Evaluating ChatGPT-4’s correctness in patient-focused informing and awareness for atrial fibrillation

Abstract

Background

As artificial intelligence and large language models continue to evolve, their application in health care is expanding. OpenAI’s Chat Generative Pre-trained Transformer 4 (ChatGPT-4) represents the latest advancement in this technology, capable of engaging in complex dialogues and providing information.

Objective

This study explores the correctness of ChatGPT-4 in informing patients about atrial fibrillation.

Methods

This cross-sectional observational study involved ChatGPT-4 in responding to a structured set of 108 questions across 10 categories related to atrial fibrillation. These categories included basic information, treatment options, lifestyle adjustments, and more, reflecting common patient inquiries. The model's responses were evaluated by a panel of 3 cardiologists on the basis of accuracy, comprehensiveness, clarity, relevance to clinical practice, and patient safety. The total correctness of ChatGPT-4 was quantitatively assessed through scores assigned in each category, and statistical analysis was performed to identify significant differences in performance across categories.

Results

ChatGPT-4 provided correct and relevant answers with considerable variability across categories. It excelled in "Lifestyle Adjustments" and "Daily Life and Management" with perfect and near-perfect scores but struggled with "Miscellaneous Concerns" scoring lower. Statistical analysis confirmed significant differences in total scores across categories (P = .020).

Conclusion

Our results suggest that while ChatGPT-4 is reliable in categories with structured and direct queries, it shows limitations when handling complex medical queries that require in-depth explanations or clinical judgment. ChatGPT-4 demonstrates promising potential as a tool for patient-focused informing in atrial fibrillation, particularly in straightforward informing content.