This paper presents a hybrid CapsNet model combined with a Convolutional Neural Network (CNN) for malaria detection from microscopic blood smear images. The model is designed to improve the accuracy and efficiency of malaria diagnosis, which is crucial for reducing morbidity and mortality. The hybrid CapsNet model is optimized using malaria data from infected and uninfected blood samples, with images processed and enhanced through rotation. The model achieves a detection rate of 99%, an accuracy of 99.08%, and a False Alarm Rate (FAR) of 0.97%, outperforming the state-of-the-art DSCN-Net model. The CapsNet model's ability to analyze the position and relationships of image objects in hierarchical relationships enhances its performance. The study aims to develop a prognostic model that can accurately identify and classify malaria-infected cells from blood smear images, demonstrating the potential of CapsNet in improving malaria diagnosis.This paper presents a hybrid CapsNet model combined with a Convolutional Neural Network (CNN) for malaria detection from microscopic blood smear images. The model is designed to improve the accuracy and efficiency of malaria diagnosis, which is crucial for reducing morbidity and mortality. The hybrid CapsNet model is optimized using malaria data from infected and uninfected blood samples, with images processed and enhanced through rotation. The model achieves a detection rate of 99%, an accuracy of 99.08%, and a False Alarm Rate (FAR) of 0.97%, outperforming the state-of-the-art DSCN-Net model. The CapsNet model's ability to analyze the position and relationships of image objects in hierarchical relationships enhances its performance. The study aims to develop a prognostic model that can accurately identify and classify malaria-infected cells from blood smear images, demonstrating the potential of CapsNet in improving malaria diagnosis.