Prediction of complications and surgery duration in primary TKA with high accuracy using machine learning with arthroplasty-specific data

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.

Accuracy of machine learning in identifying candidates for total knee arthroplasty (TKA) surgery: a systematic review and meta-analysis

BACKGROUND

The application of machine learning (ML) in predicting the requirement for total knee arthroplasty (TKA) at knee osteoarthritis (KOA) patients has been acknowledged. Nonetheless, the variables employed in the development of ML models are diverse and these different approaches yield inconsistent predictive performance of models. Therefore, we conducted this systematic review and meta-analysis to explore the feasibility of ML in identifying candidates for TKA.

METHOD

This study was conducted based on the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. This study was registered on the international prospective register of systematic reviews registration database website, PROSPERO, with a unique ID: CRD 42023443948. The study subjects were patients diagnosed with KOA. Relevant studies were searched through PubMed, Web of Science, Cochrane, and Embase until September 15, 2024. The c-index was used as the outcome measure. The risk of bias in the primary study was assessed by Prediction model Risk of Bias Assessment Tool (PROBAST). Random or fixed effects were used for the meta-analysis.

RESULTS

A total of 13 articles were included in this study, but only 11 articles with 25 models were eligible for the meta-analysis. ML models in the included studies were classified based on the source of variables, including clinical features, radiomics, and the combination of clinical features and radiomics. In the training set, the c-index was 0.713 (0.628 - 0.799) for clinical features, 0.841 (0.777 - 0.904) for radiomics, and 0.844 (0.815 - 0.873) for the combination of clinical features and radiomics. In the validation set, the c-index for ML models based on clinical features, radiomics, and the combination of clinical features and radiomics was 0.656 (0.526 - 0.786), 0.861 (0.806 - 0.916), and 0.831 (0.799 - 0.863), respectively.

CONCLUSION

The results of this meta-analysis highlighted that the ML model is feasible in identifying candidates for TKA. X-ray-based ML models exhibit the best predictive performance among the models. However, there is currently a lack of high-level research available for clinical application. Furthermore, the accuracy of ML models in identifying candidates for TKA is significantly limited by the quality of modeling parameters and database architecture. Therefore, constructing a more targeted and professional database is imperative to promote the development and clinical application of ML models.

Comparison of an AI-driven planning tool and manual radiographic measurements in total knee arthroplasty

Background

Accurate preoperative planning in total knee arthroplasty (TKA) is essential. Traditional manual radiographic planning can be time-consuming and potentially prone to inaccuracies. This study investigates the performance of an AI-based radiographic planning tool in comparison with manual measurements in patients undergoing total knee arthroplasty, using a retrospective observational design to assess reliability and efficiency.

Methods

We retrospectively compared the Autoplan tool integrated within the mediCAD software (mediCAD Hectec GmbH, Altdorf, Germany), routinely implemented in our institutional workflow, to manual measurements performed by two orthopedic specialists on pre- and postoperative radiographs of 100 patients who underwent elective TKA. The following parameters were measured: leg length, mechanical axis deviation (MAD), mechanical lateral proximal femoral angle (mLPFA), anatomical mechanical angle (AMA), mechanical lateral distal femoral angle (mLDFA), joint line convergence angle (JLCA), mechanical medial proximal tibial angle (mMPTA), and mechanical tibiofemoral angle (mTFA).Intraclass correlation coefficients (ICCs) were calculated to assess measurement reliability, and the time required for each method was recorded.

Results

The Autoplan tool demonstrated high reliability (ICC > 0.90) compared with manual measurements for linear parameters (e.g., leg length and MAD). However, the angular measurements of mLPFA, JLCA, and AMA exhibited poor reliability (ICC < 0.50) among all raters. The Autoplan tool significantly reduced the time required for measurements compared to manual measurements, with a mean time saving of 44.3 seconds per case (95 % CI: 43.5-45.1 seconds, p < 0.001).

Conclusion

AI-assisted tools like the Autoplan tool in mediCAD offer substantial time savings and demonstrate reliable measurements for certain linear parameters in preoperative TKA planning. However, the observed low reliability in some measurements, even amongst experienced human raters, suggests inherent challenges in the radiographic assessment of angular parameters. Further development is needed to improve the accuracy of automated angular measurements, and to address the inherent variability in their assessment.

