A decision tree analysis to predict clinical outcome of minimally invasive lumbar decompression surgery for lumbar spinal stenosis with and without coexisting spondylolisthesis and scoliosis.

BACKGROUND CONTEXT: Implementing machine learning techniques, such as decision trees, known as prediction models that use logical construction diagrams, are rarely used to predict clinical outcomes. PURPOSE: To develop a clinical prediction rule to predict clinical outcomes in patients who undergo minimally invasive lumbar decompression surgery for lumbar spinal stenosis with and without coexisting spondylolisthesis and scoliosis using a decision tree model. STUDY DESIGN/SETTING: A retrospective analysis of prospectively collected data. PATIENT SAMPLE: This study included 331 patients who underwent minimally invasive surgery for lumbar spinal stenosis and were followed up for ≥2 years at 1 institution. OUTCOME MEASURES: Self-report measures: The Japanese Orthopedic Association (JOA) scores and low back pain (LBP)/leg pain/leg numbness visual analog scale (VAS) scores. Physiologic measures: Standing sagittal spinopelvic alignment, computed tomography, and magnetic resonance imaging results. METHODS: Low achievement in clinical outcomes were defined as the postoperative JOA score at the 2-year follow-up <25 points. Univariate and multiple logistic regression analysis and chi-square automatic interaction detection (CHAID) were used for analysis. RESULTS: The CHAID model for JOA score <25 points showed spontaneous numbness/pain as the first decision node. For the presence of spontaneous numbness/pain, sagittal vertical axis ≥70 mm was selected as the second decision node. Then lateral wedging, ≥6° and pelvic incidence minus lumbar lordosis (PI-LL) ≥30° followed as the third decision node. For the absence of spontaneous numbness/pain, sex and lateral olisthesis, ≥3mm and American Society of Anesthesiologists physical status classification system score were selected as the second and third decision nodes. The sensitivity, specificity, and the positive predictive value of this CHAID model was 65.1, 69.8, and 64.7% respectively. CONCLUSIONS: The CHAID model incorporating basic information and functional and radiologic factors is useful for predicting surgical outcomes.

Radiological assessment of shoulder balance following posterior spinal fusion for thoracic adolescent idiopathic scoliosis.

BACKGROUND: The objective of this study was to evaluate shoulder balance following posterior spinal fusion for thoracic adolescent idiopathic scoliosis (AIS). METHODS: Twenty-four patients (22 females) with thoracic AIS who had undergone posterior fusion with segmental pedicle screws were retrospectively reviewed. The mean follow-up duration was 29 (range, 24-55) months. Fifteen patients had type 1 curves, seven had type 2 curves, and two had type 3 curves according to the Lenke classification. The proximal thoracic (PT) and main thoracic (MT) Cobb angles, percent correction of PT (PTC) and MT (MTC) curves, T1 tilt, and shoulder asymmetry according to radiographic shoulder height (RSH) were measured on preoperative, immediately postoperative, and final follow-up radiographs. The preoperative PT and MT curve side-bending percent correction (PTBC and MTBC) were also measured. The PTC:MTC ratio was employed as an index of PTC and MTC matching. Patients were divided into two groups according to radiographic findings immediately postoperatively: the balanced group (|RSH| <20 mm) and imbalanced group (|RSH| ≥20 mm). The preoperative indices (RSH, PTBC, MTBC, PTC, and MTC), preoperative and postoperative T1 tilt, and PTC:MTC ratio were compared between the two groups. RESULTS: The mean PT and MT were 33.0° and 64.2° preoperatively, 16.1° (50.5%) and 16.8° (74.0%) immediately postoperatively, and 16.9° (49.0%) and 19.2° (70.3%) at final follow-up, respectively. The mean preoperative RSH of -12.3 mm changed to +11.1 mm immediately postoperatively and improved to +5.7 mm at final follow-up. Seventeen patients were "balanced" and seven were "imbalanced" immediately postoperatively. There were significant differences in the PTC (p=0.04), postoperative T1 tilt (p=0.04), and PTC:MTC ratio (p=0.02) between the two groups (Wilcoxon rank-sum test). Only one patient had an imbalanced shoulder at the final follow-up. She had marked shoulder imbalance immediately postoperatively (RSH: +40 mm). CONCLUSIONS: Sufficient correction of PT curves that is matched with correction of MT curves is necessary to prevent postoperative shoulder imbalance. Almost all patients in our series had satisfactory results in terms of shoulder balance at final follow-up, but one patient with marked shoulder imbalance immediately postoperatively may have residual long-term shoulder imbalance.