Data availability is critical to applying machine learning and AI technologies to health. More specifically, open or FAIR data ensures that researchers can test, train and test their models. This project aims to understand some of the open data available in Kenya and to use exploratory analysis to identify interesting questions that can be addressed using the data. Specifically, we would be keen to see some of the data on HIV, Malaria, and Maternal and mental health. To understand how much public data is available, use a combination of literature search and data extraction from various public resources. In addition to the open data, which other datasets are available from public health resources like the DHSI that can be used to understand trends, like what drives certain diseases? From the list of datasets identified, select a research question about HIV, malaria, or maternal and mental health that can be addressed using the datasets you have identified, and apply machine learning techniques to explore the question.
- From the sources Identified, what is the process of accessing the data?
- Do they adhere to the data protection laws and ethical practices?
- What are the gaps and challenges?
- Identify some datasets from Kenya on HIV, Malaria or maternal and mental health, and apply machine learning