What does this research mean for the field?

Transparent ensemble machine learning models, specifically Random Forest and XGBoost, can predict mental health distress levels among Kenyan university students with near-perfect accuracy using psychosocial, academic, and financial predictors. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To develop and evaluate transparent ensemble machine learning models for predicting varying levels of mental health distress among university students in Kenya.

August 22, 2026International Journal of Psychological and Brain SciencesOpen Access

A Transparent AI-Driven Ensemble Learning Approach for Predicting Mental Health Risks among University Students in Kenya

View Full Paper

Ask AI

Bookmark

Authors

VLVictor Lumumba DMDennis MuriithiChuka University MOMonica Oundo

Discussion

Member takes

Implication

Machine learning study demonstrates high accuracy in predicting mental health distress levels among university students, indicating the viability of AI-driven early wellness screening.

Key Points

To develop and evaluate transparent ensemble machine learning models for predicting varying levels of mental health distress among university students in Kenya.
Surveyed N=1,128 students across universities in Tharaka Nithi County, Kenya, gathering demographic, academic, financial, psychosocial, and Quarter-Life Crisis variables.
Trained Random Forest and XGBoost ensemble algorithms using a 70/30 train-test split and assessed feature contributions with SHAP explainability analysis.
Both Random Forest and XGBoost models achieved 98.8% accuracy (95% CI: 96.9–99.7%), a Cohen’s Kappa of 0.978, and multi-class AUCs of 1.000 (RF) and ≥0.997 (XGBoost).
For detecting high distress, both models achieved 100% sensitivity and 100% specificity, with F1-scores of 1.000 for Random Forest and 0.988 for XGBoost.
Quarter-Life Crisis, STEM/nursing majors, personal mental health history, financial strain, and residence were identified as the strongest predictors of mental health distress.

Cite This Study

Lumumba et al. (2026) studied this question.

synapsesocial.com/papers/6a898131ca7ade938187f2f8 https://doi.org/10.11648/j.ijpbs.20261102.12

View Full Paper

Ask AI

Bookmark

Implication

Machine learning study demonstrates high accuracy in predicting mental health distress levels among university students, indicating the viability of AI-driven early wellness screening.

A Transparent AI-Driven Ensemble Learning Approach for Predicting Mental Health Risks among University Students in Kenya

Discussion

Member takes

Implication

Key Points

Cite This Study

A Transparent AI-Driven Ensemble Learning Approach for Predicting Mental Health Risks among University Students in Kenya

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider