Key result
ChatGPT-3.5 accurately answers ~60% of spinal deformity queries but consistently exceeds target patient reading levels.
Why the study?
High patient volumes limit preoperative counseling for adult spinal deformity surgery, and ChatGPT may serve to supplement patient education.
Does ChatGPT-3.5 provide accurate and readable responses to patient queries regarding adult spinal deformity surgery?
Cross-Sectional (n=19)
Does ChatGPT-3.5 provide accurate and readable responses to patient queries regarding adult spinal deformity surgery?
ChatGPT-3.5 provides mostly accurate answers to common questions about adult spinal deformity surgery, but the responses are written at a reading level too complex for average patient health literacy.
No takes yet. Share an insight, caveat, or question.
May exceed patient literacy despite moderate accuracy; leaves open whether AI can deliver accessible spine surgery information.
Hernandez et al. (2025) conducted a cross-sectional in Adult spinal deformity (ASD) (n=19). ChatGPT-3.5 was evaluated on Response accuracy assessed by spine surgeons and readability using the Flesch-Kincaid Grade Level formula. ChatGPT-3.5 provided excellent accuracy for 59.7% of adult spinal deformity surgery queries, but all responses exceeded the eighth-grade reading level by an average of 5.91 grade levels.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: