Facebook Monday introduced three types of maps to aid nonprofit organizations and universities working on public health in their efforts to stay ahead of diseases outbreaks and more efficiently reach vulnerable communities.
Facebook Data for Good policy lead Laura McGorman and research manager Alex Pompe explained in a Newsroom post, “When planning public health campaigns or responding to disease outbreaks, health organizations need information on where intended beneficiaries live, as well as real-time insights from the field. However, in much of the world, information from the most recent census is often out of date, and timely insights from remote communities are scarce.”
The three types of maps the social network unveiled are population density maps (complete with demographic estimates), movement maps and network coverage maps.
The high-resolution population density maps estimate the number of people living within 30-meter grid tiles, as well as providing insights on demographics such as the number of children under the age of five, the number of women of reproductive age and young and elderly populations.
McGorman and Pompe said the maps are not build using Facebook data, instead relying on machine vision artificial intelligence, satellite imagery and census information, adding, “By combining these publicly and commercially available datasets with Facebook’s AI capabilities, we have created population maps that are three times more detailed than any other source.”
High-resolution population density maps emerged from work Facebook began with Columbia University two years ago to use satellite imagery and census data to build detailed population maps with an eye toward improving connectivity projects, and McGorman and Pompe said the social network saw the potential impact on public health while working with groups such as the American Red Cross.
These maps helped the American Red Cross and its Missing Maps project identify areas with and without concentrations of people in Malawi, enabling on-the-ground teams to make more efficient decisions on where to deploy 3,000 health workers to deliver vaccination messaging during a measles campaign.
The elderly population in Mozambique
Women of reproductive age in Tanzania
Movement maps aggregate information from people using Facebook on their mobile phones, with location services enabled, to provide real-time snapshots into mobility patterns.
Partner organizations can then combine the data with information on specific cases of diseases to better predict where outbreaks may occur and pre-position treatments where they may be needed the most.
McGorman and Pompe wrote, “Public health officials often have challenges predicting where disease outbreaks, like malaria or cholera, will strike. However, cutting-edge research has found that pairing health system information with data on human mobility can yield valuable insights about diseases spread by human-to-human contact.”
Adam Kucharski, assistant professor in mathematical modeling at the London School of Hygiene and Tropical Medicine, added, “Population movements are crucial for the spread of many infections—from influenza to measles. But historically, it’s been very difficult for disease researchers to get information on these movement patterns.”
Movement between Greater London and surrounding areas by day
Finally, the social network is creating real-time maps that show health organizations where people can be reached with online messages alerting them to activities such as vaccination days or bed net distributions. These network coverage maps are created based on Facebook use via mobile phones on cellular networks.
McGorman and Pompe pointed out that many countries still have areas with sparse or nonexistent access to the internet, while public health officials have limited resources to conduct house-by-house visits, adding that these network coverage maps enable those public health teams to better prioritize which areas need other forms of communication.
Density of 3G network coverage availability across areas in the Democratic Republic of the Congo
The high-resolution population density maps can be found here, and organizations interested in the movement or network coverage maps can email diseaseprevmaps@fb.com.
Facebook’s partners in the effort to create these three types of maps included Direct Relief, FHI360, Harvard School of Public Health, the Institute for Health Metrics Evaluation at the University of Washington, International Medical Corps, the London School of Hygiene and Tropical Medicine, Malaria Atlas Project, the MRC Centre for Global Infectious Disease Analysis at Imperial College London, Northeastern University, Sabin Vaccine Institute, UNICEF, Wadhwani AI, the World Bank and the World Economic Forum.
Vanessa Candeias, head of Shaping the Future of Health and Healthcare at the World Economic Forum, said, “Epidemics pose a growing threat to lives and livelihoods. Mitigating their risk and impact requires every tool in the toolbox.”
via https://www.aiupnow.com
David Cohen, Khareem Sudlow