Combining CNNs and symptom data for monkeypox virus detection

The zoonotic disease monkeypox, related to smallpox, presents diagnostic challenges due to its resemblance to other illnesses with similar symptoms. In this study, we propose a robust method for monkeypox detection utilising convolutional neural networks (CNNs). Our approach integrates lesion images and symptom analysis to enhance diagnostic reliability. A dataset comprising high-definition lesion images and nine significant symptoms was employed to train the CNN model. The model classifies cases based on a probabilistic score, while symptom-based analysis is used as a secondary measure when lesion analysis is inconclusive. Built with convolutional, pooling, and fully connected layers, the model demonstrates strong predictive capabilities, effectively distinguishing monkeypox from other conditions. The study highlights the CNN model's ability to assess monkeypox risk with high confidence, even with limited high-resolution imaging data, underscoring its potential in medical diagnostics. Tables summarise the model's predictions based on symptom combinations, showcasing its practical applicability. This research emphasises the integration of CNNs with clinical symptom data as a promising tool for accurate and early monkeypox diagnosis. Future work could further refine the model by incorporating larger datasets and advanced methodologies to improve its generalisability and effectiveness in outbreak scenarios.