Related Experiment Video
Updated: Sep 10, 2025
07:00
Eye-Tracking Control to Assess Cognitive Functions in Patients with Amyotrophic Lateral Sclerosis
Published on: October 13, 2016
8.2K
Revolutionizing Patient Education: Artificial Intelligence Versus Experts in Ocular Dyskinesia Responses
Daniel Bahir1, Morris Hartstein2, Cat Burkat3
1Ophthalmology Department, Azrieli Faculty of Medicine, Tzafon Medical Center, Bar Ilan University, Poriya, Israel.
Ophthalmic Plastic and Reconstructive Surgery
|August 27, 2025
Summary
ChatGPT-3.5 excels in answering ocular dyskinesia questions, outperforming other AI models and experts in accuracy and reliability. This highlights AI's potential for patient education in managing eye movement disorders.
Area of Science:
- Ophthalmology
- Artificial Intelligence
- Medical Informatics
Background:
- Ocular dyskinesia, encompassing conditions like blepharospasm and hemifacial spasm, significantly impairs patients' quality of life.
- Accurate and reliable patient information is crucial for managing these conditions.
Purpose of the Study:
- To evaluate the effectiveness of advanced AI models (ChatGPT-3.5, GPT-4o, Gemini, Gemini Advanced) compared to expert ophthalmologists.
- To assess AI's ability to provide accurate, reliable, and patient-focused answers for ocular dyskinesia-related queries.
Main Methods:
- A panel of oculoplastic surgeons formulated 13 questions on ocular dyskinesia symptoms, treatments, and care.
- Responses from four AI models and human experts were anonymized and rated by seven international oculoplastic surgeons.
- Correctness and reliability were assessed using a 7-point Likert scale, with statistical analysis performed.
Main Results:
- ChatGPT-3.5 achieved the highest correctness (5.80) and reliability (5.68) scores, surpassing GPT-4o and expert ophthalmologists.
- GPT-4o's performance closely matched that of the expert panel.
- Gemini and Gemini Advanced models showed lower correctness and reliability scores compared to ChatGPT-3.5 and experts.
Conclusions:
- ChatGPT-3.5 shows significant potential for enhancing patient education on ocular dyskinesia with accurate, accessible information.
- While ChatGPT-4o and experts provide strong clinical insights, Gemini models need further development.
- AI holds promise in complementing human expertise for improved patient care and education in ophthalmology.
Related Concept Videos
01:17Accessory Structures of the Eye
1.9K
Optical perception, or vision, is an extraordinary sense dependent on converting light signals received via the ocular organs. These organs, known as eyes, are securely positioned within the bony cavities of the skull, called orbits. The orbits serve a dual purpose: a protective shield for the ocular globes and a stable attachment point for the soft ocular tissues. The eye's external protective mechanisms include the eyelids, which are edged with lashes that act as a barrier against foreign...
1.9K
01:11Direct-Acting Cholinergic Agonists: Therapeutic Uses
869
Direct-acting cholinergic agonists have many therapeutic uses in various medical fields. Choline esters, including acetylcholine, have limited clinical utility due to their non-selectivity and short duration of action. Still, acetylcholine and carbachol are applied topically during ophthalmologic surgery to induce miosis. Pilocarpine, a muscarinic and ganglionic stimulator, effectively treats open-angle glaucoma and alleviates xerostomia and dry mouth caused by radiotherapy or Sjögren...
869