Computational Notebooks as Co-Design Tools - Engaging Young Adults Living with Diabetes, Family Carers, and Clinicians with Machine Learning Models

Aug 6, 2026

Upload by Logic

Engaging end user groups with machine learning models can align predictive system design with people’s needs and expectations. This co-design study examines benefits and challenges of using computational notebooks to support ML model development with young adults, family carers, and clinicians. An example diabetes risk prediction model was used in codesign workshops and retrospective interviews. Participants valued interactive data visualisations for multidisciplinary learning, anticipating benefits and harms, and creating fictional feature-importance plots, while reporting difficulties including code execution and managing information and power imbalances.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages28

Reading Time1 h 11 min

AccessFree to download

Introduction

Human-centred and participatory approaches to AI design

Computational notebooks for multidisciplinary collaboration

Co-design study (workshops and interviews)

Example ML model for diabetes risk prediction

Valued notebook capabilities

Reported challenges

Ayobi, A. , Hughes, J. , Duckworth, C. J. , Dylag, J. J. , James, S. , Marshall, P. , Guy, M. J. , Kumaran, A. , Chapman, A. , Boniface, M. , & O'Kane, A. A. (2023) . Computational Notebooks as Co-Design Tools: Engaging Young Adults Living with Diabetes, Family Carers, and Clinicians with Machine Learning Models. In CHI 2023-Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems Article 300 (Conference on Human Factors in Computing Systems-Proceedings) . Association for Computing Machinery. [https://doi.org/10.1145/3544548.3581424](https://doi.org/10.1145/3544548.3581424)[ ](https://doi.org/10.1145/3544548.3581424)Peer reviewed version Link to published version (if available): 10.1145/3544548.3581424 Link to publication record on the Bristol Research Portal PDF-document This is the accepted author manuscript (AAM) . The final published version (version of record) is available online via ACM at [https://doi.org/10.1145/3544548.3581424.Please](https://doi.org/10.1145/3544548.3581424.Please) refer to any applicable terms of use of the publisher. University of Bristol – Bristol Research Portal General rights This document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: [http://www.bristol.ac.uk/red/research-policy/pure/user-guides/brp-terms/](http://www.bristol.ac.uk/red/research-policy/pure/user-guides/brp-terms/) Computational Notebooks as Co-Design Tools: Engaging Young Adults Living with Diabetes, Family Carers, and Clinicians with Machine Learning Models Amid Ayobi University College London, London, United Kingdom Jacob Hughes University of Bristol, Bristol, United Kingdom Christopher J Duckworth University of Southampton, Southampton, United Kingdom JakubJ Dylag University of Southampton, Southampton, United Kingdom Sam James University of Bristol, Bristol, United Kingdom Paul Marshall University of Bristol, Bristol, United Kingdom Matthew Guy University Hospital Southampton, Southampton, United Kingdom Anitha Kumaran University Hospital Southampton, Southampton, United Kingdom Adriane Chapman University of Southampton, Southampton, United Kingdom Michael Boniface University of Southampton, Southampton, United Kingdom Aisling Ann O'Kane University of Bristol, Bristol, United Kingdom "© Ayobi et al. 2023. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive version is being published in: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23), April 23–28, 2023, Hamburg, Germany. ACM, New York, NY, USA, 20 pages. [https://doi.org/10.1145/3544548.3581424](https://doi.org/10.1145/3544548.3581424) Engaging end user groups with machine learning (ML) models can help align the design of predictive systems with people’s needs and expectations. We present a co-design study investigating the benefits and challenges of using computational notebooks to inform ML models with end user groups. We used a computational notebook to engage young adults, carers, and clinicians with an example ML model that predicted health risk in diabetes care. Through codesign workshops and retrospective interviews, we found that participants particularly valued using the interactive data visualisations of the computational notebook to scaffold multidisciplinary learning, anticipate benefits and harms of the example ML model, and create fictional feature importance plots to highlight care needs. Participants also reported challenges, from running code cells to managing information asymmetries and power imbalances. We discuss the potential of leveraging computational notebooks as interactive co-design tools to meet end user needs early in ML model lifecycles. CCS CONCEPTS • Human-centered

FAQs

What is the purpose of using computational notebooks in this study?

The study investigates how computational notebooks can support co-design by engaging young adults, carers, and clinicians with machine learning models.

How did participants interact with the example diabetes ML model?

They participated in codesign workshops and retrospective interviews using a computational notebook that included interactive data visualisations for an ML model predicting health risk in diabetes care.

What challenges did participants report when using the notebooks?

Participants reported challenges such as running code cells and dealing with information asymmetries and power imbalances.

Aug 6, 2026

Upload by Logic