An Artificial Intelligence-Based Fuzzy Logic System for Periodontitis Risk Assessment in Patients with Type 2 Diabetes Mellitus DOI Creative Commons
Ioana Scrobotă,

G. Iova,

Olivia Andreea Marcu

et al.

Bioengineering, Journal Year: 2025, Volume and Issue: 12(3), P. 211 - 211

Published: Feb. 20, 2025

Background: Since periodontitis prevalence has increased globally and there is a bidirectional relationship between diabetes mellitus (DM), new methods of preventing screening involving DM biomarkers could impact management. We aimed to develop fuzzy system estimate the risk in patients with DM. Methods: Body mass index (BMI), glycemia (G), total cholesterol (C), triglyceride (T) measurements were collected from 87 diagnosed Oral examinations performed, number periodontal pockets (nrPPs) was determined. A developed: BMI G as inputs resulted Periodontitis Risk 1 (PRisk1) output; C T 2 (PRisk2) output. From PRisk1 PRisk2, cumulative (PCRisk) assessed. Linguistic terms linguistic grades (very small, medium, big, very big) assigned numerical variables by using 25 different membership functions. PCRisk nrPP values statistically processed. Results: In our developed system, BMI, G, C, input data estimation. correlated nrPP: when 1.881 units, unit. The logic-based effectively estimated type patients, showing significant correlation pockets. These findings highlight its potential for early diagnosis improved interdisciplinary care.

Language: Английский

An Artificial Intelligence-Based Fuzzy Logic System for Periodontitis Risk Assessment in Patients with Type 2 Diabetes Mellitus DOI Creative Commons
Ioana Scrobotă,

G. Iova,

Olivia Andreea Marcu

et al.

Bioengineering, Journal Year: 2025, Volume and Issue: 12(3), P. 211 - 211

Published: Feb. 20, 2025

Background: Since periodontitis prevalence has increased globally and there is a bidirectional relationship between diabetes mellitus (DM), new methods of preventing screening involving DM biomarkers could impact management. We aimed to develop fuzzy system estimate the risk in patients with DM. Methods: Body mass index (BMI), glycemia (G), total cholesterol (C), triglyceride (T) measurements were collected from 87 diagnosed Oral examinations performed, number periodontal pockets (nrPPs) was determined. A developed: BMI G as inputs resulted Periodontitis Risk 1 (PRisk1) output; C T 2 (PRisk2) output. From PRisk1 PRisk2, cumulative (PCRisk) assessed. Linguistic terms linguistic grades (very small, medium, big, very big) assigned numerical variables by using 25 different membership functions. PCRisk nrPP values statistically processed. Results: In our developed system, BMI, G, C, input data estimation. correlated nrPP: when 1.881 units, unit. The logic-based effectively estimated type patients, showing significant correlation pockets. These findings highlight its potential for early diagnosis improved interdisciplinary care.

Language: Английский

Citations

0