Page 115 - Read Online

Ambati et al. Art Int Surg. 2025;5:53-64 https://dx.doi.org/10.20517/ais.2024.45 Page 61

performances. We propose that the standards for multi-center validation and held-out validation and test
sets for quantifying performance - standards commonly applied across AI applications - be rigorously
applied in AI tools for spine surgery to ensure that published models have the best chance for successful
clinical translation.

Future directions
While challenges remain in further integrating AI and ML technologies into spine surgery practice, these
technologies have already made an impact on clinical care, operative planning, and procedures in the
OR. For AI technologies to continue to develop, the field of spine surgery must make a concerted
effort to collect high-quality data in the form of de-identified or HIPAA-compliant large multi-center
databases and registries, as these data can be used to fine-tune existing and develop new AI
technologies. Future surgical planning and prognostication models should leverage a wide variety of data
sources for model training, ranging from demographic and clinical data to patient radiographs and free text
from medical records. In addition, surgeons should work closely with industry and academic partners to
create robotic and augmented/mixed reality tools. As with all new technology, these efforts will require
careful oversight, fine-tuning, and comparison to existing best practices. Should spine surgery as a field
successfully apply AI models and tools, our patients stand to benefit the most through patient-specific, data-
driven surgical planning tools, increased surgical efficiency, and more accurate short and long-term
prognostication.

CONCLUSION
This narrative review highlights a selection of current developments in AI for spine surgery. Despite the
challenges discussed in the previous section, AI is already beginning to change how we practice spine
surgery. By understanding the current landscape of AI/ML tools across stages of development and clinical
scenarios ranging from pre- to intra- and postoperative contexts, we may target our efforts toward
incorporating the methods most pertinent to the challenges in our practice. One can easily imagine a near
future where AI assists in planning surgical approaches and counseling patients, integrates into
intraoperative imaging and navigation systems to enhance anatomical recognition and guide
instrumentation, and helps avoid and manage postoperative complications. By highlighting the path
forward, we identify strategies that innovation-minded spine surgeons can adopt to expedite the
development and clinical translation of these models for the benefit of our patients.

DECLARATIONS
Authors’ contributions
Made substantial contributions to the drafting of the article: Ambati VS, Saggi S, Alan N
Made substantial contributions to background research and review of existing literature: Ambati VS, Saggi
S, Dada A
Led the review article (supervising/senior author): Alan N

Availability of data and materials
Not applicable.

Financial support and sponsorship
None.

Conflicts of interest
Alan N serves as a consultant for Globus, Stryker, and Depuy Synthes. The other authors declared that there
are no conflicts of interest.