Leveraging machine learning for duration of surgery prediction in knee and hip arthroplasty - a development and validation study

BACKGROUND

Duration of surgery (DOS) varies substantially for patients with hip and knee arthroplasty (HA/KA) and is a major risk factor for adverse events. We therefore aimed (1) to identify whether machine learning can predict DOS in HA/KA patients using retrospective data available before surgery with reasonable performance, (2) to compare whether machine learning is able to outperform multivariable regression in predictive performance and (3) to identify the most important predictor variables for DOS both in a multi- and single-hospital context.

METHODS

eXtreme Gradient Boosting (XGBoost) and multivariable linear regression were used for predictions. Both models were applied to both the whole dataset which included multiple hospitals (3,704 patients), and a single-hospital dataset (1,815 patients) of the hospital with the highest case-volumes of our sample. Data was split into training (75%) and test data (25%) for both datasets. Models were trained using 5-fold cross-validation (CV) on the training datasets and applied to test data for performance comparison.

RESULTS

On test data in the multi-hospital setting, the mean absolute error (MAE) was 12.13 min (HA) / 13.61 min (KA) for XGBoost. In the single-hospital analysis, performance on test data was MAE 10.87 min (HA) / MAE 12.53 min (KA) for XGBoost. Predictive ability of XGBoost was tended to be better than of regression in all setting, however not statistically significantly. Important predictors for XGBoost were physician experience, age, body mass index, patient reported outcome measures and, for the multi-hospital analysis, the hospital.

CONCLUSION

Machine learning can predict DOS in both a multi-hospital and single-hospital setting with reasonable performance. Performance between regression and machine learning differed slightly, however insignificantly, while larger datasets may improve predictive performance. The study found that hospital indicators matter in the multi-hospital setting despite controlling for various variables, highlighting potential quality differences between hospitals.

TRIAL REGISTRATION

The study was registered at the German Clinical Trials Register (DRKS) under DRKS00019916.

OptimCLM: Optimizing clinical language models for predicting patient outcomes via knowledge distillation, pruning and quantization

BACKGROUND

Clinical Language Models (CLMs) possess the potential to reform traditional healthcare systems by aiding in clinical decision making and optimal resource utilization. They can enhance patient outcomes and help healthcare management through predictive clinical tasks. However, their real-world deployment is limited due to high computational cost at inference, in terms of both time and space complexity.

OBJECTIVE

This study aims to develop and optimize an efficient framework that compresses CLMs without significant performance loss, reducing inference time and disk-space, and enabling real-world clinical applications.

METHODS

We introduce OptimCLM, a framework for optimizing CLMs with ensemble learning, knowledge distillation (KD), pruning and quantization. Based on domain-knowledge and performance, we select and combine domain-adaptive CLMs DischargeBERT and COReBERT as the teacher ensemble model. We transfer the teacher's knowledge to two smaller generalist models, BERT-PKD and TinyBERT, and apply black-box KD, post-training unstructured pruning and post-training 8-bit model quantization to them. In an admission-to-discharge setting, we evaluate the framework on four clinical outcome prediction tasks (length of stay prediction, mortality prediction, diagnosis prediction and procedure prediction) using admission notes from the MIMIC-III clinical database.

RESULTS

The OptimCLM framework achieved up to 22.88× compression ratio and 28.7× inference speedup, with less than 5% and 2% loss in macro-averaged AUROC for TinyBERT and BERT-PKD, respectively. The teacher model outperformed five state-of-the-art models on all tasks. The optimized BERT-PKD model also outperformed them in most tasks.

CONCLUSION

Our findings suggest that domain-specific fine-tuning with ensemble learning and KD is more effective than domain-specific pre-training for domain-knowledge transfer and text classification tasks. Thus, this work demonstrates the feasibility and potential of deploying optimized CLMs in healthcare settings and developing them with less computational resources.

