Indirect Influences of Artificial Intelligence Advice on Complex Sepsis Treatment Decisions

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.

Fluoxetine Hydrochloride Treatment Influences Site-Specific ADAR Editing and Transcriptome Regulation in Arid1b +/- Mice
A. Tariq, H. Piontkivska
bioRxiv24 Sep 2026PreprintCC BY-NC-NDFull textBioinformatics & computational biologybioRxiv
Toward Enactive Artificial Intelligence
Banafsheh Rafiee, R Sutton
arXiv (Cornell University)22 May 2026PreprintLicence not statedFull text6 citedNeuroscienceOpenAlex
Growing up with artificial intelligence: An amplifier of inequalities and a public health issue
Théo Mouhoud, Thierry Baubet
L'Encéphale27 Jul 2026Peer-reviewedPublisher termsFull textGeneral biology Psychiatry & mental healthHAL
Notification: Artificial Intelligence in Autism Spectrum Disorder Diagnosis: A Scoping Review of Face, Voice, and Text Analysis Methods.
Health science reports21 Oct 2026Peer-reviewedCC BYFull textNeuroscienceEurope PMCPMC
Early Detection of Red Palm Weevil Infestation: A Systematic Review of Sensing Technologies, Artificial Intelligence, and Field Readiness
Lubna A. Gabralla, Amnah Alshahrani
Insects1 Oct 2026Peer-reviewedCC BYFull textGeneral biologyEurope PMC

Cite

BibTeX RIS

BibTeX

@misc{sivaraman2026indirect,
  title = {{Indirect Influences of Artificial Intelligence Advice on Complex Sepsis Treatment Decisions}},
  author = {Venkatesh Sivaraman and Joel Levin and Eric P. Mason and Victor Talisa and Suchi Saria and Jean Feng and Andrew J. King and Jeremy M. Kahn and Adam Perer},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.24313},
  eprint = {2610.24313},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.24313},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Indirect Influences of Artificial Intelligence Advice on Complex Sepsis Treatment Decisions
AU  - Venkatesh Sivaraman
AU  - Joel Levin
AU  - Eric P. Mason
AU  - Victor Talisa
AU  - Suchi Saria
AU  - Jean Feng
AU  - Andrew J. King
AU  - Jeremy M. Kahn
AU  - Adam Perer
PY  - 2026
DA  - 2026/10/16
PB  - arXiv
DO  - 10.48550/arxiv.2610.24313
UR  - https://arxiv.org/abs/2610.24313
AB  - 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.
ER  -

Abstract

Related

Cite