Tiffany C Ho1,2, Rutvik Shah1,3, Jyoti Mishra3, April C May3,4, Susan F Tapert3. 1. Department of Psychiatry and Behavioral Sciences, Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, CA, USA. 2. Department of Psychology, University of California, Los Angeles, Los Angeles, CA, USA. 3. Department of Psychiatry, University of California, San Diego, San Diego, CA, USA. 4. San Diego State University/University of California San Diego Joint Doctoral Program in Clinical Psychology, San Diego, CA, USA.
Abstract
BACKGROUND: While identifying risk factors for adolescent depression is critical for early prevention and intervention, most studies have sought to understand the role of isolated factors rather than across a broad set of factors. Here, we sought to examine multi-level factors that maximize the prediction of depression symptoms in US children participating in the Adolescent Brain and Cognitive Development (ABCD) study. METHODS: A total of 7,995 participants from ABCD (version 3.0 release) provided complete data at baseline and 1-year follow-up data. Depression symptoms were measured with the Child Behavior Checklist. Predictive features included child demographic, environmental, and structural and resting-state fMRI variables, parental depression history and demographic characteristics. We used linear (elastic net regression, EN) and non-linear (gradient-boosted trees, GBT) predictive models to identify which set of features maximized prediction of depression symptoms at baseline and, separately, at 1-year follow-up. RESULTS: Both linear and non-linear models achieved comparable results for predicting baseline (EN: MAE = 3.757; R2 = 0.156; GBT: MAE = 3.761; R2 = 0.147) and 1-year follow-up (EN: MAE = 4.255; R2 = 0.103; GBT: MAE = 4.262; R2 = 0.089) depression. Parental history of depression, greater family conflict, and shorter child sleep duration were among the top predictors of concurrent and future child depression symptoms across both models. Although resting-state fMRI features were relatively weaker predictors, functional connectivity of the caudate was consistently the strongest neural feature associated with depression symptoms at both timepoints. CONCLUSIONS: Consistent with prior research, parental mental health, family environment, and child sleep quality are important risk factors for youth depression. Functional connectivity of the caudate is a relatively weaker predictor of depression symptoms but may represent a biomarker for depression risk.
BACKGROUND: While identifying risk factors for adolescent depression is critical for early prevention and intervention, most studies have sought to understand the role of isolated factors rather than across a broad set of factors. Here, we sought to examine multi-level factors that maximize the prediction of depression symptoms in US children participating in the Adolescent Brain and Cognitive Development (ABCD) study. METHODS: A total of 7,995 participants from ABCD (version 3.0 release) provided complete data at baseline and 1-year follow-up data. Depression symptoms were measured with the Child Behavior Checklist. Predictive features included child demographic, environmental, and structural and resting-state fMRI variables, parental depression history and demographic characteristics. We used linear (elastic net regression, EN) and non-linear (gradient-boosted trees, GBT) predictive models to identify which set of features maximized prediction of depression symptoms at baseline and, separately, at 1-year follow-up. RESULTS: Both linear and non-linear models achieved comparable results for predicting baseline (EN: MAE = 3.757; R2 = 0.156; GBT: MAE = 3.761; R2 = 0.147) and 1-year follow-up (EN: MAE = 4.255; R2 = 0.103; GBT: MAE = 4.262; R2 = 0.089) depression. Parental history of depression, greater family conflict, and shorter child sleep duration were among the top predictors of concurrent and future child depression symptoms across both models. Although resting-state fMRI features were relatively weaker predictors, functional connectivity of the caudate was consistently the strongest neural feature associated with depression symptoms at both timepoints. CONCLUSIONS: Consistent with prior research, parental mental health, family environment, and child sleep quality are important risk factors for youth depression. Functional connectivity of the caudate is a relatively weaker predictor of depression symptoms but may represent a biomarker for depression risk.
