Related Experiment Video
Updated: Jun 17, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
End-of-life Care Patient Information Leaflets-A Comparative Evaluation of Artificial Intelligence-generated Content
Prakash G Gondode1, Puneet Khanna1, Pradeep Sharma2
1Department of Anesthesiology, Pain Medicine and Critical Care, All India Institute of Medical Sciences, New Delhi, India.
Background:
End-of-life care (EOLC) is a critical aspect of healthcare, yet accessing reliable information remains challenging, particularly in culturally diverse contexts like India.
Objective:
This study investigates the potential of artificial intelligence (AI) in addressing the informational gap by analyzing patient information leaflets (PILs) generated by AI chatbots on EOLC.
Methodology:
Using a comparative research design, PILs generated by ChatGPT and Google Gemini were evaluated for readability, sentiment, accuracy, completeness, and suitability. Readability was assessed using established metrics, sentiment analysis determined emotional tone, accuracy, and completeness were rated by subject experts, and suitability was evaluated using the Patient Education Materials Assessment Tool (PEMAT).
Results:
Google Gemini PILs exhibited superior readability and actionability compared to ChatGPT PILs. Both conveyed positive sentiments and high levels of accuracy and completeness, with Google Gemini PILs showing slightly lower accuracy scores.
Conclusion:
The findings highlight the promising role of AI in enhancing patient education in EOLC, with implications for improving care outcomes and promoting informed decision-making in diverse cultural settings. Ongoing refinement and innovation in AI-driven patient education strategies are needed to ensure compassionate and culturally sensitive EOLC.
How To Cite This Article:
Gondode PG, Khanna P, Sharma P, Duggal S, Garg N. End-of-life Care Patient Information Leaflets-A Comparative Evaluation of Artificial Intelligence-generated Content for Readability, Sentiment, Accuracy, Completeness, and Suitability: ChatGPT vs Google Gemini. Indian J Crit Care Med 2024;28(6):561-568.
Related Concept Videos
Non-equilibrium in the Cell
Documentation in Long-Term and Home Healthcare Setting
Long-Term Care Facilities
Guidelines for Writing Outcome
Patient outcomes reflect the patient's response to the goal rather than what the nurse aims to achieve. Terminology should be observable and measurable to avoid the reader's interpretation. The desired outcome should be realistic and achievable in the designated care timeframe. Expected outcomes should align with adjunctive therapies. The outcome should enhance care...
Nursing Ethical Principles II
Consider the following scenario, which illustrates how these principles are applied in the care of Mr. John, a fifty-year-old teacher diagnosed with metastatic liver cancer.
Initially, Mr. John's...
Myasthenia Gravis: Overview and Treatment
These antibodies interfere with the function of the nicotinic receptors in three ways: by binding to the receptor and disrupting acetylcholine binding; by causing cross-linking of receptors which...
Patient-centered Care

