Key result
SMOTE-Tomek fused BiLSTM model outperforms other balancing schemes for diabetes detection reaching ~94% accuracy.
Why the study?
The imbalanced nature of diabetes datasets leads to high misclassification, poor generalization, and reduced accuracy in early diagnosis.
Does a SMOTE-Tomek fused BiLSTM model improve diabetes classification accuracy in imbalanced datasets compared to other balancing schemes?
Does a SMOTE-Tomek fused BiLSTM model improve diabetes classification accuracy in imbalanced datasets compared to other balancing schemes?
A BiLSTM model combined with SMOTE-Tomek balancing effectively addresses data imbalance and achieves high accuracy in classifying diabetes cases across multiple datasets.
Answers are grounded in this paper and cite their sources.
Should not yet change diabetes screening practice; hypothesis-generating for hybrid ML balancing in imbalanced datasets.
Diabetes is the body’s inability to efficiently break down sugar or secrete enough insulin required to process glucose, which supports normal bodily functions. Diabetes, as a prevalent chronic disorder, has contributed to numerous underlying health challenges among its carriers and is classified by the WHO as the world’s deadliest disease and silent killer. Its non-communicable nature makes early diagnosis difficult, allowing progression through various stages: type I, type II, pre-diabetes, and gestational. This challenge is further compounded by the imbalanced nature of diabetes datasets, which leads to high misclassification, poor generalization, and reduced accuracy. This study predicts diabetes using a bi-directional long short-term memory (BiLSTM) model applied to two datasets: (a) PIMA Indian Diabetes and (b) Iraqi Society Dataset, to evaluate the impact of six known balancing techniques and assess their effectiveness. Results show that for PID, the SMOTE-Tomek fused BiLSTM outperforms other balancing schemes with F1, Accuracy, Precision, Recall, and Specificity scores of 0.9182, 0.9198, 0.9128, 0.9248, and 0.9208, respectively. For ISD, it also achieves the best performance with values of 0.9367, 0.9369, 0.9386, 0.9388, and 0.9313, respectively. Other balancing approaches yielded F1 scores ranging from [0.6751 to 0.9347], accuracy [0.684 to 0.9358], Precision [0.6851 to 0.9296], Recall [0.6639 to 0.9356], and specificity [0.6658 to 0.9298]. These results imply that BiLSTM is resilient to the vanishing gradient problem and can effectively classify diabetes cases with enhanced performance.
No takes yet. Share an insight, caveat, or question.
Eboka et al. (2025) studied Diabetes Mellitus. SMOTE-Tomek fused BiLSTM model vs. Other balancing schemes was evaluated on Model performance (F1, Accuracy, Precision, Recall, Specificity). A SMOTE-Tomek fused BiLSTM model outperformed other balancing schemes for diabetes detection, achieving an accuracy of 0.9198 on the PIMA Indian dataset and 0.9369 on the Iraqi Society dataset.
Synapse has enriched 10 related papers. Consider them for comparative context: