Research

My research asks how people rely on AI in decision-making settings: when they over-rely, when they override, and when they follow AI suggestions appropriately, and what interventions should be used to improve collaboration and decision performance. I've run studies across several settings: clinical assessment, misinformation detection, and group decision-making. Alongside those studies, I've built a framework for AI-assisted decision-making that pulls the field's findings into one structure, for researchers and practitioners who need to design or evaluate these systems, and for a general audience looking to improve their AI literacy and understanding of AI's impact.

AI-Assisted Decision-Making

A framework for AI-assisted decision-making, built from an evidence base of scientific studies. Every AI-assisted decision has three components: the Human and the Task, which characterize each decision setting, and the AI Assistant ecosystem, the only component that can be leveraged to improve the collaboration. It's public, it's a working draft, and it changes as the evidence base grows.

Version V1.0.0 · Updated 2026-08-20 · Read the framework →

All publications

2026
  • AI assistance in medical decision-making: the role of recommendations and explanations in simulated clinical cases M. C. Abreu, R. de Brito Duarte, B. Neves, N. Silva, R. Santos, J. Campos ACM Transactions on Computing for Healthcare Link
  • Effects of interaction and explanation type on human-AI collaboration for fake news detection R. de Brito Duarte, S. Tonati, S. Muñoz, J. Campos, F. Giannotti, R. Prada IEEE Access Link
  • Large language models approach clinician performance in ESC cardiovascular risk stratification: a vignette-based benchmark study J. Ferreira Santos, R. de Brito Duarte, I. Mota, R. C. Santos, J. M. Moreira, et al. European Heart Journal - Digital Health Link
  • Dissecting medical referrals in health services: role of physician professional networks R. de Brito Duarte, Q. Han, C. Soares BMC Health Services Research Link
2025
  • The amplifying effect of explainability in AI-assisted decision-making in groups R. de Brito Duarte, M. C. Abreu, J. Campos, A. Paiva CHI 2025: ACM Conference on Human Factors in Computing Systems Link
  • Assistant robots with an agenda foster uncooperative behaviors J. Brito, R. de Brito Duarte, H. C. Fonseca, J. Campos, F. Correia, A. Paiva 2025 IEEE International Conference on Robot and Human Interactive Communication (RO-MAN) Link
2024
  • Looking for cognitive bias in AI-assisted decision-making R. de Brito Duarte, J. Campos HHAI Workshops Link
2023
  • AI trust: Can explainable AI enhance warranted trust? R. de Brito Duarte, F. Correia, P. Arriaga, A. Paiva Human Behavior and Emerging Technologies Link