An Ensemble Neural Model for Classification of LADA Diabetes Case, Control and Variable Importance

LADA Diabetes is a complex disease, but often dismissed as a potential individual disease within its own right. A comprehensive understanding of previously unknown aspects of LADA diabetes has the potential to not only ascertain a greater comprehension of LADA but also can assist the classification of Type 1 and Type 2 diabetes, as LADA characterises the attributes of both Type 1 and Type 2 diabetes. This paper proposes a novel heterogeneous ensemble model comprising of Neural network with Feature Extraction, Neural network alongside Multilayer Perceptron with Multiple Layers with the intention of classifying LADA diabetes along with weighting the importance of conventional variables including family history, age, gender, BMI, cholesterol level, and waist size in the classification. These conventional variables are analysed based on the aforementioned three-algorithm ensemble stack, and the entire architecture is tuned for optimal classification performance. The proposed novel ensemble stack delivers a reliable prediction accuracy in the identification of case, control, and variable importance. Performance evaluation of the proposed ensemble model based on statistics such as ROC/AUC curve, precision and recall demonstrated a higher predictive accuracy of 92.00%, sensitivity of 91.77%, and specificity of 92.23% alongside a precision of 92.23%, recall at 91.79% and an F1 score of 92.02%, ultimately outperforming well-known classical classification models. Further analysis has determined waist as an important and influential variable in the classification process, whereby a 100% association of LADA diabetes with waist is exhibited.