Predicting Effects of a Digital Stress Intervention for Patients With Depressive Symptoms: Development and Validation of Meta-Analytic Prognostic Models Using Individual Participant Data
Publikation: Beiträge in Zeitschriften › Zeitschriftenaufsätze › Forschung › begutachtet
Standard
in: Journal of Consulting and Clinical Psychology, Jahrgang 92, Nr. 4, 01.04.2024, S. 226-235.
Publikation: Beiträge in Zeitschriften › Zeitschriftenaufsätze › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Predicting Effects of a Digital Stress Intervention for Patients With Depressive Symptoms
T2 - Development and Validation of Meta-Analytic Prognostic Models Using Individual Participant Data
AU - Harrer, Mathias
AU - Baumeister, Harald
AU - Cuijpers, Pim
AU - Heber, Elena
AU - Lehr, Dirk
AU - Kessler, Ronald C.
AU - Ebert, David Daniel
N1 - Funding Information: Mathias Harrer is supported by a fellowship of the Bavarian Research Institute for Digital Transformation, an institute of the Bavarian Academy of Sciences and Humanities (Grant Z.5-M7426.6.5/3/21). Publisher Copyright: © 2023 American Psychological Association
PY - 2024/4/1
Y1 - 2024/4/1
N2 - Objective: Digital stress interventions could be helpful as an “indirect” treatment for depression, but it remains unclear for whom this is a viable option. In this study, we developed models predicting individualized benefits of a digital stress intervention on depressive symptoms at 6-month follow-up. Method: Data of N = 1,525 patients with depressive symptoms (Center for Epidemiological Studies’ Depression Scale, CES-D ≥ 16) from k = 6 randomized trials (digital stress intervention vs. waitlist) were collected. Prognostic models were developed using multilevel least absolute shrinkage and selection operator and boosting algorithms, and were validated using bootstrap bias correction and internal–external cross-validation. Subsequently, expected effects among those with and without a treatment recommendation were estimated based on clinically derived treatment assignment cut points. Results: Performances ranged from R2 = 21.0%–23.4%, decreasing only slightly after model optimism correction (R2 = 17.0%–19.6%). Predictions were greatly improved by including an interim assessment of depressive symptoms (optimism-corrected R2 = 32.6%–35.6%). Using a minimally important difference of d = −0.24 as assignment cut point, approximately 84.6%–93.3% of patients are helped by this type of intervention, while the remaining 6.7%–15.4% would experience clinically negligible benefits (δˆ = −0.02 to −0.19). Using reliable change as cut point, a smaller subset (39.3%–46.2%) with substantial expected benefits (δˆ = −0.68) receives a treatment recommendation. Conclusions: Meta-analytic prognostic models applied to individual participant data can be used to predict differential benefits of a digital stress intervention as an indirect treatment for depression. While most patients seem to benefit, the developed models could be helpful as a screening tool to identify those for whom a more intensive depression treatment is needed.
AB - Objective: Digital stress interventions could be helpful as an “indirect” treatment for depression, but it remains unclear for whom this is a viable option. In this study, we developed models predicting individualized benefits of a digital stress intervention on depressive symptoms at 6-month follow-up. Method: Data of N = 1,525 patients with depressive symptoms (Center for Epidemiological Studies’ Depression Scale, CES-D ≥ 16) from k = 6 randomized trials (digital stress intervention vs. waitlist) were collected. Prognostic models were developed using multilevel least absolute shrinkage and selection operator and boosting algorithms, and were validated using bootstrap bias correction and internal–external cross-validation. Subsequently, expected effects among those with and without a treatment recommendation were estimated based on clinically derived treatment assignment cut points. Results: Performances ranged from R2 = 21.0%–23.4%, decreasing only slightly after model optimism correction (R2 = 17.0%–19.6%). Predictions were greatly improved by including an interim assessment of depressive symptoms (optimism-corrected R2 = 32.6%–35.6%). Using a minimally important difference of d = −0.24 as assignment cut point, approximately 84.6%–93.3% of patients are helped by this type of intervention, while the remaining 6.7%–15.4% would experience clinically negligible benefits (δˆ = −0.02 to −0.19). Using reliable change as cut point, a smaller subset (39.3%–46.2%) with substantial expected benefits (δˆ = −0.68) receives a treatment recommendation. Conclusions: Meta-analytic prognostic models applied to individual participant data can be used to predict differential benefits of a digital stress intervention as an indirect treatment for depression. While most patients seem to benefit, the developed models could be helpful as a screening tool to identify those for whom a more intensive depression treatment is needed.
KW - depression
KW - heterogeneity of treatment effects
KW - machine learning
KW - prognosis
KW - stress
KW - Psychology
UR - http://www.scopus.com/inward/record.url?scp=85183392771&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/d4feb648-ddc3-3bb9-afbb-f05b92821a8d/
U2 - 10.1037/ccp0000852
DO - 10.1037/ccp0000852
M3 - Journal articles
C2 - 38127574
AN - SCOPUS:85183392771
VL - 92
SP - 226
EP - 235
JO - Journal of Consulting and Clinical Psychology
JF - Journal of Consulting and Clinical Psychology
SN - 0022-006X
IS - 4
ER -