TY  - JOUR
TI  - Artificial Intelligence Based Video Processing Methods for
Predicting COVID-19: Observational Study
AB  - Objective: The aim of this study is to develop a
high-performance model and web-based clinical decision
making method to successfully distinguish and classify COVID19 from bacterial pneumonia, viral pneumonia and healthy
controls with lung ultrasound (LUS) videos using appropriate
video processing techniques and artificial intelligence (AI)
methods development of the support system. Material and
Methods: In this study, the open source LUS video dataset at
https://github.com/jannisborn/covid19_ultrasound was used. The
dataset includes 32 healthy controls, 24 COVID-19, 24 bacterial
pneumonia and 12 viral pneumonia class videos. In the video
processing stage, 300 image frames were taken from the videos in
each class. The images were divided into 80% (960) training and
20% (240) test datasets. In the modeling phase, the convolutional
neural network (CNN) method, one of the deep neural network
architectures in the keras library, was used. Accuracy, sensitivity,
specificity, precision, Matthews’ correlation coefficient and F1
score criteria are given to evaluate the performance of the model.
A web-based system has been developed that can successfully
detect COVID-19 using the, with the help of the AI-based model,
Python Flask Library. Results: The accuracy in the test dataset
was calculated as 93.39% for healthy control, COVID-19 and
viral pneumonia, and 95.07% for bacterial pneumonia.
Conclusion: According to the performance criteria values
obtained with the video processing-based CNN model, it can be
said that the developed system gives very successful predictions
in the diagnosis of COVID-19, bacterial pneumonia and viral
pneumonia.
AU  - Yağın, Burak
AU  - GÜLDOĞAN, Emek
AU  - ÇOLAK, Cemil
DO  - 10.5336/biostatic.2022-88805
PY  - 2022
JO  - Türkiye Klinikleri Biyoistatistik Dergisi
VL  - 14
IS  - 1
SN  - 1308-7894
SP  - 22
EP  - 31
DB  - TRDizin
UR  - http://search/yayin/detay/516114
ER  -