International Journal of Research and Applied Technology (INJURATECH)
Vol. 6 No. 2 (2026): December, 2026 (Issue in Progress)

Hybrid Oversampling and FT-Transformer-Based Classification for Imbalanced Clinical Tabular Data: A Multi-Dataset Statistical Evaluation

Asaad Khaleel (Computer Information Systems, Technical College of Zakho, Duhok Polytechnic University, Iraq)
Mohammed Ramadhan (Department of Computer Science, University of Zakho, Zakho, Kurdistan Region-Iraq)
Masood Abdulrahman (Computer Information Systems Department, Duhok Polytechnic University, Iraq)



Article Info

Publish Date
22 Sep 2026

Abstract

Class imbalance is a problem which is not new on the clinical data, but is not well dealt with in practice. A model trained on a skewed distribution will often claim high accuracy on the skewed dataset, but will miss almost all of the minority class, typically the class that is the most important for detection — such as the class of patients who require detection the most. The three synthetic oversampling methods tested were SMOTE and ADASYN and Borderline SMOTE, alongside the three classifiers Random Forest and Gradient Boosted Trees and a Bayesian-tuned FT-Transformer, applied to three datasets: Pima Diabetes (768 records); a cardiovascular dataset (3,000 records); and Heart Failure Clinical Records (299 records, 203 survived, 96 died). All 14 resulting configurations were tested using 5-fold cross validation repeated 5 times per fold (i.e., 25-fold-pairs), and Wilcoxon Signed-Rank tests were performed to determine if the improvements are statistically significant when compared with the baseline (RF). The answer is: Yes, they were — in many instances very much so. On Pima, ADASYN together with the tuned FT-Transformer obtained F1=0.6677 and Recall=0.8209, while for the unaugmented RF it was 0.5145 and 0.4563, respectively. In the Pima ablation study specifically, the large portion of that gain (+15.6%) was due to oversampling, with hyperparameter tuning contributing another +9.2%; these percentages are specific to the Pima/RF ablation experiment and should not be interpreted as dataset-agnostic general findings. Synthetic augmentation was tested using SHAP on the RF branch only, and did not alter the variables that the model uses.

Copyrights © 2026






Journal Info

Abbrev

injuratech

Publisher

Subject

Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

Description

INJURATECH cover all topics under the fields of Computer Science, Information system, and Applied Technology. Scope: Computer Based Education Information System Database Systems E-commerce and E-governance Data mining Decision Support System Management Information System Social Media Analytic Data ...