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

Artificial intelligence and machine learning in knee arthroplasty

BACKGROUND

Artificial intelligence (AI) and its subset, machine learning (ML), have significantly impacted clinical medicine, particularly in knee arthroplasty (KA). These technologies utilize algorithms for tasks such as predictive analytics and image recognition, improving preoperative planning, intraoperative navigation, and postoperative complication anticipation. This systematic review presents AI-driven tools' clinical implications in total and unicompartmental KA, focusing on enhancing patient outcomes and operational efficiency.

METHODS

A systematic search was conducted across multiple databases including Cochrane Central Register of Controlled Trials, Embase, OVID Medline, PubMed, and Web of Science, following the PRISMA guidelines for studies published in the English language till March 2024. Inclusion criteria targeted adult human models without geographical restrictions, specifically related to total or unicompartmental KA.

RESULTS

A total of 153 relevant studies were identified, covering various aspects of ML application for KA. Topics of studies included imaging modalities (n = 28), postoperative primary KA complications (n = 26), inpatient status (length of stay, readmissions, and cost) (n = 24), implant configuration (n = 14), revision (n = 12), patient-reported outcome measures (PROMs) (n = 11), function (n = 11), procedural communication (n = 8), total knee arthroplasty/unicompartmental knee arthroplasty prediction (n = 6), outpatient status (n = 4), perioperative efficiency (n = 4), patient satisfaction (n = 3), opioid usage (n = 3). A total of 66 ML models were described, with 48.7% of studies using multiple approaches.

CONCLUSION

This review assesses ML applications in knee arthroplasty, highlighting their potential to improve patient outcomes. While current algorithms and AI show promise, our findings suggest areas for enhancement in predictive performance before widespread clinical adoption.

Predicting 30-day reoperation following primary total knee arthroplasty: machine learning model outperforms the ACS risk calculator

The ACS risk calculator (ARC) has proven less effective in predicting patient-specific risk of early reoperation after primary total knee arthroplasty (TKA), compromising care quality and cost efficiency. This study compared the performance of a machine learning (ML) model and ARC in predicting 30-day reoperation after primary TKA using a national-scale dataset. Data of 366,151 TKAs were acquired from the ACS-NSQIP database. A random forest model was derived using ARC build-in parameters from the training dataset via techniques of hyperparameter optimization and cross-validation. The predictive performance of random forest and ARC was evaluated by metrics of discrimination, calibration, and clinical utility using the testing dataset. The ML model demonstrated good discrimination and calibration (AUC: 0.72, slope: 1.18, intercept: - 0.14, Brier score: 0.012), outperforming ARC in all metrics (AUC: 0.51, slope: - 0.01, intercept: 0.01, Brier score: 0.135) including clinical utility measured by decision curve analyses. Age (> 67 years) and BMI (> 34 kg/m2) were the important predictors of reoperation. This study suggests the superiority of ML models in identifying individualized 30-day reoperation risk following TKA. ML models may be an adjunct prediction tool in enhancing patient-specific risk stratification and postoperative care management.

[Artificial intelligence in arthroplasty]

BACKGROUND

Artificial intelligence is very likely to be a pioneering technology in arthroplasty, with a wide range of pre-, intra- and post-operative applications. The opportunities for patients, doctors and healthcare policy are considerable, especially in the context of optimized and individualized patient care.

DATA AVAILABILITY

Despite these diverse possibilities, there are currently only a few AI applications in routine clinical practice, mainly due to the limited availability of analyzable health data. AI systems are only as good as the data they are trained with. If the data is insufficient, incomplete or biased, the AI may draw false conclusions. The current results of such AI applications in arthroplasty must, therefore, be viewed critically, especially as previous data bases were not designed a priori for AI applications.

PROSPECTS

The successful integration of AI, therefore, requires a targeted focus on the development of a specific data structure. In order to exploit the full potential of AI, comprehensive clinical data volumes are required, which can only be realized through a multicentric approach. In this context, ethical and data protection issues remain a further question, and not only in orthopaedics. Cooperative efforts at national and international levels are, therefore, essential in order to research and develop new AI applications.

