Publications

Total: 126
Identifying residential neighbourhood types from settlement points in a machine learning approach
Computers, Environment and Urban Systems (2018).
Author(s): Warren C. Jochem, , Tomas J. Bird, Andrew J. Tatem
Type: method. Year: 2018
DOI: 10.1016/j.compenvurbsys.2018.01.004.

Abstract: Remote sensing techniques are now commonly applied to map and monitor urban land uses to measure growth and to assist with development and planning. Recent work in this area has highlighted the use of textures and other spatial features that can be measured in very high spatial resolution imagery. Far less attention has been given to using geospatial vector data (i.e. points, lines, polygons) to map land uses. This paper presents an approach to distinguish residential settlement types (regular vs. irregular) using an existing database of settlement points locating structures. Nine data features describing the density, distance, angles, and spacing of the settlement points are calculated at multiple spatial scales. These data are analysed alone and with five common remote sensing measures on elevation, slope, vegetation, and nighttime lights in a supervised machine learning approach to classify land use areas. The method was tested in seven provinces of Afghanistan (Balkh, Helmand, Herat, Kabul, Kandahar, Kunduz, Nangarhar). Overall accuracy ranged from 78% in Kandahar to 90% in Nangarhar. This research demonstrates the potential to accurately map land uses from even the simplest representation of structures.
Link to paper


High resolution age-structured mapping of childhood vaccination coverage in low and middle income countries
Vaccine, (2018).
Author(s): C. Edson Utazi, Julia Thorley, Victor A. Alegana, Matthew J. Ferrari, Saki Takahashi, C. Jessica E. Metcalf, Justin Lessler, Andrew J. Tatem
Type: method. Year: 2018
DOI: 10.1016/j.vaccine.2018.02.020.

Abstract: The expansion of childhood vaccination programs in low and middle income countries has been a substantial public health success story. Indicators of the performance of intervention programmes such as coverage levels and numbers covered are typically measured through national statistics or at the scale of large regions due to survey design, administrative convenience or operational limitations. These mask heterogeneities and 'coldspots' of low coverage that may allow diseases to persist, even if overall coverage is high. Hence, to decrease inequities and accelerate progress towards disease elimination goals, fine-scale variation in coverage should be better characterized.
Link to paper


Productive disruption: opportunities and challenges for innovation in infectious disease surveillance.
BMJ Global Health, (2018) .
Author(s): Caroline O. Buckee, Maria I E Cardenas, June Corpuz, Arpita Ghosh, Farhana Haque, Jahirul Karim, Ayesha S. Mahmud, Richard J Maude, Keitly Mensah, Nkengafac Villyen Motaze, Maria Nabaggala, Charlotte Jessica Eland Metcalf, Sedera Aurélien Mioramalala, Frank Mubiru, Corey M. Peak, Santanu Pramanik, Jean Marius Rakotondramanga, Eric Remera, Ipsita Sinha, Siv Sovannaroth, Andrew J Tatem, Win Zaw
Type: method. Year: 2018
DOI: 10.1136/bmjgh-2017-000538.

Abstract: Infectious diseases place an unacceptable and disproportionate social and economic burden on low-income countries. National disease control programmes have the difficult task of allocating limited budgets for interventions across regions of their countries, based on often disparate datasets of varying quality from a range of sources including clinics, hospitals, village health workers, the private sector and non-governmental organisations (NGOs). Every stage of the data collection and analysis pipeline for surveillance systems may be affected by a lack of capacity as well as by biases and misaligned incentives for reporting and managing data. Addressing these issues will be essential for effective reduction in the burden of endemic infectious diseases globally as well as to preparing for emerging epidemic threats. Meanwhile, academic researchers—often in high-income settings—are developing increasingly sophisticated methods to collect and analyse data to improve spatial estimates of disease burden using new Big Data sources, mobile-Health or m-Health approaches or mechanistic and statistical modelling techniques. While these advances leap ahead, however, many remain most useful for estimating global disease distribution,1 rather than for national control programme prioritisation. Translating these new techniques to inform policy in endemic settings remains challenging. The pronounced disconnect between health systems and academia may limit the utility of new approaches. The high burden of work placed on healthcare workers in low-income settings further limits their scope and time available for engagement with methodological developments. Despite ongoing challenges to implementation, however, there are promising analytical approaches that can leverage even patchy and low-quality data and diverse new data streams that can be productively harnessed to strengthen strategies for resource allocation when integrated with existing surveillance systems. We detail the data and analysis challenges faced by national disease control programmes, outline possible solutions offered by analytical approaches and new data-streams and conclude by outlining barriers to implementation.
Link to paper


Mapping road network communities for guiding disease surveillance and control strategies
Scientific Reportsvolume 8, Article number: 4744 (2018) .
Author(s): Emanuele Strano, Matheus P. Viana, Alessandro Sorichetta & Andrew J. Tatem.
Type: method. Year: 2018
DOI: 10.1038/s41598-018-22969-4.

Abstract: Human mobility is increasing in its volume, speed and reach, leading to the movement and introduction of pathogens through infected travelers. An understanding of how areas are connected, the strength of these connections and how this translates into disease spread is valuable for planning surveillance and designing control and elimination strategies. While analyses have been undertaken to identify and map connectivity in global air, shipping and migration networks, such analyses have yet to be undertaken on the road networks that carry the vast majority of travellers in low and middle income settings. Here we present methods for identifying road connectivity communities, as well as mapping bridge areas between communities and key linkage routes. We apply these to Africa, and show how many highly-connected communities straddle national borders and when integrating malaria prevalence and population data as an example, the communities change, highlighting regions most strongly connected to areas of high burden. The approaches and results presented provide a flexible tool for supporting the design of disease surveillance and control strategies through mapping areas of high connectivity that form coherent units of intervention and key link routes between communities for targeting surveillance.
Link to paper