Comprehensive profiling of social mixing patterns in resource poor countries: A mixed methods research protocol

Abstract

Background: Low-and-middle-income countries (LMICs) bear a disproportionate burden of communicable diseases. Social interaction data inform infectious disease models and disease prevention strategies. The variations in demographics and contact patterns across ages, cultures, and locations significantly impact infectious disease dynamics and pathogen transmission. LMICs lack sufficient social interaction data for infectious disease modeling.

Methods: To address this gap, we will collect qualitative and quantitative data from eight study sites (encompassing both rural and urban settings) across Guatemala, India, Pakistan, and Mozambique. We will conduct focus group discussions and cognitive interviews to assess the feasibility and acceptability of our data collection tools at each site. Thematic and rapid analyses will help to identify key themes and categories through coding, guiding the design of quantitative data collection tools (enrollment survey, contact diaries, exit survey, and wearable proximity sensors) and the implementation of study procedures. We will create three age-specific contact matrices (physical, nonphysical, and both) at each study site using data from standardized contact diaries to characterize the patterns of social mixing. Regression analysis will be conducted to identify key drivers of contacts. We will comprehensively profile the frequency, duration, and intensity of infants' interactions with household members using high resolution data from the proximity sensors and calculating infants' proximity score (fraction of time spent by each household member in proximity with the infant, over the total infant contact time) for each household member.

Discussion: Our qualitative data yielded insights into the perceptions and acceptability of contact diaries and wearable proximity sensors for collecting social mixing data in LMICs. The quantitative data will allow a more accurate representation of human interactions that lead to the transmission of pathogens through close contact in LMICs. Our findings will provide more appropriate social mixing data for parameterizing mathematical models of LMIC populations. Our study tools could be adapted for other studies.

Fig 1. Global map showing the location of Guatemala, India, Mozambique, and Pakistan.

Each country has one rural and one urban site. There are separate rural (Manhica and Matiari) and urban (Maputo and Karachi East) sites in Mozambique and Pakistan, respectively. In Guatemala, rural and urban clusters will be identified from the Quetzaltenango and xxx. In India, rural and urban areas will be selected from Vellore. Reprinted from GADM under a CC BY license, with permission from GADM, original copyright [2024].

Fig 2. Schematic representation of the sensors.

The sensor board consists of an antenna, flash storage device, and mini-USB port (A). A sensor will be powered by a battery and placed in a plastic case with a sealable weather-proof cover that will be disinfected in between each use (B). Sensors transmit signals only in the forward direction, thus only detecting close face-to-face interactions when hung around the neck or worn in a shirt/blouse pocket (C). The signals containing data packets are stored in the on-board memory of the sensor.

Fig 3. Flow of field visits showing data collection procedures for the three visits (contact diary study).

Fig 4. Flow of field visit showing data collection procedures for the three visits for the (proximity sensor device study).

Fig 5. Household contact network.

Contact networks will be visualized in order to depict the presence, type and characteristics of contacts (edges). Here, as an example, household members are represented as nodes color coded for relationship to the infant. The thickness of the edges represents cumulative time in contact, with thicker/darker edges representing more time spent in contact.