BACKGROUND: The treatment of depression in children and adolescents is a substantial public health challenge. This study examined artificial intelligence tools for the prediction of early outcomes in depressed children and adolescents treated with fluoxetine, duloxetine, or placebo. METHODS: The study samples included training datasets (N = 271) from patients with major depressive disorder (MDD) treated with fluoxetine and testing datasets from patients with MDD treated with duloxetine (N = 255) or placebo (N = 265). Treatment trajectories were generated using probabilistic graphical models (PGMs). Unsupervised machine learning identified specific depressive symptom profiles and related thresholds of improvement during acute treatment. RESULTS: Variation in six depressive symptoms (difficulty having fun, social withdrawal, excessive fatigue, irritability, low self-esteem, and depressed feelings) assessed with the Children's Depression Rating Scale-Revised at 4-6 weeks predicted treatment outcomes with fluoxetine at 10-12 weeks with an average accuracy of 73% in the training dataset. The same six symptoms predicted 10-12 week outcomes at 4-6 weeks in (a) duloxetine testing datasets with an average accuracy of 76% and (b) placebo-treated patients with accuracies of 67%. In placebo-treated patients, the accuracies of predicting response and remission were similar to antidepressants. Accuracies for predicting nonresponse to placebo treatment were significantly lower than antidepressants. CONCLUSIONS: PGMs provided clinically meaningful predictions in samples of depressed children and adolescents treated with fluoxetine or duloxetine. Future work should augment PGMs with biological data for refined predictions to guide the selection of pharmacological and psychotherapeutic treatment in children and adolescents with depression.
BACKGROUND: The treatment of depression in children and adolescents is a substantial public health challenge. This study examined artificial intelligence tools for the prediction of early outcomes in depressed children and adolescents treated with fluoxetine, duloxetine, or placebo. METHODS: The study samples included training datasets (N = 271) from patients with major depressive disorder (MDD) treated with fluoxetine and testing datasets from patients with MDD treated with duloxetine (N = 255) or placebo (N = 265). Treatment trajectories were generated using probabilistic graphical models (PGMs). Unsupervised machine learning identified specific depressive symptom profiles and related thresholds of improvement during acute treatment. RESULTS: Variation in six depressive symptoms (difficulty having fun, social withdrawal, excessive fatigue, irritability, low self-esteem, and depressed feelings) assessed with the Children's Depression Rating Scale-Revised at 4-6 weeks predicted treatment outcomes with fluoxetine at 10-12 weeks with an average accuracy of 73% in the training dataset. The same six symptoms predicted 10-12 week outcomes at 4-6 weeks in (a) duloxetine testing datasets with an average accuracy of 76% and (b) placebo-treated patients with accuracies of 67%. In placebo-treated patients, the accuracies of predicting response and remission were similar to antidepressants. Accuracies for predicting nonresponse to placebo treatment were significantly lower than antidepressants. CONCLUSIONS: PGMs provided clinically meaningful predictions in samples of depressed children and adolescents treated with fluoxetine or duloxetine. Future work should augment PGMs with biological data for refined predictions to guide the selection of pharmacological and psychotherapeutic treatment in children and adolescents with depression.
Authors: Stephen F Smagula; Meryl A Butters; Stewart J Anderson; Eric J Lenze; Mary Amanda Dew; Benoit H Mulsant; Francis E Lotrich; Howard Aizenstein; Charles F Reynolds Journal: JAMA Psychiatry Date: 2015-10 Impact factor: 21.596
Authors: John March; Susan Silva; Stephen Petrycki; John Curry; Karen Wells; John Fairbank; Barbara Burns; Marisa Domino; Steven McNulty; Benedetto Vitiello; Joanne Severe Journal: JAMA Date: 2004-08-18 Impact factor: 56.272
Authors: Ryan S Sultan; Christoph U Correll; Michael Schoenbaum; Marrisa King; John T Walkup; Mark Olfson Journal: J Child Adolesc Psychopharmacol Date: 2018-01-29 Impact factor: 2.576
Authors: R Uher; A Farmer; W Maier; M Rietschel; J Hauser; A Marusic; O Mors; A Elkin; R J Williamson; C Schmael; N Henigsberg; J Perez; J Mendlewicz; J G E Janzing; A Zobel; M Skibinska; D Kozel; A S Stamp; M Bajs; A Placentino; M Barreto; P McGuffin; K J Aitchison Journal: Psychol Med Date: 2007-10-09 Impact factor: 7.723
Authors: Adam Mourad Chekroud; Ryan Joseph Zotti; Zarrar Shehzad; Ralitza Gueorguieva; Marcia K Johnson; Madhukar H Trivedi; Tyrone D Cannon; John Harrison Krystal; Philip Robert Corlett Journal: Lancet Psychiatry Date: 2016-01-21 Impact factor: 27.083
Authors: Laura B Ramsey; Lisa B Namerow; Jeffrey R Bishop; J Kevin Hicks; Chad Bousman; Paul E Croarkin; Carol A Mathews; Sara L Van Driest; Jeffrey R Strawn Journal: J Am Acad Child Adolesc Psychiatry Date: 2020-08-26 Impact factor: 13.113
Authors: Carl Y Zhang; Jennifer L Vande Voort; Deniz Yuruk; Jeffrey A Mills; Graham J Emslie; Betsy D Kennard; Taryn Mayes; Madhukar Trivedi; William V Bobo; Jeffrey R Strawn; Arjun P Athreya; Paul E Croarkin Journal: J Child Adolesc Psychopharmacol Date: 2022-06 Impact factor: 3.031