Personalizing a mental health texting intervention using reinforcement learning.

Marvyn R Arévalo Avalos, Karina Rosales, Chris Karr, Caroline A Figueroa, Tiffany Luo, Suchitra Sudarshan, Vivian Yip, Adrian Aguilera

Abstract read

PubMed Full text at PMC Publisher

In one paragraph

Article in Npj mental health research, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it

0cells of the map it votes in

0citing papers in PubMed

–field-weighted citation impact

1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

8 authors.

Marvyn R Arévalo AvalosSchool of Social Welfare, University of California Berkeley, Berkeley, CA, USA.

Karina RosalesSchool of Social Welfare, University of California Berkeley, Berkeley, CA, USA.

Chris KarrAudacious Software, Chicago, IL, USA.

Caroline A FigueroaFaculty of Technology, Policy, and Management, Delft Technical University, Delft, The Netherlands.

Tiffany LuoSchool of Social Welfare, University of California Berkeley, Berkeley, CA, USA.

Suchitra SudarshanSchool of Social Welfare, University of California Berkeley, Berkeley, CA, USA.

Vivian YipSchool of Social Welfare, University of California Berkeley, Berkeley, CA, USA.

Adrian AguileraSchool of Social Welfare, University of California Berkeley, Berkeley, CA, USA. aguila@berkeley.edu.

Funding

HRSA HHS HRSA 17D34HP31028

6 · The paper itself

Abstract

StayWell is a 60-day CBT/DBT-based text messaging intervention which leverages reinforcement learning algorithms to support mental health. Participants were randomly assigned to receiving personalized messaging (adaptive arm), static messaging (random arm) or mood-monitoring only messages (control arm). A diverse sample of 1121 adults participated in a fully remote trial between December 2021 and July 2022. Across study arms, participants showed a 25% reduction in depression symptoms (PHQ-8) and 24% reduction in anxiety symptoms (GAD-7) following the intervention. We did not find statistically significant differences in PHQ-8 and GAD-7 reductions between intervention arms. Participants in the control arm had higher mood-monitoring messages response rates than those in other conditions. Finally, post-hoc exploratory analysis assessing outcomes by condition indicated that patients with minimal to mild depression symptoms (PHQ-8 < 10) benefitted from the reinforcement learning algorithm. The results of this trial suggest that StayWell is a promising text-messaging intervention to achieve reductions in depression and anxiety among diverse populations.

Identifiers

PMID41331095

DOI10.1038/s44184-025-00173-3

PMCPMC12673119

What OpenQuestion holds

Textmetadata

LicenceCC BY

Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.