Hemi-Versus Total Hip Arthroplasty in Femoral Neck Fractures? Predicting Failure on a 10-Year Data Analysis of the German Arthroplasty Registry (EPRD)

Background/Objectives: The German Arthroplasty Registry (EPRD) recorded almost 100,000 femoral neck fractures between 2013 and 2023. The aim of this study was to identify survival rates and risk factors for failure in individuals with femoral neck fractures. Methods: A dataset of 97,410 cases from the EPRD was analyzed. We compared hemiarthroplasty (HA) and total hip arthroplasty (THA) using machine learning algorithms (MLAs) and statistical modeling approaches. For the MLA, the dataset was partitioned into training and test sets, with iterative feature selection and hyperparameter search. Predictive models were developed using XGBoost classifiers. Based on the feature importance, we performed LASSO regression to assess the odds ratios for key predictors of implant failure. Results: The failure rate was 3.7% for HAs and 5.6% for THAs, with a peak six weeks after surgery. LASSO regression revealed six risk factors for failure: non-cemented stem fixation (OR: 1.022, 95% CI: 1.019-1.026), treatment type (THA vs. HA; OR: 1.013, 95% CI: 1.010-1.016), time to discharge (OR: 1.006, 95% CI: 1.006-1.006), male sex (OR: 1.003, 95% CI: 1.000-1.005), age (OR: 0.999, 95% CI: 0.999-0.999), and day of surgery (weekday vs. weekend/holiday; OR: 1.004, 95% CI: 1.002-1.008). Conclusions: Longer hospital stays, male sex, and surgeries performed on weekends or holidays were associated with higher failure risks, while cemented fixation and hemiarthroplasty showed protective effects. Given that the overall failure rate was only 4.5%, even a 1-2% change in odds represents a very large clinical effect.

Surgical factors play a critical role in predicting functional outcomes using machine learning in robotic-assisted total knee arthroplasty

PURPOSE

Predictive models help determine predictive factors necessary to improve functional outcomes after total knee arthroplasty (TKA). However, no study has assessed predictive models for functional outcomes after TKA based on the new concepts of personalised surgery and new technologies. This study aimed to develop and evaluate predictive modelling approaches to predict the achievement of minimal clinically important difference (MCID) in patient-reported outcome measures (PROMs) 1 year after TKA.

METHODS

Four hundred thirty robotic-assisted TKAs were analysed in this retrospective study. The mean age was 67.9 ± 7.9 years; the mean body mass index (BMI) was 32.0 ± 6.8 kg/m2. The following PROMs were collected preoperatively and 1-year postoperatively: knee injury and osteoarthritis outcome score for joint replacement, Western Ontario and McMaster Universities osteoarthritis index (WOMAC) Function, WOMAC Pain. Demographic data, preoperative CT scan, implant size, implant position on the robotic system and characteristics of the joint replacement procedure were selected as predictive variables. Four machine learning algorithms were trained to predict the MCID status at 1-year post-TKA for each PROM survey. 'No MCID' was chosen as the target. Models were evaluated by class discrimination (F1-score) and area under the receiver operating characteristic curve (ROC-AUC).

RESULTS

The best-performing model was ridge logistic regression for WOMAC Function (area under the curve [AUC]  = 0.80, F1 = 0.48, sensitivity = 0.79, specificity = 0.62). Variables most strongly contributing to not achieving MCID status were preoperative PROMs, high BMI and femoral resection depth (posterior and distal), supporting functional positioning principles. Conversely, variables contributing to a positive outcome (achieving MCID) were medial/lateral alignment of the tibial component, whether the procedure was an outpatient surgery and whether the patient received managed Medicare insurance.

CONCLUSION

The most predictive variables included preoperative PROMs, BMI and surgical planning. The surgical predictive variables were valgus femoral alignment and femoral rotation, reflecting the benefits of personalised surgery. Including surgical variables in predictive models for functional outcomes after TKA should guide clinical and surgical decision-making for every patient.

LEVEL OF EVIDENCE

Level III.

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.

[Endoprosthetic treatment of femoral neck fractures in Germany : Cumulative analysis of EPRD registry data from 2013 to 2020]

BACKGROUND

The German Arthroplasty Registry (EPRD) recorded nearly 52,000 femoral neck fractures treated with arthroplasty by 2020. This study aimed to identify survival rates and risk factors for hip prosthesis failure.

MATERIAL AND METHODS

The study included all patients with arthroplasty after hip fractures documented in the EPRD. Data were analyzed with focus on failure rate regarding implant, implantation technique, age, BMI, and comorbidities. For more complex analysis of dependencies, the machine learning algorithm (MLA) XGBoost (Extreme Gradient Boosting) was used.

RESULTS

The study included 51,938 patients. The failure rate was 3.7% for HEs and 5.6% for THA. The failure rate increased in male patients (p < 0.0001), those with higher BMI, young patients with a high Elixhauser Comorbidity Score (ECS) and a cementless technique. The timepoint of surgery, i.e. ,working day vs. weekend or holiday had no influence on the outcome. The feature importance (FI) generated by MLA demonstrated factors with the highest impact on failure, i.e., survival time (1029), BMI (722), and age (481).

