Discriminant functional analysis of sexual dimorphism and stature using odontometric parameters: A cross-sectional study
Bioinformation · 31.10.2026 · 22 (10) · 6984-6989
DOI: 10.6026/973206300226984 ↗Kurz gefasst
Querschnittstudie in der Zeitschrift Bioinformation, online erschienen am 31.10.2026. Verfasst von Gaushini Ramuvel.
Abstract (Originalsprache)
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 showed 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.
Zitieren
APA
Ramuvel, G. (2026). Discriminant functional analysis of sexual dimorphism and stature using odontometric parameters: A cross-sectional study. Bioinformation, 22(10), 6984-6989. https://doi.org/10.6026/973206300226984
Vancouver
Ramuvel G. Discriminant functional analysis of sexual dimorphism and stature using odontometric parameters: A cross-sectional study. Bioinformation. 2026;22(10):6984-6989. doi:10.6026/973206300226984
BibTeX
@article{Ramuvel2026,
author = {Ramuvel, Gaushini},
title = {Discriminant functional analysis of sexual dimorphism and stature using odontometric parameters: A cross-sectional study},
journal = {Bioinformation},
year = {2026},
volume = {22},
number = {10},
pages = {6984--6989},
doi = {10.6026/973206300226984}
}
EUVIMED