​UZIMA-DS: UtiliZing Health Information for Meaningful Impact in East Africa through Data Science

Project Period: 2021 – 2026

Funder: National Institute of Health

Collaborators: Aga Khan University; University of Michigan; Dalhousie University; Ottawa University; Kenya Medical Research Institute- Wellcome Trust Research Programme; Clinton Health Access Initiative

Overall Project Summary: This project aims to address the analytical and computational barriers that impede the ability to use technological advances in data science to change health care at the community and individual level. In addressing this barrier, the project is applying novel approaches to data assimilation and advanced artificial intelligence (AI)/machine learning (ML)-based methods to serve as early warning systems to critical health issues impacting Africans in two domains: maternal, new-born and child health and mental health. Ultimately, the UZIMA-DS hub will develop a scalable and sustainable platform characterised by:

  1. Harmonization of multimodal data sources for meaningful use and analyses.
  2. Leveraging temporal patterns of data to identify trajectories through prediction modelling using AI/ML-based methods, and
  3. Engaging with key stakeholders to identify pathways for dissemination and sustainability of these models into target communities.

Mental Health Project: As part of the UZIMA-DS Hub, the Brain and Mind Institute is leading the Mental Health component where we are leveraging existing surveillance data as well as novel mobile technologies (e.g., mobile apps, wearables) for the development of existing and new AI/ML-based prediction models to identify adolescents, youth, and healthcare workers at risk of depression and suicide ideation in Kenya.

The project is being rolled out in three phases in line with three aims:

  1. In aim 1, we are rolling out a longitudinal study among 900 health care workers and collecting quarterly mental health indicators such as depression and personality as well as daily data on mood, sleep, and steps, using a mobile app that is synced with a Fitbit. The data collected will help us identify behavioural indicators for mood that can be validated against AI/ML prediction models.
  2. In aim 2, we are collecting mental health indicators among 9000, 8 – 24-year-old participants within a cohort in the Kilifi Health and Demographic Surveillance System (KHDSS). This data will help us know the determinants of mental health among adolescents and young people as well as develop and validate AI/ML-based prediction models for risk of depression and suicide ideation in this cohort.
  3. In aim 3, we are enrolling university students and collecting mental health indicators as captured in the World Mental Health International College Student Initiative (WHO-ICS). The data will be used to create a cohort of participants that we can track their incidence, prevalence, and treatment of mental health disorders. The data will also be used in development of future risk prediction model and precision intervention strategies.

The findings in the mental health project will ultimately address on-going and evolving mental health needs of Africans by build a prediction infrastructure for mental health management and prevention.​