AR navigation for thoracolumbar pedicle screws: 150-patient randomized trial reports 98.0% vs 91.7% accuracy compared with CT-guided freehand
Source: Orthopaedic Surgery·Published: 2025
Authors: Ma Y, Wu J, Dong Y, Tang H, Ma X·DOI: 10.1111/os.70097Open Access
Key table: Table 4 — Group comparison of pedicle screw placement accuracy (98.0% AR vs 91.7% freehand), excellent-plus-good rates, average fluoroscopy exposures per screw, and mean time per screw. View in source
Bottom line: Augmented reality surgical navigation produced 98.0% excellent-grade pedicle screw placement (344 of 351 screws) versus 91.7% with CT-guided freehand (319 of 348 screws, p < 0.05). Average fluoroscopy use dropped from 13.25 to 7.29 exposures per screw. Interpret alongside the disclosed manufacturer affiliation.
What the study did
One hundred fifty patients requiring thoracolumbar pedicle screw fixation were enrolled across three Chinese centers and randomized 1:1 (single-blind) to AR-guided pedicle screw placement or CT-guided conventional freehand placement. The AR system (developed by Shanghai Linyan Medical Technology) overlaid real-time high-resolution imaging with virtual vertebral models to guide screw trajectories. Primary outcome was screw placement accuracy graded by the Gertzbein-Robbins classification on post-operative CT. Secondary outcomes included fluoroscopy exposures, average time per screw, and adverse events. The trial was registered and IRB-approved (Changhai Hospital, Second Military Medical University).
What they found
A total of 699 pedicle screws were placed (351 AR, 348 control). The AR-guided group achieved an excellent placement rate of 98.0% (344 of 351 screws), significantly higher than the 91.7% rate (319 of 348 screws) in the CT-guided freehand group (p < 0.05). Per protocol analysis showed excellent-plus-good rates of 99.1% versus 91.7%. Intraoperative fluoroscopy exposures per screw averaged 7.29 ± 2.90 in the AR group versus 13.25 ± 6.02 in the control group (p < 0.05). No significant difference was observed in serious adverse events.
Why it matters for orthopedic practice
Pedicle screw malposition is a primary driver of neurovascular injury, revision surgery, and litigation in spine practice. A 6.3 percentage point gain in excellent-grade placement, validated on CT, is clinically meaningful at the level of an individual screw and compounds across multi-level constructs. The nearly halved fluoroscopy burden has direct radiation-safety implications for the surgical team over a career of exposure. For spine programs evaluating navigation platforms, this trial provides a rare prospective randomized benchmark rather than a retrospective cohort.
Limitations
Co-author Yanlong Dong is affiliated with Shanghai Linyan Medical Technology, the company that developed the AR navigation system, and this represents a disclosed conflict of interest that readers should weigh when interpreting the effect size. All three participating centers are in China, limiting cross-regional generalizability. The comparator was CT-guided freehand rather than other commercially available navigation platforms, so the relative performance against O-arm, StealthStation, or robotic systems remains unknown. Follow-up was limited to the immediate post-operative period and did not include long-term clinical outcomes such as fusion rates or reoperation.
Ma Y, Wu J, Dong Y, Tang H, Ma X. Augmented reality navigation system enhances the accuracy of spinal surgery pedicle screw placement. Orthop Surg. 2025. doi:10.1111/os.70097
Publishing AI research in orthopedics?
OSCRSJ accepts case reports and series on novel AI-assisted diagnoses and surgical planning. Free to publish in 2026.
Submit a manuscriptOSCRSJ News items are editorial summaries for educational purposes. They are not clinical recommendations, endorsements, or substitutes for the primary literature. Always consult the source paper and applicable specialty-society guidelines before changing practice.