Title

Artificial intelligence prediction of force degradation in orthodontic elastics under simulated oral conditions

Authors

Akshay Gupta¹, Gouri R. Reddy²,*, Deepankar Bhatnagar³, Anand A. Tripathi^4, Sumeet Wasudeo Ghonmode⁵ & Taseer Bashir⁶

Affiliation

¹Department of Orthodontics & Dentofacial Orthopedics, Indira Gandhi Government Dental College, Amphalla, Jammu, India; ²Department of Dentistry, Shri Atal Bihari Vajpayee Medical College and Research Institute, Bengaluru,India; ³Department of Orthodontics and Dentofacial Orthopedics, MM College of Dental Sciences and Research, MMDU, Mullana, India; ⁴Department of Orthodontics and Dentofacial Orthopaedics, Aditya Dental College and Hospital, Beed, Maharashtra, India; ⁵Department of Orthodontics & Dentofacial Orthopedics, Government Dental College and Hospital, CST, Mumbai, India; ⁶Department of Oral Medicine and Radiology, Batterjee Medical College, Jeddah, Saudi Arabia; *Corresponding author

Email

Akshay Gupta - E-mail: anand.tripathi86@gmail.com
Gouri R. Reddy- E-mail: dr.gourireddy@gmail.com
Deepankar Bhatnagar - E-mail: deepankarbhatnagar101@gmail.com
Anand A. Tripathi - E-mail: tripathi86@gmail.com
Wasudeo Ghonmode - E-mail: sumeet_ghonmode@yahoo.com
Taseer Bashir - E-mail: taseer.bashir@bmc.edu.sa

Article Type

Research Article

Date

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

Abstract

Orthodontic elastics lose force rapidly in the oral environment and clinicians commonly prescribe replacement intervals without individualized prediction of residual force. Therefore, it is of interest to assess the whether artificial intelligence could predict force degradation of latex and non-latex intermaxillary elastics exposed to simulated saliva, pH variation and thermal cycling. A total of 180 elastics were stretched to three times their internal diameter and tested at baseline, 1, 6, 12, 24 and 48 hours using a universal testing machine, while environmental and image-derived features were used for machine-learning analysis. Mean force loss at 24 hours was greater in latex elastics under acidic conditions than in non-latex elastics in neutral saliva (43.6 ± 6.8% vs 31.4 ± 5.9%; p<0.001) and the random forest model predicted residual force with an RČ of 0.91 and a mean absolute error of 8.7g. Thus, artificial intelligence accurately predicted orthodontic elastic force degradation under simulated oral conditions and may assist evidence-based selection of replacement intervals.

Keywords

Orthodontic elastics, force degradation, artificial intelligence (AI), latex, non-latex, simulated saliva, machine learning (ML)

Citation

Gupta et al. Bioinformation 22(8): 5507-5511 (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.