Machine learning to predict periprosthetic joint infections following primary total hip arthroplasty using a national database

INTRODUCTION

Periprosthetic joint infection (PJI) following total hip arthroplasty (THA) remains a devastating complication for patients and surgeons. Given the implications of these infections and the current paucity of risk calculators utilizing machine learning (ML), this study aimed to develop an ML algorithm that could accurately identify risk factors for developing a PJI following primary THA using a national database.

MATERIALS AND METHODS

A total of 51,053 patients who underwent primary THA between 2013 and 2020 were identified using the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. Demographic, preoperative, intraoperative, and immediate postoperative outcomes were collected. Five ML models were created. The receiver operating characteristic curves, the area under the curve (AUC), calibration plots, slopes, intercepts, and Brier scores were evaluated.

RESULTS

The histogram-based gradient boosting (HGB) model demonstrated good PJI discriminatory ability with an AUC of 0.88. The test-specific metrics supported the model's performance and validation in predicting PJI (calibration curve slope: 0.79; intercept: 0.32; Brier score: 0.007). The top five predictors of PJI were the length of stay (> 3 days), patient weight at the time of surgery (> 94.3 kg), an American Society of Anesthesiologists (ASA) class of 4 or higher, preoperative platelet count (< 249,890/mm3), and preoperative sodium (< 139.5 mEq/L).

CONCLUSION

This study developed a highly specific ML model that could predict patient-specific PJI development following primary THA. Considering the feature importance of the top predictors of infection, surgeons should counsel at-risk patients to optimize resource utilization and potentially improve surgical outcomes.

Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review

BACKGROUND

To summarize the statistical performance of machine learning in predicting revision, secondary knee injury, or reoperations following anterior cruciate ligament reconstruction (ACLR), and to provide a general overview of the statistical performance of these models.

METHODS

Three online databases (PubMed, MEDLINE, EMBASE) were searched from database inception to February 6, 2024, to identify literature on the use of machine learning to predict revision, secondary knee injury (e.g. anterior cruciate ligament (ACL) or meniscus), or reoperation in ACLR. The authors adhered to the PRISMA and R-AMSTAR guidelines as well as the Cochrane Handbook for Systematic Reviews of Interventions. Demographic data and machine learning specifics were recorded. Model performance was recorded using discrimination, area under the curve (AUC), concordance, calibration, and Brier score. Factors deemed predictive for revision, secondary injury or reoperation were also extracted. The MINORS criteria were used for methodological quality assessment.

RESULTS

Nine studies comprising 125,427 patients with a mean follow-up of 5.82 (0.08-12.3) years were included in this review. Two of nine (22.2%) studies served as external validation analyses. Five (55.6%) studies reported on mean AUC (strongest model range 0.77-0.997). Four (44.4%) studies reported mean concordance (strongest model range: 0.67-0.713). Two studies reported on Brier score, calibration intercept, and calibration slope, with values ranging from 0.10 to 0.18, 0.0051-0.006, and 0.96-0.97 amongst highest performing models, respectively. Four studies reported calibration error, with all four studies demonstrating significant miscalibration at either two or five-year follow-ups amongst 10 of 14 models assessed.

CONCLUSION

Machine learning models designed to predict the risk of revision or secondary knee injury demonstrate variable discriminatory performance when evaluated with AUC or concordance metrics. Furthermore, there is variable calibration, with several models demonstrating evidence of miscalibration at two or five-year marks. The lack of external validation of existing models limits the generalizability of these findings. Future research should focus on validating current models in addition to developing new multimodal neural networks to improve accuracy and reliability.

Predictive Tool Use and Willingness for Surgery in Patients With Knee Osteoarthritis: A Randomized Clinical Trial

Importance

Despite the increasing number of tools available to predict the outcomes of total knee arthroplasty (TKA), the effect of these predictive tools on patient decision-making remains uncertain.

Objective

To assess the effect of an online predictive tool on patient-reported willingness to undergo TKA.

