Predicting Subjective Failure of ACL Reconstruction: A Machine Learning Analysis of the Norwegian Knee Ligament Register and Patient Reported Outcomes

Application of machine learning in the context of reoperation, outcome and management after ACL reconstruction - A systematic review

INTRODUCTION

Machine learning-based tools are becoming increasingly popular in clinical practice. They offer new possibilities but are also limited in their reliability and accuracy.

OBJECTIVES

The present systematic review updates and discusses the existing literature regarding machine learning algorithm-based tools to predict outcome and management in patients after ACL reconstruction.

METHOD

PubMed was searched for articles containing machine learning algorithms related to anterior cruciate ligament reconstruction and its outcome and management. No additional filters or time constraints were used. All eligible studies were accessed by hand.

RESULTS

After screening of 115 articles, 15 were included. Six studies evaluated predictors for reoperation after ACL surgery. Four studies investigated the clinical outcome prediction after ACL reconstruction including prediction of secondary meniscus tear and secondary knee osteoarthritis. Single topics addressed in patients with ACL reconstruction were costs, opioid use, the need for a femoral nerve block, short term complications, hospital admission, and reduction of the burden to complete the Knee Osteoarthritis and Outcome score questionnaire. Predictive power was very heterogeneous, depending on the specific research question and parameters included.

CONCLUSION

New machine-learning tools offer interesting insights into variables affecting the target outcome and general management of patients with ACL reconstruction. While present machine-learning based prediction models seem to outperform previous existing benchmark regression models, their predictive ability often is still too low to base individual decision making on them. With the rapid progress observed over the last few years, it is conceivable that this might change, however, in the foreseeable future.

Predicting ACL Reconstruction Failure with Machine Learning: Development of Machine Learning Prediction Models

Background

Anterior cruciate ligament reconstruction (ACLR) is the predominant and widely accepted treatment modality for ACL injury. However, recurrence of ACL rupture or failure of the reconstruction remains a significant challenge. Despite several studies in the literature that have developed prediction models to address this issue by identifying prognostic factors for treatment outcomes using classical statistical methods, the predictive efficacy of these models is frequently suboptimal.

Purpose

To (1) evaluate the predictive performance of different machine learning algorithms for the occurrence of failure in ACLR and (2) identify the most relevant predictors associated with this outcome.

Study Design

Cohort study; Level of evidence, 3.

Methods

A total of 680 patients who underwent ACLR between January 2012 and July 2021 were evaluated. The study outcome was ACLR failure-defined as a complete tear confirmed by magnetic resonance imaging, arthroscopy, or clinical ACL insufficiency-evaluated at a minimum 2-year follow-up. Routinely collected data were used to train 9 machine learning algorithms-including k-nearest neighbors classifier, decision tree classifier, random forest classifier, extra trees classifier, gradient boosting classifier, eXtreme Gradient Boosting, CatBoost classifier, and logistic regression. A random sample of 70% of patients was used to train the algorithms, and 30% were left for performance assessment, simulating new data. The performance of the models was evaluated with the area under the receiver operating characteristic curve (AUC).

Results

The predictive performance of most models was good, with AUCs ranging from 0.71 to 0.85. The models with the best AUC metric were the CatBoost classifier (0.85 [95% CI, 0.81-0.89]) and the random forest classifier (0.84 [95% CI, 0.77-0.90). Knee hyperextension consistently emerged as the primary predictor for ACLR failure across all models subjected to our analysis.

Conclusion

Machine learning algorithms demonstrated good performance in predicting ACLR failure. Moreover, knee hyperextension consistently emerged as the primary predictor for failure across all models subjected to our analysis.

Clinical Relevance

The findings of this study highlight the potential of machine learning as a valuable clinical tool for decision-making on surgical intervention. By offering nuanced insights, these algorithms may contribute to the evolving landscape of orthopaedic practice. Also, this study confirms knee hyperextension as an important risk factor for ACLR failure.

Patient-Reported Outcomes of Bicruciate Multiligament Versus Single Cruciate Multiligament Knee Injuries

BACKGROUND

Multiligament knee injuries (MLKIs) are heterogeneous, and bicruciate knee ligament injuries are considered a serious form of this injury. The current literature tends not to distinguish between single and bicruciate MLKI when reporting outcomes.

