EUVIMEDSkopri EUVIMED
Open access

Theoretical Exploration of Error Thresholds for Clinical AI Decision Support in Nursing: Exploratory Simulation Study Grounded in Human-AI Reliance Data

Hiroyuki Tajima

JMIR Nursing · 2026-08-05 · 9 · e99590-e99590

DOI: 10.2196/99590 ↗

At a glance

Journal article in JMIR Nursing, published online on 2026-08-05. Written by Hiroyuki Tajima. Institution: Faculty of Nursing, Shumei University, 1-1 Daigaku-cho, Yachiyo, Chiba, 276-0003, Japan, 81 47-488-2111. Major MEDLINE topics: Decision Support Systems, Clinical, Artificial Intelligence. 35 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Clinical AI decision support is being introduced into nursing practice; however, existing large language models (LLMs) demonstrate only moderate accuracy on complex clinical tasks, raising questions about the level of accuracy required for safe clinical use across varying levels of clinician experience and task complexity.

Objective

The aim of the study is to develop an empirically calibrated simulation model of human-AI reliance and error in nursing decision-making and estimate the AI accuracy required to achieve specified error rate targets.

Methods

A linear reliance model with coefficients for AI accuracy (A), clinician experience (E), and task complexity (C) was calibrated using weighted least squares against 9 empirical data points from 3 independent randomized experiments on AI-assisted decision-making (N=3502). Predicted error was computed as reliance×(1− A ) across a 27-cell factorial design. Study-level bootstrap (2000 iterations) quantified calibration uncertainty. To contextualize the simulation’s operating range, the accuracy of contemporary general-purpose LLMs on complex clinical tasks was drawn from published benchmarks.

Results

Calibration placed β A at 0.201 (bootstrap 95% CI 0.023‐0.234; P (β A >0)>.99). For the novice×high-complexity combination, the minimum AI accuracy values required to achieve error rates

Subjects

MeSH terms (MEDLINE)

Decision Support Systems, ClinicalArtificial IntelligenceHumansComputer SimulationLarge Language Models

Author keywords

Monte Carlo simulationautomation biasclinical decision supporterror thresholdlarge language modelsnursing informatics

Authors and institutions

  • Faculty of Nursing, Shumei University, 1-1 Daigaku-cho, Yachiyo, Chiba, 276-0003, Japan, 81 47-488-2111.

Cite

APA

Tajima, H. (2026). Theoretical Exploration of Error Thresholds for Clinical AI Decision Support in Nursing: Exploratory Simulation Study Grounded in Human-AI Reliance Data. JMIR Nursing, 9, e99590-e99590. https://doi.org/10.2196/99590

Vancouver

Tajima H. Theoretical Exploration of Error Thresholds for Clinical AI Decision Support in Nursing: Exploratory Simulation Study Grounded in Human-AI Reliance Data. JMIR Nursing. 2026;9:e99590-e99590. doi:10.2196/99590

BibTeX
@article{Tajima2026,
  author = {Tajima, Hiroyuki},
  title = {Theoretical Exploration of Error Thresholds for Clinical AI Decision Support in Nursing: Exploratory Simulation Study Grounded in Human-AI Reliance Data},
  journal = {JMIR Nursing},
  year = {2026},
  volume = {9},
  pages = {e99590--e99590},
  doi = {10.2196/99590}
}
Start for free →