Dismantling, optimising, and personalising internet cognitive behavioural therapy for depression: a systematic review and component network meta-analysis using individual participant data

Furukawa, Toshi A; Suganuma, Aya M; Ostinelli, Edoardo G; Andersson, Gerhard; Beevers, Christopher G.; Shumake, Jason; Berger, Thomas; Boele, Florien; Buntrock, Claudia; Carlbring, Per; Choi, Isabella; Christensen, Helen; Mackinnon, Andrew; Dahne, Jennifer; Huibers, Marcus J.H.; Ebert, David Daniel; Farrer, Louise; Forand, Nicholas R.; Strunk, Daniel R.; Ezawa, Iony D.; Forsell, Erik; Kaldo, Viktor; Geraedts, Anna; Gilbody, Simon; Littlewood, Elizabeth; Brabyn, Sally; Hadjistavropoulos, Heather D.; Schneider, Luke H.; Johansson, Robert; Kenter, Robin Maria Francisca; Kivi, Marie; Björkelund, Cecilia; Kleiboer, Annet; Riper, Heleen; Klein, Jan Philipp; Schröder, Johanna; Meyer, Björn; Moritz, Steffen; Bücker, Lara; Lintvedt, Ove; Johansson, Peter; Lundgren, Johan; Milgrom, Jeannette; Gemmill, Alan W.; Mohr, David C.; Montero-Marín, Jesús; Garcı́a-Campayo, Javier; Nobis, Stephanie; Zarski, Anna-Carlotta; O’Moore, Kathleen; Williams, Alishia D.; Newby, Jill M.; Perini, Sarah; Phillips, Rachel; Schneider, Justine; Pots, Wendy Theresia Maria; Pugh, Nicole E.; Richards, Derek; Rosso, Isabelle M.; Rauch, Scott L.; Sheeber, Lisa; Smith, Jessica; Spek, Viola; Pop, Victor J.M.; Ünlü, Burçin; Bastelaar, K.M.P. van; Luenen, Sanne van; Garnefski, Nadia; Kraaij, Vivian; Vernmark, Kristofer; Warmerdam, Lisanne; Straten, Annemieke van; Zagorscak, Pavle; Knaevelsrud, Christine; Heinrich, Manuel; Miguel, Clara; Cipriani, Andrea; Efthimiou, Orestis; Karyotaki, Eirini; Cuijpers, Pim

doi:10.1016/s2215-0366(21)00077-8

Cited by 122 publications

(92 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We understand the use of the factorial trial as an appropriate approach to understand the differential effects of each component of SAD. Although other sophisticated approaches exist, for instance, component individual patient data meta-analysis (e.g., Furukawa et al, 2021 ), the component meta-analyses are based on the indirect comparisons between different trials. Thus, there is a higher likelihood that the observed differences can be attributed not to the various components but to the differences in the settings.…”

Section: Discussionmentioning

confidence: 99%

Optimizing cognitive-behavioral therapy for social anxiety disorder and understanding the mechanisms of change: Study protocol for a randomized factorial trial

Lopes

Šipka

Krieger

et al. 2021

Internet Interventions

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Optimizing cognitive-behavioral therapy for social anxiety disorder and understanding the mechanisms of change: Study protocol for a randomized factorial trial

Lopes

Šipka

Krieger

et al. 2021

Internet Interventions

Self Cite

View full text Add to dashboard Cite

“…In the current systematic review we focus on the outcomes of the IPD (network) metaanalyses on predictors and moderators, but for most IPD meta-analyses other outcomes were also reported, typically in other papers. These other papers focused for example on negative outcomes [22][23][24] but also on other outcomes such as cost-effectiveness [25], symptom-specific outcomes (network analyses) [26], and IPD "component" network metaanalyses [27]. In this study we focus on the main outcomes of the IPD meta-analyses on depression severity and on predictors and moderators of these main outcomes.…”

Section: Characteristics Of the Included Studiesmentioning

confidence: 99%

The Contribution of “Individual Participant Data” Meta-Analyses of Psychotherapies for Depression to the Development of Personalized Treatments: A Systematic Review

