Risk factors for secondary meniscus tears can be accurately predicted through machine learning, creating a resource for patient education and intervention

Return to the Pre-Injury Level of Sport after Anterior Cruciate Ligament Reconstruction: A Practical Review with Medical Recommendations

Returning to sport after anterior cruciate ligament reconstruction (ACLR) can be a challenging and complex process for the athlete, with the rate of return to the pre-injury level of sport observed to be less than athlete expectations. Of the athletes that do return to sport (RTS), knee re-injury rates remain high, and multiple studies have observed impaired athletic performance upon RTS after ACLR as well as reduced playing time, productivity, and career lengths. To mitigate re-injury and improve RTS outcomes, multiple RTS after ACLR consensus statements/clinical practice guidelines have recommended objective RTS testing criteria to be met prior to medical clearance for unrestricted sports participation. While the achievement of RTS testing criteria can improve RTS rates after ACLR, current criteria do not appear valid for predicting safe RTS. Therefore, there is a need to review the various factors related to the successful return to the pre-injury level of sport after ACLR, clarify the utility of objective performance testing and RTS criteria, further discuss safe RTS decision-making as well as present strategies to reduce the risk of ACL injury/re-injury upon RTS. This article provides a practical review of the current RTS after ACLR literature, as well as makes medical recommendations for rehabilitation and RTS decision-making after ACLR.

Random forest identifies predictors of discharge destination following total shoulder arthroplasty

Background

Machine learning algorithms are finding increasing use in prediction of surgical outcomes in orthopedics. Random forest is one of such algorithms popular for its relative ease of application and high predictability. In the process of sample classification, algorithms also generate a list of variables most crucial in the sorting process. Total shoulder arthroplasty (TSA) is a common orthopedic procedure after which most patients are discharged home. The authors hypothesized that random forest algorithm would be able to determine most important variables in prediction of nonhome discharge.

Methods

Authors filtered the National Surgical Quality iImprovement Program database for patients undergoing elective TSA (Current Procedural Terminology 23472) between 2008 and 2018. Applied exclusion criteria included avascular necrosis, trauma, rheumatoid arthritis, and other inflammatory arthropathies to only include surgeries performed for primary osteoarthritis. Using Python and the scikit-learn package, various machine learning algorithms including random forest were trained based on the sample patients to predict patients who had nonhome discharge (to facility, nursing home, etc.). List of applied variables were then organized in order of feature importance. The algorithms were evaluated based on area under the curve of the receiver operating characteristic, accuracy, recall, and the F-1 score.

Results

Application of inclusion and exclusion criteria yielded 18,883 patients undergoing elective TSA, of whom 1813 patients had nonhome discharge. Random forest outperformed other machine learning algorithms and logistic regression based on American Society of Anesthesiologists (ASA) classification. Random forest ranked age, sex, ASA classification, and functional status as the most important variables with feature importance of 0.340, 0.130, 0.126, and 0.120, respectively. Average age of patients going to facility was 76 years, while average age of patients going home was 68 years. 78.1% of patients going to facility were women, while 52.7% of patients going home were. Among patients with nonhome discharge, 80.3% had ASA scores of 3 or 4, while patients going home had 54% of patients with ASA scores 3 or 4. 10.5% of patients going to facility were considered of partially/totally dependent functional status, whereas 1.3% of patients going home were considered partially or totally dependent (P value < .05 for all).

Conclusion

Of various algorithms, random forest best predicted discharge destination following TSA. When using random forest to predict nonhome discharge after TSA, age, gender, ASA scores, and functional status were the most important variables. Two patient groups (home discharge, nonhome discharge) were significantly different when it came to age, gender distribution, ASA scores, and functional status.

Graft failure within 2 years of isolated anterior cruciate ligament reconstruction is associated with increased risk of secondary meniscus tears

PURPOSE

A debilitating complication following anterior cruciate ligament reconstruction is a secondary meniscus tear. Currently, the literature is mixed regarding the risk factors associated with the incidence of secondary meniscus tears. The aim of this study was to investigate risk factors associated with meniscus tears following an isolated primary anterior cruciate ligament reconstruction. ACL graft failure was hypothesized to be the strongest risk factor for secondary meniscal injury occurrence.

