Application of Machine Learning for the Detection of Depression and Mindfulness as a Mitigation Method
Santiago Domingo Moquillaza Henríquez, Liliana Ruth Huamán Rondón, Nestor Marcial Alvarado Bravo, Roberto José Antonio Carbonel Pezo, Juan Faustino Infantes Loo
Journal of Computer Science June 1, 2026 DOI: 10.3844/jcssp.2026.1823.1834 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Pre-post intervention with machine learning model Peer reviewed |
|---|---|
| Intervention | Mindfulness |
| Topics | Meditation Depression |
| Keywords | Logistic regression Depression economics Mental health Novelty detection Supervised learning Stress linguistics Machine learning Artificial intelligence Clinical psychology Wilcoxon signed-rank test Regression analysis |
| Key points | Logistic regression detected depression with 91% ROC-AUC fit, 0.839 accuracy, and 0.851 precision. Mindfulness intervention significantly improved stress levels (p < 0.05 in Wilcoxon test), both overall and by sex. |
Abstract
Depression is a global mental health problem with various causes. Nowadays, with Artificial Intelligence, it can be predicted in order to take preventive measures, whether at a psychotherapeutic or pharmacological level. This research, based on a survey conducted, detects depression using logistic regression with a 91% fit to the ROC-AUC model, accuracy of 0.839188, precision 0.851354. In addition, a study is carried out applying Mindfulness as a technique to alleviate depression or chronic stress that often ends in depression, giving good results at an overall level with pre-test and post-test tests, with a significance or p value less than 5% in a Wilcoxon test, which shows that the condition of those involved in their stress level improves. Similarly, it is observed that by disaggregating the information by sex, the level of stress improves, which is a factor of Depression. The novelty of this research is that it uses a Logistic Regression algorithm to detect depression, along with the use of mindfulness to mitigate it, validating it with statistical tests.