Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199279,
        author = {Ritesh Pandit},
        title = {Predictive Data Analytics in Healthcare Using Machine Learning.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15154-15161},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199279},
        abstract = {Healthcare systems worldwide face mounting pressure to improve patient outcomes while containing costs. Predictive data analytics powered by machine learning (ML) has emerged as a high-impact approach to address this challenge. This paper presents a novel multi-algorithm comparison framework applied to clinical disease risk prediction with three original contributions: (1) a structured hyperparameter tuning protocol using GridSearchCV with 10-fold stratified cross-validation; (2) a SHAP-based explainability layer that maps model predictions to clinically interpretable feature contributions; and (3) a deployment architecture aligned with HL7 FHIR for integration with Electronic Health Record (EHR) systems. A simulated clinical dataset of 10,000 patient records is used to evaluate five ML algorithms: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and a Feedforward Neural Network. The proposed soft-voting ensemble model achieves 95.1% accuracy, 94.6% precision, 95.4% recall, an F1-score of 95.0%, and a ROC-AUC of 0.974 under 10-fold cross-validation. SHAP analysis identifies fasting blood glucose, HbA1c, and BMI as the three highest-impact predictors, aligning with established clinical guidelines.},
        keywords = {Predictive Analytics, Machine Learning, Healthcare, Random Forest, SHAP Explainability, ROC-AUC, EHR Integration, Clinical Decision Support, SMOTE, Hyperparameter Tuning},
        month = {April},
        }