🤖 AI Summary
This study addresses the challenges of translating animal experimental evidence to humans and the unclear role of artificial intelligence (AI) in supporting multi-stakeholder evidence appraisal. Through semi-structured interviews with thirteen stakeholders and requirements engineering methods, we analyzed their evidence practice challenges and needs for AI-assisted locating, screening, and extracting evidence. The findings reveal differentiated needs across diverse expertise backgrounds, clarify the value of AI in evidence retrieval, and highlight stakeholders’ cautious attitudes toward automated interpretation. Consequently, this work proposes role-sensitive design principles for AI tools, emphasizing transparency, source traceability, uncertainty communication, and human oversight. These principles establish a foundation for developing transparent and controllable AI-driven decision support systems in translational medicine.
📝 Abstract
Animal models are widely used to study human biology and health interventions, yet translating findings from animal studies to humans remains challenging. Evidence across preclinical and clinical research informs experimental and translational decisions. Artificial Intelligence (AI) tools are increasingly reshaping how this evidence is searched, synthesized, and used, but it remains unclear how they should support the diverse stakeholders involved in assessing animal-to-human evidence. We conducted semi-structured interviews with 13 stakeholders to examine their evidence practices, challenges, and expectations for AI support. We found that stakeholders approach the same incomplete evidence base with different goals, expertise, and heuristics. Participants valued AI particularly for locating, screening, and extracting evidence, but were more cautious about automated interpretation and quality judgments. They emphasized transparency, source traceability, uncertainty communication, and human oversight. Based on these findings, we derive design implications for role-sensitive AI tools that support more systematic and transparent reasoning about animal-to-human translation.