AI Tools Improve Patient Knowledge of and Confidence in Optometric Information

According to research presented at the 2025 American Optometric Association Conference in Minneapolis, MN, artificial intelligence (AI) tools used to provide optometric information to patients result in increased patient knowledge, satisfaction, and decision-making confidence.1

AI devices have been introduced into optometric care through fundus photographs, optical coherence tomography, and visual fields, utilized by clinicians to classify and detect diabetic retinopathy, macular edema, and a variety of other diseases. However, patient-facing AI programs are still relatively limited. Research on the effectiveness of AI-generated messages in conveying complicated optometric data to patients.2

To that end, MohammadEsmaeil Keypour, MSc, Taban Polyclinic of Health & Diabetes, and colleagues conducted a quasi-experimental, two-group comparison study to evaluate the impact of AI-enhanced patient education on knowledge of eye conditions, confidence in selecting corrective options, and satisfaction with optometric care.1

The study collected data on 384 adult participants aged 18-65. They were divided into an intervention group (n = 192), who were given the Eye1 AI tool, and a control group (n = 192), who received standard care. The Eye1 AI tool provided participants with a smart questionnaire on symptoms/lifestyle, risk scoring, visual health profiles, educational content and pre-visit summaries for optometrists, and personalized recommendations for eyewear and lens types.1

Keypour and colleagues established the outcome measures as knowledge (15-item pre/post test), patient satisfaction based on modified CSQ-8, and decision-making confidence based on the Likert scale. At the end of the study period, the AI group demonstrated a 35% increase in knowledge improvement compared to 20% in the control group. Similarly, 80% of the AI group reported being satisfied, while only 60% of the control group reported satisfaction. Decision confidence increased by 40% in the AI group, but only by 15% in the control group.1

Based on these data, investigators concluded that the combination of AI tools helped patients arrive at their appointments better informed by reducing cognitive load during clinical visits and increasing decision-making confidence. Additionally, they indicated that these findings align with previous studies, which have emphasized the role of AI in patient comprehension improvement and empowerment.1

However, the team did report some limitations, namely the quasi-experimental nonrandomized study design and the possibility of the Hawthorne effect due to awareness. Full blinding was infeasible during this trial, given the function of the AI programs utilized.1

Ultimately, Kepour and colleagues noted that AI tools significantly increased patient knowledge, satisfaction, and decision-making confidence. They also caution, however, that tools be used as supportive assistants rather than replacements, and that clinicians emphasize clarity, fairness, and transparency. In the future, investigators suggest further research should focus on long-term adherence and outcome tracking, as well as addressing demographic differences and AI fairness.1

“Patients appreciated AI tools when they supported human care rather than replaced it,” Keypour and colleagues wrote. “However, transparency remains essential, as some studies suggest patient trust may decrease when AI use is disclosed without explanation.”1

References

1. Keypour M. Advancements in AI-Driven Eyecare: Enhancing Patient Education, Satisfaction, and Decision-Making. Abstract presented at the 2025 American Optometric Association Conference in Minneapolis, MN, June 25-28, 2025.

2. Ting DSW, Pasquale LR, Peng L, et al. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019;103(2):167-175. doi:10.1136/bjophthalmol-2018-313173