Jan David Smeddinck
Rada Hussein
Christopher Bull
Tom Foley
Mark van Gils- 1Ludwig Boltzmann Institute for Digital Health and Prevention, Ludwig Boltzmann Gesellschaft, Salzburg, Austria
- 2Human-Centered Ubiquitous Media Research Group, LMU Munich, Munich, Germany
- 3Open Lab, School of Computing, Newcastle University, Newcastle upon Tyne, United Kingdom
- 4Population Health Sciences Institute for Foley, Newcastle University, Newcastle upon Tyne, United Kingdom
- 5School of Medicine, University College Dublin, Dublin, Ireland
- 6Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland
Editorial on the Research Topic
Supporting sustainable behavior change and empowerment in ubiquitous and learning health systems
1 Introduction
The increasing integration of digital health technologies into everyday life marks a transformative shift in healthcare and prevention. Ubiquitous digital health systems include continuous monitoring and intervention capabilities, offering unprecedented opportunities for preventive and rehabilitative healthcare, moving beyond a primary focus on addressing health problems after they symptomatically manifest. This shift is not merely characterized by technological evolution but also by a paradigmatic change towards more personalized, data-driven, and sustainable healthcare approaches. In this editorial, we underscore the potential of ubiquitous and learning health systems to revolutionize healthcare, including fostering sustainable behavior change and empowering individuals in their health journeys.
Digital health technologies are increasingly present in our day-to-day lives and are often used continuously, enabling the integration of an increasing variety of data. Such ubiquitous and often mobile digital health systems have considerable potential in enabling long-term—or even life-long disease management. Furthermore, accompanying healthcare monitoring and interventions with a focus on prevention and rehabilitation could reduce the amount and extent of events that require traditional medical treatment. This can lower individual suffering, as well as the burden on public health systems considerably (1, 2) and has the potential to increase quality-adjusted life years (3).
2 The promise of learning health systems
In the context of ubiquitous digital health technologies, learning health systems have the potential to reshape healthcare by providing continuous, context-aware and reflexively iterated healthcare and prevention systems providing benefits at individual and population levels (4). Longer-term, or even life-long health data, including patient generated and patient contributed data might deliver the concept of a digital health twin (5), which promises to act as the information driving personalized or “precision” health in an increasingly optimized manner. Learning health systems, characterized by their adaptability and iterative improvement, are pivotal in realizing the potential of ubiquitous health technologies given their rapid and continuous development. These systems can leverage data and machine learning as well as learnings from lived and practical experience to evolve and tailor healthcare interventions at the individual and system level with different levels of abstraction of learning loops (6) and with an overarching aim of enhancing the efficacy and efficiency of health services (7). The Free et al., study on pneumonia management demonstrates the potential of data-driven frameworks in supporting clinical decision support. Ultimately, LHS can be a steppingstone towards expanding quality-adjusted life years by promoting proactive health management that considers healthcare and prevention delivery as an inherently iterative process (4) in a complex socio-digital ecosystem [cf. e.g., (8)].
3 Challenges, opportunities & the need for sustainable behavior change
The pervasive nature of digital health technologies introduces several challenges, including data security, privacy, and the equitable distribution of healthcare benefits. These challenges necessitate careful consideration and responsible implementation to ensure that these technologies empower rather than disenfranchise individuals (9). Addressing equity in digital healthcare, as discussed in the context of Denmark by Eriksen et al., is crucial to ensure that these technologies benefit all segments of society equally, integrating perspectives on personal and systemic health with a focus on ensuring equitable access, empowerment and emancipation in digital healthcare. A particular challenge exists at the individual level in that sustainable behavior change is central to the vision behind approaches to healthcare and prevention that are taking a health-journey accompanying or even life-long approach. Long-term adherence to healthy lifestyle changes, facilitated by digital tools, can significantly improve health outcomes. The EPICURE study by Hayn et al., highlights how digital tools, such as wearables, can support cardiac rehabilitation but also emphasizes the need for larger, randomized controlled trials to fully understand their impact.
4 The role of personalization and adaptivity in healthcare
Personalization in healthcare, enabled by data-driven insights and rapidly developing capabilities in machine learning and artificial intelligence (10, 11), is becoming a core ambition of effective digital health systems. It allows for interventions to be tailored to individual needs and preferences, increasing their relevance and effectiveness. E.g., the scalable employment of consumer wearables can support predictive analytics and partially replace traditional manual self-reports, as indicated in the Vuong et al. study on predicting pain ratings in sickle cell disease. Notably, while the technical and procedural building blocks exist for fostering sustainable behavior change in individuals and adaptive improvements in learning health systems, both suffer from a lack of structured investigation. Research approaches that can enable efficient knowledge generation on the complex interplay of variables that determine possible improvements (or deterioration) in individual or population health are clearly needed. This encourages future work that exceeds beyond traditional randomized controlled study designs, enabling the expression (12) and systematic study of complex system configurations and mechanisms for adaptivity. This will require capable and scalable research infrastructures (13), as well as improvements in research methods at scale, for which novel artificial intelligence methods currently offer an exciting avenue of exploration, particularly due to newly evolving capabilities in readily integrating highly varied and sparse multi-modal data streams, as well as converting between structured digital (i.e., “computable”) and unstructured natural language (i.e., easily and efficiently describable) representations.
