What's Race Got to do with it? Predicting Youth Depression Across Racial Groups Using Machine and Deep Learning

TL;DR

This study employs machine learning and neural networks to predict youth depression across racial groups, revealing key factors and emphasizing the importance of diverse datasets for accurate diagnosis.

Contribution

It introduces a machine learning approach for youth depression prediction that accounts for racial differences, highlighting the need for diverse data and identifying relevant factors per racial subgroup.

Findings

ANN achieved 82.90% F1 score

SVM achieved 81.90% F1 score

Different parameters are important for different racial groups

Abstract

Depression is a common yet serious mental disorder that affects millions of U.S. high schoolers every year. Still, accurate diagnosis and early detection remain significant challenges. In the field of public health, research shows that neural networks produce promising results in identifying other diseases such as cancer and HIV. This study proposes a similar approach, utilizing machine learning (ML) and artificial neural network (ANN) models to classify depression in a student. Additionally, the study highlights the differences in relevant factors for race subgroups and advocates the need for more extensive and diverse datasets. The models train on nationwide Youth Risk Behavior Surveillance System (YRBSS) survey data, in which the most relevant factors of depression are found with statistical analysis. The survey data is a structured dataset with 15000 entries including three race subsets each consisting of 900 entries. For classification, the research problem is modeled as a supervised learning binary classification problem. Factors relevant to depression for different racial subgroups are also identified. The ML and ANN models are trained on the entire dataset followed by different race subsets to classify whether an individual has depression. The ANN model achieves the highest F1 score of 82.90% while the best-performing machine learning model, support vector machines (SVM), achieves a score of 81.90%. This study reveals that different parameters are more valuable for modeling depression across diverse racial groups and furthers research regarding American youth depression.