PURPOSE

To investigate patient-reported outcomes after surgical treatment of MLKI comparing single cruciate MLKI with bicruciate MLKI. The secondary aim was to investigate the influence of different factors on patient-reported outcomes after surgery.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

This study was designed as a cross-sectional cohort study. Patients who underwent surgical treatment for MLKI at a single level 1 trauma center between January 2013 and December 2020 were included in this study. Patient-reported outcomes included the Tegner score, Lysholm score, International Knee Documentation Committee (IKDC) subjective knee form, Knee injury and Osteoarthritis Outcome Survey (KOOS), and a visual analog scale for pain.

RESULTS

Of the 191 patients meeting the inclusion criteria, 124 (65%) agreed to participate and had a complete data set with a follow-up time at a mean 74 ± 27 months. Patients with single cruciate MLKI (type I) had significantly higher scores for IKDC (P = .007), Lysholm (P = .012), KOOS Pain (P = .04), KOOS Activities of Daily Living (P = .01), KOOS Sport and Recreation (P = .005), KOOS Quality of Life (P = .04), KOOS4 (which considers the subscales of Pain, Symptoms, Sport and Recreation, and Quality of Life) (P = .01), Tegner (P = .04), and visual analog scale for pain during activity (P = .004) when compared with patients with bicruciate MLKI (type II-type IV). Furthermore, age was significantly associated with a lower IKDC (P = .001), and an increased severity of injury was significantly associated with IKDC (P = .015), KOOS4 (P = .022), and Lysholm (P = .029) scores.

CONCLUSION

MLKIs involving a single cruciate ligament had significantly higher patient-reported postoperative outcome measures compared with bicruciate MLKIs. Age and type of injury were important predictors for outcomes. Patients presenting with dislocated knees had lower patient-reported outcomes; however, there was no significant difference in outcomes between bicruciate MLKIs and patients presenting with dislocated knees.

Predicting patient reported outcome measures: a scoping review for the artificial intelligence-guided patient preference predictor

Background

The algorithmic patient preference predictor (PPP) has been proposed to aid in decision making for incapacitated patients in the absence of advanced directives. Ethical and legal challenges aside, multiple practical barriers exist for building a personalized PPP. Here, we examine previous work using machine learning to predict patient reported outcome measures (PROMs) for capacitated patients undergoing diverse procedures, therapies, and life events. Demonstrating robust performance in predicting PROMs for capacitated patients could suggest opportunities for developing a model tailored to incapacitated ones.

Methods

We performed a scoping review of PubMed, Embase, and Scopus using the PRISMA-ScR guidelines to capture studies using machine learning to predict PROMs following a medical event alongside qualitative studies exploring a theoretical PPP.

Results

Sixty-eight studies used machine learning to evaluate PROMs; an additional 20 studies focused on a theoretical PPP. For PROMs, orthopedic surgeries (n = 33) and spinal surgeries (n = 12) were the most common medical event. Studies used demographic (n = 30), pre-event PROMs (n = 52), comorbidities (n = 29), social determinants of health (n = 30), and intraoperative variables (n = 124) as predictors. Thirty-four different PROMs were used as the target outcome. Evaluation metrics varied by task, but performance was overall poor to moderate for the best reported scores. In models that used feature importance, pre-event PROMs were the most predictive of post-event PROMs. Fairness assessments were rare (n = 6). These findings reinforce the necessity of the integrating patient values and preferences, beyond demographic factors, to improve the development of personalized PPP models for incapacitated patients.

Conclusion

The primary objective of a PPP is to estimate patient-reported quality of life following an intervention. Use of machine learning to predict PROMs for capacitated patients introduces challenges and opportunities for building a personalized PPP for incapacitated patients without advanced directives.

A Novel Machine Learning Model to Predict Revision ACL Reconstruction Failure in the MARS Cohort

Background

As machine learning becomes increasingly utilized in orthopaedic clinical research, the application of machine learning methodology to cohort data from the Multicenter ACL Revision Study (MARS) presents a valuable opportunity to translate data into patient-specific insights.

Purpose

To apply novel machine learning methodology to MARS cohort data to determine a predictive model of revision anterior cruciate ligament reconstruction (rACLR) graft failure and features most predictive of failure.

