September 25, 2025Open Access

Machine Learning classifiers for non-invasive questionnaire-based Type 2 Diabetes detection

View Full Paper

Ask AI

Bookmark

Authors

Discussion

This analysis evaluates machine learning classifiers for type 2 diabetes detection, suggesting new screening metrics.

The neural network model achieved the highest sensitivity of 86.66%, highlighting its effectiveness over others.
Cost-weighted accuracy reached 75.88%, emphasizing the importance of reducing false negatives in diabetes detection.
Three machine learning models were tested: logistic regression, random forest, and neural network, showcasing varied performances.
Using a questionnaire-based method, this approach offers a scalable and low-cost solution for effective diabetes screening.

Anthony Lau (2025) studied this question.

View Full Paper

Ask AI

Bookmark

September 25, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

This analysis evaluates machine learning classifiers for type 2 diabetes detection, suggesting new screening metrics.

The neural network model achieved the highest sensitivity of 86.66%, highlighting its effectiveness over others.
Cost-weighted accuracy reached 75.88%, emphasizing the importance of reducing false negatives in diabetes detection.
Three machine learning models were tested: logistic regression, random forest, and neural network, showcasing varied performances.
Using a questionnaire-based method, this approach offers a scalable and low-cost solution for effective diabetes screening.

Anthony Lau (2025) studied this question.

View Full Paper

Ask AI

Bookmark