Predicting Future Risk of Depressive Episode in Adolescents: The Chicago Adolescent Depression Risk Assessment (CADRA)

PURPOSE A risk prediction index, similar to those used for other disorders, such as cardiovascular disease, would facilitate depression prevention by identifying those who would benefit most from preventative measures in primary care settings. METHODS The National Longitudinal Study of Adolescent Health enrolled a representative sample of US adolescents and included a baseline survey in 1995 and a 1-year follow-up survey in 1996 (n = 4,791). We used baseline risk factors (social and cognitive vulnerability and mood) to predict onset of a depressive episode at 1-year follow-up (eg, future risk of episode) and used boosted classification and regression trees to develop a prediction index, The Chicago Adolescent Depression Risk Assessment, suitable for a personal computer or hand-held device. True and false positives and negatives were determined based on concordance and discordance, respectively, between the prediction-category–based index and actual classification-category–based 1-year follow-up outcome. We evaluated the performance of the index for the entire sample and with several depressive episode outcomes using the standard Center for Epidemiologic Studies Depression (CES-D) scale cutoffs. RESULTS The optimal prediction model (including depressed mood and social vulnerability) was a 20-item model with an area under the receiver operating characteristics curve of 0.80 (95% CI, 0.714–0.870), a sensitivity of 75%, and a specificity of 76.5%. For depressive episode, the positive predictive values in the highest risk group (level 4) was from 13.75% for a depressive episode to 63.57% for CES-D score of greater than 16 (mild to moderate depressed mood or above) at follow-up. Conversely, the negative predictive value of being in the lowest 2 levels (0 or 1) was 99.38% for a depressive episode and 89.19% for a CES-D score of greater than 16. CONCLUSIONS Our model predicts a depressive episode and other depressive outcomes at 1-year follow-up. Positive and negative predictive values could enable primary care physicians and families to intervene on adolescents at highest risk.

[1]  M M Weissman,et al.  Depressed adolescents grown up. , 1999, JAMA.

[2]  Richard M Glass,et al.  Fluoxetine, cognitive-behavioral therapy, and their combination for adolescents with depression: Treatment for Adolescents with Depression Study (TADS) randomized controlled trial. , 2005, The Journal of pediatrics.

[3]  I. Gotlib,et al.  Adolescent psychopathology: IV. Specificity of psychosocial risk factors for depression and substance abuse in older adolescents. , 1995, Journal of the American Academy of Child and Adolescent Psychiatry.

[4]  M. Hakama,et al.  Comparison of HPV test versus conventional and automation‐assisted Pap screening as potential screening tools for preventing cervical cancer , 2004, BJOG : an international journal of obstetrics and gynaecology.

[5]  M. Davies,et al.  Adolescent Depression Screening in Primary Care: Feasibility and Acceptability , 2007, Pediatrics.

[6]  Sharon A Brown,et al.  Predicting depression following mild traumatic brain injury. , 2005, Archives of general psychiatry.

[7]  J. Seeley,et al.  A randomized trial of a group cognitive intervention for preventing depression in adolescent offspring of depressed parents. , 2001, Archives of general psychiatry.

[8]  A. Simons,et al.  Vulnerability to depression among adolescents: Implications for cognitive-behavioral treatment , 2005 .

[9]  J. Garber,et al.  Vulnerability to depression in childhood and adolescence. , 2001 .

[10]  A. Tylee.  Identifying and managing depression in primary care in the United kingdom. , 2006, The Journal of clinical psychiatry.

[11]  R. Ackermann,et al.  Rational treatment choices for non-major depressions in primary care , 2002, Journal of General Internal Medicine.

[12]  B. Runeson.  Mental disorder in youth suicide , 1989, Acta psychiatrica Scandinavica.

[13]  Lillemor Lundin-Olsson,et al.  Prediction of falls among older people in residential care facilities by the Downton index , 2003, Aging clinical and experimental research.

[14]  Connie Lim,et al.  Youth risk behavior surveillance--United States, 2005. , 2006, The Journal of school health.

[15]  Yihhsing Liu.  The role of perceived social support and dysfunctional attitudes in predicting Taiwanese adolescents' depressive tendency. , 2002, Adolescence.

[16]  R. Ingram,et al.  Vulnerability to Psychopathology: Risk across the Lifespan , 2002 .

