Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
November 1, 2025Behavioral SciencesOpen Access

Systematic Review and Meta-Analysis of Explainable Machine Learning Models for Clinical Depression Detection

View Full Paper
Ask AI
Bookmark
Share

Authors

ATAriosto TrellesTFTomás Fontaines-RuízARAntonio Ponce Rojo

Discussion

Loading...

Member takes

Overview

Systematic review reveals that explainable algorithms improve clinical depression detection, suggesting enhanced interpretability and data quality matters.

Key Points

  • XGBoost exhibited the best average performance in detecting clinical depression, achieving an F1-Score of 0.86.
  • Statistical analyses of 20 studies indicated a strong correlation between F1-Score and AUC-ROC at r = 0.950, p < 0.001.
  • Analysis was guided by PRISMA and included various supervised algorithms like Random Forest and XGBoost.
  • Results highlight that data quality and context greatly influence algorithmic performance and interpretability benefits.

Cite This Study

Trelles et al. (2025) studied this question.

synapsesocial.com/papers/69054ffa1a99e50463de697dhttps://doi.org/10.3390/bs15111476
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Explainable AI for Depression Detection and Severity Classification From Activity Data: Development and Evaluation Study of an Interpretable Framework2025 · 27 citations
  2. 2Model-Agnostic Interpretability for Student Depression Screening: Integrating XAI and Multi-Criteria Model Selection2026
  3. 3Diagnostic accuracy of machine learning approaches for suicide‑related outcomes: a meta‑analysis2026
  4. 4Prediction of depressive episodes based on clinical features, cognitive characteristics, inflammation-related proteins, and EEG data2026 · 1 citations
  5. 5A Comparative Study of Various Machine Learning Techniques for Diagnosing Clinical Depression2024