Ensemble of explainable artificial intelligence predictions through discriminate regions: A model to identify COVID-19 from chest X-ray images

Abstract

Abstract In 2019, lung disease severely affected human health and was later renamed coronavirus disease 2019 (COVID-2019). Since then, several research methods have been proposed, such as reverse transcription polymerase chain reaction (RT-PCR), and disease identification through chest X-rays and computed tomography (CT) scans, to help the healthcare sector. RT-PCR was time-consuming when more patients were present, and a CT scan was costly. Several deep-learning (DL) methods were used to identify diseases using computer-aided tools. Among those convolutional neural networks (CNNs), the state of the art was adopted in the machinery to predict cancer. However, there is a lack of explainability (XAI) in how CNN predicts the disease. In this article, we construct XAI ensembles with Local Interpretation Model Agnostic Explanation(LIME), Grad CAM, and a Saliency map. It provides a visual explanation for a DL prognostic model that predicts COVID-19 respiratory infection in patients. Our quantitative experimental results have shown that ensemble XAI with an accuracy of 98.85%, although individual LIME has scored an accuracy of 99.62% on test data, is more reliable since it is the combination of models.