Study Design

Cohort study; Level of evidence, 3.

Methods

The authors prospectively recruited patients undergoing rACLR from the MARS cohort and obtained preoperative radiographs, surgeon-reported intraoperative findings, and 2- and 6-year follow-up data on patient-reported outcomes, additional surgeries, and graft failure. Machine learning models including logistic regression (LR), XGBoost, gradient boosting (GB), random forest (RF), and a validated ensemble algorithm (AutoPrognosis) were built to predict graft failure by 6 years postoperatively. Validated performance metrics and feature importance measures were used to evaluate model performance.

Results

The cohort included 960 patients who completed 6-year follow-up, with 5.7% (n = 55) experiencing graft failure. AutoPrognosis demonstrated the highest discriminative power (model area under the receiver operating characteristic curve: AutoPrognosis, 0.703; RF, 0.618; GB, 0.660; XGBoost, 0.680; LR, 0.592), with well-calibrated scores (model Brier score: AutoPrognosis, 0.053; RF, 0.054; GB, 0.057; XGBoost, 0.058; LR, 0.111). The most important features for AutoPrognosis model performance were prior compromised femoral and tibial tunnels (placement and size) and allograft graft type used in current rACLR.

Conclusion

The present study demonstrated the ability of the novel AutoPrognosis machine learning model to best predict the risk of graft failure in patients undergoing rACLR at 6 years postoperatively with moderate predictive ability. Femoral and tibial tunnel size and position in prior ACLR and allograft use in current rACLR were all risk factors for rACLR failure in the context of the AutoPrognosis model. This study describes a unique model that can be externally validated with larger data sets and contribute toward the creation of a robust rACLR bedside risk calculator in future studies.

Registration

NCT00625885 (ClinicalTrials.gov identifier).

Diagnostic performance of deep learning for leg length measurements on radiographs in leg length discrepancy: A systematic review

Purpose

To systematically review the literature regarding machine learning in leg length discrepancy (LLD) and to provide insight into the most relevant manuscripts on this topic in order to highlight the importance and future clinical implications of machine learning in the diagnosis and treatment of LLD.

Methods

A systematic electronic search was conducted using PubMed, OVID/Medline and Cochrane libraries in accordance with Preferred Reporting Items for Systematic Review and Meta-Analysis guidelines. Two observers independently screened the abstracts and titles of potential articles.

Results

A total of six studies were identified in the search. All measurements were calculated using standardized anterior-posterior long-leg radiographs. Five (83.3%) of the studies used measurements of the femoral length, tibial length and leg length to assess LLD, whereas one (16.6%) study used the iliac crest height difference to quantify LLD. The deep learning models showed excellent reliability in predicting all length measurements with intraclass correlation coefficients ranging from 0.98 to 1.0 and mean absolute error (MAE) values ranging from 0.11 to 0.45 cm. Three studies reported measurements of LLD, and the convolutional neural network model showed the lowest MAE of 0.13 cm in predicting LLD.

Conclusions

Machine learning models are effective and efficient in determining LLD. Implementation of these models may reduce cost, improve efficiency and lead to better overall patient outcomes.

Clinical Relevance

This review highlights the potential of deep learning (DL) algorithms for accurate and reliable measurement of lower limb length and leg length discrepancy (LLD) on long-leg radiographs. The reported mean absolute error and intraclass correlation coefficient values indicate that the performance of the DL models was comparable to that of radiologists, suggesting that DL-based assessments could potentially be used to automate the measurement of lower limb length and LLD in clinical practice.

Level of Evidence

Level IV.

Late (≥60 years old) and middle adulthood (40-59 years old) patients achieve similar improvement in patient-reported outcomes following ACL reconstruction

PURPOSE

This study aimed to compare the range of motion (ROM), surgical outcomes, and patient-reported outcome measures (PROMs) following anterior cruciate ligament (ACL) reconstruction outcomes in patients 60 years or older at the time of surgery to 40- to 59-year-old patients.

