AN INTELLIGENT DATA QUALITY ENHANCEMENT FRAMEWORK FOR DIABETES PREDICTION USING HYBRID PREPROCESSING TECHNIQUES
: https://doi.org/10.65725/JCISE/2/3/008
JOURNAL OF COMPUTATIONAL INTELLIGENCE SCIENCE AND ENGINEERING (JCISE) 
ISSN: 3107-8168
Volume 2 Issue 3, Jul-Sep 2026

Abstract:
Diabetes mellitus is one of the leading chronic diseases worldwide, necessitating reliable data-driven approaches for early diagnosis and clinical decision-making. The performance of machine learning models is highly dependent on the quality of the input data; however, existing studies primarily focus on prediction algorithms while providing limited attention to systematic data preprocessing. This study proposes an Intelligent Data Quality Enhancement Framework (IDQEF) that employs hybrid preprocessing techniques to improve the quality and consistency of diabetes datasets prior to predictive modeling. The proposed framework integrates data validation, missing value imputation, outlier detection, duplicate record elimination, feature scaling, and synthetic minority oversampling (SMOTE) to address data incompleteness, noise, redundancy, and class imbalance. The framework is implemented using the publicly available Kaggle Diabetes Prediction Dataset comprising demographic and clinical attributes associated with diabetes diagnosis. The effectiveness of the proposed preprocessing strategy is assessed using data quality measures and validated through baseline machine learning classifiers with standard evaluation metrics, including Accuracy, Precision, Recall, F1-score, Specificity, Matthews Correlation Coefficient (MCC), and Area Under the Receiver Operating Characteristic Curve (ROC-AUC). The proposed framework produces a clean, balanced, and standardized dataset that enhances the reliability of downstream predictive models and provides a robust foundation for subsequent feature engineering and intelligent diabetes prediction. The framework offers a practical and reproducible preprocessing pipeline that can support the development of dependable healthcare analytics systems. This abstract reflects the Phase I focus on preprocessing and dataset preparation described in your framework. 

Authors: Mrs.V. Manjuladevi, Dr. P. Periyasamy

Keywords: Diabetes Mellitus; Data Quality Enhancement; Hybrid Preprocessing; Machine Learning; Clinical Data Analytics.