Association Between Negative Cognitive Bias and Depression: A Symptom-Level Approach

Christopher G. Beevers, Michael C. Mullarkey, Justin Dainer-Best, Rochelle A. Stewart, Jocelyn Labrada, John JB Allen, John E. McGeary, Jason Shumake

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Cognitive models of depression posit that negatively biased self-referent processing and attention have important roles in the disorder. However, depression is a heterogeneous collection of symptoms and all symptoms are unlikely to be associated with these negative cognitive biases. The current study involved 218 community adults whose depression ranged from no symptoms to clinical levels of depression. Random forest machine learning was used to identify the most important depression symptom predictors of each negative cognitive bias. Depression symptoms were measured with the Beck Depression Inventory-II. Model performance was evaluated using predictive R-squared (R pred 2 ), the expected variance explained in data not used to train the algorithm, estimated by 10 repetitions of 10-fold cross-validation. Using the self-referent encoding task (SRET), depression symptoms explained 34% to 45% of the variance in negative self-referent processing. The symptoms of sadness, self-dislike, pessimism, feelings of punishment, and indecision were most important. Notably, many depression symptoms made virtually no contribution to this prediction. In contrast, for attention bias for sad stimuli, measured with the dot-probe task using behavioral reaction time (RT) and eye gaze metrics, no reliable symptom predictors were identified. Findings indicate that a symptom-level approach may provide new insights into which symptoms, if any, are associated with negative cognitive biases in depression.

Original languageEnglish (US)
Pages (from-to)212-227
Number of pages16
JournalJournal of Abnormal Psychology
Volume128
Issue number3
DOIs
StatePublished - Apr 1 2019

Fingerprint

Depression
Punishment
Reaction Time
Emotions
Equipment and Supplies

Keywords

  • Cognitive model of depression
  • Machine learning
  • Symptom importance

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry

Cite this

Beevers, C. G., Mullarkey, M. C., Dainer-Best, J., Stewart, R. A., Labrada, J., Allen, J. JB., ... Shumake, J. (2019). Association Between Negative Cognitive Bias and Depression: A Symptom-Level Approach. Journal of Abnormal Psychology, 128(3), 212-227. https://doi.org/10.1037/abn0000405

Association Between Negative Cognitive Bias and Depression : A Symptom-Level Approach. / Beevers, Christopher G.; Mullarkey, Michael C.; Dainer-Best, Justin; Stewart, Rochelle A.; Labrada, Jocelyn; Allen, John JB; McGeary, John E.; Shumake, Jason.

In: Journal of Abnormal Psychology, Vol. 128, No. 3, 01.04.2019, p. 212-227.

Research output: Contribution to journalArticle

Beevers, CG, Mullarkey, MC, Dainer-Best, J, Stewart, RA, Labrada, J, Allen, JJB, McGeary, JE & Shumake, J 2019, 'Association Between Negative Cognitive Bias and Depression: A Symptom-Level Approach', Journal of Abnormal Psychology, vol. 128, no. 3, pp. 212-227. https://doi.org/10.1037/abn0000405
Beevers, Christopher G. ; Mullarkey, Michael C. ; Dainer-Best, Justin ; Stewart, Rochelle A. ; Labrada, Jocelyn ; Allen, John JB ; McGeary, John E. ; Shumake, Jason. / Association Between Negative Cognitive Bias and Depression : A Symptom-Level Approach. In: Journal of Abnormal Psychology. 2019 ; Vol. 128, No. 3. pp. 212-227.
@article{da40f61d1a0e4be3afcfaab68570a49c,
title = "Association Between Negative Cognitive Bias and Depression: A Symptom-Level Approach",
abstract = "Cognitive models of depression posit that negatively biased self-referent processing and attention have important roles in the disorder. However, depression is a heterogeneous collection of symptoms and all symptoms are unlikely to be associated with these negative cognitive biases. The current study involved 218 community adults whose depression ranged from no symptoms to clinical levels of depression. Random forest machine learning was used to identify the most important depression symptom predictors of each negative cognitive bias. Depression symptoms were measured with the Beck Depression Inventory-II. Model performance was evaluated using predictive R-squared (R pred 2 ), the expected variance explained in data not used to train the algorithm, estimated by 10 repetitions of 10-fold cross-validation. Using the self-referent encoding task (SRET), depression symptoms explained 34{\%} to 45{\%} of the variance in negative self-referent processing. The symptoms of sadness, self-dislike, pessimism, feelings of punishment, and indecision were most important. Notably, many depression symptoms made virtually no contribution to this prediction. In contrast, for attention bias for sad stimuli, measured with the dot-probe task using behavioral reaction time (RT) and eye gaze metrics, no reliable symptom predictors were identified. Findings indicate that a symptom-level approach may provide new insights into which symptoms, if any, are associated with negative cognitive biases in depression.",
keywords = "Cognitive model of depression, Machine learning, Symptom importance",
author = "Beevers, {Christopher G.} and Mullarkey, {Michael C.} and Justin Dainer-Best and Stewart, {Rochelle A.} and Jocelyn Labrada and Allen, {John JB} and McGeary, {John E.} and Jason Shumake",
year = "2019",
month = "4",
day = "1",
doi = "10.1037/abn0000405",
language = "English (US)",
volume = "128",
pages = "212--227",
journal = "Journal of Abnormal Psychology",
issn = "0021-843X",
publisher = "American Psychological Association Inc.",
number = "3",

