Predictive Analytics for Decision-making in Healthcare (PADHE)
In this project, we will explore the application of Explainable AI (XAI) and Causal AI (CAI) methods to develop algorithms that can facilitate trustworthy decision-making in the healthcare domain. XAI is concerned with creating explanation that serves as justification for the results generated by machine learning models (AI) to make their operations transparent and results more believable. Likewise, CAI is concerned with explaining cause-and-effect relationships. Causal AI can help explain the decision-making process and the causes of a decision. XAI and CAI are two new and emerging aspects of AI that can improve human understanding of the operations of predictive (ML) models, leading to increased uptake of their results and better decision-making. Using existing open datasets and currently available datasets on infectious diseases like COVID-19 and Tuberculosis, we will create a data analytics dashboard that enables users/health practitioners to obtain guidance on the prognosis of infectious diseases. We will investigate different machine learning algorithms' performance, explainability and causal reasoning capabilities regarding specific infectious/non-infectious diseases.
Participation:
Prospective Researchers: Bachelor honours, master's, doctoral students, postdoctoral fellows, research collaborators.
Skill Requirements: Expertise in programming (Python/JavaScript/web development), software development, good communication and writing skills.
For more information on PADHE research, contact me via my email: wande.daramolaj@up.ac.za