Illustration of tailored digital health and potential new avenues

Kei Long Cheung, Santiago Hors-Fraile, Hein de Vries

Research output: Chapter in Book/Report/Conference proceedingChapterAcademic

Abstract

This chapter illustrates a previously discussed pragmatic methodology to design a tailored smoking cessation digital health program. Guided by principles of intervention planning protocols, sociocognitive theories, such as the Integrated-Change Model, are useful to design evidence-based interventions. Intervention planning protocols can be deemed highly complex and resources may be limited. The pragmatic approach discussed to design digital health simplifies this process in a four-step approach using smoking cessation as an example. Tobacco smoking remains the worldwide leading cause of death, illness, and impoverishment. Research on this topic to develop and validate tailored Digital health (dHealth) interventions is highly relevant for society. The specific change objectives can be planned based on the determinants of the Integrated-Change Model.

When designing an intervention that covers any of the behavior change phases (i.e., awareness, motivation, action) , it is needed to identify the most relevant determinants and related beliefs of each phase. This identification entails looking which determinants and related beliefs predict the transition from smoking to nonsmoking. This is usually done by combining a qualitative with a quantitative exercise. Once we know which determinants and beliefs are most relevant for our target group, we can select these items to develop the program content (i.e., messages) and the algorithm to select and send the personalized contents. At this point, choices need to be made concerning how many intervention interactions (sessions) will be useful, realistic, and feasible.

Research is needed to progress the efficacy of tailored dHealth. One approach that is especially interesting is the use of artificial intelligence to innovate the algorithms of tailoring, moving from rule-based to data-driven tailored dHealth. Using validated solutions and working with a multidisciplinary team of experts to be able to understand clinical, psychological, and artificial intelligence areas is of utmost importance to achieve safe and satisfactory results combining AI and tailoring to induce behavioral changes.
Original languageEnglish
Title of host publicationDigital Health
Subtitle of host publicationMobile and Wearable Devices for Participatory Health Applications
EditorsShabbir Syed-Abdul, Xinxin Zhu, Luis Fernandez-Luque
PublisherElsevier
Chapter9
Pages159-169
ISBN (Print)978-0-12-820077-3
DOIs
Publication statusPublished - 2021

Cite this