CONCLUSION

For younger patients with comorbidities, a cemented implantation technique should be considered. Failure rates of arthroplasties did not differ on workdays compared to weekends or holidays. MLA are suitable to analyze registry data for complex correlations of factors.

Artificial Intelligence in Surgery: A Systematic Review of Use and Validation

Background: Artificial Intelligence (AI) holds promise for transforming healthcare, with AI models gaining increasing clinical use in surgery. However, new AI models are developed without established standards for their validation and use. Before AI can be widely adopted, it is crucial to ensure these models are both accurate and safe for patients. Without proper validation, there is a risk of integrating AI models into practice without sufficient evidence of their safety and accuracy, potentially leading to suboptimal patient outcomes. In this work, we review the current use and validation methods of AI models in clinical surgical settings and propose a novel classification system. Methods: A systematic review was conducted in PubMed and Cochrane using the keywords "validation", "artificial intelligence", and "surgery", following PRISMA guidelines. Results: The search yielded a total of 7627 articles, of which 102 were included for data extraction, encompassing 2,837,211 patients. A validation classification system named Surgical Validation Score (SURVAS) was developed. The primary applications of models were risk assessment and decision-making in the preoperative setting. Validation methods were ranked as high evidence in only 45% of studies, and only 14% of the studies provided publicly available datasets. Conclusions: AI has significant applications in surgery, but validation quality remains suboptimal, and public data availability is limited. Current AI applications are mainly focused on preoperative risk assessment and are suggested to improve decision-making. Classification systems such as SURVAS can help clinicians confirm the degree of validity of AI models before their application in practice.

Personalized delayed anticoagulation therapy alleviates postoperative bleeding in total knee arthroplasty (TKA) patients

Purpose

Ecchymosis is one of the most common complications following total knee arthroplasty (TKA), which is closely related to postoperative bleeding. However, it is still controversial whether anticoagulation treatment should be continued for postoperative ecchymosis patients. We suppose that personalized delayed anticoagulation therapy could be beneficial for decreasing postoperative bleeding.

Methods

A total of 201 TKA patients were retrospectively included in this study, among whom ecchymosis patients received drug anticoagulation treatment 1-2 days later than usual, while nonecchymosis patients received regular drug anticoagulation treatment. The perioperative blood loss, coagulation state, fibrinolytic state and complications were collected and analyzed.

Results

Eighty-nine patients (44.3%) developed ecchymosis within 3 days after TKA. There were no differences in baseline characteristics between the two groups. In the ecchymosis group, higher K values and lower calculated coagulation index values were observed in thromboelastography, along with greater total blood loss and a more significant decrease in haemoglobin levels on postoperative Day 1 (POD1) compared to the nonecchymosis group. Additionally, the ecchymosis patients exhibited higher levels of fibrinogen degradation products and D-dimer (D-D) on POD1, with no differences noted on POD3, indicating that patients with ecchymosis are in a relatively hypocoagulable and hyperfibrinolytic state compared to those without ecchymosis. Therefore, the delayed anticoagulation treatment proved beneficial for correcting these postoperative conditions. No statistically significant differences were found between the two groups in postoperative complications, demonstrating that delayed anticoagulation treatment is safe.

Conclusion

Patients with ecchymosis exhibited a relatively hypocoagulable and hyperfibrinolytic state with a stronger tendency for postoperative bleeding. Delayed anticoagulation in ecchymosis patients could effectively prevent further exacerbation of postoperative bleeding by avoiding sustained hypocoagulable and hyperfibrinolysis states. Personalized delayed anticoagulation therapy could be beneficial for managing postoperative ecchymosis for TKA patients.

Level of Evidence

Level IV.

Leveraging transfer learning for predicting total knee arthroplasty failure from post-operative radiographs

Purpose

The incidence of both primary and revision total knee arthroplasty (TKA) is expected to rise, making early recognition of TKA failure crucial to prevent extensive revision surgeries. This study aims to develop a deep learning (DL) model to predict TKA failure using radiographic images.