METHODS

In this retrospective cohort study from 2015 to 2022, a 3:1 propensity match was performed to match late adulthood patients (≥60 years old) undergoing ACL reconstruction with middle adulthood (40-59 years old) ACL reconstruction patients. Patients were matched based on sex, ACL graft utilized and concomitant procedures performed during ACL reconstruction. Statistical analysis compared demographics, preoperative injury management, surgical outcomes, PROMs, and minimal clinical important difference (MCID) and substantial clinical benefit (SCB) achievement rates for all ACL reconstruction patients included.

RESULTS

Twenty late adulthood and 60 middle adulthood patients who underwent ACL reconstruction were included in the final cohort. Patients who were 60 years or older experienced no difference in reoperation rate (n.s.), incidence of retears (n.s.) or ROM (n.s.) at 1 year post-operatively. There were also no differences in International Knee Documentation Committee (ΔIKDC) (31.3 ± 19.1 vs. 34.2 ± 18.2, n.s.) or ΔPCS-12 (12.4 ± 9.8 vs. 12.9 ± 10.8, n.s.) scores at 1 year post-operatively. Furthermore, the younger and older patient cohorts demonstrated similar rates of achieving the MCID (80.0% vs. 83.3%, n.s.) and SCB (50.0% vs. 61.7%, n.s.) scores for IKDC.

CONCLUSION

Patients 60 years or older and 40- to 59-year-old patients demonstrated similar outcomes after undergoing ACL reconstruction with allograft. This study concludes that ACL reconstruction in late adulthood can still be a successful treatment option and should allow surgeons to feel more comfortable when performing indicated surgical intervention for older patients who experience an ACL tear.

LEVEL OF EVIDENCE

Level III, Therapeutic III, retrospective cohort study.

Editorial Commentary: Machine Learning and Artificial Intelligence Are Valuable Tools yet Dependent on the Data Input

Machine learning is likely to become one of the most valuable tools for predicting outcomes in patients with patellofemoral instability. Traditional statistical analysis is challenging in this diagnosis as the result of the multitude of risk factors. However, 3 important cautions must be considered. (1) Machine learning is limited by the quality of the data entered. Many of the risk factors for patellofemoral instability rely on classification systems with significant interexaminer variability and patient-reported outcomes used to track changes contain inherent biases, especially with regard to race and gender. Poor data quality will lead to unreliable predictions, or "garbage in equals garbage out." (2) The optimal machine-learning algorithms for addressing specific clinical questions remain uncertain. (3) The question of how much data we really need for accurate analysis is unresolved, which again, is completely dependent on the quality of the data. Machine learning is the future; just beware of what goes into the chicken salad.

Surgically-relevant quality of life thresholds for the Short Inflammatory Bowel Disease Questionnaire in Crohn's disease

BACKGROUND

Despite growing interest in patient-reported outcome measures to track the progression of Crohn's disease, frameworks to apply these questionnaires in the preoperative setting are lacking. Using the Short Inflammatory Bowel Disease Questionnaire (sIBDQ), this study aimed to describe the interpretable quality of life thresholds and examine potential associations with future bowel resection in Crohn's disease.

METHODS

Adult patients with Crohn's disease completing an sIBDQ at a clinic visit between 2020 and 2022 were eligible. A stoplight framework was adopted for sIBDQ scores, including a "Resection Red" zone suggesting poor quality of life that may benefit from discussions about surgery as well as a "Nonoperative Green" zone. Thresholds were identified with both anchor- and distribution-based methods using receiver operating characteristic curve analysis and subgroup percentile scores, respectively. To quantify associations between sIBDQ scores and subsequent bowel resection, multivariable logistic regression models were fit with covariates of age, sex assigned at birth, body mass index, medications, disease pattern and location, resection history, and the Harvey Bradshaw Index. The incremental discriminatory value of the sIBDQ beyond clinical factors was assessed through the area under the receiver operating characteristics curve (AUC) with an internal validation through bootstrap resampling.

RESULTS

Of the 2003 included patients, 102 underwent Crohn's-related bowel resection. The sIBDQ Nonoperative Green zone threshold ranged from 61 to 64 and the Resection Red zone from 36 to 38. When adjusting for clinical covariates, a worse sIBDQ score was associated with greater odds of subsequent 90-day bowel resection when considered as a 1-point (odds ratio [OR] [95% CI], 1.05 [1.03-1.07]) or 5-point change (OR [95% CI], 1.27 [1.14-1.41]). Inclusion of the sIBDQ modestly improved discriminative performance (AUC [95% CI], 0.85 [0.85-0.86]) relative to models that included only demographics (0.57 [0.57-0.58]) or demographics with clinical covariates (0.83 [0.83-0.84]).