}

TY - JOUR

T1 - Association Between Negative Cognitive Bias and Depression

T2 - A Symptom-Level Approach

AU - Beevers, Christopher G.

AU - Mullarkey, Michael C.

AU - Dainer-Best, Justin

AU - Stewart, Rochelle A.

AU - Labrada, Jocelyn

AU - Allen, John JB

AU - McGeary, John E.

AU - Shumake, Jason

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Cognitive models of depression posit that negatively biased self-referent processing and attention have important roles in the disorder. However, depression is a heterogeneous collection of symptoms and all symptoms are unlikely to be associated with these negative cognitive biases. The current study involved 218 community adults whose depression ranged from no symptoms to clinical levels of depression. Random forest machine learning was used to identify the most important depression symptom predictors of each negative cognitive bias. Depression symptoms were measured with the Beck Depression Inventory-II. Model performance was evaluated using predictive R-squared (R pred 2 ), the expected variance explained in data not used to train the algorithm, estimated by 10 repetitions of 10-fold cross-validation. Using the self-referent encoding task (SRET), depression symptoms explained 34% to 45% of the variance in negative self-referent processing. The symptoms of sadness, self-dislike, pessimism, feelings of punishment, and indecision were most important. Notably, many depression symptoms made virtually no contribution to this prediction. In contrast, for attention bias for sad stimuli, measured with the dot-probe task using behavioral reaction time (RT) and eye gaze metrics, no reliable symptom predictors were identified. Findings indicate that a symptom-level approach may provide new insights into which symptoms, if any, are associated with negative cognitive biases in depression.

AB - Cognitive models of depression posit that negatively biased self-referent processing and attention have important roles in the disorder. However, depression is a heterogeneous collection of symptoms and all symptoms are unlikely to be associated with these negative cognitive biases. The current study involved 218 community adults whose depression ranged from no symptoms to clinical levels of depression. Random forest machine learning was used to identify the most important depression symptom predictors of each negative cognitive bias. Depression symptoms were measured with the Beck Depression Inventory-II. Model performance was evaluated using predictive R-squared (R pred 2 ), the expected variance explained in data not used to train the algorithm, estimated by 10 repetitions of 10-fold cross-validation. Using the self-referent encoding task (SRET), depression symptoms explained 34% to 45% of the variance in negative self-referent processing. The symptoms of sadness, self-dislike, pessimism, feelings of punishment, and indecision were most important. Notably, many depression symptoms made virtually no contribution to this prediction. In contrast, for attention bias for sad stimuli, measured with the dot-probe task using behavioral reaction time (RT) and eye gaze metrics, no reliable symptom predictors were identified. Findings indicate that a symptom-level approach may provide new insights into which symptoms, if any, are associated with negative cognitive biases in depression.

KW - Cognitive model of depression

KW - Machine learning

KW - Symptom importance

UR - http://www.scopus.com/inward/record.url?scp=85060045131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060045131&partnerID=8YFLogxK

U2 - 10.1037/abn0000405

DO - 10.1037/abn0000405

M3 - Article

C2 - 30652884

AN - SCOPUS:85060045131

VL - 128

SP - 212

EP - 227

JO - Journal of Abnormal Psychology

JF - Journal of Abnormal Psychology

SN - 0021-843X

IS - 3

ER -