Design, Setting, and Participants

This parallel, double-masked, 2-arm randomized clinical trial compared predictive tool use with treatment as usual (TAU). The study was conducted between June 30, 2022, and July 31, 2023. Participants were followed up for 6 months after enrollment. Participants were recruited from a major Australian private health insurance company and from the surgical waiting list for publicly funded TKA at a tertiary hospital. Eligible participants had unilateral knee osteoarthritis, were contemplating TKA, and had previously tried nonsurgical interventions, such as lifestyle modifications, physiotherapy, and pain medications.

Intervention

The intervention group was provided access to an online predictive tool at the beginning of the study. This tool offered information regarding the likelihood of improvement in quality of life if patients chose to undergo TKA. The predictions were based on the patient's age, sex, and baseline symptoms. Conversely, the control group received TAU without access to the predictive tool.

Main Outcomes and Measures

The primary outcome measure was the reduction in participants' willingness to undergo surgery at 6 months after tool use as measured by binomial logistic regression. Secondary outcome measures included participant treatment preference and the quality of their decision-making process as measured by the Knee Decision Quality Instrument.

Results

Of 211 randomized participants (mean [SD] age, 65.8 [8.3] years; 118 female [55.9%]), 105 were allocated to the predictive tool group and 106 to the TAU group. After adjusting for baseline differences in willingness for surgery, the predictive tool did not significantly reduce the primary outcome of willingness for surgery at 6 months (adjusted odds ratio, 0.85; 95% CI, 0.42-1.71; P = .64).

Conclusions and Relevance

Despite the absence of treatment effect on willingness for TKA, predictive tools might still enhance health outcomes of patients with knee osteoarthritis. Additional research is needed to optimize the design and implementation of predictive tools, address limitations, and fully understand their effect on the decision-making process in TKA.

Trial Registration

ANZCTR.org.au Identifier: ACTRN12622000072718.

Predicting Functional Outcomes of Total Hip Arthroplasty Using Machine Learning: A Systematic Review

The aim of this review was to assess the reliability of machine learning (ML) techniques to predict the functional outcome of total hip arthroplasty. The literature search was performed up to October 2023, using MEDLINE/PubMed, Embase, Web of Science, and NIH Clinical Trials. Level I to IV evidence was included. Seven studies were identified that included 44,121 patients. The time to follow-up varied from 3 months to more than 2 years. Each study employed one to six ML techniques. The best-performing models were for health-related quality of life (HRQoL) outcomes, with an area under the curve (AUC) of more than 84%. In contrast, predicting the outcome of hip-specific measures was less reliable, with an AUC of between 71% to 87%. Random forest and neural networks were generally the best-performing models. Three studies compared the reliability of ML with traditional regression analysis: one found in favour of ML, one was not clear and stated regression closely followed the best-performing ML model, and one showed a similar AUC for HRQoL outcomes but did show a greater reliability for ML to predict a clinically significant change in the hip-specific function. ML offers acceptable-to-excellent discrimination of predicting functional outcomes and may have a marginal advantage over traditional regression analysis, especially in relation to hip-specific hip functional outcomes.

Ensemble Learning, Deep Learning-Based and Molecular Descriptor-Based Quantitative Structure-Activity Relationships

A deep learning-based quantitative structure-activity relationship analysis, namely the molecular image-based DeepSNAP-deep learning method, can successfully and automatically capture the spatial and temporal features in an image generated from a three-dimensional (3D) structure of a chemical compound. It allows building high-performance prediction models without extracting and selecting features because of its powerful feature discrimination capability. Deep learning (DL) is based on a neural network with multiple intermediate layers that makes it possible to solve highly complex problems and improve the prediction accuracy by increasing the number of hidden layers. However, DL models are too complex when it comes to understanding the derivation of predictions. Instead, molecular descriptor-based machine learning has clear features owing to the selection and analysis of features. However, molecular descriptor-based machine learning has some limitations in terms of prediction performance, calculation cost, feature selection, etc., while the DeepSNAP-deep learning method outperforms molecular descriptor-based machine learning due to the utilization of 3D structure information and the advanced computer processing power of DL.