Magnetic resonance imaging overestimates patellar height compared with radiographs

Developing a Machine-Learning Predictive Model for Retention of Posterior Cruciate Ligament in Patients Undergoing Total Knee Arthroplasty

OBJECTIVE

Predicting whether the posterior cruciate ligament (PCL) should be preserved during total knee arthroplasty (TKA) procedures is a complex task in the preoperative phase. The choice to either retain or excise the PCL has a substantial effect on the surgical outcomes and biomechanical integrity of the knee joint after the operation. To enhance surgeons' ability to predict the removal and retention of the PCL in patients before TKA, we developed machine learning models. We also identified significant feature factors that contribute to accurate predictions during this process.

METHODS

Patients' data on TKA continuously performed by a single surgeon who had intended initially to undergo implantation of cruciate-retaining (CR) prostheses was collected. During the sacrifice of PCL, we utilized anterior-stabilized (AS) tibial bearings. The dataset was split into CR and AS categories to form distinct groups. Relevant information regarding age, gender, body mass index (BMI), the affected side, and preoperative diagnosis was extracted by reviewing the medical records of the patients. To ensure the authenticity of the research, an initial step involved capturing X-ray images before the surgery. These images were then analyzed to determine the height of the medial condyle (MMH) and lateral condyle (LMH), as well as the ratios between MLW and MMH and MLW and LMH. Additionally, the insall-salvati index (ISI) was calculated, and the severity of any varus or valgus deformities was assessed. Eight machine-learning methods were developed to predict the retention of PCL in TKA. Risk factor analysis was performed using the SHApley Additive exPlanations method.

RESULTS

A total of 307 knee joints from 266 patients were included, among which there were 254 females and 53 males. A stratified random sampling technique was used to split patients in a 70:30 ratio into a training dataset and a testing dataset. Eight machine-learning models were trained using data feeding. Except for the AUC of the LGBM Classifier, which is 0.70, the AUCs of other machine learning models are all lower than 0.70. In importance-based analysis, ISI, MMH, LMH, deformity, and age were confirmed as important predictive factors for PCL retention in operations.

CONCLUSION

The LGBM Classifier model achieved the best performance in predicting PCL retention in TKA. Among the potential risk factors, ISI, MMH, LMH, and deformity played essential roles in the prediction of PCL retention.

Nonanatomical femoral tunnel positioning in isolated MPFL reconstruction is not associated with an increased risk of patellofemoral osteoarthritis after a minimum follow-up of 10 years

PURPOSE

The association between the prevalence of patellofemoral arthritis (PFA) and femoral tunnel positioning following isolated medial patellofemoral ligament reconstruction (MPFLr) has not been well described. The aim of this study was to analyse the relationship between femoral tunnel positioning and the prevalence of PFA.

METHODS

This was a single-centre study of patients undergoing an isolated MPFLr between 2006 and 2011 with a minimum of 10 years of follow-up. Outcomes assessed were the presence of PFA on radiographs, recurrence of instability requiring revision surgery and patient-reported outcomes, including Kujala, Tegner and IKDC scores. Tunnel positioning was assessed on postoperative radiographs using two radiographic methods: Schöttle's point and the grid method to localise the femoral tunnel. Patients were grouped based on tunnel positioning and compared.

RESULTS

Fifty patients were analysed at a mean follow-up of 12.4 years. Thirty-three patients (66%) had a femoral tunnel position within 7 mm of Schöttle's point and 39 (78%) within the anatomic quadrant, with the most common location according to the grid method in D4 (28%) and E4 (26%), respectively. Thirty-seven patients (74%) had a satisfactory (>80 versus <80) Kujala score at long-term follow-up. None of the examined tunnel assessment methods demonstrated a significant relationship with Tegner, Kujala or International Knee Documentation Committee scores. Patients with a femoral tunnel position >7 mm outside Schöttle's point or were considered to be in a nonanatomic position were not significantly more likely to result in unsatisfactory Kujala scores at the last follow-up. Tunnel positioning and the other tested parameters were not found to be significantly associated with the development of PFA.

