External Validation of an Artificial-intelligence Model That Automatically Predicts Spinopelvic Parameters

Introduction: SpinePose was developed in 2024 as a novel artificial intelligence (AI) tool to automatically predict spinopelvic parameters with high accuracy and without the need for manual entry. Our published results demonstrated excellent performance comparable to a fellowship-trained spine surgeon. To date, there are no studies that externally validate the performance of AI spinopelvic parameter measurement tools on external data. To assess the generalizability of SpinePose, we report its performance on an external set of heterogeneous x-rays obtained from an outside institution.

Methods: SpinePose was initially trained/validated on 761 sagittal whole-spine scoliosis films from a single institution with expert-level performance on both whole-spine and lumbosacral x-rays. In this study, the existing SpinePose model was tested on a new set of 48 whole-spine x-rays acquired at an out-of-state tertiary academic hospital. Images incorporated both instrumented and non-instrumented patients, and a wide variety of fusion constructs including complex deformity patients. Predicted measures included Sagittal Vertical Axis (SVA), Pelvic Tilt (PT), Pelvic Incidence (PI), Sacral Slope (SS), Lumbar Lordosis (LL), T1-Pelvic Angle (T1PA), and L1-Pelvic Angle (L1PA). Median errors relative to ground truth annotations were calculated to determine the model’s accuracy.

Results: Of the 48 images, 39 (79.6%) contained instrumentation, compared to (58%) in the original SpinePose training set. Median(IQR) parameter errors relative to ground-truth were SVA: [2.1mm (8.9mm), p=0.72], PT: [2.6° (5.0°) , p=0.41], SS: [3.4° (11.6°) , p=0.10], PI: [7.3° (11.8°) , p=0.03], LL: 6.3° (13.6°) , p=0.48], T1PA: [1.9° (4.0°) , p=0.55], and L1PA: [1.2° (3.5°), p=0.54].

Conclusion : SpinePose accurately predicts spinopelvic parameters on a previously unseen external validation cohort. This highlights the generalizability of SpinePose to novel images from other institutions and geographic settings with high accuracy and minimal pre-processing. The implementation of AI tools will help standardize our ability to provide spine care and assist with surgical treatment.