AI-Driven Multimodal Deep Learning for COVID-19 Prediction: A Comparative Analysis of Pre-Trained vs. Custom Models Using Cough, X-ray, and CT Scan Datasets

COVID-19, a respiratory illness that mostly attacks the human lungs emerged in 2019 and quickly became a global health crisis. Its fast transmission has necessitated the creation of effective tools that could aid in its classification. In this paper, we present an artificial intelligence multimodal deep learning model that leverages X-ray, CT-scan, and cough signals to classify COVID-19 accurately. This paper meticulously compares the effectiveness of non-pre-trained and pre-trained versions of VGG19, MobileNetv2, and ResNET across various multimodal and some unimodal models. Findings show that while the pre-trained unimodal systems for cough and X-ray outperform their non-pre-trained counterparts, the non-pre-trained CT scan model performs exceptionally well. This suggests that features learned from the VGG19 model fail to generalize effectively. Remarkably, the non-pre-trained multimodal model accomplishes an F1-score of 0.9804, slightly outperforming its pre-trained counterpart. These results indicate the potential of developing artificial intelligence models from scratch, especially for specialized datasets in multimodal scenarios. While this research advances our understanding of transfer learning within COVID-19 classification, it also emphasizes the prospects of developing custom deep-learning models for solving complex medical problems.