Page 72 - Read Online

Page 402 Johnson et al. Art Int Surg 2024;4:401-10 https://dx.doi.org/10.20517/ais.2024.40

conducted to visualize the MRI features utilized by the model for accurate classifications.

Results: Of 191 patients undergoing ASD surgery, the demographic and traditional radiographic variables were
collected, and only age was observed to be significantly different between the patients diagnosed with
pseudarthrosis (69.9 ± 10.1 years old) and those without (60.9 ± 19.9), with a t-test P-value of 0.003. The 3D-CNN
demonstrated an average Youden index of 0.49 ± 0.25 on the withheld data, with a P-value of 5.50e-3 compared
to an equivocal null model. Finally, CAM consistently revealed posterior adipose tissue to be most important in
preoperatively predicting pseudarthrosis.

Conclusion: Adipose tissue features in MRI, independent of body mass index (BMI), may be useful for
preoperatively predicting pseudarthrosis. Overall, this work demonstrates the capabilities of raw imaging AI in
spine surgery and can serve as the basis for a deeper biological inquiry into the pathogenesis of pseudarthrosis.

Keywords: Adult spinal deformity, artificial intelligence, deep learning, machine learning, magnetic resonance
imaging, pseudarthrosis

INTRODUCTION
Pseudarthrosis (or nonunion) is defined as the failure of bone to fuse following surgical fixation and is a
common complication of adult spinal deformity (ASD) surgery, with incidence rates ranging from 5%-
[1,2]
35% . Pseudarthrosis is associated with recurrent pain and neurologic symptoms, can be a reason for
reoperation, and can occur with or without rod fracture . Despite its prevalence and contribution to patient
[3]
morbidity, the risk factors for pseudarthrosis are difficult to characterize. A preoperative risk factor is
thought to be age, with multiple studies suggesting that patients over the age of 55 experience higher rates of
[4-6]
pseudarthrosis . Additionally, an intraoperative risk factor is thought to be fusion to the sacrum .
[7]
However, there remains debate in the literature about these risk factors, and few validated tools are available
for the surgeon to preoperatively prognosticate pseudarthrosis occurrence.

Due to the difficulty in prognostication, more advanced artificial intelligence (AI) modeling techniques have
been developed to augment surgical decision workflows for ASD surgery [8-16] . Specifically, Scheer et al.
developed a decision tree model from 82 variables that achieved 91% accuracy in predicting pseudarthrosis
following ASD surgery . This high level of accuracy demonstrates its promise for clinical application. An
[17]
underutilized extension of this framework is to utilize raw imaging data to augment predictive models. Of
interest, AI models that ingest raw imaging can be directly interpreted to gain insight into nuanced patient
characteristics impossible to capture in demographic variables. One imaging modality of high interest is
magnetic resonance imaging (MRI) due to the detailed soft tissue signal captured. Thus, these advanced
imaging models can aid preoperative decision-making, but more importantly, they can provide insight into
the biological variables that may drive pseudarthrosis pathogenesis.

With the above considerations, this work aims to characterize the raw preoperative MRI features that may
predict the occurrence of pseudarthrosis. In a cohort of patients undergoing ASD surgery at the major
academic medical center, we sought to: (1) develop an AI model that utilizes raw preoperative MRI to
predict pseudarthrosis following ASD surgery; and (2) interpret the model with class activation mapping
(CAM) to understand the imaging features used to classify pseudarthrosis.

METHODS
Patient population
The study included a population of 191 patients who underwent ASD surgery at a single institution from