Prim Care Companion J Clin Psychiatry 2009;11(2):86-86
© Copyright 2017 Physicians Postgraduate Press, Inc.
Objective: A risk-prediction index for depression, similar to those used for other
disorders such as cardiovascular disease, would facilitate depression prevention in
primary care settings by identifying those patients who would benefit most from preventative
Method: The National Longitudinal Study of Adolescent Health enrolled a representative
sample of U.S. adolescents and included a baseline survey in 1995 and a
1-year follow-up survey in 1996 (N = 4791). In the present study, baseline risk factors
(social and cognitive vulnerability and mood) were used to predict onset of a
depressive episode at 1-year follow-up (e.g., future risk of episode), and boosted
classification and regression trees were used to develop a prediction index, The Chicago
Adolescent Depression Risk Assessment, operable on a personal computer or
hand-held device. The researchers determined true and false positives and negatives
on the basis of concordance and discordance, respectively, between the predictioncategory–
based index and actual classification-category–based 1-year follow-up
outcome. The standard Center for Epidemiologic Studies Depression (CES-D) scale
cutoffs were used to assess the performance of the index for the entire sample and
with several depressive episode outcomes.
Results: A 20-item model with an area under the receiver operating characteristics
curve of 0.80 (95% CI = 0.714 to 0.870), a sensitivity of 75%, and a specificity
of 76.5% was found to be the optimal prediction model (including depressed mood
and social vulnerability). For depressive episode, the positive predictive value of
being in the highest risk group (level 4) was from 13.75% for a depressive episode to
63.57% for a CES-D score greater than 16 (mild-to-moderate depressed mood or
above) at follow-up, while 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
greater than 16.
Conclusions: A depressive episode and other depressive outcomes at 1-year
follow-up were successfully predicted by the model developed for this study. Primary
care physicians and families could use these positive and negative predictive
values to intervene in cases of adolescents at highest risk.