CONCLUSION

No correlation between femoral tunnel position and risk of PFA or poor outcomes was observed in patients undergoing isolated MPFLr at long-term follow-up. The impact of femoral tunnel placement on long-term outcomes in patients with PFI may be less significant than originally considered.

LEVEL OF EVIDENCE

Level IV.

Preoperative ultrasound can accurately predict the diameter of double-stranded peroneus longus tendon autografts

PURPOSE

This study aimed to determine the correlation between the intraoperative diameter of double-stranded peroneus longus tendon (2PLT) and length of the PLT autograft and preoperative ultrasound (US) measurements, as well as radiographic and anthropometric measurements. The hypothesis was that US can accurately predict the diameter of 2PLT autografts during operation.

METHODS

Twenty-six patients underwent ligament reconstruction with 2PLT autografts were included. Preoperative US was used to calculate the in situ PLT cross-sectional area (CSA) at seven levels (0, 1, 2, 3, 4, 5, 10 cm proximal to the harvest start point). Femoral width, notch width, notch height, maximum patellar length, and patellar tendon length were determined on preoperative radiographs. Intraoperative measurements of PLT were made, including all fiber lengths of PLT and diameters of 2PLT using sizing tubes calibrated to 0.5 mm.

RESULTS

CSA at 1 cm proximal to the harvest site had the highest correlation with the diameter of 2PLT (r = 0.84, P < 0.001). Calf length had the highest correlation with PLT length (r = 0.65, P < 0.001). The diameter of the 2PLT autografts could be predicted by the following formula: 4.6 + 0.2 × [sonographic CSA of PLT at 1 cm level]; the length of PLT could be predicted by the following formula: 5.6 + 0.5 × Calf length.

CONCLUSION

The diameter of 2PLT and length of PLT autografts can be accurately predicted by preoperative US and calf length measurements, respectively. Accurate preoperative prediction of the diameter and length of autologous grafts can provide the most suitable and individualized graft for patients.

LEVEL OF EVIDENCE

IV.

Evaluation of age group and sex differences in the measurement of patellar height of pediatric knee in a Korean population

INTRODUCTION

Various methods based on bony landmarks are used to determine patellar height. This study analyzed five methods for patellar height measurement on lateral knee radiographs, namely, the Insall-Salvati, Koshino-Sugimoto, Blackburne-Peel, modified Insall-Salvati, and Caton-Deschamps methods.

METHODS

Overall, 425 pediatric participants (221 males, 204 females; age range 5-18 years) were included and were divided equally into three age groups (A, 5-10 years; B, 11-13 years; and C, 13-18 years). For the comparison of the applicability of each method, the applicable probabilities for each age group and sex-based differences were analyzed using logistic regression techniques. Intra-rater reliability and inter-rater variability were analyzed by two trained raters.

RESULTS

The Koshino-Sugimoto method was applicable to all patients. The 80% applicable age of female patients was lower than that of male patients for the Blackburne-Peel (male = 11.9, female = 11) and Caton-Deschamps (male = 11.9, female = 11.1) methods. However, in the Insall-Salvati (male = 12, female = 12.1) and modified Insall-Salvati (male = 12.6, female = 13.1) methods, the 80% applicable age in male patients was lower than that in female patients. The Koshino-Sugimoto method showed the highest variability in group B, while the Insall-Salvati showed the highest variability in group C. In terms of intra-observer reliability, the Caton-Deschamps method showed the same reliability as the Insall-Salvati method, in group C.

CONCLUSIONS

Our results demonstrated differences in the reliability, variability, and applicability of patellar height measurement methods according to age group. The applicability of patellar height measurement methods also differed according to sex. Therefore, based on age group and sex, different methods should be used for patellar height measurement in pediatric patients.