Back

Feasibility and effectiveness of a smartwatch-based intervention program for ameliorating depressive symptoms: a pilot-study.

Tamm, J.; Brendler, A.; Bauer, A.; Gordon, J.; Strauss, D.; Brinkmann, R.; Degmayr, R.; Pfahl, D.; Friedrichs, M.; Schwind, J.; Spoormaker, V. I.

2025-01-19 psychiatry and clinical psychology
10.1101/2025.01.18.25320669 medRxiv
Show abstract

ObjectiveDepression remains one of the most critical healthcare concerns worldwide. While increasing patient numbers inevitably lead to a greater need for treatment, resources to adequately match this demand are limited. Digital technologies hold promises to complement standard therapeutic approaches such as psychotherapy, thereby alleviating the strain on an increasingly burdened healthcare system. This study aimed at testing a new comprehensive smartwatch-based digital intervention program administered for 12 weeks in depressed patients to aid therapeutic progression and symptom relief. MethodsSeventeen mildly to moderately depressed patients receiving the smartwatch-based intervention were compared to an existing, retrospective control group (35 patients). The intervention program comprised behavioral activation, cognitive-behavioral intervention for insomnia and physical activity interventions. Intervention effects on the reduction of depression severity, measured by the PHQ-9, were investigated using a repeated measure analysis of variance (rmANOVA). ResultsThe rmANOVA showed a significant group x time interaction for the PHQ-9 scores, F(1, 50) = 7.21, p = 0.010, with post-hoc t-tests revealing group differences after but not before the intervention. ConclusionThis study suggests that smartwatch-based interventions are feasible and effective in reducing mild to moderate depressive symptoms and could therefore be a promising stand-alone or complementary intervention to psychotherapy. Further research with a randomized controlled trial is required to validate these results.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.