Authors: Pedro Mario Pan; João R Sato; Giovanni A Salum; Luis A Rohde; Ary Gadelha; Andre Zugman; Jair Mari; Andrea Jackowski; Felipe Picon; Eurípedes C Miguel; Daniel S Pine; Ellen Leibenluft; Rodrigo A Bressan; Argyris Stringaris Journal: Am J Psychiatry Date: 2017-09-26 Impact factor: 18.112
Authors: Donald J Hagler; SeanN Hatton; M Daniela Cornejo; Carolina Makowski; Damien A Fair; Anthony Steven Dick; Matthew T Sutherland; B J Casey; Deanna M Barch; Michael P Harms; Richard Watts; James M Bjork; Hugh P Garavan; Laura Hilmer; Christopher J Pung; Chelsea S Sicat; Joshua Kuperman; Hauke Bartsch; Feng Xue; Mary M Heitzeg; Angela R Laird; Thanh T Trinh; Raul Gonzalez; Susan F Tapert; Michael C Riedel; Lindsay M Squeglia; Luke W Hyde; Monica D Rosenberg; Eric A Earl; Katia D Howlett; Fiona C Baker; Mary Soules; Jazmin Diaz; Octavio Ruiz de Leon; Wesley K Thompson; Michael C Neale; Megan Herting; Elizabeth R Sowell; Ruben P Alvarez; Samuel W Hawes; Mariana Sanchez; Jerzy Bodurka; Florence J Breslin; Amanda Sheffield Morris; Martin P Paulus; W Kyle Simmons; Jonathan R Polimeni; Andre van der Kouwe; Andrew S Nencka; Kevin M Gray; Carlo Pierpaoli; John A Matochik; Antonio Noronha; Will M Aklin; Kevin Conway; Meyer Glantz; Elizabeth Hoffman; Roger Little; Marsha Lopez; Vani Pariyadath; Susan Rb Weiss; Dana L Wolff-Hughes; Rebecca DelCarmen-Wiggins; Sarah W Feldstein Ewing; Oscar Miranda-Dominguez; Bonnie J Nagel; Anders J Perrone; Darrick T Sturgeon; Aimee Goldstone; Adolf Pfefferbaum; Kilian M Pohl; Devin Prouty; Kristina Uban; Susan Y Bookheimer; Mirella Dapretto; Adriana Galvan; Kara Bagot; Jay Giedd; M Alejandra Infante; Joanna Jacobus; Kevin Patrick; Paul D Shilling; Rahul Desikan; Yi Li; Leo Sugrue; Marie T Banich; Naomi Friedman; John K Hewitt; Christian Hopfer; Joseph Sakai; Jody Tanabe; Linda B Cottler; Sara Jo Nixon; Linda Chang; Christine Cloak; Thomas Ernst; Gloria Reeves; David N Kennedy; Steve Heeringa; Scott Peltier; John Schulenberg; Chandra Sripada; Robert A Zucker; William G Iacono; Monica Luciana; Finnegan J Calabro; Duncan B Clark; David A Lewis; Beatriz Luna; Claudiu Schirda; Tufikameni Brima; John J Foxe; Edward G Freedman; Daniel W Mruzek; Michael J Mason; Rebekah Huber; Erin McGlade; Andrew Prescot; Perry F Renshaw; Deborah A Yurgelun-Todd; Nicholas A Allgaier; Julie A Dumas; Masha Ivanova; Alexandra Potter; Paul Florsheim; Christine Larson; Krista Lisdahl; Michael E Charness; Bernard Fuemmeler; John M Hettema; Hermine H Maes; Joel Steinberg; Andrey P Anokhin; Paul Glaser; Andrew C Heath; Pamela A Madden; Arielle Baskin-Sommers; R Todd Constable; Steven J Grant; Gayathri J Dowling; Sandra A Brown; Terry L Jernigan; Anders M Dale Journal: Neuroimage Date: 2019-08-12 Impact factor: 7.400
Authors: I H Gotlib; J LeMoult; N L Colich; L C Foland-Ross; J Hallmayer; J Joormann; J Lin; O M Wolkowitz Journal: Mol Psychiatry Date: 2014-09-30 Impact factor: 15.992
Authors: Rebecca Kerestes; Christopher G Davey; Katerina Stephanou; Sarah Whittle; Ben J Harrison Journal: Neuroimage Clin Date: 2013-12-11 Impact factor: 4.881
Authors: Tiffany C Ho; Natalie L Colich; Lucinda M Sisk; Kira Oskirko; Booil Jo; Ian H Gotlib Journal: Dev Cogn Neurosci Date: 2020-02-14 Impact factor: 6.464