Page 111 - Read Online

Ambati et al. Art Int Surg. 2025;5:53-64 https://dx.doi.org/10.20517/ais.2024.45 Page 57

Table 1. Summary of studies discussed in the preoperative planning subsection, highlighting key advancements in ML applications
for preoperative radiographic and clinical tools
Area of investigation Selected studies
[17] [18]
Utilizing ML clustering methods to identify distinct phenotypes of spinal Chan et al., 2021 ; Ames et al., 2019
pathologies, presentation patterns, and radiographic parameters
[19]
Preoperative counseling based on patient specific factors Ames et al., 2019
Automated segmentation of anatomical structures from patient radiographs Spinal cord: Gros et al., 2019 [20] ; Jamaludin et al., 2017 [21]
and films Vertebral body and discs: Pang et al., 2022 [25] ; Pang et al.,
2021 [26]
[27]
Paraspinal musculature: Wesselink et al., 2022
Building upon segmentation algorithms to identify clinical correlates (e.g., Neurologic motor scores: McCoy et al., 2019 [23]
[24]
neurologic exam, osteoporosis, disc degeneration, spinal stenosis) Thoracolumbar injury classification: Doerr et al., 2022
Osteoporosis and fractures: Zhang et al., 2020 [28] ; Yabu et al.,
[29]
2021
Spinal and foraminal stenosis: Jardon et al., 2023 [30] ; Grob et al.,
[32]
2020
[31]
Lumbar spondylolisthesis: Trinh et al., 2022
Automated spinopelvic parameter calculation Berlin et al., 2023 [33] ; Wu et al., 2018 [34] ; Weng et al., 2019 [35] ;
Korez et al., 2020 [36] ; Galbusera et al., 2019 [37]
ML: Machine learning.
Perhaps the main application of AI in the OR is to guide the next generation of surgical navigation,
which currently relies on intraoperative radiography and the registration between pre- and
intraoperative images. Today’s approaches are limited by radiation exposure to the surgical team and
patient, delays in operative time caused by acquiring such images, differences in patient anatomy between
images acquired in prone and supine positions, and device failure causing navigational inaccuracy.

TM
One promising technology dubbed the Paradigm system (Proprio, Seattle, WA) aims to lessen the need
for intraoperative CT by using an optical imaging device and computer vision algorithms to align the
intraoperative patient with their preoperative imaging, potentially unlocking radiation-free navigation and
calculation of spinal anatomic parameters, which could improve safety and speed . Another competing
[38]
TM
technology, Flash 7D (SeaSpine, Carlsbad, CA), also aims to leverage optical imaging-based navigation
powered by deep learning and computer vision. These technologies are being applied to instrumentation in
[39]
lumbar degenerative disease , pediatric deformity [40,41] , and trauma [42,43] , with potential safety benefits and
reduced need for fluoroscopy.

Augmented or mixed reality, in which the surgeon wears goggles that permit them to view the operative
field with graphic overlays, also leverages devices with the capability of AI-assisted computer vision
[Figure 2]. These approaches are under development in spine surgery and also promise to help visualize
[44]
underlying anatomy to guide pedicle screw placement and to help perform osteotomies. Early research
[45]
[46]
suggests augmented reality (AR)-assisted pedicle screw placement may compare favorably to freehand
techniques in spinal deformity cases and is also being studied for screw placement in workhorse
[47]
approaches such as transforaminal lumbar interbody fusion . Our desire to minimize invasiveness while
[48]
maximizing visualization of critical structures and accuracy of instrumentation necessitates intraoperative
AI to continue making progress [Table 2].
Postoperative prognostication
One of the most common and accessible applications of AI/ML in spine surgery is predicting postoperative
outcomes. National datasets from the NIH, American College of Surgeons, and NeuroPoint Alliance, which
capture clinical and demographic data, metrics of surgical success, patient-reported outcomes, and
complications, can allow clinicians to build models forecasting both perioperative and long-term outcomes