**4. Conclusion**

Overall, the use of AI technology for disease prevention and control is still in its early stages of investigation; there is an inexplicability about AI that prevents it from being effectively incorporated into the epidemiological system, and data collection and integration capacity building is still lacking. Due to lag and other problems, AI technology has been largely restricted from playing a larger role in epidemics prevention and control. To that end, disease modeling should be used for theoretical interpretability analysis, and large multi-dimensional data processing capacities should be enhanced to compensate for the corresponding technological flaws. However, it is important to understand and acknowledge the weaknesses and potentially major prejudices associated with public health big data, and there is still space for improvement. To comply with social ethics and norms, intellectual properties in algorithm methodologies and interpretability, as well as privacy security, should be given serious consideration. AI-enabled and –enhanced evidence-based public health monitoring and response, as seen in various AI applications in the medical sector, has real potential, but there are major challenges ahead.

## **Acknowledgements**

We would like to thank Dr. Zheng Xiang from the University of Hong Kong for his support in the literature review.

### **Conflict of interest**

The authors declare no conflict of interest.
