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

German

Sepsis ist ein großes öffentliches Gesundheitsrisiko, und viele Sepsis-Patienten sterben aufgrund unwirksames hämodynamisches Management. Künstliche Intelligenz könnte hemodynamische Entscheidungen unterstützen, insbesondere in komplexen Fällen, in denen widersprüchliche Informationen und Komorbiditäten Unsicherheit und Praxis-Variation verursachen. Dennoch hängt der reale Wert dieser Systeme nicht nur von der Genauigkeit ab, sondern wie sie die Qualität der klinischen Entscheidungen beeinflussen. Wir haben zuerst rückblickend die Empfehlungen eines KI-Systems bei 6.928 Sepsis-Patienten bewertet, wobei wir festgestellt haben, dass sie sich auf die Entscheidungen der ursprünglichen Anbieter insgesamt verbessert haben, aber in komplexen Fällen deutlich schlechtere Leistungen hatten. Wir führten dann ein

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