Title

AI versus conventional methods for predicting implant stability using simulated bone models: An in vitro study

Authors

Aditi Bhatnagar¹, Mrinalini Agarwal², Tehseen Desai³, Tarang Mehta⁴,*, Gunjan Gupta⁵ & Shivendra Rajput⁵

Affiliation

¹Department of Oral and Maxillofacial Surgery, Karnavati School of Dentistry, Gandhinagar, India; ²Department of Periodontology & Implantology, Maharana, Pratap College of Dentistry and Research Centre, Gwalior, Madhya Pradesh, India; ³Department of Oral and Maxillofacial Surgery, Yogita Dental College and Hospital, Khed, Maharashtra, India; ⁴Department of Oral & Maxillofacial Pathology and Oral Microbiology, K M Shah Dental College & Hospital Sumandeep Vidyapeeth (Deemed to be University) Vadodara, Gujarat, India; ⁵Department of Periodontology, Maharana Pratap college of Dentistry and Research Centre, Gwalior, Madhya Pradesh, India; *Corresponding author

Email

Aditi Bhatnagar - E-mail: tre_2@yahoo.co.in

Mrinalini Agarwal - E-mail: mrinaliniagarwal1@gmail.com

Tehseen Desai - E-mail: tehseen7218@gmail.com

Tarang Mehta - E-mail: tarangmehta111@gmail.com

Gunjan Gupta - E-mail: drgunjan_arun@yahoo.co.in

Shivendra Rajput - E-mail: shivendra23rajput@gmail.com

Article Type

Research Article

Date

Received July 1, 2026; Revised July 31, 2026; Accepted July 31, 2026, Published July 31, 2026

Abstract

Accurate prediction of primary implant stability remains challenging because conventional chairside methods may provide inconsistent results when used individually. Therefore, it is of interest to compare the AI-based multimodal model with insertion torque, resonance frequency analysis and Periotest measurements in 120 implants placed in D2, D3 and D4 simulated bone blocks. Peak pull-out resistance and cyclic displacement served as reference standards following standardized vertical and oblique loading. The AI model achieved higher accuracy (91.7% vs. 77.8%) and lower prediction error (RMSE 3.8 vs. 7.1), with the greatest improvement in low-density bone models (p<0.001). Thus, data shows that multimodal AI prediction may provide a more objective estimate of implant stability and support pre-loading decisions following clinical validation.

Keywords

Artificial intelligence (AI), dental implant, implant stability, resonance frequency analysis, insertion torque, in vitro study

Citation

Bhatnagar et al. Bioinformation 22(7): 4159-4164 (2026)

Edited by

Hiroj Bagde

ISSN

0973-2063

Publisher

Biomedical Informatics

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.