In: The International Journal of Psychiatry in Medicine, 60 (2025), Nr. 3. pp. 330-337. ISSN 0091-2174 (Druck-Ausg.); 1541-3527 (Online-Ausg.)

PDF, English - main document Restricted access: Repository staff only until 16 September 2025. Login+Download (503kB) | Terms of use

Abstract

Background: The integration of artificial intelligence (AI; ChatGPT 4.0) into medical workflow presents a great potential to enhance efficiency and quality. The use of AI in the creation of discharge summaries is particularly promising. The course of each hospitalization is described in the discharge summary, which is given to each patient and then to his general practitioner at the end of hospital treatment. An analysis of discharge summaries in psychiatric clinics indicates that these documents must fulfill diverse and specific requirements. Nevertheless, AI-generated discharge summaries provided an opportunity to optimize information transfer and alleviate physician workload. Method: This study evaluated the quality of discharge summaries produced by clinical staff compared to those produced by an AI model (ChatGPT 4.0). Clinicians who wrote the discharge summaries were not informed about the study's purpose or methodology. The completed summaries were subsequently assessed by four attending physicians using predefined criteria. These physicians were also blinded to the study's objectives and were unaware of the individual authors of the summaries. The evaluation criteria included consistency, completeness, and comprehensibility. Additionally, the time required to prepare these summaries and its impact on overall quality were analyzed. Results:The results indicated that discharge summaries generated by AI were more efficient than discharge summaries prepared by clinic staff. AI was particularly effective in terms of coherence and information structure. Conclusion: Further research, training and development is needed to improve the accuracy and reliability of AI-generated discharge summaries.