Methods

Two patient cohorts who underwent primary TKA were retrospectively collected: one was used for the model development and the other for the external validation. Each cohort encompassed failed and non-failed subjects, according to the need for TKA revision surgery. Moreover, for each patient, one anteroposterior and one lateral radiographic view obtained during routine TKA follow-up, were considered. A transfer learning fine-tuning approach was employed. After pre-processing, the images were analyzed using a convolutional neuronal network (CNN) that was originally developed for predicting hip prosthesis failure and was based on the Densenet169 pre-trained on Imagenet. The model was tested on 20% of the images of the first cohort and externally validated on the images of the second cohort. Metrics, such as accuracy, sensitivity, specificity and area under the receiving operating characteristic curve (AUC), were calculated for the final assessment.

Results

The trained model correctly classified 108 out of 127 images in the test set, providing a classification accuracy of 0.85, sensitivity of 0.80, specificity of 0.89 and AUC of 0.86. Moreover, the model correctly classified 1547 out of 1937 in the external validation set, providing a balanced accuracy of 0.79, sensitivity of 0.80, specificity of 0.78 and AUC of 0.86.

Conclusions

The present DL model predicts TKA failure with moderate accuracy, regardless of the cause of revision surgery. Additionally, the effectiveness of the transfer learning fine-tuning approach, leveraging a previously developed DL model for hip prosthesis failure, has been successfully demonstrated.

Level of Evidence

Level III, diagnostic study.

A multiview deep learning-based prediction pipeline augmented with confident learning can improve performance in determining knee arthroplasty candidates

PURPOSE

Preoperative prudent patient selection plays a crucial role in knee osteoarthritis management but faces challenges in appropriate referrals such as total knee arthroplasty (TKA), unicompartmental knee arthroplasty (UKA) and nonoperative intervention. Deep learning (DL) techniques can build prediction models for treatment decision-making. The aim is to develop and evaluate a knee arthroplasty prediction pipeline using three-view X-rays to determine the suitable candidates for TKA, UKA or are not arthroplasty candidates.

METHODS

A study was conducted using three-view (anterior-posterior, lateral and patellar) X-rays and surgical data of patients undergoing TKA, UKA or nonarthroplasty interventions from sites A and B. Data from site A were used to derive and validate models. Data from site B were used as external test set. A DL pipeline combining YOLOv3 and ResNet-18 with confident learning (CL) was developed. Multiview Convolutional Neural Network, EfficientNet-b4, ResNet-101 and the proposed model without CL were also trained and tested. The models were evaluated using metrics such as area under the receiver operating characteristic curve (AUC), accuracy, precision, specificity, sensitivity and F1 score.

RESULTS

The data set comprised a total of 1779 knees. Of which 1645 knees were from site A as a derivation set and an internal validation cohort. The external validation cohort consisted of 134 knees. The internal validation cohort demonstrated superior performance for the proposed model augmented with CL, achieving an AUC of 0.94 and an accuracy of 85.9%. External validation further confirmed the model's generalisation, with an AUC of 0.93 and an accuracy of 82.1%. Comparative analysis with other neural network models showed the proposed model's superiority.

CONCLUSIONS

The proposed DL pipeline, integrating YOLOv3, ResNet-18 and CL, provides accurate predictions for knee arthroplasty candidates based on three-view X-rays. This prediction model could be useful in performing decision making for the type of arthroplasty procedure in an automated fashion.

LEVEL OF EVIDENCE

Level III, diagnostic study.

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.

A practical guide to the development and deployment of deep learning models for the orthopaedic surgeon: Part III, focus on registry creation, diagnosis, and data privacy

Deep learning is a subset of artificial intelligence (AI) with enormous potential to transform orthopaedic surgery. As has already become evident with the deployment of Large Language Models (LLMs) like ChatGPT (OpenAI Inc.), deep learning can rapidly enter clinical and surgical practices. As such, it is imperative that orthopaedic surgeons acquire a deeper understanding of the technical terminology, capabilities and limitations associated with deep learning models. The focus of this series thus far has been providing surgeons with an overview of the steps needed to implement a deep learning-based pipeline, emphasizing some of the important technical details for surgeons to understand as they encounter, evaluate or lead deep learning projects. However, this series would be remiss without providing practical examples of how deep learning models have begun to be deployed and highlighting the areas where the authors feel deep learning may have the most profound potential. While computer vision applications of deep learning were the focus of Parts I and II, due to the enormous impact that natural language processing (NLP) has had in recent months, NLP-based deep learning models are also discussed in this final part of the series. In this review, three applications that the authors believe can be impacted the most by deep learning but with which many surgeons may not be familiar are discussed: (1) registry construction, (2) diagnostic AI and (3) data privacy. Deep learning-based registry construction will be essential for the development of more impactful clinical applications, with diagnostic AI being one of those applications likely to augment clinical decision-making in the near future. As the applications of deep learning continue to grow, the protection of patient information will become increasingly essential; as such, applications of deep learning to enhance data privacy are likely to become more important than ever before. Level of Evidence: Level IV.

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.

Künstliche Intelligenz in der Orthopädie

Wir befinden uns in einer Phase exponentiellen Wachstums bei der Nutzung von künstlicher Intelligenz (KI). Knapp 90 % der KI-Forschung in der Orthopädie und Unfallchirurgie wurde in den letzten 3 Jahren veröffentlicht. In der Mehrzahl der Untersuchungen wurde KI zur Bildinterpretation oder als klinisches Entscheidungsinstrument eingesetzt. Die am häufigsten untersuchten Körperregionen waren dabei Wirbelsäule, Knie und Hüfte. Mit der Verbesserung der Datenerfassung verbessern sich auch die mit KI assoziierten Möglichkeiten einer genaueren Diagnostik, von patientenspezifischen Behandlungsansätzen, verbesserter Ergebnisvorhersage und erweiterter Ausbildung. KI bietet einen potenziellen Weg, um Ärztinnen und Ärzte zu unterstützen und gleichzeitig den Wert der Behandlung zu maximieren. Ein grundlegendes Verständnis dafür, was KI beinhaltet und wie sie sich auf die Orthopädie und die Patientenversorgung auswirken kann, ist unerlässlich. Dieser Artikel gibt einen Überblick über die Anwendungsbereiche von KI-Systemen in der Orthopädie und stellt sie in den komplexen Gesamtkontext bestehend aus Interessensvertretern aus Politik, Industrie, Behörden und Medizin.

Development of an image-based Random Forest classifier for prediction of surgery duration of laparoscopic sigmoid resections

PURPOSE

Sigmoid diverticulitis is a disease with a high socioeconomic burden, accounting for a high number of left-sided colonic resections worldwide. Modern surgical scheduling relies on accurate prediction of operation times to enhance patient care and optimize healthcare resources. This study aims to develop a predictive model for surgery duration in laparoscopic sigmoid resections, based on preoperative CT biometric and demographic patient data.

METHODS

This retrospective single-center cohort study included 85 patients who underwent laparoscopic sigmoid resection for diverticular disease. Potentially relevant procedure-specific anatomical parameters recommended by a surgical expert were measured in preoperative CT imaging. After random split into training and test set (75% / 25%) multiclass logistic regression was performed and a Random Forest classifier was trained on CT imaging parameters, patient age, and sex in the training cohort to predict categorized surgery duration. The models were evaluated in the test cohort using established performance metrics including receiver operating characteristics area under the curve (AUROC).

RESULTS

The Random Forest model achieved a good average AUROC of 0.78. It allowed a very good prediction of long (AUROC = 0.89; specificity 0.71; sensitivity 1.0) and short (AUROC = 0.81; specificity 0.77; sensitivity 0.56) procedures. It clearly outperformed the multiclass logistic regression model (AUROC: average = 0.33; short = 0.31; long = 0.22).

CONCLUSION

A Random Forest classifier trained on demographic and CT imaging biometric patient data could predict procedure duration outliers of laparoscopic sigmoid resections. Pending validation in a multicenter study, this approach could potentially improve procedure scheduling in visceral surgery and be scaled to other procedures.

Definitions and consequences of current alignment techniques and phenotypes in total knee arthroplasty (TKA) - there is no winner yet

Dissatisfaction following total knee arthroplasty (TKA) has been extensively documented and it was attributed to numerous factors. In recent years, significant focus has been directed towards implant alignment and stability as potential causes and solutions to this issue. Surgeons are now exploring a more personalized approach to TKA, recognizing the importance of thoroughly understanding each individual patient's anatomy and functional morphology. A more comprehensive preoperative analysis of alignment and knee morphology is essential to address the unresolved questions in knee arthroplasty effectively. The crucial task of determining the most appropriate alignment strategy for each patient arises, given the substantial variability in bone resection resulting from the interplay of phenotype and the alignment strategy chosen. This review aims to comprehensively present the definitions of different alignment techniques in all planes and discuss the consequences dependent on knee phenotypes.Level of evidence V.

