Design for Integrating Explainable AI for Dynamic Risk Prediction in Ambulance IT-systems

dc.contributor.authorWallsten, David
dc.contributor.authorAxton, Gregory
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.contributor.departmentChalmers University of Technology / Department of Computer Science and Engineeringen
dc.contributor.examinerDahlstedt, Palle
dc.contributor.supervisorWiberg, Mikael
dc.contributor.supervisorEriksson, Thommy
dc.date.accessioned2023-12-19T15:01:31Z
dc.date.available2023-12-19T15:01:31Z
dc.date.issued2023
dc.date.submitted2023
dc.description.abstractDemographic changes in the West with an increasingly elderly population puts stress on current healthcare systems. New technologies are necessary to secure patient safety. AI development shows great promise in improving care, but communicating AI decisions requires more research. In this study, a prototype of eXplainable AI (XAI) was designed for an ambulance IT system, based on an AI model for risk prediction of severe trauma to be used by Emergency Medical Services (EMS) clinicians. Knowledge was gathered for the design through ethnography, expert interviews, and a literature review. Then several ideas developed through stages of prototyping and were verified by experts in prehospital healthcare. Finally, a high-fidelity prototype was evaluated by the EMS clinicians. The design was then evaluated by seven EMS clinicians. They thought that XAI was necessary for them to trust the prediction. They make the final decision, and if they can’t base it on specific parameters, they feel they can’t make a proper judgement. In addition, the design helped in reminding EMS clinicians of things they might have missed. If given a prediction from the AI that was different from their own, it might cause them to think more about their decision, moving it away from the normally relatively automatic process and likely reducing the risk of bias. While focused on trauma, the design should be applicable to other AI models. Current models for risk prediction in ambulances have so far not seen a big benefit from using artificial neural networks (ANN) compared to more transparent models. This study can help guide the future development of AI for prehospital healthcare and give insights into the potential benefits and implications of its implementation. The report also explores the ethical implications, the complexity of the ambulance work environment and possible implications for cognitive decision processes.
dc.identifier.coursecodeDATX05
dc.identifier.urihttp://hdl.handle.net/20.500.12380/307443
dc.language.isoeng
dc.setspec.uppsokTechnology
dc.subjectComputer
dc.subjectscience
dc.subjectcomputer science
dc.subjectengineering
dc.subjectproject
dc.subjectthesis
dc.titleDesign for Integrating Explainable AI for Dynamic Risk Prediction in Ambulance IT-systems
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeInteraction design and technologies (MPIDE), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
CSE 23-70 DW GA.pdf
Storlek:
33.74 MB
Format:
Adobe Portable Document Format
Beskrivning:
License bundle
Visar 1 - 1 av 1
Hämtar...
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: