Exploring the accuracy of tooth loss prediction between a clinical periodontal prognostic system and a machine learning prognostic model
Journal of Clinical Periodontology · 2024-10 · 51 (10) · 1333-1341
DOI: 10.1111/jcpe.14023 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Periodontology, online erschienen am 07.08.2024. Verfasst von Pasquale Santamaria und 5 weiteren Autor:innen. Beteiligte Einrichtung: Periodontology Unit, Centre for Host-Microbiome Interactions, Faculty of Dentistry, Oral and Craniofacial Sciences, King's College London, London, UK. Hauptthemen laut MEDLINE: Tooth Loss, Machine Learning. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Aim
The aim of this analysis was to compare a clinical periodontal prognostic system and a developed and externally validated artificial intelligence (AI)‐based model for the prediction of tooth loss in periodontitis patients under supportive periodontal care (SPC) for 10 years. Materials and Methods Clinical and radiographic parameters were analysed to assign tooth prognosis with a tooth prognostic system (TPS) by two calibrated examiners from different clinical centres (London and Pittsburgh). The prediction model was developed on the London dataset. A logistic regression model (LR) and a neural network model (NN) were developed to analyse the data. These models were externally validated on the Pittsburgh dataset. The primary outcome was 10‐year tooth loss in teeth assigned with ‘unfavourable’ prognosis.
Results
A total of 1626 teeth in 69 patients were included in the London cohort (development cohort), while 2792 teeth in 116 patients were included in the Pittsburgh cohort (external validated dataset). While the TPS in the validation cohort exhibited high specificity (99.96%), moderate positive predictive value (PPV = 50.0%) and very low sensitivity (0.85%), the AI‐based model showed moderate specificity (NN = 52.26%, LR = 67.59%), high sensitivity (NN = 98.29%, LR = 91.45%), and high PPV (NN = 89.1%, LR = 88.6%).
Conclusions
AI‐based models showed comparable results with the clinical prediction model, with a better performance in specific prognostic risk categories, confirming AI prediction model as a promising tool for the prediction of tooth loss.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Periodontology Unit, Centre for Host-Microbiome Interactions, Faculty of Dentistry, Oral and Craniofacial Sciences, King's College London, London, UK.
- Department of Clinical and Experimental Medicine, University of Foggia, Foggia, Italy.
- Department of Periodontics and Oral Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, USA.
- Periodontology Unit, Innovative Technologies in Medicine & Dentistry Department, University "G. D'annunzio" of Chieti-Pescara, Chieti, Italy.
ORCID-Profile: Pasquale Santamaria, Giuseppe Troiano, Matteo Serroni, Andrea Ravidà, Luigi Nibali
Zitieren
APA
Santamaria, P., Troiano, G., Serroni, M., Araùjo, T. G., Ravidà, A., & Nibali, L. (2024). Exploring the accuracy of tooth loss prediction between a clinical periodontal prognostic system and a machine learning prognostic model. Journal of Clinical Periodontology, 51(10), 1333-1341. https://doi.org/10.1111/jcpe.14023
Vancouver
Santamaria P, Troiano G, Serroni M, Araùjo TG, Ravidà A, Nibali L. Exploring the accuracy of tooth loss prediction between a clinical periodontal prognostic system and a machine learning prognostic model. Journal of Clinical Periodontology. 2024;51(10):1333-1341. doi:10.1111/jcpe.14023
BibTeX
@article{Santamaria2024,
author = {Santamaria, Pasquale and Troiano, Giuseppe and Serroni, Matteo and Araùjo, Tiago G and Ravidà, Andrea and Nibali, Luigi},
title = {Exploring the accuracy of tooth loss prediction between a clinical periodontal prognostic system and a machine learning prognostic model},
journal = {Journal of Clinical Periodontology},
year = {2024},
volume = {51},
number = {10},
pages = {1333--1341},
doi = {10.1111/jcpe.14023}
}
EUVIMED