A New Scientific Achievement by the Biomedical Engineering Research Center at the University of Anbar

As part of its ongoing efforts to advance scientific research and contribute to the fields of biotechnology and medical engineering, the Biomedical Engineering Research Center at the University of Anbar has achieved a new milestone. The Director of the Center, Prof. Dr. Yousif Al-Mashhadany, has published a high-impact research article entitled: "COVID-19 IgG antibodies detection based on CNN-BiLSTM algorithm combined with fiber-optic dataset" The study was published in the Journal of Virological Methods, a peer-reviewed journal indexed in Clarivate and Scopus, classified within Q2. The journal holds an Impact Factor of 2.2 and a CiteScore of 5.8, with the electronic ISSN: 1879-0984. This publication is the result of a collaborative research effort with several Malaysian institutions, most notably the National University of Malaysia (UKM). The study proposes an innovative approach to detecting COVID-19 through a hybrid model that integrates Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks, utilizing fiber-optic data related to IgG antibodies for the SARS-CoV-2 virus. Experimental results demonstrated the proposed model's high performance, achieving a classification accuracy of 89%, recall of 88%, specificity of 90%, precision of 90%, F1-score of 89%, and a geometric mean of 89%. The model also recorded a Receiver Operating Characteristic (ROC) area of 96%. These results were benchmarked against previous studies, confirming the model’s reliability and efficiency. The outcomes indicate that the proposed hybrid model holds promising potential for the accurate classification of COVID-19 cases. It could serve as a valuable diagnostic tool in healthcare settings, particularly by enhancing the precision and specificity of detection based on IgG antibody analysis.

Research and Indexing Links:

Article on ScienceDirect:(Click Here)

Author Profile on Scopus:(Click Here)

Author Profile on Web of Science: (Click Here)