METHODS

A retrospective cohort analysis was performed using the PearlDiver Database. Patients with a primary anterior cruciate ligament reconstruction were identified in the database. Patients with concomitant knee ligament injury or meniscus injury present at the time the index procedure were excluded. Patients were grouped to those who had a secondary meniscus tear within 2 years following anterior cruciate ligament reconstruction and those who did not. Univariate analysis and multivariable regression analysis was conducted to identify significant risk factors for a secondary meniscus tear.

RESULTS

There were 25,622 patients meeting criteria for inclusion in this study. Within 2 years from the primary anterior cruciate ligament reconstruction, there were 1,781 patients (7.0%) that experienced a meniscus tear. Graft failure had the highest odds of having a postoperative meniscus tear within 2 years (OR: 4.1; CI 3.5-4.8; p < 0.002). Additional significant risk factors included tobacco use (OR: 2.0; CI 1.0-3.1; p < 0.001), increased Charlson Comorbidity Index (OR: 1.2; CI 1.1-1.4), male gender (OR: 1.1; CI 1.1-1.2; p < 0.001), obesity (OR: 1.1; CI 1.1-1.2; p < 0.001), delayed surgery (OR:1.1; CI 1.1-1.2; p < 0.002), and patients age 30 and older (OR: 1.0; CI 1.0-1.0; p < 0.001).

CONCLUSIONS

This study found that anterior cruciate ligament graft failure is the strongest predictor of post-operative meniscus tears. Other risk factors, including tobacco use, increased CCI, male gender, obesity, delayed surgery, and age 30 and older, were established, with several being modifiable. Therefore, targeted preoperative optimization of modifiable risk factors and postoperative protocols may reduce the risk of secondary meniscus tears.

LEVEL OF EVIDENCE

Level III, prognostic trial.

IL-6 induces periostin production in human ACL remnants: a possible mechanism causing post-traumatic osteoarthritis

OBJECTIVE

Perostin (POSTN) and IL-6 consistently elevated after ACL injury, and ACL has been proposed as the major source of POSTN. However, there is a lack of evidence whether IL-6 induces ACL remnants to produce POSTN. This study aimed to investigate the effect of IL-6 on POSTN production in ACL fibroblasts, which may help us understand more about the mechanism of PTOA after ACL injury and ACL reconstruction.

METHODS

ACL remnants were harvested from 27 patients undergoing ACL reconstruction. Quantitative real-time polymerase chain reaction (PCR) was performed to examine the POSTN gene expression of ACL fibroblasts after treatment of different concentrations of IL-6. The POSTN protein production of ACL fibroblasts was determined using western blot analysis. The blockers of possible signaling pathways, including PI3K/Akt, Ras/MAPK, and JAK/STAT pathways, were added to test whether the effect of IL-6 on ACL fibroblast could be attenuated. ACL fibroblast and chondrocyte co-culture was carried out to determine the influence of ACL and IL-6 on chondrocytes.

RESULTS

Quantitative real-time PCR showed that IL-6 time-dependently and dose-dependently increased POSTN gene expression of ACL fibroblast. Western blot analysis also revealed that IL-6 dose-dependently induced POSTN protein production. Regarding the chronicity of ACL injury, the POSTN protein production was comparable between ACL remnants which were derived within 3 months of injury and at least 6 months after injury. PI3K/Akt blockers could attenuate the effect of IL-6 on ACL remnants, whereas Ras/MAPK and JAK/STAT did not decrease POSTN production. The coexistence of ACL and IL-6 induced more MMP-13 and ADAMTS-4 by chondrocytes.

CONCLUSIONS

IL-6 induced ACL remnants to produce POSTN. This effect could be attenuated by the PI3K/Akt blocker. Coexistence of IL-6 and ACL remnants may accelerate post-traumatic arthritis.

Supervised machine learning and associated algorithms: applications in orthopedic surgery

Supervised learning is the most common form of machine learning utilized in medical research. It is used to predict outcomes of interest or classify positive and/or negative cases with a known ground truth. Supervised learning describes a spectrum of techniques, ranging from traditional regression modeling to more complex tree boosting, which are becoming increasingly prevalent as the focus on "big data" develops. While these tools are becoming increasingly popular and powerful, there is a paucity of literature available that describe the strengths and limitations of these different modeling techniques. Typically, there is no formal training for health care professionals in the use of machine learning models. As machine learning applications throughout medicine increase, it is important that physicians and other health care professionals better understand the processes underlying application of these techniques. The purpose of this study is to provide an overview of commonly used supervised learning techniques with recent case examples within the orthopedic literature. An additional goal is to address disparities in the understanding of these methods to improve communication within and between research teams.