Session Date: April 21, 2021
Session Description: The data available to inform public health decision-making are becoming larger, more complex, and more varied in the types of information they capture. Traditional structured “hypothesis testing” approaches used to extract decision-relevant insights from data often fall short of taking full advantage of the data. Instead, artificial intelligence (AI) and specifically machine learning (ML) techniques are required to identify patterns and relationships that are deeply embedded in large, high-dimensional data. The evolution of data sources and of the analytic methods to make sense of them can inform decision-making at all levels of the public health system, from high-level strategic planning to front-line service delivery . To take advantage of these opportunities, however, health ministries need to strengthen their platforms for organizing and integrating data, their processes for disseminating knowledge derived from these data, and their staff’s capacity to meet the leadership, analytic, and technical demands created by big data and AI. By aligning their platforms, processes, and people to this new environment, health ministries can significantly improve health outcomes for the citizens they serve. Many countries, including a number of low- and middle-income countries (LMICs), are already adapting to take advantage of these opportunities. This panel will: – frame the general types of AI solutions relevant to public health; – present specific public health solutions developed for LMICs that illustrate the opportunities associated with artificial intelligence and summarize the key lessons learned; – provide practical insights from officials from LMICs who have experienced the implementation of public health-related AI solutions in their countries; and – discuss the implications of AI for health sector planning, management, and monitoring.