Explore the possibilities of ChatGPT for ICU digital diary in the context of ICU

More Info
expand_more

Abstract

ICU survivors have been shown to face memory loss during and after their ICU stays, which contributes the psychological issues. ICU digital diary has been proven as a way of filling the memory gap, thus avoiding the development of these mental issues. EMC has currently been working on the implementation of the digital diary and a tailored strategy should be considered to support ICU nurses in using the digital diary.

As ChatGPT’s potential in the field of the ICU, this project starts with the assignment to explore the possibilities of ChatGPT for ICU digital diary in the context of the ICU. Leveraging a multidisciplinary approach, the project amalgamates insights from nurse practices, interface design, and the introduction of ChatGPT technology. Drawing on meticulous literature review, direct observations, and interviews, the results from these activities highlighted nurses’ need for patient information visualisation and guidance in their diary writing, and the possible application that ChatGPT could provide in the digital diary.

Based on the insights from research activities, a web application - Patient Diary Toolkit - was designed and developed through three rounds of design iterations. There are basically four main functionalities in this design: reviewing the patient diary, adding messages, diary tracker and ChatGPT-based assistant supporting nurses’ diary writing.

This design was evaluated with 15 participants and 5 experts through comparative testing and expert interviews, with the aim of getting insights from their perspectives about the usability, the user experience and the future potential of the design. The results of the evaluation show that the interface is intuitive and easy to understand, and the introduction of the ChatGPT-based assistant offers a practical solution for supporting nurses’ diary writing. Future recommendations including further research, optimisation of the functionality, future-focused solutions for nurses and user experience improvement have been discussed.