Design for Integrating Explainable AI for Dynamic Risk Prediction in Ambulance IT-systems
| dc.contributor.author | Wallsten, David | |
| dc.contributor.author | Axton, Gregory | |
| dc.contributor.department | Chalmers tekniska högskola / Institutionen för data och informationsteknik | sv |
| dc.contributor.department | Chalmers University of Technology / Department of Computer Science and Engineering | en |
| dc.contributor.examiner | Dahlstedt, Palle | |
| dc.contributor.supervisor | Wiberg, Mikael | |
| dc.contributor.supervisor | Eriksson, Thommy | |
| dc.date.accessioned | 2023-12-19T15:01:31Z | |
| dc.date.available | 2023-12-19T15:01:31Z | |
| dc.date.issued | 2023 | |
| dc.date.submitted | 2023 | |
| dc.description.abstract | Demographic 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.coursecode | DATX05 | |
| dc.identifier.uri | http://hdl.handle.net/20.500.12380/307443 | |
| dc.language.iso | eng | |
| dc.setspec.uppsok | Technology | |
| dc.subject | Computer | |
| dc.subject | science | |
| dc.subject | computer science | |
| dc.subject | engineering | |
| dc.subject | project | |
| dc.subject | thesis | |
| dc.title | Design for Integrating Explainable AI for Dynamic Risk Prediction in Ambulance IT-systems | |
| dc.type.degree | Examensarbete för masterexamen | sv |
| dc.type.degree | Master's Thesis | en |
| dc.type.uppsok | H | |
| local.programme | Interaction design and technologies (MPIDE), MSc |