‘Superior in logic and structure, particularly for acute conditions’
Applying artificial intelligence (AI) to discharge summaries in psychiatric clinics is among the latest topics selected for Annotations, presented on the website by the Academy’s Guidelines and Evidence-based Medicine Subcommittee.
The course of hospitalization is described in a discharge summary given to patients and their general practitioners at the end of treatment.
Integration of AI into medical workflows to enhance efficiency and quality seems particularly interesting and valid, says the author.
Summaries must fulfil diverse and specific requirements. Nevertheless, AI-generated discharge summaries offer the opportunity to optimize information transfer and alleviate the workload on physicians.
This particular study evaluates the quality of discharge summaries produced by clinical staff compared with an AI model (ChatGPT 4.0).
Completed summaries were assessed by four attending physicians using predefined criteria including consistency, completeness, and comprehensibility. The time required to prepare these summaries and their impact on overall quality were also analyzed.
Results indicated that discharge summaries generated by AI are more efficient than discharge summaries prepared by clinic staff. AI was particularly effective in terms of coherence and information structure.
More research, training and development is needed to improve the accuracy and reliability of AI-generated discharge summaries, says the author. But the study found that AI was often superior in logic and structure, particularly for acute conditions.