DESIGN: This was a narrative review.
PURPOSE: Summarize artificial intelligence (AI) fundamentals as well as current and potential future uses in spine surgery.
SUMMARY OF BACKGROUND DATA: Although considered futuristic, the field of AI has already had a profound impact on many industries, including health care. Its ability to recognize patterns and self-correct to improve over time mimics human cognitive function, but on a much larger scale.
METHODS: Review of literature on AI fundamentals and uses in spine pathology.
RESULTS: Machine learning (ML), a subset of AI, increases in hierarchy of complexity from classic ML to unsupervised ML to deep leaning, where Language Processing and Computer Vision are possible. AI-based tools have been developed to segment spinal structures, acquire basic spinal measurements, and even identify pathology such as tumor or degeneration. AI algorithms could have use in guiding clinical management through treatment selection, patient-specific prognostication, and even has the potential to power neuroprosthetic devices after spinal cord injury.
CONCLUSION: While the use of AI has pitfalls and should be adopted with caution, future use is promising in the field of spine surgery and medicine as a whole.
LEVEL OF EVIDENCE: Level IV.
Read the article: PubMed · Publisher (DOI)