EUVIMEDEUVIMED entdecken
CrossrefInfokarte

Would artificial intelligence make “Good” decisions about thyroid nodule biopsies?

Abhay Barage, Mia Austria, Emily Vertosick, Laura Boucai, Azeez Farooki, Stephanie Fish, Samantha K Newman, Armando Patrizio, Lubaina Presswala, Tyler Ryan, Mona Sabra, Rebecca Zeuren, Andrew Vickers, Gilad Kuperman, Jessica S Ancker, Scott Y H Kim, Robert Michael Tuttle, James H Flory

The Journal of Clinical Endocrinology & Metabolism · 2026-10-28

DOI: 10.1210/clinem/dgag433 ↗
AbstractBibliografische Angaben

Abstract

Abstract Background Large language models (LLMs) have shown promise for clinical decision support (CDS), but evaluation under clinical equipoise—scenarios lacking a consensus correct answer—remains rare. We evaluated commercially available LLM performance for thyroid nodule biopsy recommendations under clinical equipoise. Methods One hundred clinical vignettes describing patients with incidentally discovered thyroid nodules of varying sizes and risk features were presented to 94 clinicians, recruited by convenience sampling from professional networks, and to multiple LLMs (GPT-5, Claude Sonnet 3.5/4.0/4.5, Llama 3.2-90B, DeepSeek R1, and OpenEvidence). Responses were dichotomized as biopsy vs no biopsy. Agreement was assessed using Krippendorff alpha, and a deterministic algorithm served as a provisional benchmark. Selected LLM responses were reviewed by experts. Results Clinicians recommended biopsy in 58% of responses (95% CI 50%, 66%), with unanimous responses in only 50 vignettes. Large language model biopsy rates ranged from 46% (Claude 3.5) to 74% (Llama 3.2-90B). Large language model–clinician agreement was moderate (α = .372-.453). Agreement with the deterministic algorithm ranged from high (α = .954, Detailed Thyroid Imaging and Data Reporting System GPT-5) to low (α = .265, Claude Sonnet 4.5). Llama 3.2-90B recommended biopsy in 8 of 8 cases where clinicians unanimously recommended against it. Conclusion Large language models differed meaningfully in biopsy recommendation patterns, with potential population-level consequences. Evaluating and aligning LLMs for CDS under equipoise requires stakeholders and processes analogous to clinical guideline committees. Because LLMs used as CDS could powerfully disseminate different practice patterns, this creates new responsibilities for guideline committees and other stakeholders.

Wissen, das zu Ihrer Arbeit passt.

Vom kostenlosen Einstieg über die persönliche Recherche bis zur vollständigen Research Suite.

Tarife ansehen →

Sind alle Verlagsvolltexte enthalten?

Nein. Bibliografische Nachweise, Abstracts und Volltexte sind unterschiedliche Inhalte. Ob ein Volltext verfügbar ist, hängt von der Quelle, Open Access und Ihren vorhandenen Lizenzen ab. Ein EUVIMED-Tarif ersetzt keine zusätzlichen Verlagsrechte.

Tarife ansehen →