• Users Online: 10
  • Home
  • Print this page
  • Email this page
Home About us Editorial board Search Ahead of print Current issue Archives Instructions to authors Subscribe Contacts Login 
Year : 2021  |  Volume : 8  |  Issue : 3  |  Page : 150-156

A predictive logistic regression model for periodontal diseases

Department of Preventive Dental Sciences, College of Dentistry, Najran University, Najran, Kingdom of Saudi Arabia

Correspondence Address:
Dr. Md Zahid Hossain
Department of Preventive Dental Sciences, Division of Periodontics, College of Dentistry, Najran University, King Abdulaziz Road, Najran
Kingdom of Saudi Arabia
Login to access the Email id

Source of Support: None, Conflict of Interest: None

DOI: 10.4103/sjoralsci.sjoralsci_123_20

Rights and Permissions

Introduction: Periodontal diseases (gingivitis and periodontitis) are one of the main concerns for oral health affecting around 20%–50% of the world population. Aims: The aim of this study was to formulate a predictive model for periodontal diseases in a selected population. Materials and Methods: A hospital-based analytical study was carried out. Seven hundred male patients having different forms of periodontal diseases were included to explore the common features and possible risk factors related to periodontal diseases. Chi-squared test and t-test were performed for univariate analysis, and binary logistic regression model was adapted for multivariate analysis using SPSS v23. Results and Discussion: Four hundred and seventy (67%) and 230 (33%) patients suffered from gingivitis and periodontitis, respectively. The mean age of patients with periodontitis (37.17 ± 11.52 years) was significantly higher than those with gingivitis (26.04 ± 10.83 years). Univariate analysis showed that plaque and calculus had statistically significant relationship with gingivitis 451 (72%). Systemic diseases 18 (72%) and patients' habits 39 (76%) had statistically significant relationship with periodontitis (P < 0.05). A logistic regression model was formulated including age, risk factors, and nationality. The model was tested, and its sensitivity, specificity, and accuracy for detecting periodontal diseases were equal to 83.3%, 67.2%, and 78.0%, respectively. Conclusions: This model had a good fit and explained a significant proportion of variance in the outcome variable (periodontitis) R2 = 0.40, (χ2 (9) = 238.32, P < 0.001).

Print this article     Email this article
 Next article
 Previous article
 Table of Contents

 Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
 Citation Manager
 Access Statistics
 Reader Comments
 Email Alert *
 Add to My List *
 * Requires registration (Free)

 Article Access Statistics
    PDF Downloaded128    
    Comments [Add]    

Recommend this journal