Detecting Pneumonia Based On Chest X-Ray Images Using Reinforcement Learning

While early detection of diseases helps in managing and improving patient outcomes, most detection methods employed today are largely manual, costly, and time-consuming. Accordingly, computer-aided diagnosis is emerging as an innovative solution to improving the accuracy of detection by eliminating human errors and lowering the cost of diagnosis. One of the diseases that can benefit immensely from computer-aided diagnosis is pneumonia, which is an acute pulmonary infection accounting for thousands of hospitalizations and deaths globally. Current pneumonia detection approaches entail manually examining radiology images such as X-rays. Because of subjective variability, the outcomes of the examination are not always accurate. As a result, researchers have started to develop models based on machine learning to aid in detecting pneumonia based on chest X-ray images. Most of the models developed are based on deep learning, especially convolutional neural networks. However, these models require vast data sets for training and their accuracy values can be improved. For that reason, this paper developed a detection model based on Reinforcement Learning (RL) with convolutional neural network (CNN). The chest X-ray images of pneumonia is a data set that is used for the experiments. The obtained results confirm that applying the RL model is a good choice for detecting pneumonia. The efficacy of these model's performance was evaluated by measuring the precision, recall, F1-score, accuracy, and confusion matrix.