Correlation between peri-implant bone mineral density and primary implant stability based on artificial intelligence...

Area of Science:

• Biomaterials Science
• Dental Implantology
• Artificial Intelligence in Medicine

Background:

• Current bone mineral density (BMD) classifications for dental implants are often too broad, overlooking localized variations.
• Accurate assessment of peri-implant BMD is crucial for predicting primary implant stability.
• Existing methods may not sufficiently capture the nuanced BMD distribution around implant sites.

Purpose of the Study:

• To investigate the correlation between peri-implant bone mineral density (BMD) and primary dental implant stability.
• To evaluate a novel artificial intelligence (AI)-based BMD grading system for assessing localized BMD around implants.
• To determine if AI-derived bone mineral density coefficients (BMDC) can predict implant stability quotient (ISQ) and insertion torque value (ITV).

Main Methods:

• Utilized a new AI-based grading system to analyze BMD distribution in the implant sites of 49 patients.
• Calculated bone mineral density coefficients (BMDC) for coronal, middle, and apical regions using model and image overlap technology.
• Recorded implant stability quotient (ISQ) and insertion torque value (ITV) post-implantation.

Main Results:

• A significant positive correlation was found between BMDC and ISQ in the coronal, middle, and total implant regions (P < 0.05).
• No significant correlation was observed between BMDC and ISQ in the apical region (P > 0.05).
• BMDC values were significantly higher in implant sites with greater insertion torque values (ITV) (P < 0.05).

Conclusions:

• The AI-based BMD grading system accurately reflects BMD distribution around dental implants.
• AI-derived BMDC provides a reliable benchmark for predicting primary implant stability, particularly in coronal and middle regions.
• This AI approach enhances the assessment of bone quality for improved dental implant success rates.