CONCLUSION

In the decision-making process for bowel resection, disease-specific patient-reported outcome measures may be useful to identify patients with Crohn's disease with poor quality of life and promote a shared understanding of personalized burden.

Artificial Intelligence for Clinically Meaningful Outcome Prediction in Orthopedic Research: Current Applications and Limitations

PURPOSE OF REVIEW

Patient-reported outcome measures (PROM) play a critical role in evaluating the success of treatment interventions for musculoskeletal conditions. However, predicting which patients will benefit from treatment interventions is complex and influenced by a multitude of factors. Artificial intelligence (AI) may better anticipate the propensity to achieve clinically meaningful outcomes through leveraging complex predictive analytics that allow for personalized medicine. This article provides a contemporary review of current applications of AI developed to predict clinically significant outcome (CSO) achievement after musculoskeletal treatment interventions.

RECENT FINDINGS

The highest volume of literature exists in the subspecialties of total joint arthroplasty, spine, and sports medicine, with only three studies identified in the remaining orthopedic subspecialties combined. Performance is widely variable across models, with most studies only reporting discrimination as a performance metric. Given the complexity inherent in predictive modeling for this task, including data availability, data handling, model architecture, and outcome selection, studies vary widely in their methodology and results. Importantly, the majority of studies have not been externally validated or demonstrate important methodological limitations, precluding their implementation into clinical settings. A substantial body of literature has accumulated demonstrating variable internal validity, limited scope, and low potential for clinical deployment. The majority of studies attempt to predict the MCID-the lowest bar of clinical achievement. Though a small proportion of models demonstrate promise and highlight the utility of AI, important methodological limitations need to be addressed moving forward to leverage AI-based applications for clinical deployment.

The Future of Artificial Intelligence in Sports Medicine and Return to Play

Artificial intelligence (AI) has shown tremendous growth over the last decade, with the more recent development of clinical applications in health care. The ability of AI to synthesize large amounts of complex data automatically allows health care providers to access previously unavailable metrics and thus enhance and personalize patient care. These innovations include AI-assisted diagnostic tools, prediction models for each treatment pathway, and various tools for workflow optimization. The extension of AI into sports medicine is still early, but numerous AI-driven algorithms, devices, and research initiatives have delved into predicting and preventing athlete injury, aiding in injury assessment, optimizing recovery plans, monitoring rehabilitation progress, and predicting return to play.

Unsupervised Machine Learning of the Combined Danish and Norwegian Knee Ligament Registers: Identification of 5 Distinct Patient Groups With Differing ACL Revision Rates

BACKGROUND

Most clinical machine learning applications use a supervised learning approach using labeled variables. In contrast, unsupervised learning enables pattern detection without a prespecified outcome.

PURPOSE/HYPOTHESIS

The purpose of this study was to apply unsupervised learning to the combined Danish and Norwegian knee ligament register (KLR) with the goal of detecting distinct subgroups. It was hypothesized that resulting groups would have differing rates of subsequent anterior cruciate ligament reconstruction (ACLR) revision.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

K-prototypes clustering was performed on the complete case KLR data. After performing the unsupervised learning analysis, the authors defined clinically relevant characteristics of each cluster using variable summaries, surgeons' domain knowledge, and Shapley Additive exPlanations analysis.

RESULTS

Five clusters were identified. Cluster 1 (revision rate, 9.9%) patients were young (mean age, 22 years; SD, 6 years), received hamstring tendon (HT) autograft (91%), and had lower baseline Knee injury and Osteoarthritis Outcome Score (KOOS) Sport and Recreation (Sports) scores (mean, 25.0; SD, 15.6). Cluster 2 (revision rate, 6.9%) patients received HT autograft (89%) and had higher baseline KOOS Sports scores (mean, 67.2; SD, 16.5). Cluster 3 (revision rate, 4.7%) patients received bone-patellar tendon-bone (BPTB) or quadriceps tendon (QT) autograft (94%) and had higher baseline KOOS Sports scores (mean, 65.8; SD, 16.4). Cluster 4 (revision rate, 4.1%) patients received BPTB or QT autograft (88%) and had low baseline KOOS Sports scores (mean, 20.5; SD, 14.0). Cluster 5 (revision rate, 3.1%) patients were older (mean age, 42 years; SD, 7 years), received HT autograft (89%), and had low baseline KOOS Sports scores (mean, 23.4; SD, 17.6).

