These are just some of the recent examples, but the relation between location and disease outbreak and treatment goes back to the ancient times. Back in 470 B.C., Alcmaeon of Croton was the first Greek doctor to state that the quality of water may influence the health of people. Hippocratic treatise Airs, Waters, Places, which came out around 400 B.C., deals with the different sources, qualities and health effects of water at length. The contamination of water by lead has been a topic in the discussions concerning the health of people in Roman times. Even in those times, the indirect public health effects of water were understood to be greater than the direct effects — while droughts and floods led to food shortages and famines, food, people and pathogens moved most easily by water.
However, in 1854, during the infamous London cholera outbreak, one Dr. John Snow laid the foundation of modern epidemiology when he plotted the distribution of deaths on a local map, which ultimately helped him to trace a water pump as the source of the outbreak. “Today, disease cluster analyses, spatial comparisons, and mapping remain important methods for disease prediction, prevention, and control,” emphasizes Dr. Kristine Belesova, Deputy Director, Centre on Climate Change and Planetary Health, London School of Hygiene and Tropical Medicine.
“The earliest visualization of the relationship between place and health was in 1694 on the topic of plague containment in Italy. The value of maps as a communication tool blossomed over the next 225 years in understanding and tracking infectious diseases such as yellow fever, cholera and the 1918 influenza pandemic,” explains Dr. Este Geraghty, Chief Medical Officer, Esri. From the 1960s, when computerized Geographic Information System came into existence, the possibilities for analyzing, visualizing and detecting patterns of disease spread dramatically increased.
Since the SARS outbreak in 2003, the world has seen a revolution in applied geography through web-based tools. There are umpteen maps and charts to show the alarming spread of COVID-19 spread and how health infrastructure across countries are crumbling.
Epidemiologists have traditionally used maps when analyzing associations between location, environment and disease, and it is a given that good epidemiology science and good geographic information science go hand in hand.
While mapping and field surveys are the most commonly used techniques, increasingly, novel sources of spatial Big Data, including those from smartphones, social media and even personal wearable devices, are being analyzed to translate the patients’ addresses into longitudes and latitudes to pinpoint their location on Earth, and find insights into epidemiology, genetics, social and behavioral sciences, and infectious diseases.
For instance, as soon as the reports of first few cases of COVID-19 came out in the southern state of Kerala in India, a team of health officials and the state disaster management authorities worked on war footing to collate the entire surveillance data of the affected people into live geo-maps, with each of the primary and secondary contacts traced, marked and identified on the map. Another map shows the classification of high-risk and low-risk zones, with focus on identifying the spread and possible on ground clusters of the possible expanse of the disease.
Early detection is crucial when people are being exposed to potentially fatal diseases, and geospatial technology enables us to detect and respond to diseases in time. As Stefan Schweinfest, Director, Statistics Division, United Nations (UNSD/DESA), explains, “A health crisis is a human crisis. The immediate need for the provision of services is at the local level. We need to have the means in place to help every individual that is affected, and that presupposes of course that we know WHERE they are and WHAT services are nearby to provide the required support.”
Contextualized data and geographical insights generated from digital maps and location-based technologies such as geofencing, GPS trackers and sensors can throw historic and predictive insights on patient behaviors along with minute layers of details on the existing system discrepancies and inefficiencies, thus simplifying planning and execution of health resources and programs, points out Nikhil Kumar, Country Head — India, HERE Technologies. This can enable healthcare givers, medical practitioners and government agencies to prepare in advance for a disease outbreak, thus supporting in emergencies during an outbreak.
Naturally, all authorities are looking at data through maps and interactive visualizations in these days of crisis, because “we instinctively understand the integrative power of mapping data; where people are affected, even concentrated areas and clustering,” Schweinfest adds. Plotting on a map can bring different dimensions of a challenge together. Some are demographic questions — what is the age profile, are they in communities with senior citizens and do they have the necessary health services nearby. Some may be focused on economic activity, transport patterns, environmental factors and social behavior. Others may be able to define and identify sources or ‘hot spots’ of infections to avoid, right down to individual cities, suburbs and neighborhoods. All of these elements are critical to understand the spread of an epidemic, to predict it, to intervene, to manage it and to prevent it in the future.
