A hybrid deep learning CNN model is proposed for the detection of COVID-19 using chest X-rays. The model combines two pre-trained CNN models, VGG16 and VGG19, with pooling layers to reduce feature dimensions and dense layers for classification. The model achieves an accuracy of 92% using average pooling and SVM-linear, along with neural networks. The model is evaluated against existing CNN models such as VGG16, VGG19, EfficientNetB0, and ResNet50 using a COVID-19 radiology database. The proposed model outperforms existing models in terms of accuracy, precision, recall, and F1-score. The model is trained on 9220 images, with 70% for training, 30% for testing, and 20% for validation. The model uses a combination of feature extraction, pooling, and dense layers to classify images. The model's performance is evaluated using metrics such as recall, precision, accuracy, specificity, sensitivity, and F1-score. The results show that the proposed model achieves a high accuracy of 92% for the COVID-19 Radiography database. The model is also compared with other existing models, and it is found to be more accurate and efficient. The model is designed to assist radiologists and physicians in diagnosing COVID-19 and reducing misdiagnosis rates. The model is implemented using Python and TensorFlow, and the code is available upon request. The study concludes that the proposed hybrid deep learning model is effective for detecting COVID-19 from chest X-rays and can be used in clinical settings to improve diagnostic accuracy and reduce the burden on radiologists.A hybrid deep learning CNN model is proposed for the detection of COVID-19 using chest X-rays. The model combines two pre-trained CNN models, VGG16 and VGG19, with pooling layers to reduce feature dimensions and dense layers for classification. The model achieves an accuracy of 92% using average pooling and SVM-linear, along with neural networks. The model is evaluated against existing CNN models such as VGG16, VGG19, EfficientNetB0, and ResNet50 using a COVID-19 radiology database. The proposed model outperforms existing models in terms of accuracy, precision, recall, and F1-score. The model is trained on 9220 images, with 70% for training, 30% for testing, and 20% for validation. The model uses a combination of feature extraction, pooling, and dense layers to classify images. The model's performance is evaluated using metrics such as recall, precision, accuracy, specificity, sensitivity, and F1-score. The results show that the proposed model achieves a high accuracy of 92% for the COVID-19 Radiography database. The model is also compared with other existing models, and it is found to be more accurate and efficient. The model is designed to assist radiologists and physicians in diagnosing COVID-19 and reducing misdiagnosis rates. The model is implemented using Python and TensorFlow, and the code is available upon request. The study concludes that the proposed hybrid deep learning model is effective for detecting COVID-19 from chest X-rays and can be used in clinical settings to improve diagnostic accuracy and reduce the burden on radiologists.