Background Clinical notes are a vital and detailed source of information about patient hospitalizations. However, the sheer volume and complexity of these notes make evaluation and summarization challenging. Nonetheless, summarizing clinical notes is essential for accurate and efficient clinical decision-making in patient care. Generative language models, particularly large language models such as GPT-4, offer a promising solution by creating coherent, contextually relevant text based on patterns learned from large datasets. Methods This study describes the development of a discharge summary system using large language models. By conducting an online survey and interviews, we gather feedback from end users, including physicians and patients, to ensure the system meets their practical needs and fits their experiences. Additionally, we develop a rating system to evaluate prompt effectiveness by comparing model-generated outputs with human assessments, which serve as benchmarks to evaluate the performance of the automated model. Results Here we show that the model’s ability to interpret diagnoses borders on humanlevel accuracy, demonstrating its potential to assist healthcare professionals in routine tasks such as generating discharge summaries. Conclusions This advancement underscores the potential of large language models in clinical settings and opens up possibilities for broader applications in healthcare documentation and decision-making support.
A voice-controlled smart home system based on conversational agents can address the specific needs of older people, proactively providing support, compensating for cognitive decline, and coping with solitude, among other features. In particular, Multi-Agent Systems (MAS) platforms provide considerable support for complex adaptive systems that are naturally distributed and situated in dynamic environments, such as Ambient intelligence (AmI) applications. Such autonomous intelligent agents are capable of independent reasoning and joint analysis of complex situations to support high-level interaction with humans, besides providing typical characteristics of MAS, such as cooperation and coordinated action. In this context, we developed an approach using a MAS previously evaluated for visually impaired users, where most of the system’s functionalities are also helpful for the elderly. Our methodology is based on the four steps of the interactive design process. As a result, we determined that our approach has elements that allow for natural interaction with users, and we identified and discussed improvements and new features for future work. We believe that our findings can point to directions for building AmI systems that are capable of more natural interaction with users.
Ambient intelligence (AmI) emerged in Europe with the idea that the computational support available in a living environment can help people’s lives. AmI introduces new challenges and critical issues because this technology differs from the traditional form of interaction that is centered on a device or system. In this work, we aim to contribute to this topic by conducting a systematic literature review in order to identify Human-Computer Interaction guidelines for the design of ambient intelligence systems. We found a total of 120 guidelines from 27 papers, and we grouped similar guidelines creating different categories. These categories of guidelines later became a unified guideline incorporating also some of our own ideas. As a result, this paper identifies ten categories and guidelines to improve user interaction with ambient intelligence systems. We believe that these guidelines significantly contribute to designing more intuitive AmI systems for users, including those with disabilities.