EUVIMEDEUVIMED entdecken
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 · 05.08.2026 · 9 · e99590-e99590

DOI: 10.2196/99590 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Nursing, online erschienen am 05.08.2026. Verfasst von Hiroyuki Tajima. Beteiligte Einrichtung: Faculty of Nursing, Shumei University, 1-1 Daigaku-cho, Yachiyo, Chiba, 276-0003, Japan, 81 47-488-2111. Hauptthemen laut MEDLINE: Decision Support Systems, Clinical, Artificial Intelligence. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision Support Systems, ClinicalArtificial IntelligenceHumansComputer SimulationLarge Language Models

Stichwörter der Autor:innen

Monte Carlo simulationautomation biasclinical decision supporterror thresholdlarge language modelsnursing informatics

Autor:innen und Institutionen

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

Zitieren

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}
}
Kostenlos starten →