Cited by 135Digital Mental Health InterventionsMobile Health and mHealth ApplicationsAnxiety, Depression, Psychometrics, Treatment, Cognitive Processes

Personalization strategies in digital mental health interventions: a systematic review and conceptual framework for depressive symptoms

Open access
Hornstein, Silvan, Zantvoort, Kirsten, Lueken, Ulrike, Funk, Burkhardt, Hilbert, Kevin·2023·Frontiers in Digital Health

Abstract

Introduction: Personalization is a much-discussed approach to improve adherence and outcomes for Digital Mental Health interventions (DMHIs). Yet, major questions remain open, such as (1) what personalization is, (2) how prevalent it is in practice, and (3) what benefits it truly has. Methods: We address this gap by performing a systematic literature review identifying all empirical studies on DMHIs targeting depressive symptoms in adults from 2015 to September 2022. The search in Pubmed, SCOPUS and Psycinfo led to the inclusion of 138 articles, describing 94 distinct DMHIs provided to an overall sample of approximately 24,300 individuals. Results: Our investigation results in the conceptualization of personalization as purposefully designed variation between individuals in an intervention's therapeutic elements or its structure. We propose to further differentiate personalization by what is personalized (i.e., intervention content, content order, level of guidance or communication) and the underlying mechanism [i.e., user choice, provider choice, decision rules, and machine-learning (ML) based approaches]. Applying this concept, we identified personalization in 66% of the interventions for depressive symptoms, with personalized intervention content (32% of interventions) and communication with the user (30%) being particularly popular. Personalization via decision rules (48%) and user choice (36%) were the most used mechanisms, while the utilization of ML was rare (3%). Two-thirds of personalized interventions only tailored one dimension of the intervention. Discussion: We conclude that future interventions could provide even more personalized experiences and especially benefit from using ML models. Finally, empirical evidence for personalization was scarce and inconclusive, making further evidence for the benefits of personalization highly needed. Systematic Review Registration: Identifier: CRD42022357408.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3389/fdgth.2023.1170002

Cites

193 of 193 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Incorporating personalization strategies in digital mental health interventions designed around patients' symptoms and needs could lead to better management of depressive symptoms among healthcare workers.

    “Similarly, Hornstein et al. in their study noted that incorporating personalization strategies in digital mental health interventions specifically designed around patients’ symptoms and needs could lead to better management of depressive symptoms among healthcare workers [42].”

    From Mental Health in Healthcare Workers Post-COVID-19: A Latin American Review and Insights into Personalized Management Strategies (2024) · cites this paper as [42]

    The Introduction describes tailoring digital interventions to individual needs as a promising approach to improving care for depressive symptoms. But the paper does not establish that this applies specifically to healthcare workers; the Discussion also says direct evidence of personalization’s benefits is scarce and inconclusive. Page numbers were not available in our copy. (LLM, conf=0.88)

    Experimental — accuracy not yet measured
  • The study design does not permit definitive causal attribution to the personalization component specifically.

    “While this study design does not permit definitive causal attribution to the personalization component specifically, the observed patterns are consistent with conceptual frameworks, suggesting that content alignment with users’ cognitive-emotional profiles enhances engagement [8,34].”

    From Schema-Informed Digital Mental Health Intervention for Maladaptive Cognitive-Emotional Patterns: Randomized Controlled Trial (2025) · cites this paper as [8]

    The Discussion says that personalization was rarely directly manipulated and that the two trials that did manipulate it had small samples and inconclusive results. This supports caution about attributing effects to personalization, but the review does not assess the citing authors’ study design or establish its specific causal limitation. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. [34]Deighton J Sorrell M. The future of interactive marketing. Harv Bus Rev. (1996) 74(6): 151– 60. https://hbr.org/1996/11/the-future-of-interactive-marketing
  2. [38]Karyotaki E Efthimiou O Miguel C Bermpohl FMG Furukawa TA Cuijpers P Internet-based cognitive behavioral therapy for depression: a systematic review and individual patient data network meta-analysis. JAMA Psychiatry. (2021) 78(4): 361– 71. 10.1001/jamapsychiatry.2020.4364 33471111 PMC8027916 · DOI · Paper page

Cited by

Sorted by citations

Authors
Hornstein, S., Zantvoort, K., Lueken, U., Funk, B., & Hilbert, K.
Affiliations
  • Humboldt-Universität zu Berlin (DE)
  • Leuphana University of Lüneburg (DE)
Corresponding author
Hornstein, Silvan
Venue
Frontiers in Digital Health
Published
2023-05-22
Volume
5
Pages
1170002-1170002
ISSN
2673-253X (ISSN-L)
OpenAlex
W4377294815
Cited by
134
References
187
Citations by year
2026: 43 · 2025: 50 · 2024: 36 · 2023: 5
FWCI
4.55
Type
journal article
Language
en
Open access
Locations
  • Frontiers in Digital Health (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • edoc Publication server (Humboldt University of Berlin) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Multilingual Matters (Channel View Publications) (submittedVersion, cc-by)
  • edoc Publication server (Humboldt University of Berlin) (cc-by)
  • PubData (cc-by)
Funders
  • Deutsche Forschungsgemeinschaft (491192747)
  • Humboldt-Universität zu Berlin
Topics
  • Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
  • Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Anxiety, Depression, Psychometrics, Treatment, Cognitive Processes
Keywords
personalization, digital mental health interventions, depressive symptoms, depression, user choice, decision rules, machine learning, conceptual framework

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review