HOME   |    PDF   |   


Title

Artificial intelligence–assisted prediction of success in cortical and basal implant therapy: A comparative study

 

Authors

Dipanjan Das 1, Sachin Dev 1,*, Chayanica Midha 1, Rannbir Sachdeva 2, Ashish Sethi 3 & Harmanpreet Kaur 3

 

Affiliation

1Department of Oral & Maxillofacial Surgery, Faculty of Dental Sciences, PDM University, Sector 3A, Sarai Aurangabad, Bahadurgarh, Haryana, India; 2Department of Computer Engineering, Mukesh Patel School of Technology Management & Engineering, Mumbai, Maharashtra, India; 3Department of Periodontology, Swami Devi Dayal Dental College & Hospital, Barwala, Panchkula, Haryana, India; *Corresponding author

 

Email

Dipanjan Das - E-mail: dasdipanjan176@gmail.com
Sachin Dev - E-mail: hod.omfspdmu@gmail.com
Chayanica Midha - E-mail: chayanicamidha.omfs@gmail.com
Rannbir Sachdeva - E-mail: rannbir.healer@gmail.com
Ashish Sethi - E-mail: drsethiashish@gmail.com
Harmanpreet Kaur - E-mail: dr.harmanpreet99@gmail.com
 

Article Type

Research Article

 

Date

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

 

Abstract

Basal and cortical implants enable immediate functional loading in severely resorbed ridges, but accurate prediction of treatment success remains a clinical challenge. Therefore, it is of interest to develop and validate the logistic regression, random forest and extreme gradient boosting (XGBoost) models using clinical, radiographic and implant-related data from 240 implants placed in 96 patients, with 12-month clinical success as the primary outcome. The random forest model demonstrated the highest predictive performance (AUC 0.89), outperforming XGBoost (AUC 0.85) and logistic regression (AUC 0.79), while bone density, insertion torque, implant length and smoking status were the strongest predictors of success. Overall implant success at 12 months was 94.2%, confirming favourable outcomes for immediate-loading cortical and basal implant therapy. Thus, data shows that AI-based predictive models can improve personalised treatment planning and preoperative risk stratification for cortical and basal implant rehabilitation.

 

Keywords

Artificial intelligence (AI), basal implant, cortical implant, machine learning (ML), osseointegration, treatment outcome

 

Citation

Das et al. Bioinformation 22(10): 6468-6472 (2026)

 

Edited by

Ritik Kashwani

 

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.