Rongping Cha

Background: Intensive care unit nurses face sustained workload, vigilance and emotionally demanding care. Psychological detachment during non‐work time is an important recovery experience, but evidence in this population remains limited. Aim: To describe psychological detachment among intensive care unit nurses and identify demographic, departmental psychological support resources availability, social support and burnout dimensions associated with it. Study Design: A single‐centre cross‐sectional survey. Registered intensive care unit nurses from a tertiary grade A general hospital in eastern China were recruited by convenience sampling between June and July 2025. Participants completed demographic, psychological detachment, burnout and social support questionnaires. Descriptive analyses, univariate comparisons, correlation analyses and multivariable linear regression were performed. The study was reported in accordance with the Strengthening the Reporting of Observational Studies in Epidemiology checklist. Results: Of 220 questionnaires submitted, 199 valid responses were analysed (90.45%). The mean psychological detachment score was 11.68 ± 3.85. Mean emotional exhaustion, depersonalisation and personal accomplishment scores were 37.75 ± 8.15, 16.93 ± 4.87 and 25.91 ± 6.25, respectively. Psychological detachment correlated negatively with emotional exhaustion ( r = −0.230, p = 0.001) and positively with subjective support ( r = 0.175, p = 0.013). Departmental psychological support resources availability (B = 1.674, β = 0.216, p = 0.001), head‐nurse position (B = −4.776, β = −0.195, p = 0.004) and emotional exhaustion (B = −0.115, β = −0.243, p < 0.001) were independently associated with psychological detachment. Conclusion: In this single‐centre sample of intensive care unit nurses, the reported availability of departmental psychological support resources was associated with higher psychological detachment, whereas head‐nurse position and emotional exhaustion were associated with lower psychological detachment. Relevance to Clinical Practice: These findings suggest that critical care nursing managers may consider departmental psychological support resources availability, nursing position and emotional exhaustion when assessing recovery needs among intensive care unit nurses.

Background: Diabetes is a chronic condition requiring long-term management, and continuous health education is vital for improving disease awareness and self-management. Large language models (LLMs), advanced artificial intelligence systems trained on large text data sets, have shown promise in generating diabetes-related educational materials. While LLMs can generate accurate and readable content, most studies focus on general education based on guidelines, rather than tailoring content to individual patients’ clinical profiles. This study addresses these gaps by comparing the performance of three major LLMs (ChatGPT-4o, Doubao 1.5, and DeepSeek R1) in generating health education materials for discharged patients with diabetes. Methods: Ten de-identified medical records of discharged patients with diabetes were uploaded to the LLMs. Each model generated health education materials based on these records. Experienced diabetes nursing experts evaluated the quality of the generated materials. Results: The comprehensibility scores pass rates for all models were above 70%, with DeepSeek R1 performing the best ( P < .01). The actionability scores pass rates were below 70% for all models, with no significant differences ( P > .01). Accuracy scores for all models were ≥98%, and there were no significant differences in accuracy ( P > .01). Similarly, no significant differences were observed in personalization and effectiveness scores ( P > .01). DeepSeek R1 achieved the highest safety score, while Doubao 1.5 had the lowest safety score ( P < .01). Conclusion: While ChatGPT-4o, Doubao 1.5, and DeepSeek R1 generate accurate and comprehensible materials, concerns remain regarding their actionability and safety. These findings suggest that LLMs should be used as auxiliary tools in diabetes education, requiring further refinement for personalized and actionable content.

Background: Generative artificial intelligence (AI) has shown great potential in various fields, including health care. However, its application for developing patient education materials (PEMs), particularly for those with coronary heart disease (CHD), remains underexplored. Traditional methods for creating these materials are time-consuming and lack personalization, which limit their effectiveness. Objective: This study aims to explore the effectiveness of generative AI tools (ChatGPT and DeepSeek) at generating PEMs for patients with CHD and to compare them with materials developed by a professional medical team. Methods: In February 2025, PEMs for patients with CHD were developed using a framework designed by a professional medical team. Structured prompts were used to generate materials through 2 generative 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: The total time for manual preparation was 14 hours, while ChatGPT and DeepSeek consumed 0.62 hours and 0.78 hours, respectively. Regarding readability, the frequency of difficult words was more variable in manually written and ChatGPT materials, while DeepSeek showed more consistency. The proportion of simple sentences was highest with DeepSeek, followed by ChatGPT, with complete separation between manually written and ChatGPT ( δ =1). Content word frequency was highest in manually written PEMs, while ChatGPT had the lowest but most stable values. Personal pronouns were most frequently used in manually written PEMs, with high variability, and least used in DeepSeek, which was stable. All 3 methods had similar readability levels and reached Chinese elementary school–level readability for the proportions of simple sentences and personal pronouns, with high school–level difficulty of words and content word frequency. The understandability and actionability scores were above 70, with ChatGPT being more stable for understandability and DeepSeek being more stable for actionability. No significant differences were found between groups. In terms of accuracy, intergroup comparisons showed significant differences ( H =7.27, P =.03) but no significant differences in multiple comparisons. The direct comparison between ChatGPT and DeepSeek showed a negligible effect size ( δ =0.02), with no significant difference ( z -score=−0.06, P =.96). Accuracy issues in the AI-generated materials were noted by 4 of 8 experts. Conclusions: Generative AI significantly improved the efficiency of developing PEMs for patients with CHD. 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 related to reducing the number of difficult words and increasing content word frequency are needed to enhance readability. The accuracy of AI-generated materials still poses concerns, including potential AI “hallucinations,” and requires review by health care professionals. Generative AI holds considerable potential for generating PEMs, and future research should assess its applicability and effectiveness in real-world patient and family contexts.

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. CLINICALTRIAL 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.