Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jul 21:2022:5260231.
doi: 10.1155/2022/5260231. eCollection 2022.

The Use of Chest Radiographs and Machine Learning Model for the Rapid Detection of Pneumonitis in Pediatric

Khalaf Alshamrani  1 , Hassan A Alshamrani  1 , Abdullah A Asiri  1 , F F Alqahtani  1 , Walid Theib Mohammad  2 , Ali H Alshehri  1
Affiliations

The Use of Chest Radiographs and Machine Learning Model for the Rapid Detection of Pneumonitis in Pediatric

Khalaf Alshamrani et al. Biomed Res Int. .

Retraction in

Abstract

Pneumonia is a common lung disease that is the leading cause of death worldwide. It primarily affects children, accounting for 18% of all deaths in children under the age of five, the elderly, and patients with other diseases. There is a variety of imaging diagnosis techniques available today. While many of them are becoming more accurate, chest radiographs are still the most common method for detecting pulmonary infections due to cost and speed. A convolutional neural network (CNN) model has been developed to classify chest X-rays in JPEG format into normal, bacterial pneumonia, and viral pneumonia. The model was trained using data from an open Kaggle database. The data augmentation technique was used to improve the model's performance. A web application built with NextJS and hosted on AWS has also been designed. The model that was optimized using the data augmentation technique had slightly better precision than the original model. This model was used to create a web application that can process an image and provide a prediction to the user. A classification model was developed that generates a prediction with 78 percent accuracy. The precision of this calculation could be improved by increasing the epoch, among other subjects. With the help of artificial intelligence, this research study was aimed at demonstrating to the general public that deep-learning models can be created to assist health professionals in the early detection of pneumonia.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflicts of interest.

Figures

Figure 1
Figure 1
Chest radiographs: normal, viral pneumonia, and bacterial pneumonia.
Figure 2
Figure 2
Programming libraries.
Figure 3
Figure 3
Image size configuration script.
Figure 4
Figure 4
Script on the classification of images according to groups.
Figure 5
Figure 5
Classification of images according to type and group.
Figure 6
Figure 6
Script where the data is displayed according to the random subclassification.
Figure 7
Figure 7
CNN model script using the Sequential () function.
Figure 8
Figure 8
Compilation and training phase.
Figure 9
Figure 9
Study of the accuracy of the CNN model.
Figure 10
Figure 10
Image rotation to increase information.
Figure 11
Figure 11
Graphic representation of the process in a neural network. Relationship between Bach and iterations to visually understand the concept of an epoch.
Figure 12
Figure 12
Increased information to improve the model.
Figure 13
Figure 13
Script to save the optimized model.
Figure 14
Figure 14
Scheme of communication between the different components of the web application development.
Figure 15
Figure 15
Evolution of precision and loss compared to “epoch.”
Figure 16
Figure 16
Accuracy value generated in the initial model.
Figure 17
Figure 17
Evolution of precision and loss compared to “epoch.”
Figure 18
Figure 18
Accuracy value generated in the optimized model.
See this image and copyright information in PMC

References

    1. Daod I., Ibrahim R., Hussein A., Norsamsi N., Mazlan N. Knowledge of pneumonia among nursing staff in Mosul hospitals, Iraq. International Journal of Medical Toxicology & Legal Medicine. . 2020;23(3and4):107–116. doi: 10.5958/0974-4614.2020.00054.6. - DOI
    1. Hassan M., Al-Sadoon I. Risk factors for severe pneumonia in children in Basrah. Tropical Doctor . 2001;31(3):139–141. doi: 10.1177/004947550103100307. - DOI - PubMed
    1. Elshennawy N. M., Ibrahim D. M. Deep-pneumonia framework using deep learning models based on chest X-ray images. Diagnostics . 2020;10(9):p. 649. doi: 10.3390/diagnostics10090649. - DOI - PMC - PubMed
    1. Güneyli S., Atçeken Z., Doğan H., Altınmakas E., Atasoy K. Ç. Radiological approach to COVID-19 pneumonia with an emphasis on chest CT. Diagnostic and Interventional Radiology . 2020;26(4):323–332. doi: 10.5152/dir.2020.20260. - DOI - PMC - PubMed
    1. Jaiswal A., Tiwari P., Kumar S., Gupta D., Khanna A., Rodrigues J. Identifying pneumonia in chest X-rays: a deep learning approach. Measurement . 2019;145:511–518. doi: 10.1016/j.measurement.2019.05.076. - DOI

Publication types

LinkOut - more resources