“We know all too well that these global pandemics are matters of life and death, and it is, therefore, critical that geospatial technologies be employed to the greatest extent possible in helping address these issues,” underlines Barbara Ryan, former Director, Group on Earth Observation.
Particularly in case of an epidemic, use of geospatial information technologies can realize personnel tracking, confirmed case distribution, grid management and spatial Big Data analysis to help authorities make smart decisions in epidemic prevention and control. When combined with Big Data, geospatial information technologies can play positive roles in the rapid visualization, dissemination of epidemic information, spatial tracing of virus source, prediction of regional spreads, risk division of regions, identification of prevention and control priorities, control of resources, social emotional guidance, and panic elimination, explains Zhang Yaqing, Technical Director, Platform Center, SuperMap, whose company was involved in the COVID-19 combat operations in China.
“Through data visualization, the trend of the disease, medical treatment and other related conditions were visualized on a map. The display of layered maps enabled the hierarchical regional management and control to assist small-to-community block management,” adds Li Yunxia, Account Director, Platform Center, SuperMap. Thus, a multi-level management and control system for networked control, regional sub-control and community joint control were formed to improve the enforceability and reliability of policies and measures.
Health departments can realize the import, query and maintenance functions of the designated format of infectious disease report cards of the national CDC system, online direct reporting and exporting of infectious disease survey chart. And the early warning based on absolute data comparison, synchronic comparison, poison distribution of infectious disease report card data can be achieved.
Health departments can report and confirm incidents and allocate resources directly through the network. Different processes can be performed according to a specific event, for instance, the real-time reports of emergency events by region, time, and type, centralized query export of emergency-related cases, and real-time analysis charts of emergency events by region and time.
The allocation of basic public health resources is the allocation of resources in response to public health emergencies in daily work. Once in an emergency state, it is possible to quickly understand the use of resources and the status of available resources, which would help to coordinate resources to a great extent in emergency situations.
As we saw with the COVID-19 pandemic, and even earlier with SARS and MERS, infectious diseases that were formerly confined to remote areas now have the ability to expand their geographic range, jump species, become resistant to antimicrobial agents, and become more virulent and frequent. The combination of geospatial data from earth observation systems and public health surveillance can be used to improve public health decision-making, policy-relevant analysis and disease control, points out Ryan.
For instance, WHO, in partnership with the Bill and Melinda Gates Foundation, ran an large-scale program for polio eradication globally wherein they made extensive use of crowdsourcing and GIS technologies for predicting, preventing and controlling the spread of that disease.
“Predictive modeling can tell us areas where the greatest need or risk will be with 30, 60, and 90-day forecasts. This can help us mobilize resources in these locations in advance so that we can act faster,” says Kathryn M. Clifton, Data and Communications Manager, Information Communications Technologies for Development, Catholic Relief Services. Modeling and data analytics can inform these choices better than past events alone.
In terms of health, that’s paramount — better timing can save thousands of lives. Clifton suggests that public health should follow similar approach like in natural disasters. To avert natural disasters, areas that are at greater risk for emergencies are identified first and centers/agencies are set up to respond more quickly. The same can be done in the health arena.hat we all immediately see is the visualization of the existing spread of the virus by location, and at a particular point in time – and by particular profiles; age, gender, etc. However, predictive models of spread, that also capture behavioral aspects, are much more sophisticated and can take into account critical geospatial elements such as population density, demographic data, and transport routes,” highlights Schweinfest.
Dr. Belesova points out that increasingly geospatial data is being included in more complex models used to inform early warning systems, model disease transmission and evaluate impacts of public health interventions. Many modern epidemiological methods are based on spatial and temporal, as well as spatio-temporal analyses, including the use of geospatial and satellite data.
