Development of a periodontitis risk assessment model for primary care providers in an interdisciplinary setting

• Published in: Technology and health care Vol. 28; no. 2; pp. 143 - 154
• Main Authors: Shimpi, Neel, McRoy, Susan, Zhao, Huimin, Wu, Min, Acharya, Amit
• Format: Journal Article
• Language: English
• Published: Netherlands IOS Press BV 01.01.2020
• Subjects: Adult; Age Factors; Aged; Aged, 80 and over; Algorithms; Artificial Intelligence; Artificial neural networks; Bayes Theorem; Bayesian analysis; Blood Pressure; Body Weights and Measures; Comorbidity; Decision support systems; Decision Support Systems, Clinical - organization & administration; Decision Support Systems, Clinical - standards; Decision trees; Female; Gum disease; Health care; Humans; Learning algorithms; Learning theory; Lipids - blood; Logistic Models; Machine learning; Male; Middle Aged; Neural networks; Neural Networks, Computer; Oral Hygiene - standards; Periodontitis; Periodontitis - diagnosis; Prediction models; Primary Health Care - organization & administration; Productivity; Public health; Quality of life; Retrospective Studies; Risk assessment; Sensitivity; Sex Factors; Socioeconomic Factors; Support Vector Machine; Support vector machines; Young Adult; decision support systems clinical; health information systems; electronic health records; risk assessment tools; Data mining; periodontitis
• ISSN: 0928-7329; 1878-7401
• DOI: 10.3233/THC-191642

Periodontitis (PD), a form of gum disease, is a major public health concern as it is globally prevalent and harms both individual quality of life and economic productivity. Global cost in lost productivity is estimated at US$54 billion annually. Moreover, current PD assessment applies only after the damage has already occurred. This study proposes and tests a new PD risk assessment model applicable at point-of-care, using supervised machine learning methods. We compare the performance of five algorithms using retrospective clinical data: Naïve Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Decision Tree (DT). DT and ANN demonstrated higher accuracy in classifying the patients with high or low PD risk as compared to NB, LR and SVM. The resultant model with DT showed a sensitivity of 87.08% (95% CI 84.12% to 89.76%) and specificity of 93.5% (95% CI 91% to 95.49%). A predictive model with high sensitivity and specificity to stratify individuals into low and high PD risk tiers was developed. Validation in other populations will inform translational value of this approach and its potential applicability as clinical decision support tool.