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

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.