How to Use SciSpace AI for Literature Search and Review - Possibility and Ethical Guidelines
Literature search and review are foundational to high-quality research but they are also time-consuming and increasingly complex. How can researchers use AI tools like SciSpace to accelerate discovery without compromising academic integrity?
In this session, Paul Hassan Ilegbusi, Senior Lecturer and Deputy Director (Community Health), will explore how SciSpace AI can support literature search, evidence review, and research synthesis — particularly within public health and community-based research contexts.
The session will cover:
Using AI to streamline literature search and screening
Extracting key insights from research papers efficiently
Supporting evidence-based review and synthesis
Avoiding over-reliance on AI-generated summaries
Ethical guidelines for responsible AI use in academic research
Drawing from over two decades of experience in public health education and research, Ilegbusi will also discuss the importance of reproducibility, transparency, and human judgment in AI-assisted workflows.
This webinar is designed for public health professionals, researchers, educators, and graduate students seeking a practical and ethically grounded approach to integrating AI into literature review and research practice.
About the Author
Paul Hassan Ilegbusi is a distinguished public health expert and Senior Lecturer at Ondo State College of Health Technology, Akure, Nigeria, where he also serves as Deputy Director (Community Health). A Registered Community Health Practitioner since 1996, he brings over two decades of experience in public health education, clinical training, and research supervision.
He is an active member of several international academic and research organizations and serves as an Examiner and Clinical Skills Assessor for the Community Health Practitioners Registration Board of Nigeria (CHPRBN). A published researcher and global conference speaker, Ilegbusi is also a certified African Reproducibility Network (AREN) Local Network Lead, reflecting his strong commitment to research integrity and reproducibility.
Passionate about innovation in public health research, he advocates for the responsible integration of AI tools to enhance data analysis, evidence synthesis, and decision-making in healthcare and community research.