JMIR Publications

ABSTRACT

Background:

Due to demographic change and, more recently, the Coronavirus Disease 2019 (COVID-19), the importance of modern intensive care units (ICU) is becoming apparent. One of the key components of an ICU is the continuous monitoring of patients' vital parameters. However, existing advances in informatics, signal processing, or engineering that could alleviate the burden on ICUs have not yet been applied. This could be related to the lack of user involvement in research and development.

Objective:

This study focused on satisfaction of ICU staff with the current patient monitoring and their suggestions for future improvements. We aimed to identify aspects disturbing patient care, remote monitoring display devices, use cases for artificial intelligence (AI), and whether ICU staff is willing to improve their digital literacy or contribute to the improvement of patient monitoring. We further desired to uncover differences between the answers of the professional groups.

Methods:

This survey study was realized with ICU staff from four ICUs of a German university hospital between November 2019 and January 2020. We developed a web-based 36-item survey questionnaire by analyzing a preceding qualitative interview study with ICU staff about clinical requirements of future patient monitoring. Statistical analyses of questionnaire results included median values with their bootstrapped 95% confidence intervals, and Chi-square tests to compare the distributions of item responses of the professional groups.

Results:

Eighty-six of the 270 ICU staff members completed the survey questionnaire. The majority stated to feel confident using the patient monitoring, but high rates of false positive alarms and the many sensor cables were considered to disturb patient care. Wireless sensors, reduction of false positive alarms and hospital standard operating procedures (SOP) for alarm management were demanded. Responses to the display devices proposed for remote patient monitoring were split. Regarding its use, most respondents indicated responsibility for multiple wards or earlier alerting. AI for ICUs would be useful for early detection of complications, increased risk of mortality, and to have guidelines for therapy and diagnostics proposed. Transparency, interoperability, usability, and staff training were essential to promote usage of an AI. The majority wanted to learn more about new technologies for ICU and desired more time for it. Physicians had fewer reservations than nurses about using mobile phones for remote monitoring, and AI-based intelligent alarm management.

Conclusions:

This survey study among ICU staff revealed key improvements for patient monitoring in intensive care medicine. Hospital providers and medical device manufacturers should focus on reducing false alarms, implementing hospital alarm SOPs, introducing wireless sensors, preparing for the use of AI, and enhancing digital literacy of ICU staff. Our results may contribute to the user-centered transfer of digital technologies into practice to alleviate challenges in intensive care medicine. Clinical Trial: ClinicalTrials.gov NCT03514173; https://clinicaltrials.gov/ct2/show/NCT03514173