[17]  G. Simon.  Social and economic burden of mood disorders , 2003, Biological Psychiatry.

[18]  L. Radloff.  The use of the Center for Epidemiologic Studies Depression Scale in adolescents and young adults , 1991, Journal of youth and adolescence.

[19]  R. Geist.  Vulnerability to Psychopathology: Risk Across the Lifespan , 2005 .

[20]  R. Kessler,et al.  Epidemiology of DSM‐III‐R major depression and minor depression among adolescents and young adults in the national comorbidity survey , 1998, Depression and anxiety.

[21]  K. Rickels,et al.  Remission of generalized anxiety disorder: a review of the paroxetine clinical trials database. , 2006, The Journal of clinical psychiatry.

[22]  E. Leibenluft,et al.  Prevalence, Clinical Correlates, and Longitudinal Course of Severe Mood Dysregulation in Children , 2006, Biological Psychiatry.

[23]  C. Hammen,et al.  Family discord and stress predictors of depression and other disorders in adolescent children of depressed and nondepressed women. , 2004, Journal of the American Academy of Child and Adolescent Psychiatry.

[24]  M. Hojat,et al.  Protecting adolescents from harm. , 1998, JAMA.

[25]  E. Costello,et al.  Specificity of putative psychosocial risk factors for psychiatric disorders in children and adolescents. , 2008, Journal of child psychology and psychiatry, and allied disciplines.

[26]  Eric Bauer,et al.  An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants , 1999, Machine Learning.

[27]  S. Saxena,et al.  Prevention of mental and behavioural disorders: implications for policy and practice. , 2006, World psychiatry : official journal of the World Psychiatric Association.

[28]  H. Christensen,et al.  Delivering interventions for depression by using the internet: randomised controlled trial , 2004, BMJ : British Medical Journal.

[29]  R. Kessler,et al.  Mood disorders in children and adolescents: an epidemiologic perspective , 2001, Biological Psychiatry.

[30]  C. Gerhardt,et al.  Adolescent development: pathways and processes of risk and resilience. , 1995, Annual review of psychology.

[31]  I. Gotlib,et al.  Depression-related psychosocial variables: are they specific to depression in adolescents? , 1997, Journal of abnormal psychology.

[32]  E. Schor.  Family pediatrics: report of the Task Force on the Family. , 2003, Pediatrics.

[33]  M. Costantini,et al.  Predicting mood disorders in breast cancer patients. , 2001, European journal of cancer.

[34]  J. Garber.  Depression in children and adolescents: linking risk research and prevention. , 2006, American journal of preventive medicine.

[35]  C. Bell,et al.  Development and process evaluation of a primary care internet-based intervention to prevent depression in emerging adults. , 2007, Primary care companion to the Journal of clinical psychiatry.

[36]  B. Hankin.  Adolescent depression: Description, causes, and interventions , 2006, Epilepsy & Behavior.

[37]  Anke Bramesfeld,et al.  Possibilities for intervention in adolescents' and young adults' depression from a public health perspective. , 2006, Health policy.

[38]  R. Friedman.  Uncovering an epidemic--screening for mental illness in teens. , 2006, The New England journal of medicine.

[39]  G. Watt,et al.  The accuracy of the Framingham risk-score in different socioeconomic groups: a prospective study. , 2005, The British journal of general practice : the journal of the Royal College of General Practitioners.

[40]  G. Klerman,et al.  The Current Age of Youthful Melancholia , 1988, British Journal of Psychiatry.

[41]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[42]  L. Oakley,et al.  Health promotion for adolescents in primary care: randomised controlled trial , 2002, BMJ : British Medical Journal.

[43]  V. Schoenbach,et al.  Use of a symptom scale to study the prevalence of a depressive syndrome in young adolescents. , 1982, American journal of epidemiology.

[44]  S. Radius,et al.  Health counseling for adolescents: what they want, what they get, and who gives it. , 1988, Pediatrics.

[45]  Trish,et al.  Protecting adolescents from harm. Findings from the National Longitudinal Study on Adolescent Health. , 1997, JAMA.

[46]  Laura Kann,et al.  Youth Risk Behavior Surveillance--United States, 1993. CDC Surveillance Summaries. , 1995 .

[47]  L. Richardson,et al.  Childhood and adolescent depression: the role of primary care providers in diagnosis and treatment. , 2005, Current problems in pediatric and adolescent health care.