Accurate disease diagnosis enhances effective patient management; however, manual interpretation of complex biomedical data is time-consuming and vulnerable to error. Artificial Intelligence (AI) systems, particularly Machine Learning (ML) models, can automatically learn complex patterns from high-dimensional clinical and imaging data. The predictive performance of these methods depends critically on proper hyperparameter tuning. This study introduces a framework that integrates nonlinear feature extraction, classification, and efficient optimisation. First, kernel principal component analysis with a radial basis function kernel reduces dimensionality while preserving 95% of the variance. Second, a Multilayer Perceptron (MLP) learns to predict disease status. Finally, a modified Multiprocessing Interface Genetic Algorithm (MIGA) optimises MLP hyperparameters in parallel over ten generations. We evaluated this approach on three datasets: The Wisconsin Diagnostic Breast Cancer dataset, the Parkinson’s Telemonitoring dataset, and the Chronic Kidney Disease (CKD) dataset. The MLP tuned by the MIGA achieved the best accuracy of 99.12% for breast cancer, 94.87% for Parkinson’s Disease (PD), and 100% for CKD. These results outperform those of other methods, such as grid search, random search, and Bayesian optimisation. Compared to a standard Genetic Algorithm (GA), Kernel Principal Component Analysis (Kernel PCA) revealed nonlinear relationships that improved classification, and the MIGA’s parallel fitness evaluations reduced the tuning time by approximately 60%. The GA incurs a high computational cost due to the sequential nature of fitness evaluations. Still, our MIGA parallelizes this step, significantly reducing the tuning time and steering the MLP toward the best accuracy scores of 99.12%, 94.87%, and 100% for breast cancer, Parkinson's, and CKD, respectively. The built-in graphical user interface then enables clinicians to load data, reduce dimensions, tune hyperparameters, and run predictions without writing code, paving the way for rapid and real-world adoption.