5 Conclusion
This Research Topic brings together relevant articles around sensor-enabled, data-driven, and increasingly ubiquitous digital health. It contributes to the pathway towards individually empowering digital health technology, using e.g., predictive methods that deliver increasingly more precise and preventative approaches, with the larger aim of preserving quality-adjusted life years at the individual and societal level.
Author contributions
JS: Conceptualization, Project administration, Writing – original draft, Writing – review & editing. RH: Conceptualization, Writing – original draft, Writing – review & editing. CB: Writing – original draft, Writing – review & editing. TF: Writing – original draft, Writing – review & editing. MG: Writing – original draft, Writing – review & editing.
Acknowledgments
We thank all submitting authors for their contributions to the Research Topic. We also thank Professor Rik Crutzen for his valuable inputs in shaping the topic. We further thank Frontiers in Digital Health and the Health Informatics section for their support and editorial management of the Research Topic.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1. Abernethy A, Adams L, Barrett M, Bechtel C, Brennan P, Butte A, et al. The promise of digital health: then, now, and the future. NAM Perspectives. (2022):1–24. doi: 10.31478/202206e
2. Kvedar J, Coye MJ, Everett W. Connected health: a review of technologies and strategies to improve patient care with telemedicine and telehealth. Health Aff (Millwood). (2014) 33(2), 194–9. doi: 10.1377/hlthaff.2013.0992
3. Gentili A, Failla G, Melnyk A, Puleo V, Tanna GLD, Ricciardi W, et al. The cost-effectiveness of digital health interventions: a systematic review of the literature. Front Public Health. (2022) 10: 787135. doi: 10.3389/fpubh.2022.787135
4. Foley T, Vale L. A framework for understanding, designing, developing and evaluating learning health systems. Learn Health Sys. (2023) 7(1), e10315. doi: 10.1002/lrh2.10315
5. Venkatesh KP, Raza MM, Kvedar JC. Health digital twins as tools for precision medicine: considerations for computation, implementation, and regulation. NPJ Digit Med. (2022) 5(1):149–50. doi: 10.1038/s41746-022-00694-7
6. Sheikh K, Abimbola S. Learning health systems: Pathways to progress (Flagship Report of the Alliance for Health Policy and Systems Research). Geneva: World Health Organization. (2021). doi: 10.31219/osf.io/z7ydr
7. Friedman CP, Wong A.K, Blumenthal D. Achieving a nationwide learning health system. Sci Transl Med. (2010) 2(57), 57cm29–57cm29. doi: 10.1126/scitranslmed.3001456
8. Greenhalgh T, Wherton J, Papoutsi C, Lynch J, Hughes G, A’Court C, et al. Beyond adoption: a new framework for theorizing and evaluating nonadoption, abandonment, and challenges to the scale-up, spread, and sustainability of health and care technologies. J Med Internet Res. 1(2017) 9(11), e367. doi: 10.2196/jmir.8775
9. Mittelstadt B. (2017). Ethics of the Health-Related Internet of Things: A Narrative Review (SSRN Scholarly Paper 2932221). doi: 10.2139/ssrn.2932221
10. Moor M, Banerjee O, Abad ZSH, Krumholz HM, Leskovec J, Topol EJ, et al. Foundation models for generalist medical artificial intelligence. Nature. (2023) 616(7956):259–65. doi: 10.1038/s41586-023-05881-4
11. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. (2019) 25(1):44–65. doi: 10.1038/s41591-018-0300-7
12. Gruber S, Neumayr B, Smeddinck JD. Towards integration-preserving customization of just-in-time adaptive interventions with composite clabjects in RDF and SHACL. 2022 ACM/IEEE international conference on model driven engineering languages and systems companion (MODELS-C) (2022).
Keywords: digital health, learning health systems, behavior change, health data, health informatics, empowerment
Citation: Smeddinck JD, Hussein R, Bull C, Foley T and van Gils M (2024) Editorial: Supporting sustainable behavior change and empowerment in ubiquitous and learning health systems. Front. Digit. Health 6:1367567. doi: 10.3389/fdgth.2024.1367567
Received: 9 January 2024; Accepted: 15 January 2024;
Published: 30 January 2024.
Edited and Reviewed by: Uwe Aickelin, The University of Melbourne, Australia
© 2024 Smeddinck, Hussein, Bull, Foley and van Gils. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Jan David Smeddinck amFuLnNtZWRkaW5ja0BkaHAubGJnLmFjLmF0