CONCLUSION

Unsupervised learning identified 5 distinct KLR patient subgroups and each grouping was associated with a unique ACLR revision rate. Patients can be approximately classified into 1 of the 5 clusters based on only 3 variables: age, graft choice (HT, BPTB, or QT autograft), and preoperative KOOS Sports subscale score. If externally validated, the resulting groupings may enable quick risk stratification for future patients undergoing ACLR in the clinical setting. Patients in cluster 1 are considered high risk (9.9%), cluster 2 patients medium risk (6.9%), and patients in clusters 3 to 5 low risk (3.1%-4.7%) for revision ACLR.

External validation of the Norwegian anterior cruciate ligament reconstruction revision prediction model using patients from the STABILITY 1 Trial

PURPOSE

A machine learning-based anterior cruciate ligament (ACL) revision prediction model has been developed using Norwegian Knee Ligament Register (NKLR) data, but lacks external validation outside Scandinavia. This study aimed to assess the external validity of the NKLR model (https://swastvedt.shinyapps.io/calculator_rev/) using the STABILITY 1 randomized clinical trial (RCT) data set. The hypothesis was that model performance would be similar.

METHODS

The NKLR Cox Lasso model was selected for external validation owing to its superior performance in the original study. STABILITY 1 patients with all five predictors required by the Cox Lasso model were included. The STABILITY 1 RCT was a prospective study which randomized patients to receive either a hamstring tendon autograft (HT) alone or HT plus a lateral extra-articular tenodesis (LET). Since all patients in the STABILITY 1 trial received HT ± LET, three configurations were tested: 1: all patients coded as HT, 2: HT + LET group coded as bone-patellar tendon-bone (BPTB) autograft, 3: HT + LET group coded as unknown/other graft choice. Model performance was assessed via concordance and calibration.

RESULTS

In total, 591/618 (95.6%) STABILITY 1 patients were eligible for inclusion, with 39 undergoing revisions within 2 years (6.6%). Model performance was best when patients receiving HT + LET were coded as BPTB. Concordance was similar to the original NKLR prediction model for 1- and 2-year revision prediction (STABILITY: 0.71; NKLR: 0.68-0.69). Concordance 95% confidence interval (CI) ranged from 0.63 to 0.79. The model was well calibrated for 1-year prediction while the 2-year prediction demonstrated evidence of miscalibration.

CONCLUSION

When patients in STABILITY 1 who received HT + LET were coded as BPTB in the NKLR prediction model, concordance was similar to the index study. However, due to a wide 95% CI, the true performance of the prediction model with this Canadian and European cohort is unclear and a larger data set is required to definitively determine the external validity. Further, better calibration for 1-year predictions aligns with general prediction modelling challenges over longer periods. While not a large enough sample size to elicit the true accuracy and external validity of the prediction model when applied to North American patients, this analysis provides more support for the notion that HT plus LET performs similarly to BPTB reconstruction. In addition, despite the wide confidence interval, this study suggests optimism regarding the accuracy of the model when applied outside of Scandinavia.

LEVEL OF EVIDENCE

Level 3, cohort study.

Previous cartilage surgery is associated with inferior patient-reported outcomes after knee arthroplasty

PURPOSE

The hypothesis of the present study assumed that a history of focal cartilage lesions would not affect Knee Injury and Osteoarthritis Outcome scores (KOOSs) following knee arthroplasty compared to a matched national cohort of knee arthroplasty patients.

METHODS

Fifty-eight knee arthroplasty patients with previous surgery for focal cartilage lesions (cartilage cohort) were compared to a matched cohort of 116 knee arthroplasty patients from the Norwegian Arthroplasty Register (control group). Age, sex, primary or revision arthroplasty, type of arthroplasty (total, unicondylar or patellofemoral), year of arthroplasty surgery and arthroplasty brand were used as matching criteria. Demographic data and KOOS were obtained through questionnaires. Regression models were employed to adjust for confounding factors.

