Machine Learning-Driven Prediction of Vitamin D Deficiency Severity with Hybrid Optimization

There is a growing need to predict the severity of vitamin D deficiency (VDD) through non-invasive methods due to its significant global health concerns. For vitamin D-level assessments, the 25-hydroxy vitamin D (25-OH-D) blood test is the standard, but it is often not a practical test. This study is focused on developing a machine learning (ML) model that is clinically acceptable for accurately detecting vitamin D status and eliminates the need for 25-OH-D determination while addressing overfitting. To enhance the capacity of the classification system to predict multiple classes, preprocessing procedures such as data reduction, cleaning, and transformation were used on the raw vitamin D dataset. The improved whale optimization (IWOA) algorithm was used for feature selection, which optimized weight functions to improve prediction accuracy. To gauge the effectiveness of the proposed IWOA algorithm, evaluation metrics like precision, accuracy, recall, and F1-score were used. The results showed a 99.4% accuracy, demonstrating that the proposed method outperformed the others. A comparative analysis demonstrated that the stacking classifier was the superior choice over the other classifiers, highlighting its effectiveness and robustness in detecting deficiencies. Incorporating advanced optimization techniques, the proposed method's promise for generating accurate predictions is highlighted in the study.