Usefulness of an artificial intelligence-assisted indirect bonding method for optimizing orthodontic bracket...

Area of Science:

• Orthodontics
• Dental Technology
• Artificial Intelligence in Medicine

Background:

• Indirect bonding (IDB) is a crucial orthodontic technique for precise bracket placement.
• Traditional IDB methods have limitations in accuracy, particularly concerning bracket angulation.
• Artificial intelligence (AI) offers potential for enhancing digital workflows in orthodontics.

Purpose of the Study:

• To compare the bracket positioning accuracy between traditional and AI-assisted digital indirect bonding (IDB) methods.
• To evaluate the effectiveness of AI in optimizing orthodontic bracket positioning.
• To assess the clinical utility of AI-assisted digital IDB for orthodontists.

Main Methods:

• Twenty-five clinicians performed bracket positioning using both traditional and AI-assisted digital IDB.
• Bracket positioning accuracy was quantified via digital superimposition and compared to an optimal setup.
• Statistical analysis, including one-tailed t-tests, evaluated differences against predefined accuracy limits (0.5 mm linear, 2° tip).

Main Results:

• Both methods achieved mean linear bracket positioning differences below the 0.5 mm limit (0.28 mm mesial-distal, 0.32 mm occlusal-gingival).
• Tip angulation differences averaged 3.4°, exceeding the 2° limit, with the digital method showing higher accuracy.
• Statistically significant differences were observed for tip positioning compared to the optimal setup for both methods, but not for linear dimensions.

Conclusions:

• Traditional and AI-assisted digital IDB methods offer comparable accuracy in linear bracket positioning.
• AI shows promise for enhancing bracket angulation accuracy in digital IDB workflows.
• Clinicians using traditional IDB can transition to AI-assisted digital IDB without compromising bracket positioning accuracy.