An Innovative Ensemble Deep Learning Clinical Decision Support System For Diabetes Prediction

Abstract

Diabetes is a significant global health concern, with an increasing number of diabetic individuals at risk. Early prediction of diabetes is essential for preventing its progression and reducing the risk of severe complications such as kidney and heart diseases. This study proposes an innovative Ensemble Deep Learning (EDL) clinical decision support system for diabetes prediction with high accuracy. Three diabetes datasets are utilized: the Pima Indian Diabetes Dataset, the Diabetes Dataset from Frankfurt Hospital, Germany, and the Iraqi Diabetes Patient Dataset (IDP, to train the novel EDL models. The Extra Tree Classifier (ETC) approach is employed to extract relevant features from the data. The performance of the proposed EDL models is rigorously evaluated based on key metrics such as accuracy, precision, recall, and F-score. The study employs a variety of algorithms, including ANN, CNN, LSTM, Stack-LSTM, Stack-ANN, Stack-CNN, and CNN + LSTM, with further potential to enhance performance by exploring additional ensemble techniques such as CNN + LSTM.