Development and Translation of Human-AI Interaction Models into Working Prototypes for Clinical Decision-making

TY - GEN

T1 - Development and Translation of Human-AI Interaction Models into Working Prototypes for Clinical Decision-making

AU - Hussain, Muhammad

AU - Iacovides, Jo

AU - Lawton, Tom

AU - Sharma, Vishal

AU - Porter, Zoe

AU - Cunningham, Alice

AU - Habli, Ibrahim

AU - Hickey, Shireen

AU - Wong, Nee Ling

AU - Jia, Yan

AU - Morgan, Phillip David James

N1 - This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

PY - 2024/7/5

Y1 - 2024/7/5

N2 - In the standard interaction model of clinical decision support systems, the system makes a recommendation, and the clinician decides whether to act on it. However, this model can compromise the patient-centeredness of care and the level of clinician involvement. There is scope to develop alternative interaction models, but we need methods for exploring and comparing these to assess how they may impact clinical decision-making. Through collaborating with clinical, AI safety, and HCI experts, and patient representatives, we co-designed a number of alternative human-AI interaction models for clinical decision-making. We then translated these models into ‘Wizard of Oz’ prototypes, where we created clinical scenarios and designed user interfaces with different types of AI output. In this paper, we present alternative models of human-AI interaction and illustrate how we used a co-design approach to translate them into functional prototypes that can be tested with users to explore potential impacts on clinical decision-making.

AB - In the standard interaction model of clinical decision support systems, the system makes a recommendation, and the clinician decides whether to act on it. However, this model can compromise the patient-centeredness of care and the level of clinician involvement. There is scope to develop alternative interaction models, but we need methods for exploring and comparing these to assess how they may impact clinical decision-making. Through collaborating with clinical, AI safety, and HCI experts, and patient representatives, we co-designed a number of alternative human-AI interaction models for clinical decision-making. We then translated these models into ‘Wizard of Oz’ prototypes, where we created clinical scenarios and designed user interfaces with different types of AI output. In this paper, we present alternative models of human-AI interaction and illustrate how we used a co-design approach to translate them into functional prototypes that can be tested with users to explore potential impacts on clinical decision-making.

KW - decision-making

KW - healthcare

KW - Human-AI interaction

KW - prototyping

KW - Wizard-of-OZ

UR - http://www.scopus.com/inward/record.url?scp=85200389820&partnerID=8YFLogxK

U2 - 10.1145/3643834.3660697

DO - 10.1145/3643834.3660697

M3 - Conference contribution

AN - SCOPUS:85200389820

T3 - Proceedings of the 2024 ACM Designing Interactive Systems Conference, DIS 2024

SP - 1607

EP - 1619

BT - Proceedings of the 2024 ACM Designing Interactive Systems Conference, DIS 2024

A2 - Vallgarda, Anna

A2 - Jonsson, Li

A2 - Fritsch, Jonas

A2 - Alaoui, Sarah Fdili

A2 - Le Dantec, Christopher A.

PB - Association for Computing Machinery, Inc

T2 - 2024 ACM Designing Interactive Systems Conference, DIS 2024

Y2 - 1 July 2024 through 5 July 2024

ER -