TY - JOUR
T1 - Cross-trial prediction in psychotherapy
T2 - External validation of the Personalized Advantage Index using machine learning in two Dutch randomized trials comparing CBT versus IPT for depression
AU - Van Bronswijk, Suzanne C.
AU - Bruijniks, Sanne J E
AU - Lorenzo-Luaces, Lorenzo
AU - Derubeis, Robert J
AU - Lemmens, Lotte H.J.M.
AU - Peeters, Frenk P.M.L.
AU - Huibers, Marcus J.H.
N1 - Funding Information:
This work was supported by ZonMw, the Netherlands: [837002401]; Stichting tot Steun of the Vereniging voor Christelijke Verzorging van Geestes- en Zenuwzieken, the Netherlands.: [Grant Number NA]; research institute of Experimental Psychopathology (EPP), the Netherlands: [Grant Number NA]; Academic Community Mental Health Centre (RIAGG, now METGGZ Maastricht) in Maastricht, the Netherlands: [Grant Number NA]. We would like to acknowledge the contribution of participants and therapists of the STEPd and the FreqMech study. Furthermore, we thank Annie Raven, Annie Hendriks, Danielle Tilburgs, Nicole Billingy, Kris Wijma and Sofie Jansen for their assistance during the two studies.
Publisher Copyright:
© 2020 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
PY - 2021/1/2
Y1 - 2021/1/2
N2 - AbstractObjective: Optimizing treatment selection may improve treatment outcomes in depression. A promising approach is the Personalized Advantage Index (PAI), which predicts the optimal treatment for a given individual. To determine the generalizability of the PAI, models needs to be externally validated, which has rarely been done. Method: PAI models were developed within each of two independent trials, with substantial between-study differences, that both compared CBT and IPT for depression (STEPd: n = 151 and FreqMech: n = 200). Subsequently, both PAI models were tested in the other dataset. Results: In the STEPd study, post-treatment depression was significantly different between individuals assigned to their PAI-indicated treatment versus those assigned to their non-indicated treatment (d = .57). In the FreqMech study, post-treatment depression was not significantly different between patients receiving their indicated treatment versus those receiving their non-indicated treatment (d = .20). Cross-trial predictions indicated that post-treatment depression was not significantly different between those receiving their indicated treatment and those receiving their non-indicated treatment (d = .16 and d = .27). Sensitivity analyses indicated that cross-trial prediction based on only overlapping variables didn't improve the results. Conclusion: External validation of the PAI has modest results and emphasizes between-study differences and many other challenges.
AB - AbstractObjective: Optimizing treatment selection may improve treatment outcomes in depression. A promising approach is the Personalized Advantage Index (PAI), which predicts the optimal treatment for a given individual. To determine the generalizability of the PAI, models needs to be externally validated, which has rarely been done. Method: PAI models were developed within each of two independent trials, with substantial between-study differences, that both compared CBT and IPT for depression (STEPd: n = 151 and FreqMech: n = 200). Subsequently, both PAI models were tested in the other dataset. Results: In the STEPd study, post-treatment depression was significantly different between individuals assigned to their PAI-indicated treatment versus those assigned to their non-indicated treatment (d = .57). In the FreqMech study, post-treatment depression was not significantly different between patients receiving their indicated treatment versus those receiving their non-indicated treatment (d = .20). Cross-trial predictions indicated that post-treatment depression was not significantly different between those receiving their indicated treatment and those receiving their non-indicated treatment (d = .16 and d = .27). Sensitivity analyses indicated that cross-trial prediction based on only overlapping variables didn't improve the results. Conclusion: External validation of the PAI has modest results and emphasizes between-study differences and many other challenges.
KW - depression
KW - cognitive behavioural therapy
KW - interpersonal psychotherapy
KW - precision medicine
KW - prediction
KW - external validation
KW - MODELS
KW - REGULARIZATION
KW - IMPUTATION
KW - SELECTION
KW - THERAPY
U2 - 10.1080/10503307.2020.1823029
DO - 10.1080/10503307.2020.1823029
M3 - Article
C2 - 32964809
SN - 1050-3307
VL - 31
SP - 78
EP - 91
JO - Psychotherapy Research
JF - Psychotherapy Research
IS - 1
ER -