Functional assessment using 3D movement analysis can better predict health-related quality of life outcomes in patients with adult spinal deformity: a machine learning approach.

Introduction: Adult spinal deformity (ASD) is classically evaluated by health-related quality of life (HRQoL) questionnaires and static radiographic spino-pelvic and global alignment parameters. Recently, 3D movement analysis (3DMA) was used for functional assessment of ASD to objectively quantify patient's independence during daily life activities. The aim of this study was to determine the role of both static and functional assessments in the prediction of HRQoL outcomes using machine learning methods. Methods: ASD patients and controls underwent full-body biplanar low-dose x-rays with 3D reconstruction of skeletal segment as well as 3DMA of gait and filled HRQoL questionnaires: SF-36 physical and mental components (PCS&MCS), Oswestry Disability Index (ODI), Beck's Depression Inventory (BDI), and visual analog scale (VAS) for pain. A random forest machine learning (ML) model was used to predict HRQoL outcomes based on three simulations: (1) radiographic, (2) kinematic, (3) both radiographic and kinematic parameters. Accuracy of prediction and RMSE of the model were evaluated using 10-fold cross validation in each simulation and compared between simulations. The model was also used to investigate the possibility of predicting HRQoL outcomes in ASD after treatment. Results: In total, 173 primary ASD and 57 controls were enrolled; 30 ASD were followed-up after surgical or medical treatment. The first ML simulation had a median accuracy of 83.4%. The second simulation had a median accuracy of 84.7%. The third simulation had a median accuracy of 87%. Simulations 2 and 3 had comparable accuracies of prediction for all HRQoL outcomes and higher predictions compared to Simulation 1 (i.e., accuracy for PCS = 85 ± 5 vs. 88.4 ± 4 and 89.7% ± 4%, for MCS = 83.7 ± 8.3 vs. 86.3 ± 5.6 and 87.7% ± 6.8% for simulations 1, 2 and 3 resp., p < 0.05). Similar results were reported when the 3 simulations were tested on ASD after treatment. Discussion: This study showed that kinematic parameters can better predict HRQoL outcomes than stand-alone classical radiographic parameters, not only for physical but also for mental scores. Moreover, 3DMA was shown to be a good predictive of HRQoL outcomes for ASD follow-up after medical or surgical treatment. Thus, the assessment of ASD patients should no longer rely on radiographs alone but on movement analysis as well.

Assessment of the axial plane deformity in subjects with adolescent idiopathic scoliosis and its relationship to the frontal and sagittal planes.

PURPOSE: Investigate the axial plane deformity in the scoliotic segment and its relationship to the deformity in the frontal and sagittal planes. METHODS: Two hundred subjects with AIS (Cobb ≥ 20°) underwent low dose biplanar X-rays with 3D reconstruction of the spine and pelvis. All structural curves were considered and were distributed as follows: 142 thoracic (T), 70 thoracolumbar (TL), and 47 lumbar curves (L). Common 3D spino-pelvic and scoliosis parameters were collected such as: frontal Cobb; torsion index (TI); hypokyphosis/lordosis index (HI). Parameters were compared between each type of curvature and correlations were investigated between the 3 planes. RESULTS: Frontal Cobb was higher in all T (45 ± 19°) and TL (41 ± 15°) curves compared to L curves (35 ± 14°, p = 0.004). TI was higher in T curves when compared to TL and L curves (TI: 15 ± 8°, 9 ± 6°, 7 ± 5°, p < 0.001). HI was similar between curve types. T curves showed significant correlations between the 3 planes: Cobb vs. TI (r = 0.76), Cobb vs. HI (r = - 0.54) and HI vs. TI (r = - 0.42). The axial plane deformity was related to the frontal deformity and the type of curvature (adjusted-R2 = 0.6). CONCLUSION: Beside showing the most severe deformity frontally and axially compared to TL and L curves, the T curves showed strong correlations between the 3 planes of the deformity. Moreover, this study showed that the axial plane deformity cannot be fully determined by the frontal and sagittal deformities, which highlights the importance of 3D assessment in the setting of AIS.

A Novel Classification of 3D Rib Cage Deformity in Subjects With Adolescent Idiopathic Scoliosis.

STUDY DESIGN: This was a multicentric cross-sectional descriptive study. OBJECTIVE: To analyze patterns of 3D rib cage deformity in subjects with adolescent idiopathic scoliosis (AIS) and their relationship with the spinal deformity. SUMMARY OF BACKGROUND DATA: Subjects with AIS present with rib cage deformity that can affect respiratory functions. The 3D rib cage deformities in AIS and their relationship to the spinal deformity are still unelucidated. METHODS: A total of 200 AIS and 71 controls underwent low-dose biplanar x-rays and had their spine and rib cage reconstructed in 3-dimensional (D). Classic spinopelvic parameters were calculated in 3D and: rib cage gibbosity, thickness, width, volume and volumetric spinal penetration index (VSPI). Subjects with AIS were classified as: group I with mild rib cage deformity (n=88), group II with severe rib cage deformity (n=112) subgrouped into IIa (high gibbosity, n=48), IIb (high VSPI, n=48), and IIc (both high gibbosity and VSPI, n=16). RESULTS: Groups IIa and IIb had a higher Cobb angle (33 vs. 54 degrees and 46 degrees, respectively) and torsion index (11 vs. 14 degrees and 13 degrees, respectively) than group I. Group IIb showed more severe hypokyphosis (IIb=21 degrees; IIa=33 degrees; I=36 degrees; control=42 degrees) with a reduced rib cage volume (IIb=4731 cm3; IIa=4985 cm3; I=5257 cm3; control=5254 cm3) and thickness (IIb=135 mm; IIa=148 mm; I=144 mm; control=144 mm). Group IIa showed an increasingly large local gibbosity descending from proximal to distal levels and did not follow the axial rotation of the spine. Group IIc showed characteristics of both groups IIa and IIb. CONCLUSIONS: This new classification of 3D rib cage deformity in AIS shows that the management of cases with high VSPI (groups IIb and IIc) should focus on restoring as much kyphosis as possible to avoid respiratory repercussions. Treatment indications in groups I and IIa would follow the consensual basic principles reported in the literature regarding bracing and surgery.