AI Science Tracker
EN

Integrating multi-dimensional prosthodontic features into an interpretable XGBoost framework for cross-sectional diagnostic classification of peri-implant diseases.

Not stated in the abstract reviewed · 28 Oct 2026 · medicine

Discovery

Integrating multi-dimensional prosthodontic features into an interpretable XGBoost framework for cross-sectional diagnostic classification of peri-implant diseases.

Source check: Source checked. Not independent scientific confirmation.

Finding: An interpretable XGBoost model classified peri-implant disease from clinical and prosthodontic features. A patient-split internal holdout reported 78.9% accuracy and AUC 0.821; the source notes external validation is needed and discusses label-leakage concerns.

Technology: XGBoost classifier with interpretability analysis

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
XGBoost classifier with interpretability analysis
Test and result
Retrospective patient-split holdout evaluation reported 78.9% accuracy and AUC 0.821.
Limitation / still unknown
No external validation; retrospective classification does not establish clinical utility, and label leakage is an explicit limitation.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2026.1883041/full

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.