Three (3) University of Lagos dons have won an Artificial Intelligence Grant alongside Nivi, a US healthcare provider/company which provides consumers with on-demand, trusted, and actionable health information that enables them to make more informed and supported decisions about their health.
The Team was selected as part of the winners of USAID’s Equitable AI Challenge which was launched in 2021. The AI Challenge was organised in a bid to look for innovative and creative approaches to address gender-inequitable outcomes which can arise as a result of the use of AI technologies.
Out of a total of 28 diverse semi-finalists which attended a three-week virtual co-creation event, held between February 14 and March 1, 2022, four proposals were selected in April 2022 to receive grant awards to implement their approaches in alignment with the challenge’s objectives.
The challenge, which was carried out through DAI’s Digital Frontiers, aimed to support approaches that increase the accountability and transparency of AI systems in global development contexts in order to produce more gender-equitable outcomes.
UNILAG and Nivi are collaborating to establish a gender-aware auditing tool within their existing health chatbot technology deployment in Nigeria to promote digital health treatments. This tool will help evaluate real user interactions with the chatbot, along with the bot’s interpretation and response, incorporating user feedback on the adequacy of the bot’s response.
The Team will first incorporate automated translation from low-resourced languages, such as Hausa, into English. This will allow scalability of information processing solution, as downstream models for information extraction and then diagnosis can be leveraged in new languages without comprehensive retraining. The team also intends to introduce Yoruba and Igbo later on in the project, as well as apply the tool to improve both the existing Natural Language Processing (NLP) intent recognition modules of Nivi’s health guide chatbot and the new models developed by UNILAG through training and model testing. By building a NLP based system that is more attuned to the needs of each local population, Nivi’s health chatbot and digital health services will have the ability to reach more women, at lower cost, and help them make informed health decisions.
The UNILAG Team comprises Dr. Chika Yinka-Banjo, the Principal Investigator and Senior Lecturer at the Department of Computer Science, Faculty of Science; Dr. Mary Akinyemi of the Department of Mathematics, Faculty of Science and Deputy Director, Office of International Relations, Partnerships and Prospects and Dr. Kemi Omotubora of the Department of Commercial and Industrial Law, Faculty of Law.
The Vice-Chancellor, Prof. Oluwatoyin T. Ogundipe, FAS, on behalf of the Senate, members of staff and students of the University congratulates them on this feat.