A human-centered perspective on research challenges for hybrid human artificial intelligence in lifestyle and behavior change support

Journal Article (2025)
Author(s)

Chenxu Hao (TU Delft - Pattern Recognition and Bioinformatics)

Susanne Uusitalo (University of Oulu)

Caroline Figueroa (Malmö University, TU Delft - Information and Communication Technology)

Quirine Smit (TNO)

Michael Strange (Malmö University)

Wen-Tseng Chang (Amsterdam University of Applied Sciences)

M. I. Ribeiro (Eindhoven University of Technology)

Vanita Kouomogne Nana (University of Limerick)

Myrthe Tielman (TU Delft - Interactive Intelligence)

Maaike H.T. De Boer (TNO)

Research Group
Pattern Recognition and Bioinformatics
DOI related publication
https://doi.org/10.3389/fdgth.2025.1544185
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Pattern Recognition and Bioinformatics
Volume number
7
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

As intelligent systems become more integrated into people’s daily life, systems designed to facilitate lifestyle and behavior change for health and well-being have also become more common. Previous work has identified challenges in the development and deployment of such AI-based support for diabetes lifestyle management and shown that it is necessary to shift the design process of AI-based support systems towards a human-centered approach that can be addressed by hybrid intelligence (HI). However, this shift also means adopting a user-centric design process, which brings its own challenges in terms of stakeholder involvement, evaluation processes and ethical concerns. In this perspective paper, we aim to more comprehensively identify challenges and future research directions in the development of HI systems for behavior change from four different viewpoints: (1) challenges on an individual level, such as understanding the individual end-user’s context (2) challenges on an evaluation level, such as evaluation pipelines and identifying success criteria and (3) challenges in addressing ethical implications. We show that developing HI systems for behavior change is an interdisciplinary process that requires further collaboration and consideration from various fields.