Newest papers

Indirect Influences of Artificial Intelligence Advice on Complex Sepsis Treatment Decisions

Venkatesh Sivaraman, Joel Levin, Eric P. Mason, Victor Talisa, Suchi Saria, Jean Feng, Andrew J. King, Jeremy M. Kahn, Adam Perer · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24313 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

A sepsis é uma grande preocupação de saúde pública, e muitos pacientes com sepsis morrem devido à gestão hemodinâmica ineficaz. A inteligência artificial poderia apoiar decisões hemodinâmicas, particularmente em casos complexos onde informações conflitantes e comorbidades levam à incerteza e à variação da prática. No entanto, o valor real desses sistemas depende não apenas da precisão, mas de como eles influenciam a qualidade das decisões clínicas. Primeiro avaliamos retrospectivamente as recomendações de um sistema de IA em 6.928 pacientes com sepsis, encontrando que elas melhoraram sobre as decisões dos provedores originais em geral, mas tiveram um desempenho significativamente pior em casos complexos. Em seguida, realizamos um experimento pré-registrado com 228 médicos de cuidados críticos dos EUA para testar seu uso

Machine translation (Meta M2M100); the English original follows.

Abstract

Sepsis is a major public health concern, and many sepsis patients die due to ineffective hemodynamic management. Artificial intelligence could support hemodynamic decisions, particularly in complex cases where conflicting information and comorbidities drive uncertainty and practice variation. However, these systems' real-world value depends on not just accuracy, but how they influence the quality of clinician decisions. We first retrospectively evaluated an AI system's recommendations in 6,928 sepsis patients, finding that they improved upon the original providers' decisions overall but had significantly worse performance in complex cases. We then conducted a pre-registered experiment with 228 US critical care physicians to test their use of this imperfect advice in six complex treatment decisions, using one of three advice types designed to vary reasoning autonomy. Participants given simple model recommendations overcame poor advice, choosing optimal treatments in 56.3% of decisions compared to 31.8% if they had always followed the recommendations. They also made significantly better decisions than those receiving a less prescriptive advice type (42.9%). Physicians selectively adapted and improved weak advice, likely because it prompted them to reconsider their assessment. Our findings suggest that improving sepsis care decisions with AI may require accounting for these indirect influences resulting from human-AI collaborative reasoning.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Advice (programming), Medicine, Sepsis, Intensive care medicine, Imperfect, Quality (philosophy)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange