Complex knee reconstruction: osteotomies, ligament reconstruction, transplants, and cartilage treatment options

Improved Prediction of Knee Osteoarthritis by the Machine Learning Model XGBoost

Objectives

The accurate prediction of osteoarthritis (OA) severity in patients can be helpful to make the proper decision of intervention. This study aims to build up a powerful model to assess predictive risk factors and severity of knee osteoarthritis (KOA) in the clinical scenario.

Methods

A total of 4796 KOA cases and 1205 features were selected by feature selections from the public OA database, Osteoarthritis Initiative (OAI). Six machine learning-based models were constructed and compared for the accuracy of OA prediction. The gradient-boosting decision tree was used to identify important prediction features in the extreme gradient boosting (XGBoost) model. The performance of models was evaluated by F1-score.

Results

Twenty features were determined as predictors for KOA risk and severity, including the subject characteristics, knee symptoms/risk factors and physical exam. The XGBoost model demonstrated 100% prediction accuracy for 54.7% of examined samples, and the remaining 45.3% of samples showed Kellgren and Lawrence (KL) gradings very close to the actual levels. It showed the highest prediction accuracy with an F1-score of 0.553 among the tested six models.

Conclusions

We demonstrate that the XGBoost is the best model for the prediction of KOA severity in the six examined models. In addition, 20 risk features were determined as the essential predictors of KOA, including the physical exam, knee symptoms/risk factors and subject characteristics, which may be useful for the identification of high-risk KOA cases and for making appropriate treatment decisions as well.

Injectable and Degradable POSS-Polyphosphate-Polysaccharide Hybrid Hydrogel Scaffold for Cartilage Regeneration

The limited self-repair capacity of articular cartilage has motivated the development of stem cell therapy based on artificial scaffolds that mimic the extracellular matrix (ECM) of cartilage tissue. In view of the specificity of articular cartilage, desirable tissue adhesiveness and stable mechanical properties under cyclic mechanical loads are critical for cartilage scaffolds. Herein, we developed an injectable and degradable organic-inorganic hybrid hydrogel as a cartilage scaffold based on polyhedral oligomeric silsesquioxane (POSS)-cored polyphosphate and polysaccharide. Specifically, acrylated 8-arm star-shaped POSS-poly(ethyl ethylene phosphate) (POSS-8PEEP-AC) was synthesized and cross-linked with thiolated hyaluronic acid (HA-SH) to form a degradable POSS-PEEP/HA hydrogel. Incorporation of POSS in the hydrogel increased the mechanical properties. The POSS-PEEP/HA hydrogel showed enzymatic biodegradability and favorable biocompatibility, supporting the growth and differentiation of human mesenchymal stem cells (hMSCs). The chondrogenic differentiation of encapsulated hMSCs was promoted by loading transforming growth factor-β₃ (TGF-β₃) in the hydrogel. In addition, the injectable POSS-PEEP/HA hydrogel was capable of adhering to rat cartilage tissue and resisting cyclic compression. Furthermore, in vivo results revealed that the transplanted hMSCs encapsulated in the POSS-PEEP/HA hydrogel scaffold significantly improved cartilage regeneration in rats, while the conjugation of TGF-β₃ achieved a better therapeutic effect. The present work demonstrated the potential of the injectable, biodegradable, and mechanically enhanced POSS-PEEP/HA hybrid hydrogel as a scaffold biomaterial for cartilage regeneration.

Machine-learning-based patient-specific prediction models for knee osteoarthritis

Osteoarthritis (OA) is an extremely common musculoskeletal disease. However, current guidelines are not well suited for diagnosing patients in the early stages of disease and do not discriminate patients for whom the disease might progress rapidly. The most important hurdle in OA management is identifying and classifying patients who will benefit most from treatment. Further efforts are needed in patient subgrouping and developing prediction models. Conventional statistical modelling approaches exist; however, these models are limited in the amount of information they can adequately process. Comprehensive patient-specific prediction models need to be developed. Approaches such as data mining and machine learning should aid in the development of such models. Although a challenging task, technology is now available that should enable subgrouping of patients with OA and lead to improved clinical decision-making and precision medicine.

Lateral Meniscal Graft Transplantation: Effect of Fixation Method on Joint Contact Mechanics During Simulated Gait

BACKGROUND

Controversy exists regarding the optimal bony fixation technique for lateral meniscal allografts.

PURPOSE/HYPOTHESIS

The objective was to quantify knee joint contact mechanics across the lateral plateau for keyhole and bone plug meniscal allograft transplant fixation techniques throughout simulated gait. It was hypothesized that both methods of fixation would improve contact mechanics relative to the meniscectomized condition, while keyhole fixation would restore the distribution of contact stress closer to that of the intact knee.

STUDY DESIGN

Controlled laboratory study.

METHODS

Six human cadaveric knees were mounted on a multidirectional dynamic simulator and subjected to the following conditions: (1) native intact meniscus, (2) keyhole fixation of the native meniscus, (3) bone plug fixation of the native meniscus, and (4) meniscectomy. Contact area, peak contact stress, and the distribution of stress across the tibial plateau were computed at 14% and 45% of the gait cycle, at which axial forces are at their highest. Translation of the weighted center of contact stress throughout simulated gait was computed.

