JMIR Publications

ABSTRACT

Background:

Background:

Generative Artificial Intelligence (Gen AI) has shown great potential in various fields, including healthcare. However, its application in developing health education materials for patients, particularly those with coronary heart disease (CHD), remains underexplored. Traditional methods for creating these materials are time-consuming and lack personalization, which limits their effectiveness.

Objective:

Objective:

This study aims to explore the effectiveness of Gen AI tools(ChatGPT and DeepSeek) in generating health education materials for CHD patients and to compare them with materials developed by a professional medical team.

Methods:

Methods:

In February 2025, health education materials for CHD patients were developed using a framework designed by a professional medical team. Structured prompts were used to generate materials through two Gen AI models—ChatGPT-4o and DeepSeek R1. These AI-generated materials were compared with those created by the medical team in terms of development time, readability, understandability, actionability, and accuracy.

Results:

Results:

The manual development time for the materials was 14 hours, while the time for ChatGPT-4o was 0.62 hours, and for DeepSeek R1, it was 0.78 hours. There were no statistically significant differences between the three groups in terms difficult words(P =.875), simple sentences(P =.082), or the number of personal pronouns (P =.550).However, a statistically significant difference was found between manual and ChatGPT-4o materials in content word frequency (P < .027). All three groups had similar readability levels, with elementary-level simple sentence ratios and personal pronoun counts but high school-level difficulty words and content word frequency. The understandability and actionability scores did not differ significantly.In terms of accuracy, there was a statistically significant difference between groups (P < .026), but multiple comparisons did not reveal significant differences(P =.065). Four out of eight experts noted accuracy issues in the Gen AI-generated materials.

Conclusions:

Conclusions:

Gen AI significantly improved the efficiency of developing health education materials for CHD patients. The materials generated by ChatGPT-4o and DeepSeek R1 were comparable to the professionally written ones in terms of readability, understandability, and actionability. However, improvements in reducing difficult words and increasing content word frequency are needed to enhance readability. The accuracy of Gen AI-generated materials still poses concerns, including potential AI "hallucinations," and requires review by healthcare professionals. Gen AI holds considerable potential in generating health education materials, and future research should assess its applicability and effectiveness in real-world patient and family contexts. Clinical Trial: This study did not involve direct participation of patients, and patient-related information or data were not included. So Clinical trial number is not applicable.