eprintid: 10168535
rev_number: 7
eprint_status: archive
userid: 699
dir: disk0/10/16/85/35
datestamp: 2023-04-19 09:46:07
lastmod: 2023-04-19 09:46:07
status_changed: 2023-04-19 09:46:07
type: article
metadata_visibility: show
sword_depositor: 699
creators_name: Van Berkel, Niels
creators_name: Bellio, Maura
creators_name: Skov, Mikael B
creators_name: Blandford, Ann
title: Measurements, Algorithms, and Presentations of Reality: Framing Interactions with AI-Enabled Decision Support
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F48
keywords: Human-Centred AI, measurement, algorithms, presentation, MAP, MAP model, case studies, healthcare, medicine, decision-making, cooperative AI, Human-AI
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: Bringing AI technology into clinical practice has proved challenging for system designers and medical professionals alike. The academic literature has, for example, highlighted the dangers of black-box decision-making and biased datasets. Furthermore, end-users’ ability to validate a system’s performance often disappears following the introduction of AI decision-making. We present the MAP model to understand and describe the three stages through which medical observations are interpreted and handled by AI systems. These stages are Measurement, in which information is gathered and converted into data points that can be stored and processed; Algorithm, in which computational processes transform the collected data; and Presentation, where information is returned to the user for interpretation. For each stage, we highlight possible challenges that need to be overcome to develop Human-Centred AI systems. We illuminate our MAP model through complementary case studies on colonoscopy practice and dementia diagnosis, providing examples of the challenges encountered in real-world settings. By defining Human-AI interaction across these three stages, we untangle some of the inherent complexities in designing AI technology for clinical decision-making, and aim to overcome misalignment between medical end-users and AI researchers and developers.
date: 2023-04
date_type: published
publisher: Association for Computing Machinery (ACM)
official_url: https://doi.org/10.1145/3571815
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 2015041
doi: 10.1145/3571815
lyricists_name: Blandford, Ann
lyricists_id: AEBLA22
actors_name: Blandford, Ann
actors_id: AEBLA22
actors_role: owner
full_text_status: public
publication: ACM Transactions on Computer-Human Interaction
volume: 30
number: 2
article_number: 32
issn: 1073-0516
citation:        Van Berkel, Niels;    Bellio, Maura;    Skov, Mikael B;    Blandford, Ann;      (2023)    Measurements, Algorithms, and Presentations of Reality: Framing Interactions with AI-Enabled Decision Support.                   ACM Transactions on Computer-Human Interaction , 30  (2)    , Article 32.  10.1145/3571815 <https://doi.org/10.1145/3571815>.       Green open access   
 
document_url: https://discovery-pp.ucl.ac.uk/id/eprint/10168535/1/TOCHI_SI___Health_AI__MAP_%281%29.pdf