| Abstrakt: |
A recent study conducted by researchers at the Department of Information and Communication Technology explores the use of machine learning to identify early signs of diabetes. The study collected patient records from the University of California, Irvine machine learning repository and a questionnaire distributed in Bangladesh. The researchers applied various classifiers to the datasets and measured their performance using metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic. The results showed that the Extra Tree classifier performed the best for the Sylhet Diabetes Hospital dataset, while the Multi-Layer Perceptron achieved the highest accuracy for the collected dataset. The study suggests that certain classifiers, including Light Gradient Boosting Machine, Stacking, Hist Gradient Boosting Classifier, Random Forest, Extra Tree, Bagging, and Gradient Boosting Classifier, may provide more stable prediction results for each dataset. [Extracted from the article] |