RESULTS

Mean follow-up post knee arthroplasty surgery was 7.6 years (range 1.2-20.3) in the cartilage cohort and 8.1 (range 1.0-20.9) in the control group. The responding patients were at the time of surgery 54.3 versus 59.0 years in the cartilage and control group, respectively. At follow-up the control group demonstrated higher adjusted Knee Injury and Osteoarthritis Outcome subscores than the previous focal cartilage patients with a mean adjusted difference (95% confidence interval in parentheses): Symptoms 8.4 (0.3, 16.4), Pain 11.8 (2.2, 21.4), Activities of daily living (ADL) 9.3 (-1.2, 18.6), Sport and recreation 8.9 (-1.6, 19.4) and Quality of Life (QoL) 10.6 (0.2, 21.1). The control group also demonstrated higher odds of reaching the patient-acceptable symptom state threshold for the Knee Injury and Osteoarthritis Outcome subscores with odds ratio: Symptoms 2.7 (1.2, 6.4), Pain 3.0 (1.3, 7.0), ADL 2.1 (0.9, 4.6) and QoL 2.4 (1.0, 5.5).

CONCLUSION

Previous cartilage surgery was associated with inferior patient-reported outcomes after knee arthroplasty. These patients also exhibited significantly lower odds of reaching the patient-acceptable symptom state threshold for the Knee Injury and Osteoarthritis Outcome subscores.

LEVEL OF EVIDENCE

Level III.

Machine learning can accurately predict risk factors for all-cause reoperation after ACLR: creating a clinical tool to improve patient counseling and outcomes

PURPOSE

Identifying predictive factors for all-cause reoperation after anterior cruciate ligament reconstruction could inform clinical decision making and improve risk mitigation. The primary purposes of this study are to (1) determine the incidence of all-cause reoperation after anterior cruciate ligament reconstruction, (2) identify predictors of reoperation after anterior cruciate ligament reconstruction using machine learning methodology, and (3) compare the predictive capacity of the machine learning methods to that of traditional logistic regression.

METHODS

A longitudinal geographical database was utilized to identify patients with a diagnosis of new anterior cruciate ligament injury. Eight machine learning models were appraised on their ability to predict all-cause reoperation after anterior cruciate ligament reconstruction. Model performance was evaluated via area under the receiver operating characteristics curve. To explore modeling interpretability and radiomic feature influence on the predictions, we utilized a game-theory-based method through SHapley Additive exPlanations.

RESULTS

A total of 1400 patients underwent anterior cruciate ligament reconstruction with a mean postoperative follow-up of 9 years. Two-hundred and eighteen (16%) patients experienced a reoperation after anterior cruciate ligament reconstruction, of which 6% of these were revision ACL reconstruction. SHapley Additive exPlanations plots identified the following risk factors as predictive for all-cause reoperation: diagnosis of systemic inflammatory disease, distal tear location, concomitant medial collateral ligament repair, higher visual analog scale pain score prior to surgery, hamstring autograft, tibial fixation via radial expansion device, younger age at initial injury, and concomitant meniscal repair. Pertinent negatives, when compared to previous studies, included sex and timing of surgery. XGBoost was the best-performing model (area under the receiver operating characteristics curve of 0.77) and outperformed logistic regression in this regard.

CONCLUSIONS

All-cause reoperation after anterior cruciate ligament reconstruction occurred at a rate of 16%. Machine learning models outperformed traditional statistics and identified diagnosis of systemic inflammatory disease, distal tear location, concomitant medial collateral ligament repair, higher visual analog scale pain score prior to surgery, hamstring autograft, tibial fixation via radial expansion device, younger age at initial injury, and concomitant meniscal repair as predictive risk factors for reoperation. Pertinent negatives, when compared to previous studies, included sex and timing of surgery. These models will allow surgeons to tabulate individualized risk for future reoperation for patients undergoing anterior cruciate ligament reconstruction.

LEVEL OF EVIDENCE

III.

