Study design and protocol for investigating social network patterns in rural and urban schools and households in a coastal setting in Kenya using wearable proximity sensors

Abstract

Background: Social contact patterns shape the transmission of respiratory infections spread via close interactions. There is a paucity of observational data from schools and households, particularly in developing countries. Portable wireless sensors can record unbiased proximity events between individuals facing each other, shedding light on pathways of infection transmission. Design and methods: The aim is to characterize face-to-face contact patterns that may shape the transmission of respiratory infections in schools and households in Kilifi, Kenya. Two schools, one each from a rural and urban area, will be purposively selected. From each school, 350 students will be randomly selected proportional to class size and gender to participate. Nine index students from each school will be randomly selected and followed-up to their households. All index household residents will be recruited into the study. A further 3-5 neighbouring households will also be recruited to give a maximum of 350 participants per household setting. The sample size per site is limited by the number of sensors available for data collection. Each participant will wear a wireless proximity sensor lying on their chest area for 7 consecutive days. Data on proximal dyadic interactions will be collected automatically by the sensors only for participants who are face-to-face. Key characteristics of interest include the distribution of degree and the frequency and duration of contacts and their variation in rural and urban areas. These will be stratified by age, gender, role, and day of the week. Expected results: Resultant data will inform on social contact patterns in rural and urban areas of a previously unstudied population. Ensuing data will be used to parameterize mathematical simulation models of transmission of a range of respiratory viruses, including respiratory syncytial virus, and used to explore the impact of intervention measures such as vaccination and social distancing.

Keywords: contact networks; contact patterns; infectious disease transmission; respiratory infections; wearable proximity sensors.

Figure 1.. Map showing study locations.

( A) The location of Kilifi County within Kenya. ( B) The extent of the Kilifi Health and demographic Surveillance Site (KHDSS) within Kilifi county. ( C) The locations of rural (orange) and urban (purple) sites, highlighting the location of each of the schools and the nearby health centre.

Figure 2.. Conceptualization of an interaction framework within and between schools and households.

In this scenario, there are children (not attending school), school students and adults. Interactions can occur within or between households, and within and between students and teachers in various classes.

Figure 3.. Wireless proximity sensors.

( A) A sensor next to a ruler. ( B) and ( C) How a sensor will be worn by participants, either around the neck with a lanyard or pinned to the shirt pocket, respectively. Household participants will be able to choose the colour of the pouch ( B). Students will have a pouch with colour similar to their school shirt/blouse.

Figure 4.. Schema demonstrating the definition of contact event and contact duration.

There are 5 individuals. Each red horizontal line represents an interaction between two individuals i (1–5) and j lasting s-seconds. Individual 1 has zero contact events since the duration of contact is <20 seconds. Individual 2 has 1 contact event lasting exactly 20 secs. Individual 3 has three contact events with a 20-sec interruption between the contact events. Individuals 4 and 5 have three and six contact events lasting 60- and 120-seconds, respectively.