EUVIMEDEUVIMED entdecken
Crossref

AI-driven prediction of irrigant penetration depth in root canal systems: An in vitro study

Meetkumar Dedania

Bioinformation · 31.07.2026 · 22 (7) · 4193-4198

DOI: 10.6026/973206300224193 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformation, online erschienen am 31.07.2026. Verfasst von Meetkumar Dedania.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inadequate irrigant penetration into the apical and lateral extensions of root canal systems remains a major limitation of chemomechanical disinfection, particularly in curved and oval canals. Therefore, it is of interest to develop and validate artificial intelligence (AI) models to predict irrigant penetration depth using canal morphology, preparation size, activation method, irrigant viscosity, needle position and micro-computed tomography-derived anatomical variables from 120 extracted human mandibular premolars. Confocal imaging showed significantly greater penetration with passive ultrasonic activation (724.8 ± 105.7 µm) and laser activated irrigation (781.3 ± 112.4 µm) compared with conventional needle irrigation (412.6 ± 91.5 µm; p < 0.001). The gradient boosting model achieved the highest predictive performance (R² = 0.91, RMSE = 58.4 µm, MAE = 43.7 µm). Thus, data shows that AI based prediction accurately estimated irrigant penetration depth and it may facilitate personalized irrigation strategies based on canal anatomy and activation technique.

Zitieren

APA

Dedania, M. (2026). AI-driven prediction of irrigant penetration depth in root canal systems: An in vitro study. Bioinformation, 22(7), 4193-4198. https://doi.org/10.6026/973206300224193

Vancouver

Dedania M. AI-driven prediction of irrigant penetration depth in root canal systems: An in vitro study. Bioinformation. 2026;22(7):4193-4198. doi:10.6026/973206300224193

BibTeX
@article{Dedania2026,
  author = {Dedania, Meetkumar},
  title = {AI-driven prediction of irrigant penetration depth in root canal systems: An in vitro study},
  journal = {Bioinformation},
  year = {2026},
  volume = {22},
  number = {7},
  pages = {4193--4198},
  doi = {10.6026/973206300224193}
}
Kostenlos starten →