What type of study is this?

September 10, 2025American Journal of Artificial IntelligenceOpen Access

Evaluating the Performance of Selected Single Classifiers with Incorporated Explainable Artificial Intelligence (XAI) in the Prediction of Mental Health Distress Among University Students

View Full Paper

Ask AI

Bookmark

Authors

VLVictor LumumbaChuka University DMDennis MuriithiChuka University MOMonicah Buyatsi OundoChuka University

Discussion

Member takes

Implication

Analysis shows that explainable AI methods improve predictions of mental health in university students, suggesting enhanced mental health interventions.

Key Points

The support vector machine model achieved an accuracy of 97.6% in predicting mental health distress levels.
SHAP analysis identified key factors like academic pressure and lifestyle as influential predictors of mental distress.
Single classifiers such as KNN and MLR demonstrated moderate predictive power compared to SVM.
The study emphasizes the need for integrating interpretable AI models into mental health frameworks in institutions.

Cite This Study

Lumumba et al. (2025) studied this question.

synapsesocial.com/papers/68c1d9a154b1d3bfb60fbc96 https://doi.org/10.11648/j.ajai.20250902.15

View Full Paper

Ask AI

Bookmark

Implication

Analysis shows that explainable AI methods improve predictions of mental health in university students, suggesting enhanced mental health interventions.

Evaluating the Performance of Selected Single Classifiers with Incorporated Explainable Artificial Intelligence (XAI) in the Prediction of Mental Health Distress Among University Students

Discussion

Member takes

Implication

Key Points

Cite This Study

Evaluating the Performance of Selected Single Classifiers with Incorporated Explainable Artificial Intelligence (XAI) in the Prediction of Mental Health Distress Among University Students

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider