Expectations and requirements of surgical staff for an AI-supported clinical decision support system for older patients: a qualitative study
ABSTRACT
Background:
The SURGE-Ahead project aims to develop a clinical decision support system (CDSS) supporting treatment and continuity of care (COC) for acute, geriatric surgical patients. The system will support surgical staff by 1) displaying treatment proposals from a geriatric perspective based on data extracted from the hospital information system and relevant assessments for geriatric patients and 2) displaying an AI-generated suggestion for the best discharge option.
Objective:
Get insight into current challenges when treating geriatric patients from the perspective of surgical professionals and assess their wishes, worries, and ethical considerations regarding the use of an AI-supported CDSS.
Methods:
A qualitative study in the form of personal interviews with physicians, nurses, physiotherapists, and social workers, employed in surgical departments at a university hospital in southern Germany, was conducted in April 2022. Interviews were conducted in person, transcribed and coded by two researchers using content and thematic analysis.
Results:
Interviewees mentioned multiple challenges in geriatric patient care (e.g. cognitive impairment, pre-existing diseases, medication), the lack of existing technical solutions, and a wish for more support by geriatric experts. A CDSS is believed to provide a holistic picture of geriatric patients, facilitate communication, and accelerate processes. Difficulties in handling a CDSS and a negative impact on the patient-caregiver relationship is feared by some interviewees.
Conclusions:
In conclusion, an AI-supported CDSS could improve geriatric patient care. Easy access, intuitive usability, and automatic data transfer need to be considered during development. The caregiver-patient relationship should be protected by keeping the highest decision authority with humans.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.