Key result
ChatGPT-4.5 scores ~0.2 points higher than standard expert responses for oral anticoagulant advice accuracy.
Why the study?
Patients increasingly use large language model chatbots for health information, but their reliability in high-risk cardiovascular therapies such as oral anticoagulation remains uncertain.
Do large language models provide accurate, clear, and complete responses to patient questions regarding oral anticoagulant therapy compared to standard expert responses?
Cross-Sectional
Two blinded clinical pharmacists
Responses randomized using a computer-generated sequence
Do large language models provide accurate, clear, and complete responses to patient questions regarding oral anticoagulant therapy compared to standard expert responses?
ChatGPT-4.5 generates highly accurate, clear, and complete patient educational material on oral anticoagulants, performing comparably or better than other LLMs and standard reference responses.
Answers are grounded in this paper and cite their sources.
May support LLM tools for oral anticoagulant education; hypothesis-generating and should not yet alter clinical practice.
Background Large language model (LLM)–based chatbots are increasingly used by patients for health information; however, their reliability in high-risk cardiovascular therapies such as oral anticoagulation remains uncertain. This study evaluated the perceived accuracy, clarity, and completeness of LLM-generated responses to common patient queries compared with standard-derived expert responses (SDERs). Methods A cross-sectional comparative study evaluated responses generated by ChatGPT-4.5, Gemini Pro 2.5, and DeepSeek-V3 to 11 frequently asked questions related to five oral anticoagulants: warfarin, dabigatran, apixaban, rivaroxaban, and edoxaban. Responses were generated using a standardized patient-focused prompt. SDERs were developed by cardiologists and clinical pharmacists using authoritative references. All responses were anonymized and independently assessed by two blinded clinical pharmacists using a five-point Likert scale evaluating accuracy, clarity, and completeness. Interrater reliability was assessed using linearly weighted Cohen's κ, and group comparisons were analyzed using the Friedman test with post hoc adjustments. Results Interrater reliability ranged from fair to almost perfect (κ = 0.31–0.84). ChatGPT-4.5 achieved the highest mean ratings across all evaluation domains, particularly for completeness. Significant differences were observed among response sources for accuracy, clarity, and completeness ( p < 0.05). Warfarin-related queries demonstrated significant differences in accuracy and completeness across response sources, whereas responses for direct oral anticoagulants showed no significant differences. Conclusion ChatGPT-4.5 received the highest mean expert ratings for patient education regarding oral anticoagulants. Performance differences were most evident for warfarin-related queries, whereas responses for direct oral anticoagulants were broadly comparable across sources.
No takes yet. Share an insight, caveat, or question.
Khan et al. (2026) conducted a cross-sectional in Patient education on oral anticoagulant therapy. ChatGPT-4.5 vs. Standard-derived expert responses (SDERs) was evaluated on Accuracy of medical content (5-point Likert scale) (p=0.0022). ChatGPT-4.5 received the highest mean expert ratings for perceived accuracy, clarity, and completeness of responses to patient questions on oral anticoagulants compared to standard-derived expert responses.
Synapse has enriched 10 related papers. Consider them for comparative context: