Modifiable risk factors predicting major depressive disorder at four year follow-up: a decision tree approach
Why the study?
Does a decision tree methodology improve the prediction of major depressive disorder compared to logistic regression in a community cohort?
Population
6,605 individuals from the community in the Canberra region, Australia, comprising 2,105 20-24 year olds…
Comparison
Decision tree methodology to predict the… vs Logistic regression analysis
Design
Cohort
Follow-up
4 years
Authors
Discussion
Loading...
Member takes
Implication
May improve MDD risk prediction in community cohorts; hypothesis-generating and requires external validation before clinical use.
Structured PICO
Does a decision tree methodology improve the prediction of major depressive disorder compared to logistic regression in a community cohort?
P
Population
6,605 individuals from the community in the Canberra region, Australia, comprising 2,105 20-24 year olds, 2,323 40-44 year olds, and 2,177 60-64 year olds.
I
Intervention
Decision tree methodology to predict the presence of major depressive disorder
C
Comparator
Logistic regression analysis
O
Outcome
Presence of major depressive disorder after four years of follow-up
A decision tree approach offers better sensitivity and specificity than logistic regression for predicting major depressive disorder over a four-year period.
Cite This Study
Batterham et al. (2009) studied this question.