Cuijpers

Čihařová

Quero

et al. 2022

JPM

Self Cite

View full text Add to dashboard Cite

While randomized trials typically lack sufficient statistical power to identify predictors and moderators of outcome, “individual participant data” (IPD) meta-analyses, which combine primary data of multiple randomized trials, can increase the statistical power to identify predictors and moderators of outcome. We conducted a systematic review of IPD meta-analyses on psychological treatments of depression to provide an overview of predictors and moderators identified. We included 10 (eight pairwise and two network) IPD meta-analyses. Six meta-analyses showed that higher baseline depression severity was associated with better outcomes, and two found that older age was associated with better outcomes. Because power was high in most IPD meta-analyses, non-significant findings are also of interest because they indicate that these variables are probably not relevant as predictors and moderators. We did not find in any IPD meta-analysis that gender, education level, or relationship status were significant predictors or moderators. This review shows that IPD meta-analyses on psychological treatments can identify predictors and moderators of treatment effects and thereby contribute considerably to the development of personalized treatments of depression.

show abstract

“…gesammelt, und deren Bedeutung für einzelne Symptome wird analysiert. Neben Verhaltensänderungen sollen Apps auch „Drug like“-Effekte erzielen, wie dies für psychiatrische Erkrankungen – aber noch nicht für die Rheumatologie – bereits gezeigt wurde [ 28 ].…”

Section: Rolle Von Arzt Und Patientunclassified

Künstliche Intelligenz-unterstützte Behandlung in der Rheumatologie

Hügle

Kalweit

2021

Z Rheumatol

View full text Add to dashboard Cite

ZusammenfassungComputergesteuerte klinische Entscheidungssysteme finden seit Längerem Einzug in die Praxis. Deren primäre Ziele sind die Verbesserung der Behandlungsqualität, Zeitersparnis oder Fehlervermeidung. Meist handelt es sich um regelbasierte Algorithmen, die in elektronische Patientenakten integriert werden, z. B. um Medikamenteninteraktionen zu erkennen. Durch künstliche Intelligenz (KI) können klinische Entscheidungssysteme disruptiv weiterentwickelt werden. Aus Daten wird durch maschinelles Lernen konstant neues Wissen geschaffen, um individuelle Krankheitsverläufe bei Patienten vorherzusagen, Probleme schneller zu erkennen, Phänotypen zu identifizieren oder die Therapieentscheidung zu unterstützen. Solche Algorithmen für rheumatologische Erkrankungen gibt es bereits. Am weitesten fortgeschritten hierbei sind die automatisierte Bilderkennung sowie Vorhersagen zum Krankheitsverlauf bei der rheumatoiden Arthritis. Von nutzerfreundlichen, durch Schnittstellen vernetzten KI-Entscheidungssystemen kann aber noch nicht gesprochen werden. Zudem sind die Algorithmen oft noch nicht genügend validiert und reproduzierbar. Anstatt die KI-unterstützte Wahl der Behandlung dem Arzt oder der Ärztin vorzugeben, wird KI eher als hybride Entscheidungsunterstützung dienen – immer unter Einbezug sowohl des Experten als auch des Patienten. Es gibt zudem ein großes Bedürfnis nach Sicherheit durch nachvollziehbare und auditierbare Algorithmen, um die Qualität und Transparenz von KI-unterstützten Therapieempfehlungen nachhaltig zu gewährleisten.

show abstract

Dismantling, optimising, and personalising internet cognitive behavioural therapy for depression: a systematic review and component network meta-analysis using individual participant data

Cited by 122 publications

References 41 publications

Optimizing cognitive-behavioral therapy for social anxiety disorder and understanding the mechanisms of change: Study protocol for a randomized factorial trial

Optimizing cognitive-behavioral therapy for social anxiety disorder and understanding the mechanisms of change: Study protocol for a randomized factorial trial

The Contribution of “Individual Participant Data” Meta-Analyses of Psychotherapies for Depression to the Development of Personalized Treatments: A Systematic Review

Künstliche Intelligenz-unterstützte Behandlung in der Rheumatologie

Contact Info

Product

Resources

About