Predictors Using Machine Learning of Complete Peroneal Nerve Palsy Recovery After Multiligamentous Knee Injury: A Multicenter Retrospective Cohort Study

Background

Peroneal nerve (PN) palsy is one of the most debilitating sequelae of multiligamentous knee injuries (MLKIs). There is limited research on recovery from complete PN palsy.

Purpose/Hypothesis

The purpose of this study was to characterize PN injuries and develop a predictive model of complete PN recovery after MLKI using machine learning. It was hypothesized that elevated body mass index (BMI) would be predictive of lower likelihood of recovery.

Study Design

Case-control study; Level of evidence, 3.

Methods

The authors conducted a retrospective review of patients seen at 2 urban hospital systems for treatment of MLKI with associated complete PN palsy, defined as the presence of complete foot drop with or without sensory deficits on physical examination. Recovery was defined as the complete resolution of foot drop. A random forest (RF) classifier algorithm was used to identify demographic, injury, treatment, and postoperative variables that were significant predictors of recovery from complete PN palsy. Validity of the RF model was assessed using overall accuracy, F1 score, and area under the receiver operating characteristic curve (AUC).

Results

Overall, 16 patients with MLKI with associated complete PN palsy were included in the cohort. Among them, 75% (12/16) had documented knee dislocation requiring reduction. Complete recovery occurred in 4 patients (25%). Nerve contusions on magnetic resonance imaging were more common among patients without PN recovery, but there were no other significant differences between recovery and nonrecovery groups. The RF model found that older age, increasing BMI, and male sex were predictive of worse likelihood of PN recovery. The model was found to have good validity, with a classification accuracy of 75%, F1 score of 0.86, and AUC of 0.64.

Conclusion

The RF model in this study found that increasing age, BMI, and male sex were predictive of decreased likelihood of nerve recovery. While further study of machine learning models with larger patient data sets is required to identify the most superior model, these findings present an opportunity for orthopaedic surgeons to better identify, counsel, and treat patients with MLKIs and concomitant complete PN palsy.

Examining the Bone Bruise Patterns in Multiligament Knee Injuries With Peroneal Nerve Injury

BACKGROUND

Tibiofemoral bone bruise patterns seen on magnetic resonance imaging (MRI) are associated with ligamentous injuries in the acutely injured knee. Bone bruise patterns in multiligament knee injuries (MLKIs) and particularly their association with common peroneal nerve (CPN) injuries are not well described.

PURPOSE

To analyze the tibiofemoral bone bruise patterns in MLKIs with and without peroneal nerve injury.

STUDY DESIGN

Case series; Level of evidence, 4.

METHODS

We retrospectively identified 123 patients treated for an acute MLKI at a level 1 trauma center between January 2001 and March 2021. Patients were grouped into injury subtypes using the Schenck classification. Within this cohort, patients with clinically documented complete (motor and sensory loss) and/or partial CPN palsies on physical examination were identified. Imaging criteria required an MRI scan on a 1.5 or 3 Tesla scanner within 30 days of the initial MLKI. Images were retrospectively interpreted for bone bruising patterns by 2 board-certified musculoskeletal radiologists. The location of the bone bruises was mapped on fat-suppressed T2-weighted coronal and sagittal images. Bruise patterns were compared among patients with and without CPN injury.

RESULTS

Of the 108 patients with a MLKI who met the a priori inclusion criteria, 26 (24.1%) were found to have a CPN injury (N = 20 complete; N = 6 partial) on physical examination. For CPN-injured patients, the most common mechanism of injury was high-energy trauma (N = 19 [73%]). The presence of a grade 3 posterolateral corner (PLC) injury (N = 25; odds ratio [OR], 23.81 [95% CI, 3.08-184.1]; P = .0024), anteromedial femoral condyle bone bruising (N = 24; OR, 21.9 [95% CI, 3.40-202.9]; P < .001), or a documented knee dislocation (N = 16; OR, 3.45 [95% CI, 1.38-8.62]; P = .007) was significantly associated with the presence of a CPN injury. Of the 26 patients with CPN injury, 24 (92.3%) had at least 1 anteromedial femoral condyle bone bruise. All 20 (100%) patients with complete CPN injury also had at least 1 anteromedial femoral condyle bone bruise on MRI. In our MLKI cohort, the presence of anteromedial femoral condyle bone bruising had a sensitivity of 92.3% and a specificity of 64.6% for the presence of CPN injury on physical examination.

CONCLUSION

In our MLKI cohort, the presence of a grade 3 PLC injury had the greatest association with CPN injury. Additionally, anteromedial femoral condyle bone bruising on MRI was a highly sensitive finding that was significantly correlated with CPN injury on physical examination. The high prevalence of grade 3 PLC injuries and anteromedial tibiofemoral bone bruising suggests that these MLKIs with CPN injuries most commonly occurred from a hyperextension-varus mechanism caused by a high-energy blow to the anteromedial knee.