Press Releases

Development of a Machine Learning Tool for Home-Based Assessment of Periodontitis

Published on: March 16, 2024

Alexandria, VA, USA – A study aiming to develop a machine learning (ML) tool that allows individuals to perform periodontal self-assessment at home through simple survey was presented at the 102nd General Session of the IADR, which was held in conjunction with the 53rd Annual Meeting of the American Association for Dental, Oral, and Craniofacial Research and the 48th Annual Meeting of the Canadian Association for Dental Research, on March 13-16, 2024, in New Orleans, LA, USA.

The abstract, “Development of a Machine Learning Tool for Home-Based Assessment of Periodontitis” was presented during the “Innovations in Oral Disease Mechanisms and Diagnostic Techniques” Oral Session that took place on Saturday, March 16, 2024 at 2 p.m. Central Standard Time (UTC-6). 

The study, by Zoe Xiaofang Zhu of Tufts University School of Dental Medicine, Boston, MA, USA, utilized the NHANES database and ML algorithms proficient in handling complex tabular datasets. Extensive data was extracted and classified the individuals aged 30 and over into different stages using 2017 periodontal disease classification. The study constructed 13 categorical- and 14 numerical-features and divided datasets into train/validation/test sets with an 8:1:1 ratio. In model development, the study established a baseline model with Logistic Regression using multinomial-output, then performed Ensemble Methods and Support Vector Machine. 

The baseline model exhibited an overall precision and recall performance above 60%. After models comparation on validation-set, the best-performing-model was selected and evaluated on test-set for real-world application insights. The model demonstrated well-behaved classification performance without overfitting. Feature importance analysis was conducted to select top-features for survey design. 

The study established a proof-of-concept showcasing the predictive capabilities of patient demography, lifestyle, systemic conditions, and oral care habits in determining periodontitis stages, and developed a user-friendly survey tool for individuals with limited access to dental care to self-evaluate and bring the potential periodontal issue to their attention.

 About IADR

 The International Association for Dental, Oral, and Craniofacial Research (IADR) is a nonprofit organization with a mission to drive dental, oral, and craniofacial research for health and well-being worldwide. IADR represents the individual scientists, clinician-scientists, dental professionals, and students based in academic, government, non-profit, and private-sector institutions who share our mission. Learn more at www.iadr.org

About AADOCR 

The American Association for Dental, Oral, and Craniofacial Research (AADOCR) is a nonprofit organization with a mission to drive dental, oral, and craniofacial research to advance health and well-being. AADOCR represents the individual scientists, clinician-scientists, dental professionals, and students based in academic, government, non-profit, and private-sector institutions who share our mission. AADOCR is the largest division of IADR. Learn more at www.aadocr.org.