Application of machine learning in the prevention of periprosthetic joint infection following total knee arthroplasty: a systematic review

BACKGROUND

Machine learning is a promising and powerful technology with increasing use in orthopedics. Periprosthetic joint infection following total knee arthroplasty results in increased morbidity and mortality. This systematic review investigated the use of machine learning in preventing periprosthetic joint infection.

METHODS

A systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. PubMed was searched in November 2022. All studies that investigated the clinical applications of machine learning in the prevention of periprosthetic joint infection following total knee arthroplasty were included. Non-English studies, studies with no full text available, studies focusing on non-clinical applications of machine learning, reviews and meta-analyses were excluded. For each included study, its characteristics, machine learning applications, algorithms, statistical performances, strengths and limitations were summarized. Limitations of the current machine learning applications and the studies, including their 'black box' nature, overfitting, the requirement of a large dataset, the lack of external validation, and their retrospective nature were identified.

RESULTS

Eleven studies were included in the final analysis. Machine learning applications in the prevention of periprosthetic joint infection were divided into four categories: prediction, diagnosis, antibiotic application and prognosis.

CONCLUSION

Machine learning may be a favorable alternative to manual methods in the prevention of periprosthetic joint infection following total knee arthroplasty. It aids in preoperative health optimization, preoperative surgical planning, the early diagnosis of infection, the early application of suitable antibiotics, and the prediction of clinical outcomes. Future research is warranted to resolve the current limitations and bring machine learning into clinical settings.

Effect of Combined Kinematic Chain Exercise on Physical Function, Balance Ability, and Gait in Patients with Total Knee Arthroplasty: A Single-Blind Randomized Controlled Trial

Total knee arthroplasty (TKA) is an effective treatment for end-stage osteoarthritis. However, evidence of combined kinematic chain exercise (CCE) in early-phase rehabilitation after TKA remains lacking. This study investigated the effects of CCE training on physical function, balance ability, and gait in 40 patients who underwent TKA. Participants were randomly assigned to the CCE (n = 20) and open kinematic chain exercise (OKCE) groups (n = 20). The CCE and OKCE groups were trained five times a week (for 4 weeks) for 30 min per session. Physical function, range of motion (ROM), balance, and gait were assessed before and after the intervention. The time × group interaction effects and time effect as measured with the Western Ontario and McMaster Universities Osteoarthritis Index, ROM, Knee Outcome Survey-Activities of Daily Living, balancing ability (e.g., confidence ellipse area, path length, and average speed), and gait parameters (e.g., timed up-and-go test, gait speed, cadence, step length, and stride length) were statistically significant (p < 0.05). In the group comparison of pre- and postintervention measurements for all variables, the CCE group showed substantial improvements compared to the OKCE group (p < 0.05). Both groups showed significant within-group improvement from baseline to postintervention. Our results suggest that CCE training positively affects physical function, balance ability, and gait as an early intervention for patients undergoing TKA.

Patient-reported impairment following TKA is reduced when a computationally simulated predicted ideal alignment is achieved

PURPOSE

Joint dynamics following Total Knee Arthroplasty (TKA) may influence patient-reported outcome. Simulations allow many knee alignment approaches to a single patient to be considered prior to surgery. The simulated kinematics can be matched to patient-reported outcome to predict kinematic patterns most likely to give the best outcome. This study aims to validate one such previously developed algorithm based on a simulated deep knee bend (the Dynamic Knee Score, DKS).

METHODS

1074 TKA patients with pre- and post-operative Computerised Tomography (CT) scans and 12-month post-operative Knee Injury and Osteoarthritis Outcomes (KOOS) Scores were identified from the 360 Med Care Joint Registry. Landmarking and registration of implant position was performed on all CT scans, and each of the achieved TKAs was computationally simulated and received a predictive outcome score from the DKS. In addition, a set of potential alternative surgical plans which might have been followed were simulated. Comparison of patient-reported issues and DKS score was evaluated in a counter-factual study design.

RESULTS

Patient-reported impairment with the knee catching and squatting was shown to be 30% lower (p = 0.005) and 22% lower (p = 0.026) in patients where the best possible DKS result was the one surgically achieved. Similar findings were found relating attainment of the best tibial slope and posterior femoral resection DKS plans to patient-reported difficulty straightening the knee (40% less likely, p < 0.001) and descending stairs (35% less likely, p = 0.006).

