Artificial Intelligence (A.I.) has been strongly adopted by the commercial and academic sectors, but its adoption by governmental public health has been far less extensive. This is in part due to a dearth of training resources tailored to the public health workforce. As a result, many A.I. techniques with the potential to improve operations for the benefit of the public’s health remain unleveraged. This presentation will review several classes of disease surveillance problems that can be effectively addressed using A.I. and convey them in simple terms. The content will be tailored to public health staff that frequently interface with data systems; a statistics or programming background is not required. The presentation is intended to spur discussions that accelerate the adoption of technologies with the potential to improve health outcomes for the populations we serve.
- Describe several classes of disease surveillance problems that can be effectively addressed using A.I. methods.
- Explain pivotal concepts from the field of Deep Learning (DL) that the public health workforce will need to understand to effectively ideate and co-create generative A.I. solutions to disease surveillance problems at the organizational and national levels.
- Discuss how to accelerate the adoption of technologies to achieve public health goals.