PulDi-COVID: Chronic obstructive pulmonary (lung) diseases with COVID-19 classification using ensemble deep convolutional neural network from chest X-ray images to minimize severity and mortality rates

[Display omitted] •Proposed an SSE strategy with the awareness of varied class-level accuracies for different DL models. SSE models achieve superior performance by minimizing the variance of prediction errors to the competing base learners.•Applied nine-class classification using chronic lung diseases with COVID-19 cases detection. The performance of the eight best influential transfer learning CNNs and 13 SSE models has been thoroughly evaluated with the proposed PulDi-COVID experimentally, showing the promising results of PulDi-COVID. The main aim of SSE is to reduce the error rate and enhance accuracy.•To provide a pulmonary disease predictions study with COVID-19 disease using DL application models with X-ray images rather than laboratory findings.•Several hyper-parameters, including batch size, early stopping, epochs, and optimization strategies, have been investigated.Publicly available three repositories are used with online augmentation while assessing the X-ray instances for all nine lung classes, including COVID-19.•Finally, based on comparative performance analysis, perfect architecture to be produced, which will help investigators build a better practical CNN-based approach for earlier-stage identification of pulmonary illnesses with COVID-19 contamination.•As evident from the explanations from recently developed systems, it's almost necessary to predict the other chronic pulmonary diseases and COVID-19 infections to avoid the mortalities of a patient. This research will be helpful for clinicians and radiologists to minimize the workload, severity, and deaths of COVID-19 patients because the mortality rate may increase as chronic lung diseases present in COVID-19 affected individuals. In the current COVID-19 outbreak, efficient testing of COVID-19 individuals has proven vital to limiting and arresting the disease's accelerated spread globally. It has been observed that the severity and mortality ratio of COVID-19 affected patients is at greater risk because of chronic pulmonary diseases. This study looks at radiographic examinations exploiting chest X-ray images (CXI), which have become one of the utmost feasible assessment approaches for pulmonary disorders, including COVID-19. Deep Learning(DL) remains an excellent image classification method and framework; research has been conducted to predict pulmonary diseases with COVID-19 instances by developing DL classifiers with nine class CXI. However, a few claim to have strong prediction results;