RESULTS

Both bony fixation techniques improved contact mechanics relative to the meniscectomized condition. The keyhole technique was not significantly different from the intact condition for the following metrics: contact area, peak contact stress, distribution of force between the meniscal footprint and cartilage-to-cartilage contact, and the position of the weighted center of contact. In contrast, bone plug fixation resulted in a significant decrease of 21% to 28% in contact area at 14% and 45% of the simulated gait cycle, a significant increase in peak contact stresses of 34% at 45% of the gait cycle, and a shift in the weighted center of contact, which increased forces in the cartilage-to-cartilage contact area at 45% of the gait cycle.

CONCLUSION

While both keyhole and bone plug fixation methods improved lateral compartment contact mechanics relative to the meniscectomized knee, keyhole fixation restored contact mechanics closer to that of the intact knee.

CLINICAL RELEVANCE

Method of meniscal fixation is under the direct control of the surgeon. From a biomechanics perspective, keyhole fixation is advocated for its ability to mimic intact knee joint contact mechanics.

Posterior tibial slope and further anterior cruciate ligament injuries in the anterior cruciate ligament-reconstructed patient

BACKGROUND

An injury to the anterior cruciate ligament (ACL) is a multifactorial event influenced by intrinsic and extrinsic risk factors. Recently, the geometry of the proximal tibia has come under focus as a possible risk factor for an ACL injury.

HYPOTHESIS

An increased posterior tibial slope is associated with an increased risk of further ACL injuries in the previously ACL-reconstructed patient.

STUDY DESIGN

Case-control study; Level of evidence, 3.

METHODS

A total of 200 consecutive patients with isolated ACL ruptures who underwent primary reconstruction with hamstring autografts were enrolled in a prospective longitudinal study over 15 years. The posterior tibial slope was measured from a lateral knee radiograph by 2 blinded observers. The data were analyzed for the association between an increased posterior tibial slope and the incidence of further ACL injuries. Interobserver reliability of the posterior tibial slope measurements was assessed.

RESULTS

Radiographs and follow-up were available for 181 of the 200 enrolled patients. Fifty patients had a further injury to either the ACL graft or the contralateral knee. The mean posterior tibial slope of those with a further ACL injury was 9.9° compared with 8.5° for those with no further injury (P = .001). The mean posterior tibial slope for those with both an ACL graft and contralateral ACL rupture was 12.9°. The odds of further ACL injuries after reconstruction were increased by a factor of 5, to an incidence of 59%, in those with a posterior tibial slope of ≥12°.

CONCLUSION

An increased posterior tibial slope is associated with increased odds of a further ACL injury after ACL reconstruction. The increased risk is most pronounced in those with a posterior tibial slope of ≥12°.

Articular cartilage regeneration with autologous peripheral blood progenitor cells and hyaluronic acid after arthroscopic subchondral drilling: a report of 5 cases with histology

PURPOSE

The purpose of this study was to evaluate the quality of articular cartilage regeneration after arthroscopic subchondral drilling followed by postoperative intraarticular injections of autologous peripheral blood progenitor cells (PBPCs) in combination with hyaluronic acid (HA).

METHODS

Five patients underwent second-look arthroscopy with chondral core biopsy. These 5 patients are part of a larger pilot study in which 180 patients with International Cartilage Repair Society grade III and IV lesions of the knee joint underwent arthroscopic subchondral drilling followed by postoperative intra-articular injections. Continuous passive motion was used on the operated knee 2 hours per day for 4 weeks. Partial weight bearing was observed for the first 6 to 8 weeks. Autologous PBPCs were harvested 1 week after surgery. One week after surgery, 8 mL of the harvested PBPCs in combination with 2 mL of HA was injected intra-articularly into the operated knee. The remaining PBPCs were divided into vials and cryopreserved. A total of 5 weekly intra-articular injections were given.

RESULTS

Second-look arthroscopy confirmed articular cartilage regeneration, and histologic sections showed features of hyaline cartilage. Apart from the minimal discomfort of PBPC harvesting and localized pain associated with the intra-articular injections, there were no other notable adverse reactions.

CONCLUSIONS

Articular hyaline cartilage regeneration is possible with arthroscopic subchondral drilling followed by postoperative intraarticular injections of autologous PBPCs in combination with HA.

LEVEL OF EVIDENCE

Level IV, therapeutic case series.

Indications for allografts

Allografts continue to be popular in orthopaedic reconstruction procedures of the knee. Approximately 1 million musculoskeletal allografts were distributed in the United States in 2004 alone. Ligament allografts, osteochondral allografts, and meniscal transplants have all demonstrated success in knee reconstructions. The advantages of allograft tissue include the lack of donor site morbidity, shorter operative times, ease of sizing, and a lack of clinically significant immunologic reactions. These advantages should be weighed against the risk for disease transmission, increased cost, and increased time of graft incorporation. Throughout the consent process, comprehensive patient education is imperative to assist in this important decision.