An artificial neural network model based on standing lateral radiographs for predicting sitting pelvic tilt in healthy adults

Abstract

BackgroundSpinopelvic motion, the cornerstone of the sagittal balance of the human body, is pivotal in patient-specific total hip arthroplasty.PurposeThis study aims to develop a novel model using back propagation neural network (BPNN) to predict pelvic changes when one sits down, based on standing lateral spinopelvic radiographs.MethodsYoung healthy volunteers were included in the study, 18 spinopelvic parameters were taken, such as pelvic incidence (PI) and so on. First, standing parameters correlated with sitting pelvic tilt (PT) and sacral slope (SS) were identified via Pearson correlation. Then, with these parameters as inputs and sitting PT and SS as outputs, the BPNN prediction network was established. Finally, the prediction results were evaluated by relative error (RE), prediction accuracy (PA), and normalized root mean squared error (NRMSE).ResultsThe study included 145 volunteers of 23.1 ± 2.3 years old (M:F = 51:94). Pearson analysis revealed sitting PT was correlated with six standing measurements and sitting SS with five. The best BPNN model achieved 78.48% and 77.54% accuracy in predicting PT and SS, respectively; As for PI, a constant for pelvic morphology, it was 95.99%.DiscussionIn this study, the BPNN model yielded desirable accuracy in predicting sitting spinopelvic parameters, which provides new insights and tools for characterizing spinopelvic changes throughout the motion cycle.

Sagittal balance in sitting and standing positions: A systematic review of radiographic measures

“…We gathered radiographic data from the literature that presented normal spinal measurements [ 3 , [36] , [37] , [38] , 40 , 42 , [44] , [45] , [46] , [47] ]. Ten articles were found to publish sitting and standing radiographic measures with a total sample size of 1066 subjects.…”

“…When sitting in a natural position, a vague C shape is formed, which can significantly affect the values of various measures [ 18 ]. Two studies indicated the use of a natural sitting position [ 44 , 46 ], while the remaining indicated an erect sitting position [ 3 , [36] , [37] , [38] , 40 , 42 , 45 , 47 ]. This was not controlled for in our systematic review and should be a noted limitation.…”

“…Studies in healthy populations are now emerging that show significant changes in measures between sitting and standing radiograph markers that may even be influenced by age, gender, and other modifications in body position [ 3 , 12 , 17 , 20 , [36] , [37] , [38] , [39] , [40] ]. Additionally, work is being performed in the artificial neural network space to predict sitting measures based on standing radiographs to inform surgical correction [ [41] , [42] , [43] ]. Therefore, the goal of this review is to understand the literature discussing sitting radiographs to be able to create a more informed approach to evaluating surgical goals.…”