For instance, the Centre on Climate Change and Planetary Health of the London School of Hygiene and Tropical Medicine uses advanced modeling techniques to link data on infectious diseases with climate and other environmental changes and develop early warning systems driven by earth observation data. Other examples include identifying spatial and environmental risk factors for infectious diseases by applying geo-statistical and Machine Learning approaches using aerial (drone) and satellite-based remote sensing data to assess how ecological and environmental changes impact infectious disease transmission.
The School is also collaborating with World Resources Institute for developing a Planetary Health Watch — a system aimed at integrated monitoring of factors related to health impacts of global environmental changes, drivers of these changes, and policy responses to protect health.
Dr. Belesova, however, warns that one has to be careful when reporting and visualizing data on COVID-19 cases. “These are cases that have not been tested or even visible. Countries currently have different capacity to test for the disease, which affects the proportion of cases that is captured in data on confirmed cases.”
Agrees Dr. Geraghty. “While plotting cases is a critical step to understanding information, emergencies like the COVID-19 pandemic require informed action. We need platforms and tools that can support actions like gathering and storing foundational data and newly collected data, analyzing inputs, providing decision support, prioritizing resource allocation, performing fieldwork and evaluating outcomes.”
GeoAI or Geospatial Artificial Intelligence is an emerging scientific discipline that combines innovations in spatial science, Artificial Intelligence methods in Machine Learning, Big Data mining, and high-performance computing to extract knowledge from spatial Big Data.
GeoAI is increasingly being used to model and capture the environment around us, linking locations in which we live and work, or people/elements we interact with, to explore their potential role in influencing health outcomes. There is also extensive research into GeoAI being used for hypothesis generation, conducting new data linkages and predicting disease occurrence.
With the development of mobile technology, the users’ locations can be identified by mobile phone, which means signalling data can obtain personnel location information to track personnel trajectories. The disease prevention and control organizations can analyze close contact groups based on the travel information of diagnoses. Thus they can quickly find suspected patients and close contacts through data retrospective analysis, which is the so-called “contact tracking” and helps to quarantine and cut off the source of infection in time, explains Zhang.
Location analytics provide useful tools to model behaviors and inform actions. From maps that analyze the genetic profile of the virus as it spreads from place to place to AI techniques that make sense of human movement data, we can enhance our understanding of viral transmission, determine if public health recommendations are being followed and predict whether travel bans and other measures will quell the spread of disease, adds Dr. Geraghty.
There are examples where GeoAI was used in infectious disease modelling or prediction of disease occurrence and for disease surveillance. For instance, Deep Learning recurrent neural networks were used for real-time influenza forecasting at regional and city spatial scales in the US using spatial Big Data on Google Flu Trends and climate data (such as precipitation, temperature, sun exposure) from the National Climatic Data Centre. Geotagged tweets were analyzed against the CDC influenza-like illness (ILI) dataset to predict real-time regional ILI in the US using an artificial neural network (ANN) optimized by an artificial tree algorithm.
China earlier used Machine Learning to accurately forecast dengue outbreak in 2014 using climate data, weekly dengue fever cases, and research queries on the Chinese Internet search engine Baidu.
Advancements in Artificial Intelligence have also seen a growing interest in real-time syndromic surveillance based on social media data in recent years. Deep Learning algorithms can be applied to Twitter data to detect illness outbreaks and then to build up and display information about these outbreaks, including relevant news articles, to provide situational awareness. In the US, this has demonstrated an ability to detect symptoms for Influenza-like illness, which were then confirmed from the CDC Morbidity and Mortality Weekly Reports (MMWR). There is further research onto improve on this surveillance system to incorporate disease-specific information (e.g., mode of transmission) to enhance disease forecasting accuracy.
When a major epidemic comes, the impact of panic on social operation may exceed the viral disease itself. To this end, it is necessary to track and evaluate the spatial spread of social emotions by analyzing massive social media data. For instance, as Li of SuperMap says, when facing an epidemic, public behavior might be irrational, highly infectious, and conformable. It is required to build a knowledge base of epidemic-related emotions and to dig out the dynamic evolution of public opinion in time, space and semantics aspects from social media.
