Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.


An estimated 250 million people worldwide have schistosomiasis infections, of which 80% are in sub-Saharan Africa. In 2017, schistosomiasis caused at least 1.43 million disability adjusted life years. Blood flukes (parasitic worms) cause schistosomiasis. Transmission to humans is via contact with freshwater sources that are contaminated through open defecation/urination and harbour competent intermediate snail hosts. Water, sanitation, and hygiene (WASH) interventions are promoted as interventions to reduce pathogen transmission.

Consistently identifying effective WASH interventions that reduce schistosomiasis infection risks is challenging. One reason entails the heterogeneity in human activities that puts individuals at risk of infection. Exposure to parasites varies based on occupation, gender, and household role. And, there are challenges in measuring activities in water. We currently lack the granularity to identify who enters the water at what time for what duration and which activity.

Wearable cameras offer the potential to measure activities from first person perspectives. Previously unrecognized activities that may contribute to parasite exposure could be identified. When layered with infection data, there is the opportunity to identify the composition of activities that most affect the probability of infection and new WASH strategies. This project will undertake the monitoring of activities of a rural village in Uganda, with the aims of capturing image data from individuals aged 1+ years.

research experience, research methods and training

This project will involve:

1) Developing data collection protocols to collect GPS and wearable camera data (in addition to traditional self-reported risk factors).

2) Constructing annotation protocols to manually identify water contact activities from wearable camera data.

3) Developing and validating a multi-modal supervised machine learning classification scheme to automatically identify water contact activities.

4) Investigating epidemiological cross-sectional associations of activities with schistosomiasis infection prevalence and intensity.

The student will gain skills in literature review, study design, primary data collection, data analysis, statistical programming, machine learning, and research presentation.


This project requires fieldwork in rural Uganda in close collaboration with the Vector Control Division at the Uganda Ministry of Health. Experienced field teams from the Uganda Ministry of Health will co-lead the primary data collection with the primary supervisor.

Wearable sensor training will be provided as well as guidance on statistical machine learning and schistosomiasis epidemiology. Access to previous protocols for labeling wearable sensor data will be available.

prospective candidate

Ideally postgraduate training, e.g. MSc/MPhil, in global health, epidemiology, computer science, statistics, or a related discipline. Strong interest in parasitic infections and good communication skills are necessary.