EUVIMEDEUVIMED entdecken
LeitlinieOpen Access · CC BY 4.0

Large language models for tympanostomy patient education: readability and guideline adherence

Shreeya Bahethi, Hetal Lad, Shrey Shah, Sudeepti Vedula, Brian Manzi

European Archives of Oto-Rhino-Laryngology · 2026-10 · 283 (11) · 7483-7490

DOI: 10.1007/s00405-026-10612-2 ↗

Kurz gefasst

Leitlinie in der Zeitschrift European Archives of Oto-Rhino-Laryngology, online erschienen am 16.09.2026. Verfasst von Shreeya Bahethi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology-Head and Neck Surgery, Hackensack University Medical Center, Hackensack, NJ, 07662, USA. Hauptthemen laut MEDLINE: Large Language Models, Middle Ear Ventilation, Patient Education as Topic, Comprehension. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To evaluate the accuracy and readability of large language model (LLM)-generated patient education materials regarding tympanostomy tube placement.

Methods

Over a two-month period, ChatGPT 4o, Gemini 2.5 Flash, and Google Search AI were prompted daily using long-form and layered prompt formats covering typical concerns regarding tympanostomy. Responses were scored on a 12-point rubric adapted from the AAO-HNS Clinical Practice Guidelines (CPG), assessing diagnostic accuracy, procedural clarity, and postoperative care. Readability was evaluated using Flesch Reading Ease and Flesch-Kincaid Grade Level. For each model and prompt type, average scores and variability were analyzed with 95% confidence intervals. Between-model differences were tested with Welch’s t -tests and Cohen’s d; temporal trends were analyzed via linear regression.

Results

For long-form outputs, Google Search AI and Gemini 2.5 Flash demonstrated the highest mean CPG adherence (96.4% and 96.6%, respectively), both significantly exceeding ChatGPT 4o (84.3%; both P < .001; Cohen’s d ≈ 2.05). For layered prompt sessions, Google Search AI again demonstrated the highest adherence (91.7%), followed by Gemini 2.5 Flash (88.1%) and ChatGPT 4o (76.2%). Guideline adherence was temporally stable across all models ( P > .05 for most). All outputs exceeded the recommended sixth-grade reading threshold (mean FKGL, 9.4 for long-form; 10.6 for layered), with no statistically significant readability differences between prompt strategies.

Conclusions

Google Search AI demonstrated the highest guideline concordance, though all models produced material too complex for typical patient comprehension. Structured prompting enhances clinical accuracy, but readability remains a key barrier to accessibility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsMiddle Ear VentilationPatient Education as TopicComprehensionGuideline AdherenceHumans

Stichwörter der Autor:innen

Artificial intelligenceClinical practice guidelinesLarge language modelsPatient educationReadabilityTympanostomy

Autor:innen und Institutionen

  • Department of Otolaryngology-Head and Neck Surgery, Hackensack University Medical Center, Hackensack, NJ, 07662, USA.
  • Department of Otolaryngology-Head and Neck Surgery, Rutgers New Jersey Medical School, 90 Bergen Street, Suite 8100, Newark, NJ, 07103, USA.
  • Department of Otolaryngology-Head and Neck Surgery, Rutgers New Jersey Medical School, 90 Bergen Street, Suite 8100, Newark, NJ, 07103, USA. brian.manzi@rutgers.edu.

Zitieren

APA

Bahethi, S., Lad, H., Shah, S., Vedula, S., & Manzi, B. (2026). Large language models for tympanostomy patient education: readability and guideline adherence. European Archives of Oto-Rhino-Laryngology, 283(11), 7483-7490. https://doi.org/10.1007/s00405-026-10612-2

Vancouver

Bahethi S, Lad H, Shah S, Vedula S, Manzi B. Large language models for tympanostomy patient education: readability and guideline adherence. European Archives of Oto-Rhino-Laryngology. 2026;283(11):7483-7490. doi:10.1007/s00405-026-10612-2

BibTeX
@article{Bahethi2026,
  author = {Bahethi, Shreeya and Lad, Hetal and Shah, Shrey and Vedula, Sudeepti and Manzi, Brian},
  title = {Large language models for tympanostomy patient education: readability and guideline adherence},
  journal = {European Archives of Oto-Rhino-Laryngology},
  year = {2026},
  volume = {283},
  number = {11},
  pages = {7483--7490},
  doi = {10.1007/s00405-026-10612-2}
}
Kostenlos starten →