study findings show excellent model performance, highlighting the potential of these computational models to assist in preoperative patient optimization and counselling to improve revision THA patient outcomes.

LEVEL OF EVIDENCE

Level III, case-control retrospective analysis.

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

Background

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

Methods

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

Results

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

Discussion

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

Understanding Artificial Intelligence and Predictive Analytics: A Clinically Focused Review of Machine Learning Techniques

»

Machine learning and artificial intelligence have seen tremendous growth in recent years and have been applied in numerous studies in the field of orthopaedics.

»

Machine learning will soon become critical in the day-to-day operations of orthopaedic practice; therefore, it is imperative that providers become accustomed to and familiar with not only the terminology but also the fundamental techniques behind the technology.

»

A foundation of knowledge regarding machine learning is critical for physicians so they can begin to understand the details in the algorithms that are being developed, which provide improved accuracy compared with clinicians, decreased time required, and a heightened ability to triage patients.