CONCLUSION

The DKS has been shown to correlate with presence of patient-reported impairments post-TKA and the resultant algorithm can be applied in a pre-operative planning setting. Outcome optimization in the future may come from patient-specific selection of an alignment strategy and simulations may be a technological enabler of this trend.

LEVEL OF EVIDENCE

III (Retrospective Cohort Study).

Circulating biomarker-based risk stratifications individualize arch repair strategy of acute Type A aortic dissection via the XGBoosting algorithm

Aims

The incremental usefulness of circulating biomarkers from different pathological pathways for predicting mortality has not been evaluated in acute Type A aortic dissection (ATAAD) patients. We aim to develop a risk prediction model and investigate the impact of arch repair strategy on mortality based on distinct risk stratifications.

Methods and results

A total of 3771 ATAAD patients who underwent aortic surgery retrospectively included were randomly divided into training and testing cohorts at a ratio of 7:3 for the development and validation of the risk model based on multiple circulating biomarkers and conventional clinical factors. Extreme gradient boosting was used to generate the risk models. Subgroup analyses were performed by risk stratifications (low vs. middle-high risk) and arch repair strategies (proximal vs. extensive arch repair). Addition of multiple biomarkers to a model with conventional factors fitted an ABC risk model consisting of platelet-leucocyte ratio, mean arterial pressure, albumin, age, creatinine, creatine kinase-MB, haemoglobin, lactate, left ventricular end-diastolic dimension, urea nitrogen, and aspartate aminotransferase, with adequate discrimination ability {area under the receiver operating characteristic curve (AUROC): 0.930 [95% confidence interval (CI) 0.906-0.954] and 0.954, 95% CI (0.930-0.977) in the derivation and validation cohort, respectively}. Compared with proximal arch repair, the extensive repair was associated with similar mortality risk among patients at low risk [odds ratio (OR) 1.838, 95% CI (0.559-6.038); P = 0.316], but associated with higher mortality risk among patients at middle-high risk [OR 2.007, 95% CI (1.460-2.757); P < 0.0001].

Conclusion

In ATAAD patients, the simultaneous addition of circulating biomarkers of inflammatory, cardiac, hepatic, renal, and metabolic abnormalities substantially improved risk stratification and individualized arch repair strategy.

Pre-injury performance is most important for predicting the level of match participation after Achilles tendon ruptures in elite soccer players: a study using a machine learning classifier

PURPOSE

Achilles tendon ruptures (ATR) are career-threatening injuries in elite soccer players due to the decreased sports performance they commonly inflict. This study presents an exploratory data analysis of match participation before and after ATRs and an evaluation of the performance of a machine learning (ML) model based on pre-injury features to predict whether a player will return to a previous level of match participation.

METHODS

The website transfermarkt.com was mined, between January and March of 2021, for relevant entries regarding soccer players who suffered an ATR while playing in first or second leagues. The difference between average minutes played per match (MPM) 1 year before injury and between 1 and 2 years after the injury was used to identify patterns in match participation after injury. Clustering analysis was performed using k-means clustering. Predictions of post-injury match participation were made using the XGBoost classification algorithm. The performance of this model was evaluated using the area under the receiver operating characteristic curve (AUROC) and Brier score loss (BSL).

RESULTS

Two hundred and nine players were included in the study. Data from 32,853 matches was analysed. Exploratory data analysis revealed that forwards, midfielders and defenders increased match participation during the first year after injury, with goalkeepers still improving at 2 years. Players were grouped into four clusters regarding the difference between MPMs 1 year before injury and between 1 and 2 years after the injury. These groups ranged between a severe decrease (n = 34; - 59 ± 13 MPM), moderate decrease (n = 75; - 25 ± 8 MPM), maintenance (n = 70; 0 ± 8 MPM), or increase (n = 30; 32 ± 13 MPM). Regarding the predictive model, the average AUROC after cross-validation was 0.81 ± 0.10, and the BSL was 0.12, with the most important features relating to pre-injury match participation.

CONCLUSION

Most players take 1 year to reach peak match participation after an ATR. Good performance was attained using a ML classifier to predict the level of match participation following an ATR, with features related to pre-injury match participation displaying the highest importance.

LEVEL OF EVIDENCE

I.