Prophylactic and therapeutic measures for emerging and re-emerging viruses: artificial intelligence and machine learning - the key to a promising future

Purpose: Emerging and re-emerging viral infections are accountable for fatal outbreaks across the globe. In the light of the COVID-19 catastrophe and mpox exigency, the gaps in prophylactic measures have been envisaged. Emerging and re-emerging infections like poxviruses, Zika, Marburg, Ebola, Hanta, Nipah viruses have further challenged the healthcare sector by putting additional burden on therapeutic and diagnostic limitations. In the present review we also highlighted potential implications of artificial intelligence for long term solutions. Methods: Artificial Intelligence (AI) and Machine Learning (ML)-based models have shown promise in accelerating the discovery of new antivirals or potential vaccine candidates. Deep learning (DL) based algorithms can integrate prodigious global data comprising epidemiology, genomics, pathology and molecular behaviour. Subsequently, support vector machine/ random forest/ neural network guided interpretations can comprehensively compile the available datasets for therapeutic and diagnostic predictions. Results: The present review compiled the various AI-based algorithms and servers which were used for modelling studies as well as prophylactic measures during recent viral outbreaks. The impact of AI on surveillance, outcome prediction, patient monitoring, genomic tracking, clinical assistance, therapeutic screening, drug/ vaccine design and other experimental studies were emphasized. Conclusions: The present review not only highlighted public-health management models but also provide leads in potential therapeutic targets as well as vaccine/ antiviral candidates. To support the context, the issues with existing therapeutic strategies are also overviewed and the prospects were identified. This review discusses a wide range of applications of AI and ML pertaining to the clinical domain.