Machine Learning‐Based Model for Predicting Short‐ and Long‐Term Growth in Untreated Class III Malocclusion
Maria Denisa Statie, Michele Nieri, Valentina Rutili, Lorenzo Buffoni, Lorenzo Chicchi, Pietro Auconi, Veronica Giuntini, James A McNamara, Lorenzo Franchi · 2026
Read Machine Learning‐Based Model for Predicting Short‐ and Long‐Term Growth in Untreated Class III Malocclusion by Maria Denisa Statie, Michele Nieri, Valentina Rutili, Lorenzo Buffoni, Lorenzo Chicchi, Pietro Auconi, Veronica Giuntini, James A McNamara, Lorenzo Franchi (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-13543202.txt.
Description
Maria Denisa Statie and co-authors train a machine learning model to forecast jaw growth in untreated bite problems, in a 2026 study. The condition, class III malocclusion, pushes the lower jaw forward. Knowing how it will grow guides treatment timing. The team followed one hundred forty-four untreated subjects over time. Head X-rays were taken at several points. Sixteen landmarks were marked on each film as coordinates.
A graph neural network learned the growth patterns. Most of the sample trained the model, and the rest tested it. Short-term forecasts covered sixteen test subjects. Long-term forecasts covered thirteen. Most landmarks were predicted well. Points on the lower jaw proved hardest. Their average errors ran from about two to four and a half millimeters. The front and back jaw points strayed most. The authors say the model is accurate overall. Jaw points, though, need better handling before clinical trust.
Catalog record
| CREATOR | Maria Denisa Statie, Michele Nieri, Valentina Rutili, Lorenzo Buffoni, Lorenzo Chicchi, Pietro Auconi, Veronica Giuntini, James A McNamara, Lorenzo Franchi |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |