Skip to content

Artificial Intelligence Versus Maunal Planning in Robot Assisted Spinal Surgery

Artificial Intelligence Versus Manual Planning in Patients Undergoing Robot-assisted Pedicle Screw Internal Fixation: a Prospective Controlled Study

Status
Not yet recruiting
Phases
NA
Study type
Interventional
Source
ClinicalTrials.gov
Registry ID
NCT06416631
Enrollment
100
Registered
2024-05-16
Start date
2024-05-25
Completion date
2026-05-01
Last updated
2024-05-16

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Surgery

Brief summary

The goal of this clinical trial is to learn if the artificial intelligence technology helps to improve the efficiency in robot assited spinal surgery. The main questions it aims to answer are: Does the AI technology shorter the mannual planning time of screw trajectories? Does the AI technology affect the surgical accuracy? Researchers will compare the artificial intelligence technology to the conventional mannual planning in robotic surgery. Participants who met inclusion criteria and do not have any exclusion criterion will be randomized to artificial intelligence or mannual planning group.

Detailed description

Study design: multicenter, non-inferiority, open-label, randomized controlled trial in patients undergoing robotic spinal surgery. Monitoring: Monitoring of patient's safety and effectiveness data is performed by a designated independent Data Safety and Monitoring Board (DSMB). The DSMB watches over the ethics of conducting the study in accordance with the Declaration of Helsinki. Sample Size Calculation: Group size calculation is focused on demonstrating non-inferiority. Assuming that the percentage of clinically acceptable screws would be 90% in the artificial intelligence planning group and 95% in the manual planning group, with a non-inferiority margin of 10% and a one-sided significance level of 2.5%, we calculated that a sample of 79 screws per treatment group would give the trial approximately 95% power to show noninferiority of artificial intelligence planning group to manual planning group with regard to the primary end point.

Interventions

PROCEDUREartificial intelligence based screw planning

artificial intelligence technology helps to plan screws in robot assisted spinal surgery

PROCEDUREmanually screw planning

the screw trajcetories are manually planned

Sponsors

Beijing Jishuitan Hospital
Lead SponsorOTHER

Study design

Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
TREATMENT
Masking
NONE

Eligibility

Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
Yes

Inclusion criteria

* Admission to one of the participating centers; * Need for and start of robotic spinal surgery * Patients had complete medical records and imaging data;

Exclusion criteria

* Age less than 18 years; * Patients with severe comorbidities; * Patients diagnosed with tumor diseases; * Inability to carry out the intervention (mental of physical conditions that limited participation); * Patients with morbid obesity (body mass index \> 40); * Missing medical records and imaging data; * Patients with suspected or confirmed pregnancy; * Patients participating in another RCT with the same clinical endpoint, or interventions possibly compromising the primary outcome; * No informed consent.

Design outcomes

Primary

MeasureTime frameDescription
The accuracy of screw positioning or placement1 monthaccording to the Gertzbein and Robbins scale, including grade A (screw was completely within the pedicle), grade B (pedicle cortical breach \<2 mm), grade C (pedicle cortical breach \<4 mm), grade D (pedicle cortical breach \<6 mm), and grade E (pedicle cortical breach \>6 mm). Grade A + B were considered clinically acceptable. The percentage of clinically acceptable screws was recorded.

Secondary

MeasureTime frameDescription
The planning time1 dayTime from start to finish of planning
postoperative complication3 monthNerve injury, epidural hematoma, and infection

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026