COVID-19 Prognostic Assistant Using Medical Imaging

Diagnostic imaging is fundamental in the clinical work-up of patients with a suspected or confirmed COVID-19 infection. With the integration of artificial intelligence (AI) and machine learning (ML) algorithms, technological improvements in diagnostic imaging have resulted in an improvement in the accuracy of test interpretation and the extraction of prognostic information relevant to decision-making. This study aims to train a COVID-19 Prognostic Model that would help diagnose a patient's x-ray imaging result. The proponents acquired images from publicly available datasets in Kaggle. Vision Transformer (ViT) was used to train the model, and its performance was measured using accuracy, specificity, and sensitivity. Results show that the models trained were able to achieve as high as 95% accuracy, 96% specificity and 98% for sensitivity.

top viewed thesis

1. Records Management System of Municipal Agriculture, Sto. Tomas, La Union 2022-11

2. Record Management System for the Instruction Office of DMMMSU-SLUC 2018-04

3. Online Ordering System for Ryan and Ced Pizza 2022-05

4. Development of Online Examination System for Joyland School, Inc. 2022-05

5. Network Infrastructure Plan for Don Eufemio F. Eriguel Memorial National High School 2017-04