Ceiling Effect of the Combined Norwegian and Danish Knee Ligament Registers Limits Anterior Cruciate Ligament Reconstruction Outcome Prediction

BACKGROUND

Clinical tools based on machine learning analysis now exist for outcome prediction after primary anterior cruciate ligament reconstruction (ACLR). Relying partly on data volume, the general principle is that more data may lead to improved model accuracy.

PURPOSE/HYPOTHESIS

The purpose was to apply machine learning to a combined data set from the Norwegian and Danish knee ligament registers (NKLR and DKRR, respectively), with the aim of producing an algorithm that can predict revision surgery with improved accuracy relative to a previously published model developed using only the NKLR. The hypothesis was that the additional patient data would result in an algorithm that is more accurate.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

Machine learning analysis was performed on combined data from the NKLR and DKRR. The primary outcome was the probability of revision ACLR within 1, 2, and 5 years. Data were split randomly into training sets (75%) and test sets (25%). There were 4 machine learning models examined: Cox lasso, random survival forest, gradient boosting, and super learner. Concordance and calibration were calculated for all 4 models.

RESULTS

The data set included 62,955 patients in which 5% underwent a revision surgical procedure with a mean follow-up of 7.6 ± 4.5 years. The 3 nonparametric models (random survival forest, gradient boosting, and super learner) performed best, demonstrating moderate concordance (0.67 [95% CI, 0.64-0.70]), and were well calibrated at 1 and 2 years. Model performance was similar to that of the previously published model (NKLR-only model: concordance, 0.67-0.69; well calibrated).

CONCLUSION

Machine learning analysis of the combined NKLR and DKRR enabled prediction of the revision ACLR risk with moderate accuracy. However, the resulting algorithms were less user-friendly and did not demonstrate superior accuracy in comparison with the previously developed model based on patients from the NKLR alone, despite the analysis of nearly 63,000 patients. This ceiling effect suggests that simply adding more patients to current national knee ligament registers is unlikely to improve predictive capability and may prompt future changes to increase variable inclusion.

MCID and PASS in Knee Surgeries. Theoretical Aspects and Clinical Relevance References

The application and interpretation of patient-reported outcome measures (PROM), following knee injuries, pathologies, and interventions, can be challenging. In recent years, the literature has been enriched with metrics to facilitate our understanding and interpretation of these outcome measures. Two commonly utilized tools include the minimal clinically important difference (MCID) and the patient acceptable symptoms state (PASS). These measures have demonstrated clinical value, however, they have often been under- or mis-reported. It is paramount to use them to understand the clinical significance of any statistically significant results. Still, it remains important to know their caveats and limitations. In this focused report on MCID and PASS, their definitions, methods of calculations, clinical relevance, interpretations, and limitations are reviewed and presented in a simple approach.

Predicting Patient-Reported Outcomes Following Surgery Using Machine Learning

Patient-reported outcomes (PROs) enable providers to identify differences in treatment effectiveness, postoperative recovery, quality of life, and patient satisfaction. By allowing a shift from disease-specific factors to the patient perspective, PROs provide a tailored patient-centric approach to shared decision-making. Artificial intelligence (AI) and machine learning (ML) techniques can facilitate such shared decision-making and improve patient outcomes by accurate prediction of PROs. This article aims to provide a comprehensive review of the use of AI and ML models in predicting PROs following surgery through an overview of common predictive algorithms and modeling techniques, as well as current applications and limitations in the surgical field.

Editorial Commentary: Machine Learning in Medicine Requires Clinician Input, Faces Barriers, and High-Quality Evidence Is Required to Demonstrate Improved Patient Outcomes

Machine learning (ML) and artificial intelligence (AI) may be described as advanced statistical techniques using algorithms to "learn" to evaluate and predict relationships between input and results without explicit human programming, often with high accuracy. The potentials and pitfalls of ML continue to be explored as predictive modeling grows in popularity. While use of and optimism for AI continues to increase in orthopaedic surgery, there remains little high-quality evidence of its ability to improve patient outcome. It is up to us as clinicians to provide context for ML models and guide the use of these technologies to optimize the outcome for our patients. Barriers to widespread adoption of ML include poor quality data, limits to compliant data sharing, few clinicians who are expert in ML statistical techniques, and computing costs including technology, infrastructure, personnel, energy, and updates.