Patients Prefer Human Empathy, but Not Always Human Wording: A Single-Blind Within-Subject Trial of GPT-Generated vs. Clinician Discharge Texts in Emergency Ophthalmology
Clinics and Practice · 14.11.2025 · 15 (11) · 208
DOI: 10.3390/clinpract15110208 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinics and Practice, online erschienen am 14.11.2025. Verfasst von Dea Samardzic und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, University Hospital of Split, 21000 Split, Croatia. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Written discharge explanations are crucial for patient understanding and safety in emergency eye care, yet their tone and clarity vary. Large language models (LLMs, artificial intelligence systems trained to generate human-like text) can produce patient-friendly materials, but direct, blinded comparisons with clinician-written texts remain scarce. This study compared patient perceptions of a routine clinician-written discharge text and a GPT-5-generated explanation, where GPT-5 (OpenAI) is a state-of-the-art LLM, based on the same clinical facts in emergency ophthalmology. The primary objective was empathy; secondary outcomes included clarity, detail, usefulness, trust, satisfaction, and intention to follow advice.
Methods
We conducted a prospective, single-blind, within-subject study in the Emergency Ophthalmology Unit of the University Hospital Centre Split, Croatia. Adults (n = 129) read two standardized texts (clinician-written vs. GPT-5-generated), presented in identical format and in randomized order under masking. Each participant rated both on Likert scales with 1–5 points. Paired comparisons used Wilcoxon signed-rank tests with effect sizes, and secondary outcomes were adjusted using the Benjamini–Hochberg false discovery rate.
Results
Empathy ratings were lower for the GPT-5-generated text than for the clinician-written text (means 3.97 vs. 4.30; mean difference −0.33; 95% CI −0.44 to −0.22; p < 0.001). After correcting for multiple comparisons, no secondary outcome differed significantly between sources. Preferences were evenly split (47.8% preferred GPT-5 among those expressing a preference).
Conclusions
In emergency ophthalmology, GPT-5-generated explanations approached clinician-written materials on most perceived attributes but were rated less empathic. A structured, human-in-the-loop workflow—in which LLM-generated drafts are reviewed and tailored by clinicians—appears prudent for safe, patient-centered deployment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ophthalmology, University Hospital of Split, 21000 Split, Croatia.
- Department of Anesthesiology and Intensive Care, University Hospital of Split, 21000 Split, Croatia.
- Department for Pathophysiology, University of Split School of Medicine, 21000 Split, Croatia.
- Department of Ophtalmology, Poliklinika Skara Kolega, 21000 Split, Croatia.
ORCID-Profile: Sandro Glumac, Josip Vrdoljak, Marija Skara Kolega, Ante Kreso
Zitieren
APA
Samardzic, D., Curkovic, J., Okmazic, D., Glumac, S., Vrdoljak, J., Skara Kolega, M., & Kreso, A. (2025). Patients Prefer Human Empathy, but Not Always Human Wording: A Single-Blind Within-Subject Trial of GPT-Generated vs. Clinician Discharge Texts in Emergency Ophthalmology. Clinics and Practice, 15(11), 208. https://doi.org/10.3390/clinpract15110208
Vancouver
Samardzic D, Curkovic J, Okmazic D, Glumac S, Vrdoljak J, Skara Kolega M, et al. Patients Prefer Human Empathy, but Not Always Human Wording: A Single-Blind Within-Subject Trial of GPT-Generated vs. Clinician Discharge Texts in Emergency Ophthalmology. Clinics and Practice. 2025;15(11):208. doi:10.3390/clinpract15110208
BibTeX
@article{Samardzic2025,
author = {Samardzic, Dea and Curkovic, Jelena and Okmazic, Donald and Glumac, Sandro and Vrdoljak, Josip and Skara Kolega, Marija and Kreso, Ante},
title = {Patients Prefer Human Empathy, but Not Always Human Wording: A Single-Blind Within-Subject Trial of GPT-Generated vs. Clinician Discharge Texts in Emergency Ophthalmology},
journal = {Clinics and Practice},
year = {2025},
volume = {15},
number = {11},
pages = {208},
doi = {10.3390/clinpract15110208}
}
EUVIMED