By using Internet social data as a data source, the public topic categories from social data related to the epidemic can be obtained based on the construction of topic extraction and sentiment classification framework by topic models and Machine Learning methods. Based on the complex networks, the changing network of public topic can be built. Also, by using the network model, the public dynamic changes in topical emotions can be characterized. These outcomes contribute to the reveal of the temporal, spatial and semantic distribution characteristics and evolution patterns of public topic views under the COVID-19, adds Zhang.
According to Luis Sanz, CEO, CARTO, innovative statistical methods and computational tools can be used for public health surveillance including spatio-temporal models for disease risk prediction, cluster detection, and travel-related spread of disease, which can further inform strategic policy in reducing the burden of diseases.
“We are seeing an increasing trend of using geospatial tools for prevention and containment. An example of using geospatial for analysis and not just visualization is this risk analysis carried out by researchers in Spain, Brazil and the US,” he points out.
The COVID-19 Map of Propagation Risk in the three countries aims to show the results of the estimated epidemic risk right down to the municipal level by modelling the epidemic spread which takes into account the recurrent mobility patterns (commuting) among municipalities. Incidentally, update of the map risk for Spain has been suspended temporarily due to unavailability of real mobility data following the declaration of a state of alarm in the country.
The AsistenciaCovid19 app is an interesting example. While the primary and initial aim of the app is to reduce the pressure on emergency systems and track the status of symptoms when people are taking care of themselves at home, it also provides a method to understand the pandemic from a spatio-temporal perspective. Since there is a location element to the data being collected, the local authorities can visualize infections on an interactive map and perform geospatial analysis to determine high risk areas. Governments can see how symptoms change over time and by location, allowing them to act faster in certain hotspots.
Kumar points to the emergence of wearables and connected devices in the past few years that are capable of collecting a reasonable amount of individual health information such as heart rate patterns, sleeping patterns, etc. “Integrating this data into GIS technologies could help healthcare workers to uncover long term geographic trends in health of certain demographics or individuals living within certain regions, thus opening new realms of healthcare research and providing insights not previously attainable,” he believes.
As of March 31, 2020, US had the maximum number of Coronavirus cases, leaving behind China and Italy
At present, it seems prima facie geospatial tools are being used mostly for data visualization. While there have been sporadic initiatives in spatial modelling of public healthcare information for disease prediction and prevention, what is wanting is a sophisticated integration of spatial analysis and GIS.
Even in cases where it is being used for predictive modelling, the efforts are either localized or too small to be implemented on a global scale. The biggest example of this is while the World Health Organization (WHO) houses a map gallery within its Global Health Observatory, it hosts no exclusive geospatial data on health in crises environments. There has been some effort once the enormity of COVID-19 outbreak became clear, but most of it is reactive and not proactive.
Interestingly, in an internal survey of development organizations by Geospatial Media, it emerged that Health, which is SDG number 3, is not as big a priority area as compared to Land Rights, Environment Protection, Community Development and Emergency Response. (Graph 1) Even otherwise, disciplines such as urban planning and infrastructure, agriculture, natural resources and others have outpaced public and humanitarian health sciences in applying geospatial technologies. This reflects in the priority areas for businesses as emerged in the Geospatial World Business Leaders’ Outlook 2020, a survey of 100+ CEOs and business leaders where health didn’t find a mention (Graph 2), in the top ten list.
Healthcare organizations and medical practitioners usually have access to vast amounts of operational data that mostly tells a small part of the patient and treatment story. Converging spatial technology with medical data through visual mapping and predictive models could lead to informed treatment decisions and creation of timely health interventions, says Kumar.
However, Clifton points out that often what happens in the health space is that national governments contribute this information to international health officials and few people know about these efforts. “In the development sector we could utilize community mapping better to plan how communities will respond to a health crisis. Improving planning for events like this is very important to make sure resources are in place to help the most vulnerable,” she says. Clifton agrees that there is an issue in prioritizing of the efforts since in general, acute or ongoing crises are always prioritize over potential crises.