Type 2 Diabetes
Conditions
Keywords
Oral Health, Machine Learning, Diabetes Type 2
Brief summary
This study aims to explore the potential of using machine learning (ML) algorithms to predict Diabetes type2, based on oral health and demographic data. The objective is to evaluate the effectiveness of various ML models and identify the most relevant oral health indicators for predicting type 2 diabetes in individuals with mild cognitive impairment aged 60 and above.
Detailed description
This cross-sectional study utilizes oral health and demographic data from the Swedish National Study on Aging and Care (SNAC-B). Participants aged 60 years or older with Mild Cognitive Impairment will be included in the analysis. The data will be used to develop and evaluate machine learning models for predicting type 2 diabetes. Objectives: 1. Primary Objective: To assess the potential of oral health parameters for binary classification of type 2 diabetes or not. 2. Secondary Objective: To identify the most influential oral health parameters contributing to type 2 diabetes predictions. 3. Tertiary Objective: To compare the performance of Random Forest (RF), Support Vector Machine (SVM), and CatBoost (CB) classifiers in predicting type 2 diabetes using oral health data.
Interventions
OTHERA dataset comprising participants withT2D will be used to evaluate the classification performance of various machine learning techniques.
A dataset comprising participants with T2D will be used to evaluate the classification performance of various machine-learning techniques.
Sponsors
Blekinge Institute of Technology
Study design
Observational model
CASE_CONTROL
Time perspective
CROSS_SECTIONAL
Eligibility
Sex/Gender
ALL
Age
60 Years to No maximum
Healthy volunteers
Yes
Inclusion criteria
* Individuals aged 60 years or older. * Participants with recorded oral health parameters with or without Diabetes type2
Exclusion criteria
• Individuals with Diabetes type1
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Detection perfomance | 12 months | Description: The study measures the classification performance of Machine Learning classifier. Performance metrics, Accuracy, precision, recall, F1-Score and confusion matrix will be used for the evaluation. The examination of the most important features relied on SHAP summary plots, providing visualizations of the influence of parameter groups on the output, organized by their importance. This importance is based on SHAP values, offering insights into features' effects on the ML model's decision-making process |
Countries
Sweden
Contacts
Primary ContactJohan Flyborg, DDS, PhD
Outcome results
None listed