Latent-space clustering and feature interpretation in GraphCROC-Encoded periodontal disease, focusing on anterior and posterior bone loss prediction
Sarvagya Sharma, Deepavalli Arumuganainar, Pradeep Kumar Yadalam · 2026
Read Latent-space clustering and feature interpretation in GraphCROC-Encoded periodontal disease, focusing on anterior and posterior bone loss prediction by Sarvagya Sharma, Deepavalli Arumuganainar, Pradeep Kumar Yadalam (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13571138.txt.
Description
Sharma, Arumuganainar, and Yadalam present a 2026 paper on GraphCROC, a graph model for gum disease that predicts bone loss around teeth. Gum disease eats the ligament and bone holding teeth, driven by plaque, immunity, habits, and illnesses like diabetes. Standard charts read clinical and X-ray data apart, missing how teeth relate. Their model treats each tooth as a node in a network.
Two streams encode tooth-level measures and edge-level bone loss, fused by a cross-matching module. Ninety patients trained the system against three rival baselines. Reconstruction error beat them all in early results. The authors also cluster the model's inner space to read which features drive front versus back bone loss.
Catalog record
| CREATOR | Sarvagya Sharma, Deepavalli Arumuganainar, Pradeep Kumar Yadalam |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |