ABSTRACT
OBJECTIVE: There are limited data about the influence of the lumbar paraspinal muscles on the maintenance of sagittal alignment after pedicle subtraction osteotomy (PSO) and the risk factors for sagittal realignment failure. The authors aimed to investigate the influence of preoperative lumbar paraspinal muscle quality on the postoperative maintenance of sagittal alignment after lumbar PSO. METHODS: Patients who underwent lumbar PSO with preoperative lumbar MRI and pre- and postoperative whole-spine radiography in the standing position were included. Spinopelvic measurements included pelvic incidence, sacral slope, pelvic tilt, L1-S1 lordosis, T4-12 thoracic kyphosis, spinosacral angle, C7-S1 sagittal vertical axis (SVA), T1 pelvic angle, and mismatch between pelvic incidence and L1-S1 lordosis. Validated custom software was used to calculate the percent fat infiltration (FI) of the psoas major, as well as the erector spinae and multifidus (MF). A multivariable linear mixed model was applied to further examine the association between MF FI and the postoperative progression of SVA over time, accounting for repeated measures over time that were adjusted for age, sex, BMI, and length of follow-up. RESULTS: Seventy-seven patients were recruited. The authors' results demonstrated significant correlations between MF FI and the maintenance of corrected sagittal alignment after PSO. After adjustment for the aforementioned parameters, the model showed that the MF FI was significantly associated with the postoperative progression of positive SVA over time. A 1% increase from the preoperatively assessed total MF FI was correlated with an increase of 0.92 mm in SVA postoperatively (95% CI 0.42-1.41, p < 0.0001). CONCLUSIONS: This study included a large patient cohort with midterm follow-up after PSO and emphasized the importance of the lumbar paraspinal muscles in the maintenance of sagittal alignment correction. Surgeons should assess the quality of the MF preoperatively in patients undergoing PSO to identify patients with severe FI, as they may be at higher risk for sagittal decompensation.
ABSTRACT
BACKGROUND CONTEXT: Degenerative lumbar spondylolisthesis (DLS) is a prevalent spinal disorder, often requiring surgical intervention. Accurately predicting surgical outcomes is crucial to guide clinical decision-making, but this is challenging due to the multifactorial nature of postoperative results. Traditional risk assessment tools have limitations, and with the advent of machine learning, there is potential to enhance the precision and comprehensiveness of preoperative evaluations. PURPOSE: We aimed to develop a machine-learning algorithm to predict surgical outcomes in patients with degenerative lumbar spondylolisthesis (DLS) undergoing spinal fusion surgery, only using preoperative data. STUDY DESIGN: Retrospective cross-sectional study. PATIENT SAMPLE: Patients with DLS undergoing lumbar spinal fusion surgery. OUTCOME MEASURES: This study aimed to predict the occurrence of lower back pain (LBP) ≥4 on the numeric analogue scale (NAS) 2 years after surgery. LBP was evaluated as the average pain patients experienced at rest in the week before questioning. NAS ranges from 0 to 10, 0 representing no pain and 10 representing the worst pain imaginable. METHODS: We conducted a retrospective analysis of prospectively enrolled patients who underwent spinal fusion surgery for degenerative lumbar spondylolistheses at our institution in the United States between January 2016 and December 2018. The initial patient characteristics to be included in the training of the model were chosen by clinical expertise and through a literature review and included demographic characteristics, comorbidities, and radiologic features. The data was split into a training and validation datasets using a 60/40 split. Four different machine learning models were trained, including the modern XGBoost model, logistic regression, random-forest, and support vector machine (SVM). The models were evaluated according to the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. An AUC of 0.7 to 0.8 was considered fair, 0.8 to 0.9 good, and ≥ 0.9 excellent. Additionally, a calibration plot and the Brier score were calculated for each model. RESULTS: A total of 135 patients (66% female) were included. A total of 38 (28%) patients reported LBP ≥ 4 after 2 years, representing the positive class. The XGBoost model demonstrated the best performance in the validation set with an AUC of 0.81 (95% CI 0.67-0.95). The other machine learning models performed significantly worse: with an AUC of 0.52 (95% CI 0.37-0.68) for the SVM, 0.56 (95% CI 0.37-0.76) for the logistic regression and an AUC of 0.56 (95% CI 0.37-0.78) for the random forest. In the XGBoost model age, composition of the erector spinae, and severity of lumbar spinal stenosis as were identified as the most important features. CONCLUSIONS: This study represents a novel approach to predicting surgical outcomes in spinal fusion patients. The XGBoost demonstrated a better performance compared with classical models and highlighted the potential contributions of age and paraspinal musculature atrophy as significant factors. These findings have important implications for enhancing patient care through the identification of high-risk individuals and modifiable risk factors. As the incorporation of machine learning algorithms into clinical decision-making continues to gain traction in research and clinical practice, our insights reinforce this trajectory by showcasing the potential of these techniques in forecasting surgical results.
