In a remarkable showcase of cutting-edge research and innovation, Beatriz Merino from BEAMER’s Work Package 2 participated in the 25th International Conference on Human-Computer Interaction, hosted at the prestigious AC Bella Sky Hotel and Bella Center.
The conference served as a global platform for sharing advancements in the realm of human-computer interaction. Beatriz represented BEAMER and presented groundbreaking work accomplished within the project.
Her presentation revolved around the outcomes of Work Package 2, a pivotal phase involving the execution of a comprehensive stakeholder strategy. This expertly designed approach aimed to gather essential model requirements, playing a crucial role in shaping the direction of BEAMER’s research. The presentation delved into the intricacies of stakeholder engagement and highlighted results obtained through this collaborative approach.
A conference highlight was the acceptance of BEAMER’s study titled ‘Multi-stakeholder Approach for Designing an AI Model to Predict Treatment Adherence’.
This remarkable achievement underscores BEAMER’s commitment to developing innovative solutions that bridge the gap between technology and healthcare. In this study, semi-structured interviews were conducted with eleven stakeholders from four groups: patients, healthcare professionals, data scientists, and pharmacists. The needs and requirements received were categorised into four key aspects that were translated into requirements and needs: understanding the nature of the drivers, scope, and impact of the problem; identifying data sources; understanding relevant data points; and addressing potential ethical issues.
“We are thrilled to have our work recognized at such a prestigious international forum,” said Beatriz. “This acknowledgement is a testament to the hard work of the entire BEAMER team and the collaborative spirit of our stakeholders.”
Explore the study’s publication here, offering readers an in-depth exploration of the innovative approach and its potential impact on treatment adherence prediction.