The Humanitarian Engineering Initiative (HEI) at the American University of Beirut (AUB) has completed an innovative project titled “Health Information Bot Assistant – HIBA: AI-mediated Interactive Health Messaging for Community Health Promotion in Low-Middle Income Countries." Funded by the Bill & Melinda Gates Foundation - Grand Challenges Grants, HIBA leverages artificial intelligence (AI) to provide accessible, real-time, and reliable health communication for underserved populations in low- and middle-income countries.
HIBA's importance lies in addressing systemic gaps in health communication through several measures. These include context-sensitive development, which draws insights from community assessments to deliver health messages; AI optimization utilizing GPT-4 and ReAct prompt engineering to minimize inaccuracies and hallucinations; dynamic information updates that enable real-time adaptations to emerging health challenges, such as disease outbreaks. Continuous feedback loops supported by a robust testing framework and human oversight ensure alignment with evidence-based guidelines.
The technology was developed based on a context assessment in Lebanon and Jordan, conducted by AUB in collaboration with the International Federation of Red Cross and Red Crescent Societies (IFRC) and national Red Cross and Red Crescent Societies. The assessment identified community-specific health literacy needs and cultural nuances, ensuring the chatbot's messages are both accurate and culturally appropriate. Recently, HIBA was deployed in displacement centers using QR-coded posters, where it provided users with a private and secure channel to access health information. HIBA could prove to be a transformative tool for displaced populations, particularly those affected by the ongoing crisis in Lebanon.
The chatbot's ability to provide health information in multiple languages and formats (text and audio) ensures inclusivity, empowering users to make informed health decisions regardless of literacy barriers. While the full impact of HIBA on health behaviors is yet to be assessed, preliminary outreach metrics, such as interaction frequency and topic trend analysis, indicate high levels of user engagement.
The multidisciplinary approach of the Humanitarian Engineering Initiative (HEI), combining expertise from the Faculty of Health Sciences (FHS) and the Maroun Semaan Faculty of Engineering and Architecture (MSFEA), was pivotal in the development of HIBA. This collaboration harnessed the strengths of engineering and public health to create an innovative, AI-enabled health communication platform. The engineering team contributed their expertise in artificial intelligence, machine learning, natural language processing (NLP), and system architecture, designing a scalable, multilingual chatbot capable of responding to user queries. Simultaneously, the public health team ensured that the platform provided credible and accurate information, while also aligning with the health literacy levels, cultural contexts, and specific needs of marginalized communities. By integrating technological advancements with public health priorities, the team developed a tool that not only disseminates reliable and accessible health information but also overcomes systemic barriers like literacy, language, and stigma. This seamless fusion of disciplines exemplifies how engineering and public health can converge to address critical global challenges, delivering practical, community-driven solutions like HIBA.