Using Artificial Intelligence ChatGPT to Access Medical Information About Chemical Eye Injuries: Comparative Study
Layan Yousef Alharbi1, Rema Rashed Alrashoud1, Bader Shabib Alotaibi1
1College of Medicine, Imam Mohammad Ibn Saud Islamic University (IMSIU), Prince Mohammed Ibn Salman Ibn Abdulaziz Road, Riyadh, 13318, Saudi Arabia, 966 532816087.
Background:
Chemical ocular injuries are a major public health issue. They cause eye damage from harmful chemicals and can lead to severe vision loss or blindness if not treated promptly and effectively. Although medical knowledge has advanced, accessing reliable and understandable information on these injuries remains a challenge. This is due to unverified web-based content and complex terminology. Artificial intelligence tools like ChatGPT provide a promising solution by simplifying medical information and making it more accessible to the general public.
Objective:
This study aims to assess the use of ChatGPT in providing reliable, accurate, and accessible medical information on chemical ocular injuries. It evaluates the correctness, thematic accuracy, and coherence of ChatGPT's responses compared with established medical guidelines and explores its potential for patient education.
Methods:
A total of 9 questions were entered into ChatGPT regarding various aspects of chemical ocular injuries. These included the definition, prevalence, etiology, prevention, symptoms, diagnosis, treatment, follow-up, and complications. The responses provided by ChatGPT were compared with the International Classification of Diseases-9 and International Classification of Diseases-10 guidelines for chemical (alkali and acid) injuries of the conjunctiva and cornea. The evaluation focused on criteria such as correctness, thematic accuracy, and coherence to assess the accuracy of ChatGPT's responses. The inputs were categorized into 3 distinct groups, and statistical analyses, including Flesch-Kincaid readability tests, ANOVA, and trend analysis, were conducted to assess their readability, complexity, and trends.
Results:
The results showed that ChatGPT provided accurate and coherent responses for most questions about chemical ocular injuries, demonstrating thematic relevance. However, the responses sometimes overlooked critical clinical details or guideline-specific elements, such as emphasizing the urgency of care, using precise classification systems, and addressing detailed diagnostic or management protocols. While the answers were generally valid, they occasionally included less relevant or overly generalized information. This reduced their consistency with established medical guidelines. The average Flesch Reading Ease Score was 33.84 (SD 2.97), indicating a fairly challenging reading level, while the Flesch-Kincaid Grade Level averaged 14.21 (SD 0.97), suitable for readers with college-level proficiency. The passive voice was used in 7.22% (SD 5.60%) of sentences, indicating moderate reliance. Statistical analysis showed no significant differences in the Flesch Reading Ease Score (P=.38), Flesch-Kincaid Grade Level (P=.55), or passive sentence use (P=.60) across categories, as determined by one-way ANOVA. Readability remained relatively constant across the 3 categories, as determined by trend analysis.
Conclusions:
ChatGPT shows strong potential in providing accurate and relevant information about chemical ocular injuries. However, its language complexity may prevent accessibility for individuals with lower health literacy and sometimes miss critical aspects. Future improvements should focus on enhancing readability, increasing context-specific accuracy, and tailoring responses to a person's needs and literacy levels.
